What’s new in the FAQs?
Below are listed in reverse chronological order the additions to the online FAQs:
 Stata for Linux:
How do I install Stata 18 on a Unix/Linux machine using the download tar file?
(updated 25 April 2023)
 Stata for Windows:
How can I install Stata 18 from the command line without GUI under Windows?
(updated 25 April 2023)
 Stata for Windows:
How do I install Stata 18 for Windows on a network drive?
(updated 25 April 2023)
 Statistics:
Why do I get an “invalid group specification r(198)” error when I fit a differenceindifferences (DID) model by using didregress or xtdidregress?
(Added 02 February 2022)
 Data management:
Why does my Excel datetime value seem to be behind in Stata?
(Added 16 November 2020)
 Stata for Mac:
Will Stata run on Macs with Apple Silicon?
(Added 10 November 2020)
 Stata for Mac:
Will Stata 15 or earlier run on Macs with Apple Silicon?
(Updated 10 November 2020)
 Stata for Mac:
Is Stata 13 or earlier compatible with macOS 10.15 (Catalina) or newer?
(Added 16 October 2019)
 Data management:
How do I get information from Excel into Stata?
(Updated 14 October 2019)
 Statistics:
How can I use Monte Carlo simulations to estimate power in Stata?
How can I integrate a simulation program into the power command? (Updated 8 October 2019)
 Data management:
How do I export tables from Stata?
(Updated 8 October 2019)
 Python integration:
How do I use thirdparty Python packages in the Python environment from within Stata?
(Added 7 October 2019)
 Bayesian analysis:
How can I run multiple Markov chains in parallel? (Added 26 June 2019)
 Linux:
How do I use Matplotlib with Stata for Linux?
(Added 26 June 2019)
 Statistics:
Why did I get an error saying "no paths from latent variable to
observed variables" from sem or gsem? Why did I get error message
"option lclass() is not allowed with models specified with continuous
latent variables" from gsem?
(Added 05 November 2018)
 Mac:
What is the minimum macOS requirement for Stata 15?
(Added 24 October 2018)
 Programming language:
How can I pass arguments to my dofiles?
(Updated 16 November 2017)
 Programming:
Is there any way to get around the option limit in
Stata’s syntax command?
(Updated 28 July 2017)
 Data management:
How can I use columnmode selection (select rectangles) and editing in the Dofile Editor?
(Added 28 July 2017)
 Data management:
Stata is reading in my variables as string instead of numeric. What should I do?
(Updated 03 July 2017)
 Data management:
I am having problems with the reshape command. Can you give further guidance?
(Updated 03 July 2017)
 Data management:
How do I select a subset of observations using a complicated criterion?
(Updated 03 July 2017)
 Data management:
How do I compute the number of distinct observations?
(Updated 03 July 2017)
 Data management:
How do I calculate the maximum or minimum seen so far in a sequence?
(Updated 27 June 2017)
 Statistics:
How do I analyze multiple failuretime data using Stata?
(Updated 26 June 2017)
 Statistics:
What is the relationship between baseline hazard and baseline hazard contribution?
(Updated 26 June 2017)
 Statistics:
How is the number of observations computed for subpopulation estimation?
(Updated 26 June 2017)
 Statistics:
Why can't a subject die at time 0? Why can't a subject enter and die at the same time in the Cox model?
(Updated 26 June 2017)
 Statistics:
What metaanalysis features are available in Stata?
(Updated 26 June 2017)
 Data management:
How do I check a variable for a range of diagnosis or procedure codes?
(Updated 26 June 2017)
 Data management:
How do I convert my ICD9 codes from a string type to a numeric type?
(Updated 26 June 2017)
 Statistics:
What is the difference between "endogeneity" and "sample selection bias"?
(Updated 26 June 2017)
 Statistics:
How do I impose the restriction that rho is zero using the heckman command with full ml?
(Updated 26 June 2017)
 Statistics:
Why is the pseudoR^{2} for tobit negative or greater than one?
(Updated 26 June 2017)
 Statistics:
What is the effect of specifying aweights with regress?
(Updated 26 June 2017)
 Statistics:
For twostage leastsquares (2SLS/IV/ivregress) estimates, why is the Rsquared statistic not printed in some cases?
(Updated 26 June 2017)
 Statistics:
How can I pool data (and perform Chow tests) in linear regression without constraining the residual variances to be equal?
(Updated 26 June 2017)
 Statistics:
Why do I get the error message "outcome does not vary" when I perform a logistic or logit regression?
(Updated 26 June 2017)
 Statistics:
How can I do logistic regression or multinomial logistic regression with aggregated data?
(Updated 26 June 2017)
 Statistics:
How can I calculate percentile ranks?
(Updated 26 June 2017)
 Statistics:
How can I get an Rsquared value when a Stata command does not supply one?
(Updated 26 June 2017)
 Statistics:
Why do I see different pvalues, etc., when I change the base level for a factor in my regression?
(Updated 26 June 2017)
 Windows:
Why do I get slightly different results when running a ml procedure on Stata/SE and Stata/MP?
(Updated 26 June 2017)
 Statistics:
Why does the test command sometimes produce chisquared and other times F statistics?
(Updated 26 June 2017)
 Statistics:
What is the delta method and how is it used to estimate the standard error of a transformed parameter?
(Updated 26 June 2017)
 Statistics:
How do I calculate values of the beta function?
(Updated 26 June 2017)
 Statistics:
How do I get the Euler–Mascheroni constant gamma = 0.57721... in Stata?
(Updated 26 June 2017)
 Statistics:
How can I get confidence intervals for predicted probabilities after probit?
(Updated 26 June 2017)
 Statistics:
How do I obtain confidence intervals for the predicted probabilities after logistic regression?
(Updated 26 June 2017)
 Statistics:
How are the standard errors and confidence intervals computed for relativerisk ratios (RRRs) by mlogit?
(Updated 26 June 2017)
 Statistics:
How do I fit a bivariate probit model with partial observability and a single dependent variable?
(Updated 26 June 2017)
 Statistics:
What is the relation between the official multipleimputation command, mi, and the communitycontributed ice and mim commands?
(Updated 26 June 2017)
 Statistics:
How can I account for clustering when creating imputations with mi impute?
(Updated 26 June 2017)
 Statistics:
How can I combine results other than coefficients in e(b) with multiply imputed data?
(Updated 26 June 2017)
 Statistics:
Where can I find a description of the various timeseries operators?
(Updated 26 June 2017)
 Statistics:
Why doesn't summarize accept pweights?
(Updated 26 June 2017)
 Statistics:
How do I obtain percentiles for survey data?
(Updated 26 June 2017)
 Statistics:
Are the estimates produced by probit and logit with the vce(cluster clustvar) option true maximum likelihood estimates?
(Updated 26 June 2017)
 Statistics:
How can I use Stata to calculate power by simulation?
(Updated 26 June 2017)
 Statistics:
Can Stata estimate a Rasch model?
(Updated 26 June 2017)
 Data management:
How do I create individual identifiers numbered from 1 upwards?
(Updated 26 June 2017)
 Data management:
How do I get information from Excel into Stata?
(Updated 26 June 2017)

Mac FAQ:
How do I install Stata from a terminal?
(Added 25 January 2017)
 Data management:
How do I create dummy variables?
(Updated 14 July 2016)
 Data management:
How do I convert my ICD9 codes from a string type to a numeric type?
(Added 24 February 2016)
 Data management:
How do I check a variable for a range of diagnosis or procedure codes?
(Added 24 February 2016)
 Data management:
How do I label my diagnosis or procedure codes with their descriptions?
(Added 24 February 2016)
 Mac:
When I try to update Stata, why do I get cannot write in directory /Applications/Stata /.tmp with error code r(603);?
(Added 27 January 2016)
 Mac:
How do I find a crash log on a Mac?
(Added 03 December 2015)
 Data management:
How do I accumulate the results
of immediate commands?
(Updated 29 October 2015)
 Statistics:
How can I use Stata to calculate power by simulation?
(Updated 29 October 2015)
 Data management:
How can I save a Stata dataset so that it can be read a previous
version of Stata?
(Updated 22 July 2015)
 Mac:
Is Stata compatible with Mac OS X 10.7 (Lion), Mac OS X 10.6 (Snow Leopard), and Mac OS X 10.5 (Leopard)?
(Updated 26 June 2015)
 Statistics:
Can mi estimate work with communitycontributed and unsupported commands?
(Added 24 June 2015)
 Unix:
How do I install Stata on a Unix/Linux machine?
(Updated 01 May 2015)
 Programming language:
Where is the official ado directory?
(Updated 01 May 2015)
 Programming:
I coded 'a'^2 and got the wrong
sign. Why?
(Updated 01 May 2015)
 Programming:
How do I add an observation to a dataset when
coding an adofile?
(Updated 01 May 2015)
 Statistics:
How can I account for clustering when creating imputations with mi impute?
(Updated 01 May 2015)
 Statistics:
How can I do logistic regression or multinomial logistic regression with aggregated data?
(Updated 27 April 2015)
 Windows:
How do I install Stata?
(Added 27 April 2015)
 Mac:
How do I install Stata?
(Added 27 April 2015)
 Statistics:
How can I compute the Chow test statistic?
(Updated 15 April 2015)
 Statistics:
How large should the bootstrapped samples be relative to the total number of cases in the dataset?
(Updated 15 April 2015)
 Statistics:
How can I use Stata to calculate power by simulation?
(Updated 15 April 2015)
 Resources:
When was Stata first released? When were later versions released?
