# Multivariate regression

#### rkeenan37

##### New Member
Hello,
I am using SPSS 20.0 and am running a multivariate regression using the GLM procedure.
I would like to know how to test whether the relationship between one independent variable (X1)
and one dependent variable (Y1) is equivalent to the relationship between another independent
variable (X2) and another dependent variable (Y2). In other words, if (X1 Y1) = (X2 Y2).

Would anyone know how to write this using syntax? Thank you for any help.

#### noetsi

##### Fortran must die
I was not aware there was even a method, let alone a synatx to do that. I am not sure what you mean by equivalent, but I don't think you can ever test that. You can compare the relative value of models with tests such as AIC.

##### New Member
Hello,

I am new this foum But i need help i have 5 dependent variable and each depdent vaiable is measure in licker scale of 5 and 6 independent variable and each 6 indepenent variable is laso measue on licket scale of 5 which regression i should apply .

Please provide all the details and all the links to do in SPSS. Many thanks

#### noetsi

##### Fortran must die
With a dependent variable that has five levels (and is ordinal) you should consider ordered logistic regression or (if the assumptions of this method are violated which they often are) try multinomial logistic regression. SPSS does both but I work primarily in SAS and don't know enough to suggest how to do this in SPSS (other than it has the capacity to do this). UCLA has some awesome links with SPSS, you should look for one on ordered logistic regression.

##### New Member
Thanks nobie.

Can u tell me can i use multivate mutilpe regression

#### noetsi

##### Fortran must die
that can mean many things. You can use multivariate logistic regression. You can not use multivariate linear regression.

#### jamier

##### New Member
Hi guys,

I am looking at a multi variate regression with time series data. I am basically looking at finding out the impact that oil prices (WTI and Brent crude) have on a stock indexes returns. I unfortunately do not have access to a statistical software program and I am using NUMxl. I wanted to ask if I use the data analysis add-in in excel and run a regression with the two oil benchmark returns as my independent variables and the stock index returns as my dependent if that is sufficient to determine whether the oil prices have indeed had an influence/impact on the past stock market returns. I have run the Augemented Dickey Fuller (ADF) test for stationarity and determined that the data sets are indeed stationary and therefore do not have unit roots. If you could provide any feedback that would be greatly appreciated.

Thank you for the help.