Explore BrainMass

Multiple regression analysis

Welcome to the fifth SLP of the course. For this module I am again going to refer you to the data you have been collecting. Answer the following questions in reference to your data.

Can you perform a multiple regression analysis with the data you have been collecting without changing that data or adding to it? Why or why not?

(Note: For an additional predictor variable X2 to be useful, it should be correlated with the dependent variable Y, but NOT correlated with another predictor X1. Example: Suppose we want to predict...

Y = growth rate of a food crop

...using the following predictor:

X1 = mean daytime temperature during growing season, in degrees F.

That would probably work. But now, suppose we try to use an additional predictor X2, where

X2 = mean daytime temperature during the growing season, in degrees C.

This would add nothing to the prediction, since it's the same information as X1, only expressed in different numbers. On the other hand, if we used...

X2 = mean daily rainfall during the growing season, in inches

...we'd probably improve our prediction of Y.)

Can you perform a multiple regression analysis using ONLY the data you've been collecting? Why or why not?

Write a 2-3 page paper addressing the issue above.


Solution Summary

Step by step method for multiple regression analysis is discussed here. Regression coefficients, coefficient of determination, scatter diagram and significance of regression model are explained in the solution.