(Updated 09 April 2015)
 Statistics:
How are average marginal effects and their standard errors
computed by margins using the delta method?
(Added 04 August 2014)
 Data management:
I am having problems with the
reshape command. Can you give further guidance?
(Updated 28 February 2014)
 Statistics:
How can I take random samples
from an existing dataset?
(Updated 28 February 2014)
 Windows:
How do I set up an ODBC data source name in Windows?
(Added 05 February 2014)
 Mac:
How do I access Stata’s application support directory in OS X 10.7 and newer?
(Added 26 August 2013)
 Statistics:
How do I fit a regression with interval constraints in Stata?
(Updated 17 July 2013)
 Statistics:
How do I get the variance–covariance matrix or coefficient vector?
(Updated 26 June 2013)
 Windows:
Does Stata run on Windows RT?
(Updated 03 April 2013)
 Technical support:
What are other sources of support?
(Updated 25 January 2013)
 Resources:
How can I learn more about Stata?
(Updated 24 January 2013)
 Mac:
Does Stata support the MacBook Pro with Retina display?
(Updated 23 January 2013)
 Resources:
The Stata Journal FAQ
(Updated 21 January 2013)
 Resources:
The Statalist FAQ
(Updated 21 November 2012)
 Windows:
How can I determine if my computer/operating system is 64bit?
(Updated 29 October 2012)
 Windows:
Does Stata run on Windows 8?
(Added 25 October 2012)
 Windows:
Does Stata run on Windows RT?
(Added 25 October 2012)
 Data management:
How do I list observations in a group that differ on a variable?
(Updated 26 September 2012)
 Resources:
The Statalist FAQ
(Updated 23 August 2012)
 Mac:
Does Stata support the MacBook Pro with Retina display?
(Added 03 July 2012)
 Resources:
The Statalist FAQ
(Updated 21 March 2012)
 Mac:
Multiple installations of Stata
(Added 01 March 2012)
 Resources:
The Statalist FAQ
(Updated 01 February 2012)
 Resources:
When was Stata first released? When were later versions released?
(Updated 30 January 2012)
 Data management:
How can I replace missing values
with previous or following nonmissing values or within sequences?
(Updated 26 January 2012)
 Statistics:
How is the number of observations computed for subpopulation estimation?
(Added 14 October 2011)
 Statistics:
How do I fit a linear regression with interval (inequality) constraints in Stata?
(Added 11 October 2011)
 Data management:
How can I save a Stata dataset so that it can be read a previous
version of Stata?
(Updated 01 September 2011)
 Resources:
The Statalist FAQ
(Updated 29 July 2011)
 Resources:
When was Stata first released? When were later versions released?
(Updated 28 July 2011)
 Web:
What does the error r(?) mean when I try to connect to the Internet from
within Stata?
(Updated 27 July 2011)
 Programming language:
Where is my personal ado directory?
(Updated 27 July 2011)
 Programming language:
Why don’t my communitycontributed estimation commands work in Stata 11 or Stata 12?
(Updated 27 July 2011)
 Programming language:
How do I modify an adofile created for previous versions of Stata to support
factor variables and the collinearity behavior introduced in Stata 11?
(Updated 27 July 2011)
 Programming:
I have a certain version of Stata and have come across a communitycontributed
program that is apparently written for a later version of Stata. What are my
options?
(Updated 27 July 2011)
 Programming language:
What is the difference between a release marker and a version number
in an adofile?
(Updated 27 July 2011)
 Programming language:
How can I automatically execute certain commands every time I start Stata?
(Updated 27 July 2011)
 Programming language:
How can I pass arguments to my dofiles?
(Updated 27 July 2011)
 Programming language:
Where is the official ado directory?
(Updated 27 July 2011)
 Graphics:
Line artifacts in filled contour plot
(Added 26 July 2011)
 Data management:
How do you process very large datasets in Stata?
(Updated 26 July 2011)
 Data management:
How can I save a Stata dataset so that it can be read a previous
version of Stata?
(Updated 26 July 2011)
 Statistics:
What are the divisors used in xtgee?
(Updated 26 July 2011)
 Statistics:
Why do I get an error message when I try to run a repeated measures ANOVA?
(Updated 26 July 2011)
 Statistics:
How can I form various tests comparing the different levels of a categorical
variable after anova or regress?
(Updated 26 July 2011)
 Statistics:
How does xtgls differ from regression clustered with robust standard errors?
(Updated 26 July 2011)
 Statistics:
How can there be an intercept in the fixedeffects model estimated by
xtreg, fe?
(Updated 26 July 2011)
 Statistics:
What are some of the problems with stepwise regression?
(Updated 26 July 2011)
 Statistics:
Can Stata estimate a Rasch model?
(Updated 26 July 2011)
 Statistics:
What is the relation between the official multipleimputation command, mi, and
the communitycontributed ice and mim commands?
(Updated 26 July 2011)
 Statistics:
How can I account for clustering when creating imputations with mi impute?
(Updated 26 July 2011)
 Statistics:
How can I combine results other than coefficients in e(b) with multiply
imputed data?
(Updated 26 July 2011)
 Statistics:
When I use the eyex option of margins, what is it actually computing and how
does it relate to the coefficients of the loglinear model?
(Updated 26 July 2011)
 Statistics:
Are the estimates produced by the probit and logit with the vce(cluster
clustvar) option true maximum likelihood estimates?
Is there a difference between the estimates produced by the svy: probit, with
psu variable specified in svyset command, and probit, vce(cluster
clustvar) (and, similarly, between svy: logit, with psu variable
specified in svyset, and logit vce(cluster clustvar))?
(Updated 26 July 2011)
 Statistics:
Why do Stata’s xtgee standard errors differ from those reported by
SAS’s PROC GENMOD?
(Updated 26 July 2011)
 Statistics:
For twostage least squares (2SLS/IV/ivregress) estimates, why is the Rsquared
statistic not printed in some cases?
For twostage least squares (2SLS/IV/ivregress) estimates, why is the Model Sum of
Squares sometimes negative?
For threestage least squares (3SLS/reg3) estimates, why are the Rsquared and
Model Sum of Squares sometimes negative?
(Updated 26 July 2011)
 Statistics:
How can you specify a term other than residual error as the denominator in a
single degreeoffreedom F test after ANOVA?
(Updated 26 July 2011)
 Statistics:
Why are there so many formulas for the inverse of Mills' ratio?
What if I have censoring from above/below in my Heckman selection model?
(Updated 26 July 2011)
 Statistics:
What metaanalysis features are available in Stata?
(Updated 26 July 2011)
 Statistics:
Why are observations that are noninformative about the dependent variable, but
are known to be selected, excluded by heckman from the estimation sample?
(Updated 26 July 2011)
 Statistics:
Why do I see different pvalues, etc., when I change the base level for
a factor in my regression?
Why does the pvalue for a term in my
ANOVA not agree with the pvalue for the coefficient for that term in
the corresponding regression?
(Updated 26 July 2011)
 Statistics:
How does the anova command handle collinearity?
(Updated 26 July 2011)
 Statistics:
The results from estimation commands display only twosided tests for the
coefficients. How can I perform a onesided test?
(Updated 26 July 2011)
 Statistics:
Why doesn’t summarize accept pweights?
What does summarize calculate when you use aweights?
(Updated 26 July 2011)
 Statistics:
Can I do n:1 matching with the mcc command?
(Updated 26 July 2011)
 Statistics:
How do I impose the restriction that rho is zero using the heckman command
with full ml?
(Updated 26 July 2011)
 Statistics:
What roles does the time variable play in xtgls?
(Updated 26 July 2011)
 Statistics:
Why do estimation commands sometimes omit variables?
(Updated 26 July 2011)
 Statistics:
Where can I find a description of the various timeseries operators?
(Updated 26 July 2011)
 Statistics:
Why does xtreg with the mle option produce different results from xtreg with
only the re option?
(Updated 26 July 2011)
 Statistics:
Is there a way to estimate a nonlinear combination with nlcom, when the
error “expression too long” is displayed?
(Updated 26 July 2011)
 Statistics:
How do I convert my spelltype data into a survival dataset?
How do I stset my spelltype data?
(Updated 26 July 2011)
 Statistics:
Why can't a subject die at time 0?
Why can't a subject enter and die at the same time in Cox?
(Updated 26 July 2011)
 Statistics:
How do I fit a regression with interval constraints in Stata?
(Updated 26 July 2011)
 Statistics:
How do I get a bootstrap vector of results?
(Updated 26 July 2011)
 Statistics:
How can I estimate correlations and their level of significance
with survey data?
(Updated 26 July 2011)
 Statistics:
Why do I sometimes get negative
eigenvalues when using the pf and ipf options of factor?
(Updated 26 July 2011)
 Statistics:
Can you explain Chow tests?
(Updated 26 July 2011)
 Statistics:
Should the pvalue given with a paired ttest always be lower
than the signrank?
(Updated 26 July 2011)
 Statistics:
How can I compute the Chow test statistic?
(Updated 26 July 2011)
 Statistics:
If we change the order of cluster sampling and stratification when sampling
the population, would the svyset command be different?
(Updated 26 July 2011)
 Statistics:
How do I estimate recursive systems using a subset of available instruments?
(Updated 26 July 2011)
 Statistics:
Must I use all of my exogenous variables as instruments when estimating
instrumental variables regression?
(Updated 26 July 2011)
 Statistics:
Why don’t the decomposed variances in xtsum add up?
(Updated 28 June 2007)
 Statistics:
How can I generate a variable relating panel data to a reference panel?
