Advertisement
If you have a new account but are having problems posting or verifying your account, please email us on hello@boards.ie for help. Thanks :)
Hello all! Please ensure that you are posting a new thread or question in the appropriate forum. The Feedback forum is overwhelmed with questions that are having to be moved elsewhere. If you need help to verify your account contact hello@boards.ie

help! econometrics urgent!!! output

Options
  • 20-11-2011 8:09pm
    #1
    lolliemc
    Registered Users Posts: 21 ✭


    I've ran a regression with my constant variable as company profit and I'm regressing this against No of directors in company, independent directors, CEO total pay, ceo internal vs external, CEO as chairman, ceo bonus and ceo salary. My output reads as follows: constant coefficient 35.1492
    No of directors -0.264809, independent directors -0.649217, ceo total pay 1.04371e-007, CEO internal vs external -2.50570, ceo as chairman 0.912526 ceo bonus is 8.13679e-007 and ceo salary -2.93029e-006
    my r^2 is 0.30
    F (10,64) = 2.774 (0.07)

    please help! what does this all mean?!! urgent!


Comments

  • Options
    #2
    SBWife
    Registered Users Posts: 1,287 ✭✭✭SBWife


    It means you should have gone to class more often.

    There are serious problems with your regression in that there is significant amounts of auto-correlation between your factors. The idea behind doing regression analysis is that you explain one variable in this case company profit using several INDEPENDENT variables. Your variables are not independent of each other - specifically you have multiple measures of corporate governance and multiple measures of CEO pay. As a result your output is garbage.


  • Options
    #3
    lolliemc
    Registered Users Posts: 21 ✭lolliemc


    can u tell me how do I fix it? please


  • Options
    #4
    SBWife
    Registered Users Posts: 1,287 ✭✭✭SBWife


    I think you need to do multiple regressions looking for the individual variables which provide the most explanation as measured by the r-squared and then incorporate the best choices into the explanatory equation - but to be honest I haven't done significant econometrics work since I did my Masters 20 years ago. My advice would be to pull out a textbook and work through how to design a good regression analysis.


  • Options
    #5
    andrew
    Moderators, Science, Health & Environment Moderators, Society & Culture Moderators Posts: 3,368 Mod ✭✭✭✭andrew


    OP, when you say you don't understand any of it, do you really mean any of it? If that is the case, then there's more you need to know than people here could reasonably be expected to explain, and doing a serious amount of study is pretty much your only option.


Advertisement