Exam #2 Laboratory #2 Correlations and Regression on SPSS



Psyc451Exam #1 Lab#3 Name: ______________________Comparing Nested & Non-nested Models data pack1mod.savWalk-through #1The criterion variable is GGPG, with the predictors GREQ, GREV, GREA, averate (ratings taken from letters of recommendation, upub (whether on not they published while an undergraduate) and UGPA. This set of predictors naturally divides into two groups of predictors: GRE scores vs. averate, upub & UGPA. This leads to three models:a full model including GREQ, GREV, GREA, averate, upub & UGPAa reduced model including GREQ, GREV & GREA -- GRE modela reduced mode including averate, upub & UGPA -- UGRAD modelSo, there are three model comparisons:Comparing the full model with the GREQ, GREA & GREV model comparing nested modelsComparing the full model with the averate, upub & UGPA model comparing nested modelsComparing the GRE model with the model including averate, upub & UGPA model comparing non-nested modelsGet and interpret the full model. Fill in the following R = ____________ R? = _____________ F = ___________ df = _____, ________ p = ________ N = ________Predictorbβp-valueDoes the predictor contribute?greqgrevgreaaverateugpapubconstant2. Get the GRE model. Fill in the followingR = ____________ R? = _____________ F = ___________ df = _____, ________ p = ________ N = ________Predictorbβp-valueDoes the predictor contribute?greqgrevgreaconstant3. Get the UGRAD model. Fill in the followingR = ____________ R? = _____________ F = ___________ df = _____, ________ p = ________ N = ________Predictorbβp-valueDoes the predictor contribute?averateugpapubconstantCompare the Full model and the GRE model – twice, once using SPSS and once using the FZT programUsing SPSS – enter the full model and remove the non-GRE predictors (the convention is to report the R?Δ as positive)R? Δ = _____________ FΔ = ________ df = ___ , ________ p = _________ Conclusion?Using FZT (the convention is to report the R?Δ as positive)R? Δ = _____________ FΔ = ________ df = ___ , ________ p = _________ Conclusion?Compare the Full model and the UGRAD model – twice, once using SPSS and once using the FZT programUsing SPSS – enter averate, upub & UGPA and then enter the GRE predictors (the convention is to report the R?Δ as positive)R? Δ = _____________ FΔ = ________ df = ___ , ________ p = _________ Conclusion?Using FZT (the convention is to report the R?Δ as positive)R? Δ = _____________ FΔ = ________ df = ___ , ________ p = _________ Conclusion?Compare the GRE model and the UGRAD model Correlation between models = ________ p = ______ N = ______Use the FZT program (remember to enter “R” not “R2” values) and obtain: Steiger’s Z = ___________ p = _________ Conclusion ?Write it all up – following the example in the handout!Your Turn #1Dataset pack2mod.savGet and interpret the full model. Fill in the followingCriterion Variable: DepressionR = ____________ R? = _____________ F = ___________ df = _____, ________ p = ________ N = ________Predictorbβp-valueDoes the predictor contribute?stressSESsalsatfindepmartrait anxietyconstant2. Get the financial model. Fill in the followingR = ____________ R? = _____________ F = ___________ df = _____, ________ p = ________ N = ________Predictorbβp-valueDoes the predictor contribute?SESsalsatfindepconstant3. Get the attribute model. Fill in the followingR = ____________ R? = _____________ F = ___________ df = _____, ________ p = ________ N = ________Predictorbβp-valueDoes the predictor contribute?stressmartrait anxconstantCompare the Full model and the financial model – twice, once using SPSS and once using the FZT programUsing SPSS – enter the full model and remove the non-financial predictors (the convention is to report the R?Δ as positive)R? Δ = _____________ FΔ = ________ df = ___ , ________ p = _________ Conclusion?Using FZT (the convention is to report the R?Δ as positive)R? Δ = _____________ FΔ = ________ df = ___ , ________ p = _________ Conclusion?Compare the Full model and the attribute model – twice, once using SPSS and once using the FZT programUsing SPSS – enter the full model and remove the non-attribute predictors (the convention is to report the R?Δ as positive)R? Δ = _____________ FΔ = ________ df = ___ , ________ p = _________ Conclusion?Using FZT (the convention is to report the R?