(Updated 28 June 2007)
 Statistics:
How do I obtain bootstrapped standard errors with panel data?
(Updated 26 July 2011)
 Statistics:
Why does clogit sometimes report a coefficient but missing value for the
standard error, confidence interval, etc.?
(Updated 26 July 2011)
 Statistics:
How do I estimate a nonlinear modelusing ml?
(Updated 26 July 2011)
 Data management:
How do I create dummy variables?
(Updated 26 July 2011)
 Data management:
How can I convert other
packages' files to Stata format data files?
(Updated 26 July 2011)
 Resources:
How can I learn more about Stata?
(Updated 26 July 2011)
 Mac:
FAQ overview
(Updated 25 July 2011)
 Mac:
Is Stata compatible with Mac OS X 10.5 (Leopard),
Mac OS X 10.6 (Snow Leopard), and Mac OS X 10.7 (Lion)?
(Updated 25 July 2011)
 Mac:
Why am I unable to copy graphs and
tables from Stata into other applications?
(Updated 25 July 2011)
 Mac:
Starting Stata remotely
(Updated 25 July 2011)
 Mac:
Executing Stata in background (batch) mode
(Updated 25 July 2011)
 Mac:
Starting Stata from a shell
(Updated 25 July 2011)
 Mac:
Will Stata 9 for Mac run on Intel Macs?
(Updated 25 July 2011)
 Unix:
FAQ overview
(Updated 25 July 2011)
 Unix:
How do I run xstata while connected to a Unix
machine from my Windows or Macintosh computer?
(Updated 25 July 2011)
 Windows:
FAQ overview
(Updated 25 July 2011)
 Windows:
How do I install Stata 11 for Windows on a network drive?
(Updated 25 July 2011)
 Windows:
Why is Stata running very slowly?
(Updated 25 July 2011)
 Windows:
How do I run Stata for Windows in
batch mode?
(Updated 25 July 2011)
 Windows:
What kind of machine should I purchase to make Stata run most effectively?
(Updated 25 July 2011)
 Windows:
What are the hardware requirements to run Stata?
(Updated 25 July 2011)
 Data management:
FAQ overview
(Updated 25 July 2011)
 Data management:
How do I deal with multiple responses?
(Updated 25 July 2011)
 Data management:
How do I select a subset of
observations using a complicated criterion?
(Updated 25 July 2011)
 Data management:
Can infile read a hierarchical dataset?
(Updated 25 July 2011)
 Data management:
How
do you efficiently define group characteristics in your data in order to
create subsets?
(Updated 25 July 2011)
 Data management:
How can I generate a variable
containing the last of several dates?
(Updated 25 July 2011)
 Data management:
How can I sample clusters, not individuals?
(Updated 25 July 2011)
 Data management:
How can I list, drop, and keep a
consecutive set of variables without typing the names individually?
(18 March 1997)
 Resources:
How do I cite the Stata software, documentation, and FAQs?
(Updated 25 July 2011)
 Resources:
How do I cite the Stata software, documentation, and FAQs?
(Updated 20 April 2011)
 Web:
Why do I receive the error message “c(showbaselevels) undefined
r(133)” when running an estimation command in Stata 11?
(Added 04 April 2011)
 Mac:
Stata 9: Will Stata 8 for Mac run on Intel Macs?
(Added 19 November 2010)
 Mac:
Stata 8: Will Stata 8 for Mac run natively in OS X?
(Updated 19 November 2010)
 Mac:
Stata 7: Will Stata 7 for Mac run natively in OS X?
(Updated 19 November 2010)
 Statistics:
How can I combine results other than
coefficients in e(b) with multiply imputed data?
(Added 15 October 2010)
 Windows:
How do I get the haver command to run in 64bit Stata
11 on Microsoft Windows?
(Added 07 September 2010)
 Statistics:
How do I fit a bivariate probit
model with partial observability and only one dependent variable?
(Updated 17 August 2010)
 Windows:
How do I load large datasets (>1Gb) under
Windows? I receive an error r(909) saying “op. sys. refuses to provide
memory”.
(Updated 09 August 2010)
 Statistics:
How large should the bootstrapped samples be relative to the total number of cases in the dataset?
(Updated 06 August 2010)
 Resources:
The Statalist FAQ
(Updated 03 June 2010)
 Resources:
When was Stata first released? When were later versions released?
(Updated 03 June 2010)
 Statistics:
Why do I see different pvalues, etc.,
when I change the base level for a factor in my regression?
Why does the pvalue for a term in my
ANOVA not agree with the pvalue for the coefficient for that term in
the corresponding regression?
(Added 24 May 2010)
 Windows: Why do I receive the error r(603) when trying to update Stata running on Vista or Windows 7?
(Updated 05 April 2010)
 Resources:
The Statalist FAQ
(Updated 29 March 2010)
 Statistics:
What is the relation between the official
multipleimputation command, mi, and the communitycontributed ice and mim
commands?
(Added 02 October 2009)
 Windows:
Why do I receive the error “Installation ended prematurely because of
an error” on a Windows Vista machine?
(Added 25 September 2009)
 Resources:
How do I cite the Stata software and FAQs?
(Updated 23 September 2009)
 Programming language:
How do I modify an adofile to support factor variables and the collinearity behavior new to Stata 11?
(Added 13 August 2009)
 Programming language:
Why don’t my communitycontributed estimation commands work in Stata 11 or Stata 12?
(Added 13 August 2009)
 Statistics:
Why do I get an
error message when I try to run a repeated measures ANOVA?
(Updated 11 August 2009)
 Programming language:
Where is my personal ado directory?
(Updated 07 August 2009)
 Programming language:
Where is the official ado directory?
(Updated 07 August 2009)
 Resources:
The Statalist FAQ
(Updated 05 August 2009)
 Statistics:
How do I keep all levels of my categorical variable in my model? How do I specify a cell means model?
(Added 04 August 2009)
 Unix:
How do I install Stata in a directory other than /usr/local/stata?
(Updated 03 August 2009)
 Unix:
64bit AIX installation notes
(Updated 03 August 2009)
 Statistics:
How can I form various tests
comparing the different levels of a categorical variable after anova or
regress?
(Updated 03 August 2009)
 Statistics:
I am using a probit model, and
margins says that my marginal effect is greater than 1. Can that be correct?
(Updated 31 July 2009)
 Unix:
I’m getting the error message “Fontconfig error: Cannot load default config file” when launching Stata. What does that mean?
(Updated 31 July 2009)
 Statistics:
When I use the eyex option of
margins, what is it actually computing and how does it relate to the coefficients
of the loglinear model?
(Updated 31 July 2009)
 Statistics:
Why do estimation commands sometimes omit variables?
(Updated 31 July 2009)
 Statistics:
I am using margins after an
estimation that has timeseries operators in the independent variable list.
How does margins calculate the means of the independent variables?
(Updated 30 July 2009)
 Statistics:
Why doesn't summarize accept
pweights? What does summarize calculate when you use aweights?
(Updated 30 July 2009)
 Statistics:
Is there a way in Stata to do
stepwise regression with svylogit or any of the svy commands?
(Updated 30 July 2009)
 Statistics:
How can I use Stata to calculate
power by simulation?
(Updated 29 July 2009)
 Statistics:
How does the anova command handle collinearity?
(Updated 28 July 2009)
 Statistics:
How do I analyze multiple
failuretime data using Stata?
(Updated 28 July 2009)
 Programming language:
How can I
use Stata to solve a system of nonlinear equations?
(Updated 22 July 2009)
 Resources:
How do I obtain Adobe Reader for viewing Stata’s PDF documentation?
(Added 16 July 2009)
 Resources:
What are the recommended PDF viewer settings for Stata documentation?
(Added 16 July 2009)
 Windows:
How do I install Stata 11 for Windows on a network drive?
(Added 13 July 2009)
 Windows:
How can I install Stata 11 from the command line without GUI under Windows?
(Added 30 June 2009)
 Statistics:
What metaanalysis features are available in Stata?
(Updated 08 April 2009)
 Statistics:
What metaanalysis features are available in Stata?
(Updated 06 March 2009)
 Mac:
How can I determine if my computer/operating system is 64bit?
(Updated 25 February 2009)
 Programming:
I have a certain version of Stata and have come
across a communitycontributed program that is apparently written for a later version
of Stata. What are my options?
(Added 04 February 2009)
 Statistics:
Why does Fisher’s exact test
disagree with the confidence interval for the odds ratio?
(Added 30 January 2009)
 Unix:
How do I run xstata while connected to a Unix
machine from my Windows or Macintosh computer?
(Updated 12 December 2008)
 Resources:
When was Stata first released? When were later versions released?
(Updated 14 August 2008)
 Resources:
The Statalist FAQ
(Updated 14 August 2008)
 Statistics:
How do I fit a regression with interval constraints in Stata?
(Updated 31 July 2008)
 Windows:
How can I determine if my computer/operating system is 64bit?
(Updated 31 July 2008)
 Windows:
How do I run Stata for Windows in
batch mode?
(Updated 02 July 2008)
 Statistics:
Why do I get an
error message when I try to run a repeated measures ANOVA?
(Revised 29 May 2008)
 Mac:
Why am I unable to copy graphs and tables from Stata into other applications?
(Added 23 April 2008)
 Statistics:
Is there a way to estimate a nonlinear combination with nlcom, when the
error “expression too long” is displayed?
(Addd 29 February 2008)
 Mac:
Why does pressing Return after clicking on a variable in the Variables
window sometimes output the variable twice?
