**[MI] mi estimate using** -- Estimation using previously saved estimation
results

__Syntax__

Compute MI estimates of coefficients using previously saved estimation
results

**mi** __est__**imate** **using** *miestfile* [**,** *options*]

Compute MI estimates of transformed coefficients using previously saved
estimation results

**mi** __est__**imate** [*spec*] **using** *miestfile* [**,** *options*]

where *spec* may be one or more terms of the form **(**[*name***:**] *exp***)**. *exp* is
any function of the parameter estimates allowed by **nlcom**.

*miestfile***.ster** contains estimation results previously saved by **mi**
**estimate, saving(***miestfile***)**; see **[MI] mi estimate**.

*options* Description
-------------------------------------------------------------------------
Options
__ni__**mputations(***#***)** specify number of imputations to use;
default is to use all existing
imputations
__i__**mputations(***numlist***)** specify which imputations to use
__est__**imations(***numlist***)** specify which estimation results to use
__mcerr__**or** compute Monte Carlo error estimates
__ufmit__**est** perform unrestricted FMI model test
**nosmall** do not apply small-sample correction to
the degrees of freedom

Tables
[__no__]__citab__**le** suppress/display standard estimation table
containing parameter-specific confidence
intervals; default is **citable**
__dftab__**le** display degrees-of-freedom table; **dftable**
implies **nocitable**
__vart__**able** display variance information about
estimates; **vartable** implies **citable**
*table_options* control table output
*display_options* control columns and column formats, row
spacing, display of omitted variables
and base and empty cells, and
factor-variable labeling

Reporting
__l__**evel(***#***)** set confidence level; default is **level(95)**
**dots** display dots as estimations are performed
__noi__**sily** display any output from **nlcom** if
transformations are specified
**trace** trace **nlcom** if transformations are
specified; implies **noisily**
**replay** replay command-specific results from each
individual estimation in *miestfile***.ster**;
implies **noisily**
__cmdleg__**end** display the command legend
__nogr__**oup** suppress summary about groups displayed
for **xt** commands
*me_options* control output from mixed-effects commands

Advanced
**errorok** allow estimation even when **nlcom** errors
out in some imputations; such
imputations are discarded from the
analysis

__coefl__**egend** display legend instead of statistics
__nowarn__**ing** suppress the warning about varying
estimation sample
__noerrn__**otes** suppress error notes associated with
failed estimation results in
*miestfile***.ster**
__showimp__**utations** show imputations saved in *miestfile***.ster**
*eform_option* display coefficients table in
exponentiated form
**post** post estimated coefficients and VCE to
**e(b)** and **e(V)**
-------------------------------------------------------------------------
**coeflegend**, **nowarning**, **noerrnotes**, **showimputations**, *eform_option*, and
**post** do not appear in the dialog box.

*table_options* Description
-------------------------------------------------------------------------
__nohead__**er** suppress table header(s)
__notab__**le** suppress table(s)
**nocoef** suppress table output related to
coefficients
__nocmdleg__**end** suppress command legend that appears in
the presence of transformed coefficients
when **nocoef** is used
**notrcoef** suppress table output related to
transformed coefficients
__noleg__**end** suppress table legend(s)
__nocnsr__**eport** do not display constraints
-------------------------------------------------------------------------

See **[MI] mi estimate postestimation** for features available after
estimation. To replay results, type **mi** **estimate** without arguments.

__Menu__

**Statistics > Multiple imputation**

__Description__

**mi estimate using** *miestfile* is for use after **mi estimate,**
**saving(***miestfile***):** .... It allows obtaining multiple-imputation (MI)
estimates, including standard errors and confidence intervals, for
transformed coefficients or the original coefficients, this time
calculated on a subset of the imputations. The transformation can be
linear or nonlinear.

__Options__

+---------+
----+ Options +----------------------------------------------------------

**nimputations(***#***)** specifies that the first *#* imputations be used; *#* must be
M_min <= *#* <= M, where M_min = 3 if **mcerror** is specified and M_min =
2, otherwise. The default is to use all imputations, M. Only one of
**nimputations()**, **imputations()**, or **estimations()** may be specified.

**imputations(***numlist***)** specifies which imputations to use. The default is
to use all of them. *numlist* must contain at least two numbers
corresponding to the imputations saved in *miestfile***.ster**. If **mcerror**
is specified, *numlist* must contain at least three numbers. You can
use the **showimputations** option to display imputations currently saved
in *miestfile***.ster**. Only one of **nimputations()**, **imputations()**, or
**estimations()** may be specified.

