Thread: Multiple regression - data organization

Hello,

I need to setup multiple regression model for estimating trousers' prices based on their attributes. I have data for period 2001-2005 for 130 trousers. Not all of the trousers were available during this period. I also need to include GDP in the model for every observed year.

I'm confused with this: e.g. trousers A were available in year 2001 and 2002 and trousers B in 2002 and 2003. I have columns in Excel designating all relevant attributes and GDP for certain year for every trousers. GDP was different for every year.

How should I organize the best my data in Excel in order to perform regression? Should I first enter the data for for all available trousers models in 2001 with corresponding GDP (last column), and then data below for 2002 with corresponding GDP, etc.?

I mean domething like this:

Model | Year | Attribute1 | GDP
AAAAA | 2001 | aaaaaaaa | 2,000,000
BBBBB | 2001 | bbbbbbbb | 2,000,000
AAAAA | 2002 | aaaaaaaa | 2,500,000
BBBBB | 2002 | bbbbbbbb | 2,500,000

Many thanks.

John

I honestly have no idea... but I'm very curious to find out whether GDP is correlated with any of the trouser attributes