(Updated 26 February 2008)
 Resources:
The Stata Journal FAQ
(Updated 05 February 2008)
 Windows:
Why do I get different results when running a ml procedure on Stata/SE and Stata/MP?
(Added 30 January 2008)
 Statistics:
How do I obtain percentiles for survey data?
(Added 10 January 2008)
 Unix:
Why does Stata 10’s graphical user interface
perform so slowly on a Windows X server such as Hummingbird Exceed?
(Added 13 December 2007)
 Unix:
Do you have a version of Stata that runs in a computer cluster environment?
(Added 13 November 2007)
 Unix:
How do I prevent Stata(GUI) from crashing when executed remotely through X11 forwarding?
(Added 29 October 2007)
 Windows:
How do I load large
datasets (>1Gb) under Windows? I receive an error r(909) saying “op. sys.
refuses to provide memory”.
(Updated 23 October 2007)
 Unix:
I’m getting the warning message “Error converting format to locale encoding:
Conversion from character set ‘UTF8' to ‘646’ is not supported” when
launching Stata. What does this mean?
(Added 20 September 2007)
 Mac:
Why does Stata crash when I open the Data Editor in Stata for Macintosh?
(Added 10 September 2007)
 Data management:
How can I apply the original value
and variable labels after using the reshape command?
(Added 30 August 2007)
 Data management:
How do I set up an ODBC Data
Source Name for Stata on Mac or Linux?
(Updated 30 August 2007)
 Unix:
Why is my output not
aligned correctly on Stata for Unix?
(Added 30 August 2007)
 Data management:
How do I convert date variables into Stata elapsed
time when the numbers run together, like “4151999”?
(Updated 30 August 2007)
 Statistics:
What is the relationship between
baseline hazard and baseline hazard contribution?
(Updated 24 August 2007)
 Statistics:
What is the difference between
randomeffects and populationaveraged estimators?
(Updated 09 August 2007)
 Statistics:
What is the difference between
the linear and nonlinear methods that mfx uses?
(Updated 09 August 2007)
 Statistics:
Why does stsum sometimes report
missing values for the percentiles for survival time?
(Updated 09 August 2007)
 Statistics:
How can the standard errors with
the cluster option be smaller than those without the cluster option?
(Updated 08 August 2007)
 Statistics:
How do the ML estimation commands
(e.g., logit and probit) compute the model chisquared test when they estimate
robust standard errors on clustered data?
(Updated 08 August 2007)
 Statistics:
Are the estimates produced by the
probit and logit with the vce(cluster clustvar) option true maximum likelihood estimates?
Is there a difference between the estimates produced by the svy: probit, with psu variable specified in svyset command, and probit, vce(cluster clustvar) (and, similarly, between svy: logit,
with psu variable specified in svyset, and logit vce(cluster clustvar))?
(Updated 08 August 2007)
 Statistics:
Which references should I cite when using the
vce(cluster clustvar) option
to obtain Stata’s clustercorrelated robust estimate of variance?
(Updated 07 August 2007)
 Statistics:
How can I do a Chow test with the
robust variance estimates, that is, after estimating with regress, robust?
(Updated 07 August 2007)
 Statistics:
Why do I obtain different results when executing xttobit on the same data in different sessions?
(Updated 07 August 2007)
 Statistics:
Must I use all of my exogenous variables as instruments when estimating
instrumental variables regression?
(Updated 27 July 2007)
 Statistics:
How do I estimate recursive systems using a subset of available instruments?
(Updated 26 July 2007)
 Windows:
How do I load large
datasets (>1Gb) under Windows? I receive an error r(909) saying “op. sys.
refuses to provide memory”.
(Updated 26 July 2007)
 Windows:
Why do I receive the error “cannot open C:\Program
Files\Stata10\STATA.LIC” on a Windows Vista machine?
(Added 24 July 2007)
 Mac:
Why does clicking on a variable in the Variables window or command in the
Review window sometimes bring the window to the front?
(Added 23 July 2007)
 Mac:
Why does pressing Return after clicking on a variable in the Variables
sometimes output the variable twice?
(Added 23 July 2007)
 Mac:
Why does rightclicking in the Variables or Review window sometimes clear
multiple selections?
(Added 23 July 2007)
 Statistics:
When I run mfx, I am getting the
warning message "warning: predict() expression unsuitable for standard error
calculation. Option nose imposed". What does that mean?
(Updated 23 July 2007)
 Statistics:
How do I obtain bootstrapped standard errors with panel data?
(Updated 20 July 2007)
 Statistics:
How can I get confidence intervals for predicted
probabilities after probit?
(Updated 19 July 2007)
 Statistics:
How can I obtain confidence
intervals for predicted probabilities after logistic regression?
(Updated 19 July 2007)
 Unix:
Why do I receive the error "libtiff.so.3: cannot open" when trying to run Stata on a Linux machine?
(Added 19 July 2007)
 Unix:
How do I run the dynamically linked
version of Stata 10 on Linux?
(Added 02 July 2007)
 Statistics:
How do I estimate a nonlinear model
using ml?
(Updated 29 June 2007)
 Statistics:
How can I generate a variable
relating panel data to a reference panel?
(Updated 28 June 2007)
 Resources:
When was Stata first released? When were later versions released?
(Updated 28 June 2007)
 Windows:
Why do I receive the error "Unable to Locate DLL"
upon launching Stata 10 on Windows 2000?
(Added 27 June 2007)
 Unix:
How do I install 64bit AIX?
(Added 25 June 2007)
 Resources:
How do I cite the Stata software and
FAQs?
(Updated 19 June 2007)
 Graphics:
How do I graph data onto a map with spmap (preferred)?
(Added 04 May 2007)
 Statistics:
How do I fit a linear regression with interval constraints in Stata?
(Updated 13 April 2007)
 Statistics:
How do I calculate row medians?
(Added 26 March 2007)
 Data management:
How do I calculate measures such
as percent improved minus percent deteriorated?
(Updated 26 March 2007)
 Data management:
How can I identify first and last occurrences systematically in panel data?
(Updated 26 March 2007)
 Data management:
How can I drop spells of missing
values at the beginning and end of panel data?
(Updated 26 March 2007)
 Windows: Why do I receive the error r(603) when trying to update Stata running on Vista?
(Added March 2007)
 Data management:
How do I identify neighbors of points or areas on a rectangular grid in Stata?
(Updated March 2007)
 Unix:
How do I install Stata on a Unix/Linux machine?
(Added 19 January 2007)
 Data management:
How do I connect to a database by using a Stata plugin?
(Updated 16 January 2007)
 Statistics:
What metaanalysis features are available in Stata?
(Added 08 January 2007)
 Windows:
How do I load large
datasets (>1Gb) under Windows? I receive an error r(909) saying "op. sys.
refuses to provide memory".
(Updated 11 December 2006)
 Data management:
Why am I
getting an error message that there is "insufficient disk space"?
(Updated 11 December 2006)
 Data management:
How do I connect to a database by using a Stata plugin?
(Added 04 December 2006)
 Mac:
How do I increase the memory
allocated to Stata?
(Added 08 November 2006)
 Statistics:
Which
references should I cite when using the cluster() option to obtain Stata's
clustercorrelated robust estimate of variance?
(Updated 06 November 2006)
 Data management:
How do I identify neighbors of points or areas on a rectangular grid in Stata?
(Updated November 2006)
 Statistics:
How do I fit a linear regression with interval constraints in Stata?
(Added 31 October 2006)
 Statistics:
Why does xtgee sometimes report that convergence was not achieved?
(Added 26 October 2006)
 Data management:
How do I calculate the maximum or minimum seen so far in a sequence?
(Added 19 October 2006)
 Data management:
How do I calculate the number of distinct values seen so far?
(Added 07 September 2006)
 Programming:
Is there any way to get around the 70option limit in
Stata’s syntax command?
(Added 15 August 2006)
 Graphics:
What kind of graphs can I create in Stata?
(Added 21 July 2006)
 Statistics:
The results from estimation commands display only twosided tests for the coefficients. How can I perform a onesided test?
(Added 20 July 2006)
 Unix:
Why does Stata/MP on Solaris cause high CPU usage with the default value of environment variable SUNW_MP_THR_IDLE?
(Added 20 July 2006)
 Mata:
In Stata, can I use Mata matrices that are larger than Stata’s matsize?
(Added 19 July 2006)
 Mata:
How can I perform clustermat on a Mata matrix?
(Added 19 July 2006)
 Mata:
How can I send clustermat a matrix larger than the currently set matsize?
(Added 19 July 2006)
 Windows:
How do I run Stata
remotely on my Windowsbased PC?
(Updated 11 July 2006)
 Windows:
How can I automatically install Stata under Windows?
(Added 10 July 2006)
 Statistics:
If we change the order of cluster sampling and stratification when sampling
the population, would the svyset command be different?
(Added 03 May 2006)
 Graphics:
How do I graph data onto a map with tmap?
(Added 18 April 2006)
 Resources:
When was Stata first released? When were later versions released?
(Added 21 February 2006)
 Resources:
How do I share a new command with Stata users?
(Added 15 February 2006)
 Windows:
What kind of performance increase can I expect in going from 32bit to 64bit Stata?
(Added 15 February 2006)
 Unix:
What kind of performance increase can I expect in going from 32bit to 64bit Stata?
(Added 15 February 2006)
 Data management:
How do I deal with a report of repeated time values within panel?
(Added 20 December 2005)
 Statistics:
How do I obtain bootstrapped standard errors with panel data?
