I have a ordinal dependent variable with levels from 1 to 10.My independent variables are interval,nominal,ordinal and binary.Now if I want to establish the relationship between dependent and independent variable ,what is the ideal regression methodology.
If you have 10 levels of your depdent variable than it is likely interval like and you can probably run OLS. There are forms of logistic regression that use ordinal data in their analysis, but with ten levels of your dependent variable I am not sure how useful they would be. OLS is a lot easier to interpret as well.
You should run a skew and kurtosis test of your dependent variable and a QQ plot to see if the data is normally distributed. If it is close I would try OLS.