PSYC 201 – Correlations lab Correlations in SPSS for Windows • Click Analyze • Click Correlate • Click Bivariate • Click on each variable you are interested in and then click the on the arrow beside the Variables box. This will move that variable into the Variables box. Keep doing this until you’ve selected all of the variables you’re interested in. • Under options, ask for means and standard deviations. Click Continue to return to the Bivariate Correlations window. Click continue • Click OK • In the output window, the section at the top of the box gives you the correlation matrix of all the variables selected (in this case there were only two). • The Sig. (2-tailed) section provides the probability level for the test of whether the correlation coefficient is significantly different from zero. If this number is less than or equal to .05, the correlation in significant. If you didn’t want to have to deal with this section of the output window, you could always evaluate the significance of the correlation by using the table from the back of the Welkowitz book. • The bottom section provides the sample size used to generate the correlation coefficient. Scatterplots in SPSS • Click Graphs • Click Scatter • Select Simple, then click Define • Select the variables to go on the X and Y axes. Click OK Practice data sets/problems are presented on pages 2-4 of this handout.1. An investigator obtains scores for a person’s age in years and their score on a measure of memory function. Higher scores on the memory task reflect better memories. The investigator has predicted that the two variables will be significantly correlated. a. What is the correlation between the two variables? b. What is the percentage of overlap in the information provided by the two variables? c. Please provide a scatterplot of the relationship between the two variables. d. Have the assumptions of no restriction of range and linearity be met? Why or why not. e. Please test the significance of the correlation coefficient. Be sure to include both the null and alternative hypotheses, your decision rule for deciding whether or not to reject the null hypothesis, your decision about whether to reject the null hypothesis, and your conclusion. f. What can the investigator say about the relationship between age and memory? g. Please provide a scatterplot of these data with age on the X-axis and Memory Function on the Y-axis. Age Memory ----- ---------- 23 16 45 18 18 21 61 9 56 12 79 9 41 15 33 10 67 8 30 142. An investigator obtains scores for job stress and scores for job satisfaction. Higher scores on the job stress measure indicate higher levels of job stress. Scores for the measure of job stress can range from 3 to 25. Higher scores on the measure of job satisfaction reflect higher levels of job satisfaction. Scores on the measure of job satisfaction can range from 35 to 100. The investigator has predicted that the two variables will be significantly correlated. a. What is the correlation between the two variables? b. What is the percentage of overlap in the information provided by the two variables? c. Please provide a scatterplot of the relationship between the two variables. d. Have the assumptions of no restriction of range and linearity be met? Why or why not? e. Please test the significance of the correlation coefficient. Be sure to include both the null and alternative hypotheses, your decision rule for deciding whether or not to reject the null hypothesis, your decision about whether to reject the null hypothesis, and your conclusion. f. What can the investigator say about the relationship between job stress and job satisfaction? Job Job Stress Satisfaction ------ -------------- 6 41 15 56 9 39 29 78 12 47 25 85 31 43 17 56 21 51 27 41 3. Please make up the data to obtain a negative correlation between a child’s age and the number of hours of sleep. Use at least 12 subjects. a. Use SPSS to display the correlation coefficient. b. Use SPSS to display the fact that your correlation is significantly different from zero. c. Provide a scatterplot of the relationship between your two variables. d. Have the assumptions of no restriction of range and linearity be met? Why or why not.Non-SPSS problems 4. An investigator has determined that the correlation between measures of anxiety and depression is +.45. There are 42 people in the sample. a. Write a sentence in APA format that states whether or not the correlation coefficient in significantly different from zero. b. What are the null and alternative hypotheses for this test. c. What is the researcher entitled to conclude on the basis of this test. d. What is the proportion of overlap in the information provided by these two variables. 5. An investigator is interested in the relationship between levels of stress at work and self-reports of overall health. The researcher conducts a study with 102 participants and determines that the Pearson correlation coefficient between these two variables is +.41. a. Write a sentence in APA format that states whether or not the correlation coefficient in significantly different from zero. b. What are the null and alternative hypotheses for this test. c. What is the researcher entitled to conclude on the basis of this test. d. What is the proportion of overlap in the information provided by these two