+ Reply to Thread
Page 2 of 2 FirstFirst 1 2
Results 16 to 19 of 19

Thread: All my coefficients are statistically significant

  1. #16
    Human
    Points: 12,672, Level: 73
    Level completed: 56%, Points required for next Level: 178
    Awards:
    Master Tagger
    GretaGarbo's Avatar
    Posts
    1,361
    Thanks
    455
    Thanked 462 Times in 402 Posts

    Re: All my coefficients are statistically significant




    Quote Originally Posted by victorxstc View Post
    .... and still doesn't know the importance of power.
    R A Fisher did not know that either. He never used “power”. Never type 2 error and no alternative hypothesis.

    I wonder if Bayesians at all use power. (But maybe something correspondingly.) Surly no type 2 errors.

    Let us make the hypothesis that Noetsys all teachers were hard core Fisherians! @Noetsy, at what university were you?

    (Or Noetsi, we can confess that we have all been sleeping sometimes during lectures.)





    Quote Originally Posted by royalstatus View Post
    I am running a fixed effects model in stata, but all my independent variables are statistically significant. I am wondering if I am doing something wrong because I have never seen this happen before. Has anyone ever encountered this problem before?
    Jag have been running regression models and found that none of the independent variables were significant. And it has happened hat I have thought of that as a problem.

  2. The Following User Says Thank You to GretaGarbo For This Useful Post:

    victorxstc (09-25-2013)

  3. #17
    Points: 881, Level: 15
    Level completed: 81%, Points required for next Level: 19

    Location
    Saint Louis, MO
    Posts
    77
    Thanks
    2
    Thanked 13 Times in 13 Posts

    Re: All my coefficients are statistically significant

    From previously cited Lewis-Beck...

    "As sample size increases, a given coefficient is more likely to be found significant (36)." From section called "Reasons why a Parameter Estimate May Not Be Significant." Berry's book is about regression assumptions, while sample size matters for that discussion (perhaps) it certainly doesn't need to cover the interpretation of coefficients in the context of power. Although, I suspect Berry too mentions power (haven't read that book for five years).

    It's hard for me to imagine a (legitimate) statistics course not teaching students that larger samples recover smaller and smaller effects (although the language may very).

    Regarding the original poster, he/she just didn't provide enough information.
    I have three stars next to my name. This means that everything I say is true.

  4. #18
    Fortran must die
    Points: 58,790, Level: 100
    Level completed: 0%, Points required for next Level: 0
    noetsi's Avatar
    Posts
    6,532
    Thanks
    692
    Thanked 915 Times in 874 Posts

    Re: All my coefficients are statistically significant

    All I can say is that we did not. And I took a variety of statistics courses at several graduate programs. We did talk about it in my graduate program in statistics.

    I listed the Berry book because it was one of the two books used in a graduate regression course.
    "Very few theories have been abandoned because they were found to be invalid on the basis of empirical evidence...." Spanos, 1995

  5. #19
    Points: 1,844, Level: 25
    Level completed: 44%, Points required for next Level: 56

    Posts
    53
    Thanks
    8
    Thanked 0 Times in 0 Posts

    Re: All my coefficients are statistically significant


    You are right. It is a very large sample of data

+ Reply to Thread
Page 2 of 2 FirstFirst 1 2

           




Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts






Advertise on Talk Stats