I am trying to lookon the impact of intercropping and rotation on MAHFP ( months of adequate household food provisions )and HDDS( household dietary diversity score). As these dependent variables are count data type, I am planning to use negative binomial regression model (xtnbreg) but i am not sure how to deal with exposure variable to be used in the model. Moreover neither the mean and variance of the outcome variables are equal, as a result i am not sure whether to use poisson or negative binomial model. I really appreciate for any suggestions ?
I really do not know how accurate the results would be if you will use the negative binomial regression method. I would rather prefer to use the simple polynomial regression. It is because the the data obtained would not follow the equation ax+by-c=0. Hope you got my point.
- Badges
- Science topic
- Similar topics
- Agricultural Science
- Agronomy
- Crop Science