(Added 29 November 2005)
 Graphics:
How can I show scale breaks on graphs?
(Updated 28 November 2005)
 Statistics:
How do I estimate recursive systems using a subset of available instruments?
(Added 22 November 2005)
 Data management:
What are regular expressions and how can I use them in Stata?
(Added 27 October 2005)
 Programming language:
How can I
use Stata to solve a system of nonlinear equations?
(Updated 14 October 2005)
 Statistics:
I am using a probit model, and
mfx says that my marginal effect is greater than 1. Can that be correct?
(Updated 12 October 2005)
 Windows:
How does a Stata network license work?
(Added 4 October 2005)
 Unix:
How does a Stata network license work?
(Added 4 October 2005)
 Mac:
How does a Stata network license work?
(Added 4 October 2005)
 Windows:
What are the hardware requirements to run Stata?
(Updated 4 October 2005)
 Unix:
What are the hardware requirements to run Stata?
(Updated 4 October 2005)
 Mac:
What are the hardware requirements to run Stata?
(Updated 4 October 2005)
 Mata:
How can I calculate the Fourier coefficients of a discretely sampled function in Stata?
(Added 4 October 2005)
 Data management:
How can I create variables containing percent summaries?
(Added 4 October 2005)
 Statistics:
Can I use mfx on survey data with unweighted means?
(Updated 30 September 2005)
 Statistics:
Why should I not do a likelihoodratio test after an ML estimation (e.g.,
logit, probit) with clustering or pweights?
(Updated 30 September 2005)
 Graphics:
How can I best get box plots on logarithmic scales?
(Added 28 September 2005)
 Data management:
How do I remove leading or trailing zeros from string variables?
(Added 20 September 2005)
 Data management:
How do I go through the groups of a variable in order of their first
occurrence in the dataset?
(Added 16 September 2005)
 Data management:
How do I split a string variable
into parts?
(Updated 29 August 2005)
 Data management:
Is there a way to tell Stata to try all values of a particular variable in a foreach statement without specifying them?
(Updated 25 August 2005)
 Statistics:
How large should the bootstrapped samples be relative to the total number of cases in the dataset?
(Updated 15 August 2005)
 Statistics:
Can you explain Chow tests?
(Updated 10 August 2005)
 Statistics:
How can I pool data (and perform Chow tests) in linear regression without
constraining the residual variances to be equal?
(Updated 03 August 2005)
 Statistics:
Must I use all of my exogenous variables as instruments when estimating instrumental variables regression?
(Updated 28 July 2005)
 Statistics:
How can I compute the Chow test statistic?
(Updated 28 July 2005)
 Statistics:
How does Stata's implementation of GEE differ from other implementations?
(Updated 25 July 2005)
 Statistics:
Why do I obtain different results when executing xttobit on the same data in different sessions?
(Updated 25 July 2005)
 Statistics:
How do I get a bootstrap vector of results?
(Updated 22 July 2005)
 Statistics:
Is my boss correct in saying that the pvalue given with a paired ttest should always be lower than the signrank?
(Updated 22 July 2005)
 Statistics:
Why does bootstrap give a warning message for noneclass commands?
(Updated 05 July 2005)
 Statistics:
How do you test the equality of regression coefficients that are generated
from two different regressions, estimated on two different samples?
(Updated 01 July 2005)
 Windows:
How can I determine if my computer/operating system is 64bit?
(Added 27 June 2005)
 Unix:
How can I determine if my computer/operating system is 64bit?
(Added 27 June 2005)
 Mac:
How can I determine if my computer/operating system is 64bit?
(Added 27 June 2005)
 Statistics:
When I run mfx, I am getting the error message "Predict option unsuitable for marginal effects". What does that mean?
(Updated 15 February 2005)
 Resources:
The Statalist FAQ
(Updated 06 December 2004)
 Data management:
How do I export tables from Stata?
(Added 03 December 2004)
 Windows:
How do I install Stata for Windows on a network drive?
(Updated 02 December 2004)
 Programming language:
How do I process parallel lists?
(Updated 01 December 2004)
 Statistics:
Which
references should I cite when using the cluster() option to obtain Stata's
clustercorrelated robust estimate of variance?
(Updated 11 November 2004)
 Web:
What does the error r(?) mean when I try to connect to the Internet from
within Stata?
(Added 15 November 2004)
 Statistics:
Why do I get an "unbalanced data" error message when I run nlogit?
(Added 13 October 2004)
 Data management:
How do I identify neighbors of points or areas on a rectangular grid in Stata?
(Added 11 October 2004)
 Statistics:
When I run mfx, I am getting
the warning message "warning: Derivative missing. Try rescaling variable mpg".
What does that mean?
(Updated 17 September 2004)
 Statistics:
I am using a model with
interactions. How can I obtain marginal effects and their standard
errors?
(revised 13 August 2004)
 Statistics:
How do you fit
a model when the dependent variable is a proportion?
(Updated 04 August 2004)
 Windows:
What kind of machine should I purchase to make Stata run most effectively?
(Added 30 July 2004)
 Data management:
How do I count the number of distinct strings across a set of
variables?
(Added 30 July 2004)
 Windows:
How do I get the Review
and Variables windows to behave as they did before?
(Added 30 July 2004)
 Statistics:
I am using a model with
interactions. How can I obtain marginal effects and their standard
errors?
(Added 18 May 2004)
 Statistics:
When I use the eyex option of
mfx, what is it actually computing and how does it relate to the coefficients
of the loglinear model?
(revised 18 May 2004)
 Data management:
Can I use ODBC to write to an
existing Excel file?
(Added 08 April 2004)
 Statistics:
I am using a probit model, and
mfx says that my marginal effect is greater than 1. Can that be correct?
(Added 06 April 2004)
 Statistics:
I need to run mfx more than
once on my dataset, and it's taking a long time. What can I do to make it run
as fast as possible?
(Added 06 April 2004)
 Statistics:
Can I use mfx on survey data with
unweighted means?
(Added 06 April 2004)
 Statistics:
What is the eyex option of mfx
actually computing?
(Added 06 April 2004)
 Statistics:
What does the nodrop option do
in mfx?
(Added 06 April 2004)
 Statistics:
I am using mfx after an
estimation that has an offset. How does mfx take that into account?
(Added 06 April 2004)
 Statistics:
Running mfx on my dataset takes
a long time, and I am worried it may have crashed. How can I tell if it is
still running?
(Added 06 April 2004)
 Statistics:
I am only interested in obtaining a
few of the marginal effects for a few independent variables. How can I do
that?
(Added 06 April 2004)
 Statistics:
When I run mfx, I am getting the
warning message "warning: predict() expression unsuitable for standard error
calculation. Option nose imposed". What does that mean?
(Added 06 April 2004)
 Statistics:
When I run mfx, I am getting
the error message "Predict option unsuitable for marginal effects". What does
that mean?
(Added 06 April 2004)
 Statistics:
When I run mfx, I am getting
the warning message "warning: Derivative missing. Try rescaling variable mpg".
What does that mean?
(Added 24 March 2004)
 Statistics:
What is the difference between
the linear and nonlinear methods that mfx uses?
(Added 24 March 2004)
 Statistics:
How do I fit a bivariate probit
model with partial observability and only one dependent variable?
(Added 18 March 2004)
 Windows:
How much memory does your computer
need to run Stata for Windows?
(Added 18 March 2004)
 Programming language:
How do I assign multiple
backslash characters to macros in Stata?
(Added 18 March 2004)
 Data management:
How do I identify leap years in
Stata?
(Added 23 January 2004)
 Data management:
I am having problems with the
reshape command. Can you give further guidance?
(Updated 17 December 2003)
 Data management:
Why do I get rows of missing
data when I use infile?
(Added 11 December 2003)
 Statistics:
How do I test for panellevel
heteroskedasticity and autocorrelation?
(revised 09 December 2003)
 Statistics:
How do I get the
Euler–Mascheroni constant gamma = 0.57721 ... in Stata?
(Added 02 December 2003)
 Statistics:
How can I get an
Rsquared value when a Stata command does not supply one?
(Added 24 September 2003)
 Data management:
How can I replace missing values
with previous or following nonmissing values or within sequences?
(revised 19 September 2003)
 Statistics:
How can you specify a term
other than residual error as the denominator in a single degreeoffreedom
F test after ANOVA?
(revised 10 September 2003)
 Statistics:
How can I form various tests
comparing the different levels of a categorical variable after anova or
regress?
(revised 10 September 2003)
 Graphics:
How can I get
"nice" date labels on a graph?
(revised 03 September 2003)
 Graphics:
How can I get
"nice" time of day labels on a graph?
(revised 03 September 2003)
 Programming language:
New Dialog FAQs section
(Added 14 August 2003)
 Graphics:
How can I get
a histogram with varying bin widths?
(Added 10 June 2003)
 Data management:
How can I convert other
packages' files to Stata format data files?
(Added 14 May 2003)
 Programming language:
What can
you tell me about the Windows 98 operating system and dialogs?
(Added 05 May 2003)
 Programming language:
What can you tell me about using the
.idlg files that are written by StataCorp and used in their dialogs?
(Added 05 May 2003)
 Programming language:
How can I take care of
prerequisites in dialog boxes?
(Added 05 May 2003)
 Programming language:
What can you tell me about using
the .idlg files that are written by StataCorp and used in their graphics
dialogs?
(Added 05 May 2003)
 Statistics:
Why does xtgls not report an
Rsquared statistic?
