Multiple Regression

Use the profiles-b.sav dataset to analyze the data as indicated and provide answers to the questions. ( this is the link of profiles-b.sav: http://s3-euw1-ap-pe-ws4-cws-documents.ri-prod.s3.amazonaws.com/9781138289734/data/profile-b.sav

The researchers would like to determine what variables significantly predict individual income "rincmdol".The possible predictor variables are:age, hrs1 (hours worked per week), educ (years of education), maeduc (years of education for mother), paeduc (years of education for father).

The researchers have already determined that there are some outliers and influential data points.Thus, before beginning the regression analysis, select only those cases where MAH_1 (a variable in the dataset) <=22.458.Then proceed to answer the questions below.

1.Create a scatterplot matrix.Can you assume linearity and normality?Explain why or why not.

2.Create a residual plot to determine if the normality and homoscedasticity assumptions are satisfied.In order to get the residuals, you need to first conduct the regression analysis on the full model.

**No need to interpret and describe the model results at this point, save it for the following question.

3.Conduct the multiple regression again, this time incorporating the "tolerance" statistics.Is multicollinearity a problem?Describe.

4.Does the model significantly predict rincmdol?Indicate yes or no, and explain how you made the decision using the results from the ouptput.

5.Create the regression equation for the model.

6.Order the significant regression coefficients by magnitude (i.e., largest impact to smallest impact).

7.Write a paragraph explaining the results as you would in an article.