When you perform regression analysis, you want to check the relationship (how they correlate) between the response/dependent variable and independent variables. Usually you can only do that for one variable at a time, but you may want to check the relationship between one independent variable against a model, and then you use partial regression. If you want to check the influence of the dependent variables in you model you should use stepwise regression instead.

Hope it helps,

Regards!

We use partial regression coefficient to measure the expected change in the dependent variable associated with a one unit change in an independent variable holding the other independent variables constant.

thank you so much dear Ricardo Almeida Ibrahim Jimoh

what is a best model logit regression or linear regression when some varibale are continours and some are discreate i.e. age, size of land holding and caste, level of education

Its depend on your dependent variable...if it is continuous then use simple and if categorical then use logit...independent can be either...its doesn't matter for both regression