Δ as positive)R? Δ = _____________ FΔ = ________ df = ___ , ________ p = _________ Conclusion?Compare the financial model and the attribute model Correlation between models = ________ p = ______ N = ______Use the FZT program (remember to enter “R” not “R2” values) and obtain: Steiger’s Z = ___________ p = _________ Conclusion ?Write it all up – following the example in the handout!Walk-Through # 2- Population & Criteria Model Comparisons Comparing Models of Different Populations dataset regcomplab_1.savCriterion: Stress Get and compare the bivariate stats related to the criterion for each groupMen N = 102Women N = 102ComparisonPredictorrp-valuerp-valueFisher’s ZGroup r difference?frssfasssosscredithrsworkhrsGet the multiple regression model for each group.Men R = ________ R? = _________ F = ________ df = _____, ________ p = ________ N = _________ Women R = ________ R? = _________ F = ________ df = _____, ________ p = ________ N = _________ MenWomenb comparisonPredictor bβp-value bβp-valueZp-valuefrssfasssosscredithrsworkhrsConstant3. Compare the “Fit” of the model in the two groups using Fisher’s Z-testFisher’s Z = _____________ p = ___________ Conclusion:4. Compare the “structure” of the model for the two groups Make the comparison using the women’s dataa. r womenmodel, stress = ________ r menmodel, stress = __________ N = ___________b. r womenmodel, menmodel = _________ p = ________ Conclusion:c. Compare the direct and indirect fits Steiger’s Z =_________ p = _________ Conclusion:d. Compare the regression weights for each predictor across populations. What are the differences?5. Write it up, following the example in the paring Models of Different Criteria dataset regcomplab_2.sav.savCriterion: depression (BDI) and loneliness (RULS) Get and compare the correlations of each predictor with these two criteria.r depression, loneliness = _________ N = _____________DepressionLonelinessComparisonPredictorrp-valuerp-valueSteiger’s Zr difference?agegenderstressstate anxtssGet the multiple regression model for each criterionDepression R = ________ R? = _________ F = ________ df = _____, ______ p = _______ N = _______ Loneliness R = ________ R? = _________ F = ________ df = _____, ______ p = _______ N = _______ DepressionLonelinessb comparisonPredictor bβp-value bβp-valueZp-valueagegenderstressstate anxtssConstant3. Compare the “structure” of the model for the two populations use loneliness as the criteriona. r lonelinessmodel, loneliness = ___________ r depressionmodel, loneliness = __________ N = ___________b. r depressionmodel, lonelinessmodel = _________ p = ________ Conclusion:c. Compare the direct and indirect model fit Steiger’s Z =_________ p = __________ Conclusion:d. What are the apparent differences between the regression weights of the two models?4. Write it up, following the example in the handout.Your Turn #2Comparing Models of Different Populations dataset pack1mod.savCriterion: GGPA Get and compare the bivariate stats related to the criterion for each groupMen N = 49Women N = 54ComparisonPredictorrp-valuerp-valueFisher’s ZGroup r difference?progUGPAGREAGREQGREVGet the multiple regression model for each group.Men R = ________ R? = _________ F = ________ df = ____, ______ p = ________ N = _________ Women R = ________ R? = _________ F = ________ df = ____, ______ p = ________ N = _________ MenWomenb comparisonPredictor bβp-valueZβp-valueZp-valueprogUGPAGREAGREQGREVConstant3. Compare the “Fit” of the model in the two groups using Fisher’s Z-testFisher’s Z = _____________ p = __________ Conclusion:4. Compare the “structure” of the model for the two groups Make the comparison using the women’s dataa. r womenmodel, GGPA = ________ r menmodel, GGPA = __________ N = ___________b. r womenmodel, menmodel = _________ p = ________ Conclusion:c. Compare the direct and indirect fits Steiger’s Z =_________ Conclusion:d. Compare the regression weights for each predictor across populations. What are the differences?5. Write it up, following the example in the paring Models of Different Criteria dataset pack1mod.savCriterion: GGPA & UGPA Get and compare the correlations of each predictor with these two criteria.r UGPA, GGPA = _________ N = _____________UGPAGGPAComparisonPredictorrp-valuerp-valueSteiger’s Zr difference?proggenderGREAGREQGREVGet the multiple regression model for each criterionUGPA R = ________ R? = _________ F = ________ df = ____, ______ p = ________ N = _________ GGPA R = ________ R? = _________ F = ________ df = ____, ______ p = ________ N = _________ UGPAGGPAb comparisonPredictor bβp-valueZβp-valueZp-valueproggenderGREAGREQGREVConstant3. Compare the “structure” of the model for the two populations use GGPA as the criteriona. r UGPAmodel, GGPA = ___________ r GGPAmodel, GGPA = __________ N = ___________b. r UGPAmodel, GGPAmodel = _________ p = ________ Conclusion:c. Compare the direct and indirect model fit Steiger’s Z =_________ Conclusion:d. What are the apparent difference between the regression weights of the two models?4. Write it up, following the example in the handout.About the “Your Turn,” your Laboratory Project and the ConferenceYou may use the same criterion/predictors you used last week, change some, or change all of them -- your choice. Remember, a “good story” isn’t just “a set of all significant” predictors. Rather, it is a combination of things that do and don’t correlate/have multivariate contributions, so we can tell an interesting story about how these variables relate to the criterion.So, use this assignment to compared nested & non-nested modelsHave a mix of “kinds of predictors” (demographics, etc.)Have a mix of significant and nonsignificant multivariate contributors (6-8 predictors is plenty!!!)You may try multiple criterion variables in any data set, but you must present below data from at least 2 different data sets!Your Turn #3Get and interpret the full model. Fill in the followingCriterion Variable: _________________ R = ____________ R? = _____________ F = ___________ df = _____, ________ p = ________ N = ________Predictorbβp-valueDoes the predictor contribute?constantModel #1:____________. Fill in the followingR = ____________ R? = _____________ F = ___________ df = _____, ________ p = ________ N = ________Predictorbβp-valueDoes the predictor contribute?constantModel #2:____________. Fill in the followingR = ____________ R? = _____________ F = ___________ df = _____, ________ p = ________ N = ________Predictorbβp-valueDoes the predictor contribute?constantCompare the Full model and the model #1 – twice, once using SPSS and once using the FZT programUsing SPSS – enter the full model and remove the non-model #1 predictors (the convention is to report the R?Δ as positive)R? Δ = _____________ FΔ = ________ df = ___ , ________ p = _________ Conclusion?Using FZT (the convention is to report the R?Δ as positive)R? Δ = _____________ FΔ = ________ df = ___ , ________ p = _________ Conclusion?Compare the Full model and the model #2 – twice, once using SPSS and once using the FZT programUsing SPSS – enter the full model and remove the non-model #2 predictors (the convention is to report the R?Δ as positive)R? Δ = _____________ FΔ = ________ df = ___ , ________ p = _________ Conclusion?Using FZT (the convention is to report the R?Δ as positive)R? Δ = _____________ FΔ = ________ df = ___ , ________ p = _________ Conclusion?Compare model #1 and model #2 Correlation between models = ________ p = ______ N = ______Use the FZT program (remember to enter “R” not “R2” values) and obtain: Steiger’s Z = ___________ p = _________ Conclusion?Write it up, following the example in the handout.Your Turn #4Get and interpret the full model. Fill in the followingCriterion Variable: _________________R = ____________ R? = _____________ F = ___________ df = _____, ________ p = ________ N = ________Predictorbβp-valueDoes the predictor contribute?constantModel #1:____________. Fill in the followingR = ____________ R? = _____________ F = ___________ df = _____, ________ p = ________ N = ________Predictorbβp-valueDoes the predictor contribute?constantModel #2:____________. Fill in the followingR = ____________ R? = _____________ F = ___________ df = _____, ________ p = ________ N = ________Predictorbβp-valueDoes the predictor contribute?constantCompare the Full model and the model #1 – twice, once using SPSS and once using the FZT programUsing SPSS – enter the full model and remove the non-model #1 predictors (the convention is to report the R?Δ as positive)R? Δ = _____________ FΔ = ________ df = ___ , ________ p = _________ Conclusion?Using FZT (the convention is to report the R?Δ as positive)R? Δ = _____________ FΔ = ________ df = ___ , ________ p = _________ Conclusion?Compare the Full model and the model #2 – twice, once using SPSS and once using the FZT programUsing SPSS – enter the full model and remove the non-model #2 predictors (the convention is to report the R?Δ as positive)R? Δ = _____________ FΔ = ________ df = ___ , ________ p = _________ Conclusion?Using FZT (the convention is to report the R?