**estimations(***numlist***)** does the same thing as **imputations(***numlist***)**, but
this time the imputations are numbered differently. Say that
*miestfile***.ster** was created by **mi estimate** and **mi estimate** was told to
limit itself to imputations 1, 3, 5, and 9. With **imputations()**, the
imputations are still numbered 1, 3, 5, and 9. With **estimations()**,
they are numbered 1, 2, 3, and 4. Usually, one does not specify a
subset of imputations when using **mi estimate**, and so usually, the
**imputations()** and **estimations()** options are identical. The specified
*numlist* must contain at least two numbers. If **mcerror** is specified,
*numlist* must contain at least three numbers. Only one of
**nimputations()**, **imputations()**, or **estimations()** may be specified.

**mcerror** specifies to compute Monte Carlo error (MCE) estimates for the
results displayed in the estimation, degrees-of-freedom, and
variance-information tables. MCE estimates reflect variability of MI
results across repeated uses of the same imputation procedure and are
useful for determining an adequate number of imputations to obtain
stable MI results; see White, Royston, and Wood (2011) for details
and guidelines.

MCE estimates are obtained by applying the jackknife procedure to
multiple-imputation results. That is, the jackknife pseudovalues of
MI results are obtained by omitting one imputation at a time; see **[R]**
**jackknife** for details about the jackknife procedure. As such, the
Monte Carlo error computation requires at least three imputations.

If **level()** is specified during estimation, MCE estimates are obtained
for confidence intervals with the specified confidence level instead
of using the default 95% confidence level. If any of the options
described in **[R]** *eform_option* is specified during estimation, MCE
estimates for the coefficients, standard errors, and confidence
intervals in the exponentiated form are also computed. **mcerror** can
also be used upon replay to display MCE estimates. Otherwise, MCE
estimates are not reported upon replay even if they were previously
computed.

**ufmitest** specifies that the unrestricted fraction missing information
(FMI) model test be used. The default test performed assumes equal
fractions of information missing due to nonresponse for all
coefficients. This is equivalent to the assumption that the
between-imputation and within-imputation variances are proportional.
The unrestricted test may be preferable when this assumption is
suspect provided the number of imputations is large relative to the
number of estimated coefficients.

**nosmall** specifies that no small-sample correction be made to the degrees
of freedom. By default, individual tests of coefficients (and
transformed coefficients) use the small-sample correction of Barnard
and Rubin (1999), and the overall model test uses the small-sample
correction of Reiter (2007).

+--------+
----+ Tables +-----------------------------------------------------------

All table options below may be specified at estimation time or when
redisplaying previously estimated results.

**citable** and **nocitable** specify whether the standard estimation table
containing parameter-specific confidence intervals is displayed. The
default is **citable**. **nocitable** can be used with **vartable** to suppress
the confidence interval table.

**dftable** displays a table containing parameter-specific degrees of freedom
and percentages of increase in standard errors due to nonresponse.
**dftable** implies **nocitable**.

**vartable** displays a table reporting variance information about MI
estimates. The table contains estimates of within-imputation
variances, between-imputation variances, total variances, relative
increases in variance due to nonresponse, fractions of information
about parameter estimates missing due to nonresponse, and relative
efficiencies for using finite M rather than a hypothetically infinite
number of imputations. **vartable** implies **citable**.

*table_options* control the appearance of all displayed table output:

**noheader** suppresses all header information from the output. The
table output is still displayed.

**notable** suppresses all tables from the output. The header
information is still displayed.

**nocoef** suppresses the display of tables containing coefficient
estimates. This option affects the table output produced by
**citable**, **dftable**, and **vartable**.

**nocmdlegend** suppresses the table legend showing the command line,
used to produce results in *miestfile***.ster**, from the output. This
legend appears above the tables containing transformed
coefficients (or above the variance-information table if **vartable**
is used) when **nocoef** is specified.

**notrcoef** suppresses the display of tables containing estimates of
transformed coefficients (if specified). This option affects the
table output produced by **citable**, **dftable**, and **vartable**.

**nolegend** suppresses all table legends from the output.

**nocnsreport**; see **[R] estimation options**.

*display_options*: **noci**, __nopv__**alues**, __noomit__**ted**, **vsquish**, __noempty__**cells**,
__base__**levels**, __allbase__**levels**, __nofvlab__**el**, **fvwrap(***#***)**, **fvwrapon(***style***)**,
**cformat(***%fmt***)**, **pformat(%***fmt***)**, and **sformat(%***fmt***)**; see **[R] estimation**
**options**.

+-----------+
----+ Reporting +--------------------------------------------------------

**level(***#***)**; see **[R] estimation options**.

**dots** specifies that dots be displayed as estimations of transformed
coefficients are successfully completed. An **x** is displayed if **nlcom**
fails to estimate one of the transformed coefficients specified in
*spec*. This option is relevant only if transformations are specified.