(Added 24 April 2003)
 Data management:
How do I set up an ODBC Data
Source Name for Stata on Mac or Linux?
(Added 15 April 2003)
 Data management:
Is there a way to tell Stata to
try all values of a particular variable in a foreach statement without
specifying them?
(Added 7 April 2003)
 Data management:
Why doesn't
the destring command in Stata include an encode option?
(revised 31 March 2003)
 Graphics:
How can I get
"nice" time of day labels on a graph?
(Added 27 February 2003)
 Statistics:
Why do I get an
error message when I try to run a repeated measures ANOVA?
(revised 20 February 2003)
 Data management:
Why am I
getting an error message that there is "insufficient disk space"?
(Added 20 February 2003)
 Statistics:
Which
references should I cite when using the cluster() option to obtain Stata's
clustercorrelated robust estimate of variance?
(Added 12 February 2003)
 Statistics:
How do I
bootstrap a vector of results?
(Added 11 February 2003)
 Resources:
The Statalist FAQ
(Updated 6 February 2003)
 Mac:
Will Stata 8 for
Macintosh run natively in OS X?
(Updated 27 January 2003)
 Mac:
Setting the default
endofline delimiter
(Added 27 January 2003)
 Mac:
Executing Stata in
background (batch) mode
(Added 27 January 2003)
 Mac:
Advanced starting of
Stata
(Added 27 January 2003)
 Mac:
How do I increase the memory
allocated to Stata?
(Updated 27 January 2003)
 Mac:
Stata is displaying graphs
using the old scheme even though the setting is for the new scheme.
(Added 27 January 2003)
 Data management:
I want to calculate a variable
containing weighted group summary statistics, but I do not want to collapse
the data and egen does not support weights. How can I do this?
(Added 24 January 2003)
 Statistics:
For twostage least squares
(2SLS/IV/ivreg) estimates, why is the Rsquared statistic not printed in some
cases? For twostage least squares (2SLS/IV/ivreg) estimates, why is the
Model Sum of Squares sometimes negative? For threestage least squares
(3SLS/reg3) estimates, why are the Rsquared and Model Sum of Squares
sometimes negative?
(Updated 20 January 2003)
 Data management:
How do I deal with multiple
responses?
(Added 15 January 2003)
 Statistics:
What are the differences between
predict and adjust?
(Added 25 September 2002)
 Data management:
How can I collapse my dataset
and keep the same variable labels?
(Added 25 September 2002)
 Data management:
How do I identify runs of
consecutive observations in panel data?
(Added 20 August 2002)
 Programming language:
How do I signal that there are
alternative types of arguments to program options?
(Added 20 August 2002)
 Data management:
How do I select a subset of
observations using a complicated criterion?
(Added 25 July 2002)
 Statistics:
How can I generate a variable
relating panel data to a reference panel?
(Added 18 July 2002)
 Statistics:
What do I do when one of the
survey estimators returns an error message, "stratum with only one PSU
detected"?
(Added 12 July 2002)
 Statistics:
Is there any
difference between using tsset and iis and tis before xt commands?
(Added 12 July 2002)
 Statistics:
How can I calculate percentile
ranks?
How can I
calculate plotting positions?
(Added 10 July 2002)
 Graphics:
How can I get "nice" date
labels on a graph?
(Added 11 June 2002)
 Data management:
How can I save one or more parts
of a large dataset?
(Added 31 May 2002)
 Windows:
Why will the new executable not
work after I updated Stata? Why is the old executable (wstata.old) still
running after I updated the executable?
(Updated 17 May 2002)
 Data management:
Each morning I have to set my
memory size to, say, 20m. The default, 1m, is not sufficient for my data. Is
there a way of changing the default setting?
(Added 19 March 2002)
 Data management:
How do I compute the number of
distinct observations?
(Added 28 February 2002)
 Statistics:
Why do I sometimes get negative
eigenvalues when using the pf and ipf options of factor?
(Added 25 February 2002)
 Statistics:
Why does the cumulative
proportion of variance sometimes exceed 1 when using the pf and ipf options of
factor?
(Added 25 February 2002)
 Data management:
How do I tabulate cumulative
frequencies?
(Added 25 February 2002)
 Statistics:
How do I calculate least square
means in Stata?
(Added 14 February 2002)
 Statistics:
How do I estimate a nonlinear model
using ml?
(Added 14 February 2002)
 Programming language:
What is the difference between a
release marker and a version number in an adofile?
(Added 25 January 2002)
 Windows:
How can I convert a Stata graph
to .wmf (Windows metafile) format and preserve the color?
(Added 4 January 2002)
 Data management:
How do you
process very large datasets in Stata?
(Added 3 January 2002)
 Statistics:
Can you explain
Chow tests?
(Added 2 January 2002)
 Resources:
I see references to
the findit and ssc commands on Statalist, but my Stata does not recognize
these commands. What should I do?
(Added 17 December 2001)
 Windows:
Why can't I
click in Stata's Command Window in Windows 2000/XP?
(Updated 12 December 2001)
 Statistics:
How can I
calculate moving averages for panel data?
(Added 12 December 2001)
 Data management:
How
do you efficiently define group characteristics in your data in order to
create subsets?
(Added 05 December 2001)
 Statistics:
How do I
impose the restriction that rho is zero using the heckman command with full
ml?
(Added 29 November 2001)
 Unix:
How do I display graphs while
connected to a Unix machine from my Windows or Macintosh computer?
(Updated 27 November 2001)
 Resources:
The Statalist FAQ
(Updated 27 November 2001)
 Statistics:
How can I use Stata to calculate
power by simulation?
(Added 19 November 2001)
 Statistics:
How large should the bootstrapped
samples be relative to the number of cases in the dataset?
(Added 16 November 2001)
 Statistics:
How can I estimate
correlations and their level of significance with survey data?
(Added 15 November 2001)
 Data management:
How do I list observations in a
group that differ on a variable?
(Added 7 November 2001)
 Graphics:
How can I show scale breaks
on graphs?
(Added 2 November 2001)
 Statistics:
How do I calculate values of the
beta function?
(Added 2 November 2001)
 Data management:
I am having problems with the
reshape command. Can you give further guidance?
(Updated 2 November 2001)
 Data management:
How do I split a string variable
into parts?
(Added 25 October 2001)
 Statistics:
How do you specify the variance
function in nbreg to coincide with Cameron and Trivedi's (Regression analysis
of count data, page 62) NB1 and NB2 variance functions?
(Added 23 October 2001)
 Statistics:
What is the
difference between the models fit using nbreg, dispersion(mean) and nbreg,
dispersion(constant)?
(Added 23 October 2001)
 Data management:
How can
I put the current date and time in my log files?
(Updated 23 October 2001)
 Graphics:
How do I make my graphs come
out square?
(Added 22 October 2001)
 Data management:
How do I
perform multiple operations on data records if a condition is met?
(Added 22 October 2001)
 Statistics:
What is the difference between
‘endogeneity’ and ‘sample selection bias’?
(Added 16 October 2001)
 Data management:
What is
true and false in Stata?
(Added 16 October 2001)
 Windows:
How do I load large
datasets (>1Gb) under Windows? I receive an error r(909) saying "op. sys.
refuses to provide memory".
(Added 11 October 2001)
 Statistics:
What is the relationship between
baseline hazard and baseline hazard contribution?
(Added 11 October 2001)
 Data management:
Stata is
reading in my variables as string, whereas they should be numeric. What should
I do?
(Added 11 October 2001)
 Statistics:
How can I calculate the pseudo
R^{2} for xtprobit?
(Added 2 October 2001)
 Resources:
The Statalist FAQ
(Updated 27 September 2001)
 Statistics:
Is it possible
to include a constant term (intercept) in ordered probit model within Stata?
What is the relationship between ordered probit and probit?
(Added 20 September 2001)
 Unix:
Why won't Stata allow large
datasets even when I am using a 64bit Irix machine?
(Added 18 September 2001)
 Unix:
The Stata 7
installation requires uncompress, but on Mandrake 8, uncompress is not
installed. How do I install it?
(Added 18 September 2001)
 Data management:
I am having
problems with the reshape command. Can you give further guidance?
(Added 11 September 2001)
 Mac:
Will Stata for
Macintosh run natively in OS X?
(Updated 28 August 2001)
 Statistics:
How does one
estimate a model when the dependent variable is a proportion?
(Added 21 August 2001)
 Data management:
Is there a way to tell Stata to try
all values of a particular variable in a for statement without specifying
them?
(Added 16 August 2001)
 Statistics:
Why does bs now give a warning
message for noneclass commands?
(Added 16 August 2001)
 Statistics:
Does Stata support any multiple
comparison tests following twoway ANOVA?
(Added 07 August 2001)
 Statistics:
How can you
specify a term other than residual error as the denominator in a single
degreeoffreedom F test after ANOVA?
(Added 07 August 2001)
 Data management:
How do I
perform elementbyelement operations on matrices?
(Added 27 July 2001)
 Data management:
How do I produce a dataset based on
all possible pairs of identifiers within each group?
(Added 18 July 2001)
 Resources:
The Stata Journal FAQ
(Added 28 June 2001)
 Statistics:
How do I test for panellevel
heteroskedasticity?
(Added 28 June 2001)
 Programming language:
How can I
use Stata to solve a system of nonlinear equations?
(Added 28 June 2001)
 Data management:
How do I
get information from Excel into Stata?
(Updated 15 June 2001)
 Data management:
How do I create variables
summarizing for each individual properties of the other members of a
group?
