Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
sample size [was: Re: st: From: Abekah Nkrumah ...]
From
Nick Cox <[email protected]>
To
"[email protected]" <[email protected]>
Subject
sample size [was: Re: st: From: Abekah Nkrumah ...]
Date
Thu, 2 May 2013 14:44:30 +0100
No. Whatever inference procedures you used already use sample size to
come up with an answer.
You might need to worry about whether the inference makes sense, e.g.
in precisely what sense your data are a sample, but you can focus on
what the results mean scientifically and practically.
OLS doesn't define a model; it's just an estimation method.
Best to use meaningful titles.
Nick
[email protected]
On 2 May 2013 14:16, <[email protected]> wrote:
> I have estimated OLS and Probit models using pooled cross-country
> datasets. Due to the pooling of data from multiple countries I have a
> very large obervations (N). I am wondering if there is any additional
> test I may have to run to ensure that my estimates are not merely
> significant because of the large N
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/