0

I need some help with my master's dissertation.

I am using a simple regression, often used in literature that establishes a relationship between Price=B1+B2 Equity+ Net Result.

However, in reviewing the results I have the following problem:

-> If we analyse separately the equity variable(X) in relation to price(Y) it is significant at the 5% level, however in the model with the net result it is no longer significant.

-> In the following year separately or together the equity variable is significant.

I am afraid that in the defense of the dissertation the question will be raised because in a model (year 2017) equity is not significant and in the following year it is.

p.s the correlation between variables and own capital is very high but close for the two years 0.8

kjetil b halvorsen
  • 77,844
Cat Almeida
  • 1
  • 1
    Could you build a common model for the two years? – kjetil b halvorsen Feb 06 '20 at 15:11
  • thank you for your comment! the metedology used in the study is composed of two analyses in which both use the same base model is only disaggregated , so they are already a common model, is there any other way that sugest? – Cat Almeida Feb 06 '20 at 16:04
  • Can you show the details (that is, formulas) of the model you have used? – kjetil b halvorsen Feb 06 '20 at 16:05
  • I think I have found out what the problem is, maybe it is because in one model I was including the half-yearly net income and in the other model the annual net income and these differences may be affecting the explanatory power of own capital. How can I explain that the inclusion of different variables in the model may be affecting the significance of the others? – Cat Almeida Feb 06 '20 at 20:11
  • 1
    Then maybe you can answer your own question? As for the last Q in comment, see for instance https://stats.stackexchange.com/questions/338789/predictor-flipping-sign-in-regression-with-no-multicollinearity (and a LOT of other posts here, do a serch) – kjetil b halvorsen Feb 06 '20 at 20:16

0 Answers0