(Added 22 May 2001)
 Statistics:
I am only interested
in obtaining a few of the marginal effects for a few independent variables.
How can I do that?
(Added 21 May 2001)
 Statistics:
How does mfx
calculate the marginal effects of dummy variables?
(Added 21 May 2001)
 Statistics:
When do I need to
specify the nonlinear option with mfx?
(Added 21 May 2001)
 Statistics:
I am not interested
in the standard errors of the marginal effects. Can mfx display only the
marginal effects?
(Added 21 May 2001)
 Data management:
How many significant digits are
there in a float?
(Added 11 May 2001)
 Data management:
Why does the mod(x,y) function
sometimes give puzzling results? Why is mod(0.3,0.1) not equal to 0?
(Added 25 April 2001)
 Programming language:
Why does
a program defined by an adofile sometimes not work when given a string
comparison?
(Added 25 April 2001)
 Windows:
Memory reference
errors and Windows crashes
(Added 19 April 2001)
 Statistics:
How should I
interpret changing quadchk results?
(Added 19 April 2001)
 Data management:
Why doesn't
the destring command in Stata include an encode option?
(Added 16 April 2001)
 Statistics:
How do you test
the equality of regression coefficients that are generated from two different
regressions, estimated on two different samples?
(Added 12 April 2001)
 Statistics:
Where can I find a
description of the various timeseries operators?
(Added 12 April 2001)
 Statistics:
How do I get
the correct variance–covariance matrix from the bs routine?
(Added 12 April 2001)
 Mac:
When will Stata for OS X be available,
and how much will it cost?
(Added 3 April 2001)
 Statistics:
How do I obtain the standard error
of the predicted probability with logistic regression analysis?
(Added 22 March 2001)
 Statistics:
How can I obtain the standard error
of the regression with streg?
(Added 12 March 2001)
 Statistics:
How can I produce adjusted means
after ANOVA?
(Added 08 March 2001)
 Statistics:
Why are observations that are
noninformative about the dependent variable, but are known to be selected,
excluded by heckman from the estimation sample?
(Added 08 March 2001)
 Statistics:
What are some of
the small sample adjustments to the sandwich estimate of variance?
(Added 08 March 2001)
 Statistics:
Why do I obtain
different results when executing xttobit on the same data in different
sessions?
(Added 08 March 2001)
 Statistics:
What is the between
estimator?
(Added 08 March 2001)
 Programming language:
How can I automatically execute
certain commands every time I start Stata?
(Added 08 March 2001)
 Programming language:
Why do I get puzzling results with
the for command and local or global macros?
(Added 08 March 2001)
 Windows:
How do I run Stata for Windows in
batch mode?
(Added 08 March 2001)
 Resources:
How can I download and install the
StataQuest menu additions to Stata 7?
(Added 02 March 2001)
 Mac:
My computer crashes during
installation.
I'm getting a "Type 1" or "Type 11" error.
(Added 02 March 2001)
 Statistics:
How do you compute marginal
effects after ologit/oprobit/mlogit using mfx?
(Added 07 February 2001)
 Statistics:
How can I take random samples
from an existing dataset?
(Updated 11 December 2000)
 Resources:
The Statalist FAQ
(Updated 5 October 2000)
 Graphics:
How can I create a pie or
bar chart containing categorical data?
(Added 30 August 2000)
 Data management:
How can I replace missing values
with previous or following nonmissing values?
(Added 23 August 2000)
 Data management:
Why can't I compare two values that
I know are equal?
(Added 27 July 2000)
 Statistics:
Must I use all of my exogenous
variables as instruments when estimating instrumental variables
regression?
(Added 21 July 2000)
 Graphics:
How do I make a frequency
plot using Stata?
(Added 20 July 2000)
 Data management:
How can I put the current
date and time in my log files?
(Added 28 June 2000)
 Data management:
How can I replace an
observation of a variable with a different observation for another
variable?
(Added 28 June 2000)
 Data management:
Why do I get the error message
"no room to add more observations"?
(Added 28 June 2000)
 Programming:
I have an if command in my
program that only seems to evaluate the first observation, what's going
on?
(Added 28 June 2000)
 Windows:
What hardware specifications does
Stata recommend for my computer?
(Added 28 June 2000)
 Windows:
How do I install Stata on a
Windows network?
(Added 27 June 2000)
 Windows:
How can I edit a Stata graph in
MS Word?
(Added 2 June 2000)
 Resources:
The Statalist FAQ
(Updated 24 May 2000)
 Windows:
Clicking on large datasets
(14 April 2000)
 Statistics:
What are the divisors used in
xtgee?
(24 March 2000)
 Statistics:
How are estimates of rho
outside the bounds [1,1] handled in the twostep Heckman estimator?
(9 March 2000)
 Resources:
The Statalist FAQ
(Updated 9 March 2000)
 Windows:
I just updated my executable but
the old executable (wstata.old) is still running.
(2 March 2000)
 Resources:
How can I download and install the
StataQuest menu additions to Stata?
(23 February 2000)
 Statistics:
Why do I get an error message when
I try to run a repeated measures ANOVA?
(23 February 2000)
 Data management:
I cannot use the by command with
the command I need. Is there anything I can do instead?
(17 February 2000)
 Data management:
Why am I getting a message that
there is no room on my hard drive?
(8 February 2000)
 Programming:
Why does my dofile or adofile
produce different results every time I run it?
(7 February 2000)
 Internet:
How can I obtain update
information from the Internet at work and put it on diskette to update my
computer at home?
(20 January 2000)
 Resources:
The Statalist FAQ
(Updated 14 January 2000)
 Statistics:
How can I do logistic regression
or multinomial logistic regression with grouped data?
(Updated 14 January 2000)
 Data management:
How do I create a variable that
contains a repeating sequence of numbers?
(22 December 1999)
 Data management:
How do I convert date variables
into Stata elapsed time when the numbers run together, like "4151999"?
(22 December 1999)
 Graphics:
How can I change the format
of data for my axes?
(14 December 1999)
 Statistics:
How can I pool data (and perform
Chow tests) in linear regression without constraining the residual variances
to be equal?
(10 December 1999)
 Programming:
Why is post giving a syntax
error?
(3 December 1999)
 Programming:
I coded 'a'^2 and got the wrong
sign. Why?
(3 December 1999)
 Programming:
How do I remove collinear
variables from a varlist
(3 December 1999)
 Statistics:
How can I estimate stepwise Cox
models?
(2 December 1999)
 Statistics:
What is the delta method and how
is it used to estimate the standard error of a transformed parameter?
(2 December 1999)
 Statistics:
How can I obtain the correlation
matrix as a Stata matrix?
(2 December 1999)
 Programming:
How do I add an observation to a dataset when
coding an adofile?
(2 December 1999)
 Data management:
Is there a way to put leading
zeros in output?
(2 December 1999)
 Data management:
How big will my dataset be?
(2 December 1999)
 Data management:
How do I create individual
identifiers numbered from 1 upwards?
(1 December 1999)
 Statistics:
How can I estimate a
fixedeffects regression with instrumental variables?
(30 November 1999)
 Technical support:
Contacting Stata Technical
Support
(Updated 19 November 1999)
 Statistics:
Why does clogit sometimes report
a coefficient but missing value for the standard error, confidence interval,
etc.?
(19 November 1999)
 Statistics:
Why is there no intercept in the
clogit model?
(19 November 1999)
 Statistics:
In clogit, why can't I use
covariates that are constant within panel?
(19 November 1999)
 Resources:
New category
(12 November 1999)
 Resources:
How do I cite the Stata software and
FAQs?
(12 November 1999)
 Resources:
How can I learn more about
Stata?
(12 November 1999)
 Resources:
Are there courses on Stata?
(12 November 1999)
 Resources:
What are Stata NetCourses?
(12 November 1999)
 Resources:
Are there books on Stata?
(12 November 1999)
 Resources:
Are there Stata user groups or
meetings?
(12 November 1999)
 Data management:
How do I get information from
Excel into Stata?
(11 November 1999)
 Statistics:
How do I convert my spelltype
data into a survival dataset? How do I stset my spelltype data?
(4 November 1999)
 Statistics:
How do I analyze multiple
failuretime data using Stata?
(4 November 1999)
 Statistics:
How do I test endogeneity?
How do I perform a Durbin–Wu–Hausman test?
(2 November 1999)
 Data management:
How do I create a variable
recording whether any member of a group (or all members of a group) possess
some characteristic?
(26 October 1999)
 Data management:
How can I create a dataset
(matrix) of means (other stats) of variables from the current dataset?
(25 October 1999)
 Statistics:
Why do stcox and cox sometimes
produce missing standard errors?
(21 October 1999)
 Statistics:
How can I form various tests
comparing the different levels of a categorical variable after anova or
regress?
(18 October 1999)
 Graphics:
How many items can be
identified in the legend?
(18 October 1999)
 Statistics:
How are the standard errors
and confidence intervals computed for relative risk ratios (RRRs) by
mlogit?
(8 October 1999)
 Statistics:
How are the standard errors
and confidence intervals computed for odds ratios (ORs) by logistic?
(8 October 1999)
 Statistics:
How are the standard errors
and confidence intervals computed for hazard ratios (HRs) by stcox and
streg?
(8 October 1999)
 Programming:
Why do some nested for commands
produce an error?
(28 September 1999)
 Windows:
How do I save a .wmf file in
color?
(15 September 1999)
 Statistics:
How does xtgls differ from
regression clustered with robust standard errors?
