Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Autocorrelation in Panel Data, xtregar and xtreg

From   "Roger B. Newson" <>
Subject   Re: st: Autocorrelation in Panel Data, xtregar and xtreg
Date   Mon, 08 Apr 2013 10:28:03 +0100

Strictly speaking, it is entirely possible for Stata (or other software) to evaluate a P-value to zero, when the true P-value is smaller than the system precision limits. However, it is a valid point that P-values in general ought to be formatted as, where x and y are digits and z is a natiral number. In an age of megaSNP genome scans, "P<0.0005" is not as good as "P=0".


Roger B Newson BSc MSc DPhil
Lecturer in Medical Statistics
Respiratory Epidemiology and Public Health Group
National Heart and Lung Institute
Imperial College London
Royal Brompton Campus
Room 33, Emmanuel Kaye Building
1B Manresa Road
London SW3 6LR
Tel: +44 (0)20 7352 8121 ext 3381
Fax: +44 (0)20 7351 8322
Web page:
Departmental Web page:

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

On 08/04/2013 10:09, Nick Cox wrote:
Massimiliano wrote

"the Prob > F is usually smaller than 0.05 (actually being equal to
0.00 several times)"

No; this is a misconception. If Stata reports a P-value as 0 to the
number of decimal places given, that is what is meant. 0.000, for
example, means only <0.0005. No P-value from a test of this kind is
exactly zero.

On a point of English usage: I advise against expressions such as "a
panel data". It's true that many English dictionaries and style guides
condone "data" as a singular noun, but that usage, which is very
recent,  still strikes me as unidiomatic English, awkward even
informally. In contrast, "a panel dataset", "a panel data set", "some
panel data" are all alternatives that appear much more widely

I know that languages change -- but that's a good reason to support
what is also StataCorp house style, namely that "dataset" is a good
word that should sound fine to English learners and users at all


On 8 April 2013 09:45, Massimiliano Sassone
<> wrote:

I am using Stata 11 to analyze a panel data composed of 279
observations, derived from 31 regions over a 9-year period.

In order to check for autocorrelation on several models, I ran the
Wooldridge test by inputting the -xtserial- command. Since the Prob >
F is usually smaller than 0.05 (actually being equal to 0.00 several
times), I understood that we fail to reject the null hypothesis and
that, therefore, the data is strongly autocorrelated.
*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index