Δ as positive)R? Δ = _____________ FΔ = ________ df = ___ , ________ p = _________ Conclusion?Compare model #1 and model #2 Correlation between models = ________ p = ______ N = ______Use the FZT program (remember to enter “R” not “R2” values) and obtain: Steiger’s Z = ___________ p = _________ Conclusion?Write it up, following the example in the handout.Your Turn #5Dataset __________________Comparing Models of Different Populations Criterion: _______________________Get and compare the bivariate stats related to the criterion for each groupGroup 1 N = ___Group 2 N = ___ComparisonPredictorrp-valuerp-valueFisher’s ZGroup r difference?Get the multiple regression model for each group.Group1 R = ________ R? = _________ F = ________ df = _____, ________ p = ________ N = _________ Group2 R = ________ R? = _________ F = ________ df = _____, ________ p = ________ N = _________ Group1Group2b comparisonPredictor bβp-value bβp-valueZp-valueConstant3. Compare the “Fit” of the model in the two groups using Fisher’s Z-testFisher’s Z _________________ p = __________ Conclusion:4. Compare the “structure” of the model for the two groups Make the comparison using the Group2’s dataa. r group1model, criterion = ________ r group2model, criterion = __________ N = ___________b. r group1model, group2model = _________ p = ________ Conclusion:c. Compare the direct and indirect fits Steiger’s Z =_________ p = __________ Conclusion:d. Compare the regression weights for each predictor across populations. What are the differences?5. Write it up, following the example in the paring Models of Different Criteria Criterion #1: _______________Criterion #2: _______________Get and compare the correlations of each predictor with these two criteria.r criterion1, criterion2 = _________ N = _____________criterion1criterion2ComparisonPredictorrp-valuerp-valueSteiger’s Zr difference?Get the multiple regression model for each criterioncriterion1 R = ________ R? = _________ F = ________ df = _____, ________ p = ________ N = _________ criterion2 R = ________ R? = _________ F = ________ df = _____, ________ p = ________ N = _________ Criterion1Criterion2b comparisonPredictor bβp-value bβp-valueZp-valueConstantCompare the “structure” of the model for the two populations use criterion2 as the criteriona. r criterion1model, criterion2 = ___________ r criterion2model, criterion2 = __________ N = ___________b. r criterion1model, criterion2model = _________ p = ________ Conclusion:c. Compare the direct and indirect model fit Steiger’s Z =_________ p = _________ Conclusion:d. What are the apparent differences between the regression weights of the two models?Write it up, following the example in the handout.Your Turn #6Dataset __________________Comparing Models of Different Populations Criterion: _______________________Get and compare the bivariate stats related to the criterion for each groupGroup 1 N = ___Group 2 N = ___ComparisonPredictorrp-valuerp-valueFisher’s ZGroup r difference?Get the multiple regression model for each group.Group1 R = ________ R? = _________ F = ________ df = _____, ________ p = ________ N = _________ Group2 R = ________ R? = _________ F = ________ df = _____, ________ p = ________ N = _________ Group1Group2b comparisonPredictor bβp-value bβp-valueZp-valueConstant3. Compare the “Fit” of the model in the two groups using Fisher’s Z-testFisher’s Z _________________ p = __________ Conclusion:4. Compare the “structure” of the model for the two groups Make the comparison using the Group2’s dataa. r group1model, criterion = ________ r group2model, criterion = __________ N = ___________b. r group1model, group2model = _________ p = ________ Conclusion:c. Compare the direct and indirect fits Steiger’s Z =_________ p = __________ Conclusion:d. Compare the regression weights for each predictor across populations. What are the differences?5. Write it up, following the example in the paring Models of Different Criteria Criterion #1: _______________Criterion #2: _______________Get and compare the correlations of each predictor with these two criteria.r criterion1, criterion2 = _________ N = _____________criterion1criterion2ComparisonPredictorrp-valuerp-valueSteiger’s Zr difference?Get the multiple regression model for each criterioncriterion1 R = ________ R? = _________ F = ________ df = _____, ________ p = ________ N = _________ criterion2 R = ________ R? = _________ F = ________ df = _____, ________ p = ________ N = _________ Criterion1Criterion2b comparisonPredictor bβp-value bβp-valueZp-valueConstantCompare the “structure” of the model for the two populations use criterion2 as the criteriona. r criterion1model, criterion2 = ___________ r criterion2model, criterion2 = __________ N = ___________b. r criterion1model, criterion2model = _________ p = ________ Conclusion:c. Compare the direct and indirect model fit Steiger’s Z =_________ p = _________ Conclusion:d. What are the apparent differences between the regression weights of the two models?Write it up, following the example in the handout. ................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download