# Question: Let s revisit some data that we looked at in Chapter

Let’s revisit some data that we looked at in Chapter 8, in Table 8.1. Let X = Gender, coded 1 = male, 2 = female. Let Y = height. Using SPSS, run a bivariate regression to predict Height from Gender. If you do not still have your output from analyses you ran in Chapter 8 also run the Pearson correlation between Gender and Height, and the independent samples t test comparing mean heights for male and female groups.

Here is the bivariate regression to predict height from gender:

Here is the Pearson r (which could also be called a point biserial correlation) between gender and height:

Here is the independent samples t test to compare mean height for gender groups with gender coded 1 = male and 2 = female:

a. Compare the F for your bivariate regression with the t from your independent samples t test. How are these related?

b. Compare the multiple R from your bivariate regression with the r from your bivariate correlation; compare the R2 from the regression with an 2 effect size computed by hand from your t test. How are these related?

c. What do you conclude regarding these three ways of analyzing the data?

Here is the bivariate regression to predict height from gender:

Here is the Pearson r (which could also be called a point biserial correlation) between gender and height:

Here is the independent samples t test to compare mean height for gender groups with gender coded 1 = male and 2 = female:

a. Compare the F for your bivariate regression with the t from your independent samples t test. How are these related?

b. Compare the multiple R from your bivariate regression with the r from your bivariate correlation; compare the R2 from the regression with an 2 effect size computed by hand from your t test. How are these related?

c. What do you conclude regarding these three ways of analyzing the data?

## Answer to relevant Questions

Discuss the two forms of the regression equation: raw score and z score, and their verbal interpretations. When is each form of the analysis more useful? Discuss each of the following as a means of illustrating the partial correlation between X1 and Y, controlling for X2: what can each analysis tell you about the strength and the nature of this relationship? I. Scatter plots ...How can you report the effect size and significance test for each individual predictor variable? How does orthogonal coding of dummy variables differ from dummy and effect coding? How is a weighted average of group means, different from an unweighted average of group means? What is the “weighting” factor? Under what circumstances would each type of mean be preferred?Post your question