(25 August 1999)
 Statistics:
How can I convert Stata's
parameterization of ordered probit and logistic models to one in which a
constant is estimated? Why is there no constant term reported in ologit and
oprobit?
(25 August 1999)
 Windows:
Stata will not save my
preferences under Windows NT. How can I save my windows preferences in
Windows NT?
(17 August 1999)
 Unix:
How do I get around the "device
busy" error while installing Stata on Solaris?
(17 August 1999)
 Data management:
How can I save a Stata 6 dataset
so that it can be read in Stata 5?
(10 August 1999)
 Statistics:
How can I do a Chow test with the
robust variance estimates, that is, after estimating with regress, robust?
(23 July 1999)
 Statistics:
Why does test sometimes produce
chisquared and other times F statistics? How are the chisquared and F
distributions related?
(23 July 1999)
 Statistics:
Why does stsum sometimes report
missing values for the percentiles for survival time?
(23 July 1999)
 Statistics:
Why are there so many formulas
for the inverse of Mills' ratio? What if I have censoring from above/below in
my Heckman selection model?
(26 May 1999)
 Internet:
Why can my browser reach sites on
the web but Stata can't?
(27 April 1999)
 Statistics:
For twostage least squares
(2SLS/IV/ivreg) estimates, why is the Rsquared statistic not printed in some
cases? For twostage least squares (2SLS/IV/ivreg) estimates, why is the
Model Sum of Squares sometimes negative? For threestage least squares
(3SLS/reg3) estimates, why are the Rsquared and Model Sum of Squares
sometimes negative?
(20 April 1999)
 Windows:
Help stopped working; how do I fix
it?
(19 April 1999)
 Statistics:
Why do Stata's xtgee standard
errors differ from those reported by SAS's PROC GENMOD?
(19 April 1999)
 Statistics:
How can I obtain confidence
intervals for predicted probabilities after logistic regression?
(19 April 1999)
 Technical support:
New category
(16 April 1999)
 Statistics:
How can I obtain the
correlation between the factors after an oblique rotation?
(9 April 1999)
 Statistics:
Why does xtreg with the mle
option produce different results from xtreg with only the re option?
(6 April 1999)
 Unix:
How do I read data from a pipe?
(15 March 1999)
 Data management:
How do I accumulate the results
of immediate commands?
(12 March 1999)
 Unix:
Why does the cpio command
not work under Red Hat 5.2?
(10 March 1999)
 Statistics:
What is the difference between
randomeffects and populationaveraged estimators?
(13 January 1999)
 Statistics:
What is the difference between
biprobit/heckprob and the STB commands?
(13 January 1999)
 Statistics:
How can I fit an extreme value or
gompit regression?
(13 January 1999)
 Statistics:
How does Stata's xtgee handle
singletons with exchangeable correlation?
(13 January 1999)
 Statistics:
Where are the Wald tests for zinb that appear in the manual?
(13 January 1999)
 Statistics:
What are completely determined
panels?
(13 January 1999)
 Statistics:
Can Stata estimate a Rasch
model?
(05 January 1999)
 Statistics:
How can the standard errors with
the cluster option be smaller than those without the cluster option?
(24 July 1998)
 Statistics:
Why does Weibull with entry and
exit times produce different results from Weibull with duration?
(8 July 1998)
 Data management:
How do I implement SASlike ARRAYs
in Stata?
(23 June 1998)
 Statistics:
Why do Stata and SAS differ in
the results that they report for the stratified Generalized Wilcoxon Test for
timetoevent data?
(4 June 1998)
 Statistics:
How can I do logistic regression
or multinomial logistic regression with grouped data?
(4 June 1998)
 Statistics:
How can I get predicted
probabilities after svylogit, svyprobt, svymlog, svyolog, or svyoprob?
(4 June 1998)
 Statistics:
Is it possible to analyze survey data
with two or more levels of clustering with the svy commands?
(7 May 1998)
 Statistics:
What are some of the problems
with stepwise regression?
(7 May 1998)
 Statistics:
For twostage least squares (2SLS)
estimates, why is the Rsquared statistic not printed in some cases?
(Updated 28 April 1998)
 Statistics:
Do the svy commands handle zero
weight differently than nonsvy commands do?
(28 April 1998)
 Statistics:
Why do Stata's cc and cci commands
report different confidence intervals than Epi Info?
(22 April 1998)
 Data management:
The updated (28 Jan 1998)
reshape command
(21 April 1998)
 Data management:
Why does reshape give a
toomanyvariables error?
(21 April 1998)
 Graphics:
How do I connect points only
within groups?
(23 March 1998)
 Windows:
Why does Windows 95 seem to be
swapping even though I haven't allocated all available memory to Stata?
(19 February 1998)
 Statistics:
What are the advantages of
using the robust variance estimator over the standard maximumlikelihood
variance estimator in logistic regression?
(26 January 1998)
 Statistics:
Are the estimates produced by the
probit and logit with the cluster() option true maximum likelihood estimates?
Is there a difference between the estimates produced by the svyprobt, psu()
command and probit, cluster() (and, similarly, between svylogit, psu() and
logit, cluster())?
(18 December 1997)
 Graphics:
How do I join paired points
on a graph?
(19 November 1997)
 Statistics:
Why were the timings in the
American Statistician (August 1997) review of the svy commands so slow?
(23 October 1997)
 Statistics:
How can there be an intercept in
the fixedeffects model estimated by xtreg, fe?
(23 October 1997)
 Data management:
How do I identify duplicate
observations in my data?
(15 October 1997)
 Windows:
Stata is crashing —
Do you have a Logitech mouse?
(12 September 1997)
 Windows:
How do I create a Postscript
(or EPS) file of my graphs?
(27 August 1997)
 Statistics:
Is it possible to analyze survey data
with two or more levels of clustering with the svy commands?
(15 August 1997)
 Statistics:
Why should I not do a
likelihoodratio test after an ML estimation (e.g., logit and probit) with
clustering or pweights?
(15 August 1997)
 Statistics:
How do the ML estimation commands
(e.g., logit and probit) compute the model chisquared test when they estimate
robust standard errors on clustered data?
(15 August 1997)
 Statistics:
Can Stata's ML routine converge and
produce answers that look good even when it shouldn't?
(15 August 1997)
 Unix:
I am having trouble running Stata
for Linux on my Linux computer. What is wrong?
(18 July 1997)
 Data management:
How can I produce a tabulation
of a string variable that is listed in logical rather than alphabetical
order?
(4 July 1997)
 Statistics:
Why does the goodnessoffit
chisquared test reported by poisson change when the counts and exposures are
grouped differently?
(4 July 1997)
 Mac:
My computer crashes during
the installation.
(10 June 1997)
 Windows:
Stata is crashing  Do you
have a Toshiba laptop?
(9 June 1997)
 Statistics:
Why is the pseudoR^2 for tobit
negative or greater than one?
(9 June 1997)
 Statistics:
What is the effect of specifying
aweights with regress or fit?
(5 June 1997)
 Statistics:
In ordered probit and logit, what
are the cut points?
(3 June 1997)
 Statistics:
How can I compute the Chow test
statistic?
(30 May 1997)
 Statistics:
Why do I get the message "outcome does not vary" when I perform a logistic or
logit regression?
(7 May 1997)
 Data management:
I am having trouble converting a
SAS dataset to a Stata dataset using Stat/Transfer. What is wrong?
(11 April 1997)
 Data management:
Why do I get the error
"wrong number of values" when I use insheet to read
data from Excel?
(9 April 1997)
 Data management:
How do I create dummy
variables?
(25 March 1997)
 Statistics:
What is the difference between sts
list and ltable?
(24 March 1997)
 Statistics:
Is my boss correct in saying
that the pvalue given with a paired ttest should always be lower than the
signrank?
(24 March 1997)
 Statistics:
How does the anova command handle
collinearity?
(24 March 1997)
 Statistics:
What is the pseudo R2 in the weibull
output?
(24 March 1997)
 Statistics:
"I am running clogit and get the
message Note: multiple positive outcomes within groups
encountered. Is this something I should worry about or is this a
normal message?"
(24 March 1997)
 Statistics:
Why can't a subject die at time
0? Why can't a subject enter and die at the same time in Cox?
(18 March 1997)
 Windows:
I just installed Stata 5.0
for Windows, but I used only two of the three disks. What is wrong?
(18 March 1997)
 Programming:
I just downloaded and installed an
adofile from an early STB (before STB7), and I am having trouble running it.
What's wrong?
(18 March 1997)
 Data management:
Why is x>1000 true when x
contains missing values?
(18 March 1997)
 Data management:
Can I apply the label values
command to more than one variable at once? I want to attach the same value
labels to several variables.
(18 March 1997)
 Statistics:
Is there a nested logit
command?
(18 March 1997)
 Statistics:
For twostage least
squares (2SLS) estimates, why is the Rsquared statistic not printed out in
some cases?
(17 March 1997)
 Data management:
Is there any direct way to save
into a new variable the frequencies obtained by applying the command
tabulate?
(17 March 1997)
 Statistics:
How do I estimate a Cox model with
timevarying parameters?
(25 February 1997)
 Statistics:
Why don't the old huber results
match the new robust versions?
(25 February 1997)
 Statistics:
How can I get robust standard
errors for tobit?
(25 February 1997)
 Statistics:
What roles does the time variable
play in xtgls?
(25 February 1997)
 Statistics:
How does Stata's implementation of
GEE differ from other implementations?
(25 February 1997)
 Statistics:
Why must weights be constant
within panel for xtgee?
(25 February 1997)