[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: missing p-value from t-test

From   "Newson, Roger B" <>
To   <>
Subject   st: RE: missing p-value from t-test
Date   Fri, 23 May 2008 15:59:13 +0100

As the standard error is zero, the t-statistic (mean difference divided
by standard error) is undefined, and so is the corresponding P-value. So
the P-value is supposed to be missing. You can only test the null
hypothesis if you can estimate the population standard error using
something other than the sample standard error. I do not know enough
about your example to know whether this might be feasible.

I don't know whether the things you are testing are in fact parameter
estimates. However, if they are, then you might be able to use the
-lincom- command.

I hope this helps.


Roger B Newson
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.

-----Original Message-----
[] On Behalf Of
Sent: 23 May 2008 15:31
To: Statalist
Subject: st: missing p-value from t-test

Dear  stata-users,

My appologies for a beginner's question.  I'm estimating the following
model using OLS:
lnROA=alpha + beta(1)*lnW(1) + beta(2)*lnW(2) + beta(3)*lnW(3) + gamma*D
+ epsilon.

Then I calculate an E statistic that equals the sum of beta(1), beta(2),
and beta(3). I want to test whether E=0, using a t-test:
ttest  E==0

One-sample t test
Variable |     Obs        Mean    Std. Err.   Std. Dev.   [95% Conf.
 E_CZE_B |      38   -.0550183           0           0   -.0550183
    mean = mean(E_CZE_B)                             t =        .
Ho: mean = 0                                 degrees of freedom =

    Ha: mean < 0                 Ha: mean != 0                 Ha: mean
> 0
 Pr(T < t) =      .         Pr(|T| > |t|) =      .       Pr(T > t) =

I would like to know why all the p-values are missing here? Is it
because E is a fixed value for all observations? If this is the case,
how can I test this hypothesis, i.e. E=0?

Any help would be very much appreciated.

*   For searches and help try:

Privileged, confidential or patient identifiable information may be
contained in this message. This information is meant only for the use of
the intended recipients. If you are not the intended recipient, or if
the message has been addressed to you in error, do not read, disclose,
reproduce, distribute, disseminate or otherwise use this transmission.
Instead, please notify the sender by reply e-mail, and then destroy all
copies of the message and any attachments.

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2023 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index