I have a problem with an linear regression model in which I have 2 dependent variables. Both are highly correlated with each other and should both be explained by the linear model

`y = Xbeta + u`

I´am asking myself if I can perform a seemingly unrelated regression (SUR) or a multivariate regression model because I am not sure about the differences between this two approaches.

I would be glad if someone can help me in this case.

Thank you very much.

**Contents**hide

#### Best Answer

As mentioned in the Wikipedia: SUR is equivalent to the equation-by-equation OLS under the following two conditions:

`i. When there are no cross-equation correlations between the error terms ii. When each equation contains exactly the same set of regressors. `

That being said, if your model and data don't satisfy above two cases, then you can proceed with the SUR.

### Similar Posts:

- Solved – Share of variance explained by one variable
- Solved – Is binary logistic regression a special case of multinomial logistic regression when the outcome has 2 levels
- Solved – Feature correlation and their effect of Logistic Regression
- Solved – How to generate correlated test data that has Bernoulli, categorical, and continuous vectors (in R)
- Solved – Correlated features produce strange weights in Logistic Regression