Dear colleagues,
From the screenshot, you can see my OLS estimations between institutional variables and oil-related predictor variables. My main hypothesis was that oil-related variables have a negative impact on institutional quality (according to Resource curse theory); however, my estimations produced mixed results, giving both positive and negative coefficients. In this case, what should I do? How do I accept or reject the alternative hypothesis that I have already mentioned.? Thank you beforehand.
Best
Ibrahim
dear Babak Jamshidi
I have not found any multicollinearity in my models according to centered VIF values.
Thank you, dear Ette Etuk
Unfortunately, I am still a bit confused.
Your null hypothesis is that all the effects of the independent variables are negative. If the experiment is such that some independent variables have negative effects and some positive, provided the effects are statistically significant, the null hypothesis cannot hold. It must be rejected.
Your null hypothesis is that all the effects of the independent variables are negative. If the experiment is such that some independent variables have negative effects and some positive, provided the effects are statistically significant, the null hypothesis cannot hold. It must be rejected.
Ibrahim -
Centering does not take out all collinearity. Also, interactions between "independent" variables can be complicated. Once you use several independent variables, you may not be able to tell a lot about the individual variable contributions. That makes "explanation" more dubious than overall "prediction" performance. Trying to say what a variable's contribution may be might, I think, best be discussed in context with other variables. Perhaps you could look at a series of reduced models to study how the variables work together.
[I would not worry about p-values. They are not good stand-alone statistics. But when you said "hypothesis test," I don't think that is what you meant anyway.]
Cheers - Jim
Thank you, dear James R Knaub
I thought that I will be able to test my hypothesis given the results of the picture. However, I think aside from the multicollinearity problem, I will need additional analysis to support my hypothesis.
Best
Ibrahim
Is your independent variables have positive effect on your dependent variable? If yes, the null hypothesis will be accepted but if otherwise, the null hypothesis will be rejected sir.
dear Oyetoun Dunmola
As you can see from the screenshot, I have mixed results which is the exact reason that makes me confused. Which means that some of my independent variables have positive, some negative impact.
Best
Ibrahim
- Badges
- Science topic
- Similar topics
- Medicine
- Physiology
- Biosignals
- Biomedical Signal Processing
- Statistical Analysis