Orthogonalization of time series data

Dear MATLAB community,

I have economic time series data (Y), which I would like to control for a range of other economic variables, such as consumer price index (CPI), or employment (EMPL).

I am planning to use a multiple time series regression model, with Y as the dependent variable and CPI and EMPL as independent variables (there are a few more, but I only mention those two for the sake of parsimony).

I would then like to store the residuals as my now cleaned data.

What techniques/commands would you recommend?

Thank you very much in advance!

Chris

[Harsha Medikonda]

Refer to the following links that might be helpful

http://www.mathworks.com/help/releases/R2013a/econ/examples/time-series-regression-vii-forecasting.html

http://www.mathworks.com/help/releases/R2013a/stats/multivariate-regression-1.html

http://www.mathworks.com/help/releases/R2013a/stats/examples/time-series-regression-of-airline-passenger-data.html

http://www.mathworks.com/help/releases/R2013a/finance/demonstration-program.html

Answer 1

[Muthu Annamalai]

Sounds like

eig

maybe useful, and you may find principal component analysis (PCA) of interest too.

See PCA