Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Global command to format output

From   Roger Newson <>
Subject   Re: st: Global command to format output
Date   Mon, 18 Nov 2002 21:07:05 +0000

At 14:35 18/11/02 +0000, Clive Payne wrote:
I'm a new Stata user. While I'm very impressed with the range of statistical
models which can be fitted in Stata and its programmability, I'm less impressed with the formatting of the standard modelling output (although I must admit to only having used regress so far). Often there is a spurious accuracy with too many significant digits in the output and decimal points are not often alligned. So my question is:

is there a GLOBAL way of setting/resetting the number of significant digits and the number of digits after the decimal point?

(I could do this in Glim 25 years ago!)
As Nick Cox says, the short answer is no. However, I myself usually get around this by using the -parmest- package, downloadable from SSC. (Type -ssc desc parmest- or -net search parmest- to find out more.) -parmest- creates output data sets with one observation per estimated parameter, or one observation per estimated parameter per by-group, and data on parameter estimates, confidence limits, P-values and other parameter attributes specified by the user. Once the user has such a data set in the memory, s/he can type something like

format estimate min95 max95 %8.2f
format p %8.1e
list parm estimate min95 max95 p

and have a listing of the parameter estimates to 2 decimal places, and the P-values in scientific notation (as P-values should be). It is also possible for users to do other tricks, like confidence interval plots for immediate impact in a presentation, which is ideally done using Nick Cox's very useful -hplot- command (type -ssc describe hplot- or -net search hplot-).

A tutorial on the use of the -parmest- package, containing some fairly advanced examples, can be found in the website of the 2002 UK Stata User Meeting at

where it can be downloaded. However, users are warned that some of the examples presented will now cause -parmest- to report an error, because -parmest- now requires the user to specify at least one of the options -saving-, -norestore- and/or -fast-, in order to specify whether s/he wants the output data set to be stored in a disk file, written to the memory (overwriting pre-existing data), or both. For these examples to work as presented, the user should specify the -norestore- option.

I hope this helps.


Roger Newson
Lecturer in Medical Statistics
Department of Public Health Sciences
King's College London
5th Floor, Capital House
42 Weston Street
London SE1 3QD
United Kingdom

Tel: 020 7848 6648 International +44 20 7848 6648
Fax: 020 7848 6620 International +44 20 7848 6620
or 020 7848 6605 International +44 20 7848 6605

Opinions expressed are those of the author, not the institution.

* For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index