**noisily** specifies that any output from **nlcom**, used to obtain the
estimates of transformed coefficients, be displayed. This option is
relevant only if transformations are specified.

**trace** traces the execution of **nlcom**. **trace** implies **noisily** and is
relevant only if transformations are specified.

**replay** replays estimation results from *miestfile***.ster**, previously saved
by **mi estimate,** **saving(***miestfile***)**. This option implies **noisily**.

**cmdlegend** requests that the command line corresponding to the estimation
command used to produce the estimation results saved in
*miestfile***.ster** be displayed. **cmdlegend** may be specified at run time
or when redisplaying results.

**nogroup** suppresses the display of group summary information (number of
groups, average group size, minimum, and maximum) as well as other
command-specific information displayed for **xt** commands.

*me_options*: __stddev__**iations**, __var__**iance**, __noret__**able**, __nofet__**able**, and
__estm__**etric**. These options are relevant only with the mixed-effects
commands **meqrlogit** (see **[ME] meqrlogit**), **meqrpoisson** (see **[ME]**
**meqrpoisson**), and **mixed** (see **[ME] mixed**). See the corresponding
mixed-effects commands for more information. The **stddeviations**
option is the default with **mi estimate using**. The **estmetric** option
is implied when **vartable** or **dftable** is used.

+----------+
----+ Advanced +---------------------------------------------------------

**errorok** specifies that estimations of transformed coefficients that fail
be skipped and the combined results be based on the successful
estimation results. The default is that **mi estimate** stops if an
individual estimation fails. If the *miestfile***.ster** file contains
failed estimation results, **mi estimate using** does not error out; it
issues notes about which estimation results failed and discards these
estimation results in the computation. You can use the **noerrnotes**
option to suppress the display of the notes.

The following options are available with **mi** **estimate** **using** but are not
shown in the dialog box:

**coeflegend**; see **[R] estimation options**. **coeflegend** implies **nocitable** and
cannot be combined with **citable** or **dftable**.

**nowarning** suppresses the warning message at the bottom of table output
that occurs if the estimation sample varies and **esampvaryok** is
specified. See *Potential problems that can arise when using mi*
*estimate* in **[MI] mi estimate** for details.

**noerrnotes** suppresses notes about failed estimation results. These notes
appear when *miestfile***.ster** contains estimation results, previously
saved by **mi estimate,** **saving(***miestfile***)**, from imputations for which
the estimation command used with **mi estimate** failed to estimate
parameters.

**showimputations** displays imputation numbers corresponding to the
estimation results saved in *miestfile***.ster**. **showimputations** may be
specified at run time or when redisplaying results.

*eform_option*; see **[R]** *eform_option*. **mi estimate using** reports results in
the coefficient metric under which the combination rules are applied.
You may use the appropriate *eform_option* to redisplay results in
exponentiated form, if desired. If **dftable** is also specified, the
reported degrees of freedom and percentage increases in standard
errors are not adjusted and correspond to the original coefficient
metric.

**post** requests that MI estimates of coefficients and their respective VCEs
be posted in the usual way. This allows the use of
*estimation_command*-specific postestimation tools with MI estimates.
There are issues; see *Using the command-specific postestimation tools*
in **[MI] mi estimate postestimation**. **post** may be specified at
estimation time or when redisplaying previously estimated results.

__Example__

Use previously saved estimates to obtain estimate of the ratio of
coefficients; (1) make the previously saved estimates
**. webuse mhouses1993s30**
**. mi estimate, saving(miest): regress price tax sqft age nfeatures ne**
**custom corner**

(2) use previously saved estimates to obtain estimate of the desired
ratio
**. mi estimate (ratio: _b[age]/_b[sqft]) using miest**

Compute Monte Carlo error estimates of coefficients and the ratio of
coefficients
**. mi estimate (ratio: _b[age]/_b[sqft]) using miest, mcerror**

If you just ran this example, when you are through, erase file containing
previous estimates,
**. erase miest.ster**

__Stored results__

See Stored results in **[MI] mi estimate**.

__References__

Barnard, J., and D. B. Rubin. 1999. Small-sample degrees of freedom with
multiple imputation. *Biometrika* 86: 948-955.

Reiter, J. P. 2007. Small-sample degrees of freedom for multi-component
significance tests with multiple imputation for missing data.
*Biometrika* 94: 502-508.

White, I. R., P. Royston, and A. M. Wood. 2011. Multiple imputation
using chained equations: Issues and guidance for practice.
*Statistics in Medicine* 30: 377-399.