Explore BrainMass
Share

# Correlation and Regression with SPSS Statistical Results

This content was COPIED from BrainMass.com - View the original, and get the already-completed solution here!

Can someone help me to condense the statistical results of the attached "Correlation and Regression results" done by the SPSS program? The test looks at: Is there a relationship between people feelings about the bible and how often they attend religious services, and/or Does Religious preference (X) affect respondents' (Y) feelings about Pornography Laws? I have included an example of how I need to condense the paper as well as the SPSS results (SEE ATTACHED RESULTS). The results on the paper must provide the following information.

a) State the statistical assumptions for this test.
b) Develop the null hypothesis and the alternative hypothesis.
c) Use SPSS to calculate a correlation coefficient and a simple linear regression. You can decide which should be the independent (predictor) variable and which should be the dependent (criterion) variable. (SEE ATTACHED SPSS RESULTS)
d) Decide whether to reject or retain the null hypothesis.
e) Generate a scatterplot to visually assess the relationship between two variables. (SEE ATTACHED RESULTS)
f) Generate syntax and output files in SPSS. (SEE ATTACHED RESULTS)
g) Based on your SPSS analysis, report the results using correct APA format.

© BrainMass Inc. brainmass.com March 22, 2019, 1:09 am ad1c9bdddf
https://brainmass.com/psychology/abnormal-psychology/correlation-regression-spss-statistical-results-525296

#### Solution Preview

a) The assumptions for correlation and regression are 1) scores on x and scores on y must be normally distributed, 2) there must be a linear relationship between x and y, and 3) you must have homoscedastic data, meaning that the spread of y scores on each x score must be similar. That is, if the difference between the highest and lowest y score is 10 when x is small, it should also be approximately 10 when x is large, and for all scores of x in between.

b) The null hypothesis always states that the effect you're interested in finding does NOT exist. In this case, your null hypothesis would be that there is no relationship between feelings towards the bible and religious service attendance, while your alternative hypothesis would be that there is a relationship. The significance test for regression is literally just the significance test for correlation, so you would use these same hypotheses for both analyses (correlation and regression). We usually state hypotheses mathematically, as follows:

Ho: rho=0
Ha: rho does not = 0

That is, rho is the measure of the correlation in the population. Your null hypothesis is that rho is 0 (there is no ...

#### Solution Summary

The expert examines correlation and regression with SPSS statistical results.

\$2.19