Unit 7 Multiple Regression – Dummy Coding

We will be recoding the data in order to run a multiple regression with dummy coding.

Recall that dummy coding refers to the coding of nominal or categorical variables into a single multiple regression equation rather than developing a separate regression equation for each level or group.

The criterion variable for your study is GPA. The predictor variables are ADDSC, IQ, SEX, and ENGG. Notice that the first two variables are continuous and the last two are discrete. Since dummy coding requires k-1 variables, the variable SEX does not need to be recoded. ENGG, however, has four possible values and therefore requires three dummy coded variables. You will need to recode this variable for this unit in order to run your multiple regression.

As a reminder, the datafile is based on Howell and Huessy (1985), who reported on a study of 386 children who, during childhood, had or had not exhibited symptoms of attention deficit disorder (ADD), previously known as hyperkinesis or minimal brain dysfunction.

In 1965, teachers of all second grade school children in a number of schools in northwestern Vermont were asked to complete a questionnaire for each of their students dealing with behaviors commonly associated with ADD. Questionnaires about these same children were again completed when they were in the fourth and fifth grades. For purposes of this data set only, those three scores were averaged to produce a score labeled ADDSC. The higher the score, the more ADD-like behaviors the child exhibited. At the end of the ninth grade and again at the end of the twelfth grade, information on the performance of these children was obtained from school records. There the data offered the opportunity to examine questions about whether later behavior can be predicted from earlier behavior and to examine academically related variables and their relationships.

A description of each variable follows:

• ADDSC           The average of the three ADD-like behavior scores obtained in elementary school.
• SEX                 1 = male; 2 = female.
• REPEAT         1 = repeated at least one grade; 0 = did not repeat a grade.
• IQ                    IQ obtained from a group-administered IQ test.
• ENGL              Level of English in ninth grade: 1 = college prep; 2 = general; 3 = remedial.
• ENGG              Grade in English in ninth grade; 4 = A; 3 = B, etc.
• GPA                 Grade point average in ninth grade.
• SOCPROB     Social problems in ninth grade: 1 = yes; 0 = no.
• DROPOUT     1 = dropped out during high school; 0 = did not drop out.

For this assignment you will again write a full research report, following APA style guidelines, and submit this report as your assignment.

Keep in mind that this assignment looks at:

• The accuracy and completeness of your analysis and output.
• The accuracy and completeness of your interpretation.
• How well you communicate the study and the results of the analysis in your report.

Submit your paper with your integrated output as a single file in the assignment area. Again, since you are integrating your output into the report, you do not need to attach it as a separate file.

Price: $8.69

Solution: The downloadable solution consists of 5 pages, 369 words and 6 charts.
Deliverable: Word Document