Statalist


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

RE: st: re: tsset with non-integers


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: re: tsset with non-integers
Date   Thu, 7 May 2009 19:06:38 +0100

While we're chuckling at what appears to be poor practice elsewhere, let's remember that all statistical programs basically assume at some level that users take responsibility for what they do. 

For example, suppose your -tsset- your data. So, Stata has been told that you have time series data. 

Now you do a t-test on some data using -ttest-. 

Does Stata come up with a warning that this test assuming independence might not make sense? 

Nick 
n.j.cox@durham.ac.uk 

Antoine Terracol

John Antonakis wrote:
> Also, I just check and saw what SPSSs command does: it seems to check 
> for serial correlation in adjacent observations. 

Wow!

Does it issue a message warning the user that the test might or might 
not make sense according to the data and sort order?


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index