I have a problem in my thesis results of OLS regression being insignificant.

I have 3 sectors and each sector has 130 observations.

Is this sample size is sufficient or not ?

Can anyone suggest some reason why my results are insignificant?

  • 1
    $\begingroup$ Hi Ammad, welcome to CV. Please avoid writing your questions in ALL CAPS; it looks to many users as if you are shouting; it's also more difficult to read. You might like to read through the faq, especially the first few sections. $\endgroup$ – Glen_b May 19 '13 at 12:35
  • 2
    $\begingroup$ Perhaps you do not have a problem and that there is a story to be told as to why your results are insignificant. That said, "if you torture the data long enough, it will confess". What's the model that you estimated? Did you try dropping any of the sectors? Can you provide some more information? $\endgroup$ – Graeme Walsh May 19 '13 at 12:42

390 is a very decent sample size. Since you haven't posted any details of the results, all we can do is list some possible reasons:

1) Your model is wrong - the relationship you tested is too weak to detect

2) Your model is wrong - you have left out variables that are important

3) Your model is wrong - you have violated the assumptions in some way that diminishes significance

are three broad possibilities.

  • 1
    $\begingroup$ There's also the simple possibility that the relationship isn't weak (in the ordinary, non-statistical sense that a unit change in one of the $x$'s produces a meaningful change in the $y$), but the variation is large. This however does correspond to your item (1) is we take 'weak' in the sense of being measured in standard deviations rather than units. $\endgroup$ – Glen_b May 19 '13 at 23:49
  • 1
    $\begingroup$ Good point; "weak" is yet another term that statisticians use slightly differently than other English users. $\endgroup$ – Peter Flom May 20 '13 at 0:38

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.