Attachment # 00010373 - statistic_assignment_1.docx
statistic_assignment_1.docx (1886.83 KB)
Raw Preview of Attachment:
(refer to the detailed question and attachment below)
STATISTICS ASSIGNMENTIn this exercise, you’ll have a chance to practice some techniques and procedures related to regression analysis, using data (more or less) from the Darr and Johns (2003) academic politics study used as part of this module’s case. The data are comprised of a number of attitude measures and demographic characteristics of a relatively large (N=620) group of faculty members at a large university, obtained at the time of a major crisis in university operations. The variables are:Demographics:Age, Years in dept, Rank, Sex, salary, level, tch_rating, minority, admin_resp, Science, degree_tier, pub_prestigeAttitudes:Role ambiguity, Role conflict, Task conflict, Relationship conflict, Political perceptionsRespondent perceptions of responsibility in current crisis:Fault, blame A full codebook is available here. The data in SPSS format are available here.Please consult the presentation on regression for specific guidance on how to run various tests.For this exercise, we’ll be using the demographic variables. We’ll use the others later.Start by bonding with your data and forming a personal relationship with it. Prepare appropriate descriptive statistics – remember, means and standard deviations (and possibly histograms) for interval variables, frequency tables for categorical and dummy variables. Try to tidy up your tables following the procedures outlined in the presentation on table-tidying. Are there any things of interest in these descriptive statistics?For interval scale variablesDescriptive StatisticsNMinimumMaximumMeanStd. DeviationAge62026.01099492608071.26954196578248.280000000000028.519999999999996Yearsindept62014216.327.877salary6192591621226661955.7930858.052tch_rating6195.5810.669.7392.66609pub_prestige6191.66.03.3111.1372Valid N (listwise)619StatisticsRankSexminorityadmin_respSciencedegree_tierlevelNValid620620619619619620619Missing25252626262526RankFrequencyPercentValid PercentCumulative PercentValid114121.922.722.7233451.853.976.6314522.523.4100.0Total62096.1100.0MissingSystem253.9Total645100.0SexFrequencyPercentValid PercentCumulative PercentValid026240.642.342.3135855.557.7100.0Total62096.1100.0MissingSystem253.9Total645100.0minorityFrequencyPercentValid PercentCumulative PercentValid015524.025.025.0146471.975.0100.0Total61996.0100.0MissingSystem264.0Total645100.0admin_respFrequencyPercentValid PercentCumulative PercentValid015924.725.725.7146071.374.3100.0Total61996.0100.0MissingSystem264.0Total645100.0ScienceFrequencyPercentValid PercentCumulative PercentValid017126.527.627.6144869.572.4100.0Total61996.0100.0MissingSystem264.0Total645100.0degree_tierFrequencyPercentValid PercentCumulative PercentValid048074.477.477.4114021.722.6100.0Total62096.1100.0MissingSystem253.9Total645100.0levelFrequencyPercentValid PercentCumulative PercentValid132049.651.751.7213921.622.574.238012.412.987.148012.412.9100.0Total61996.0100.0MissingSystem264.0Total645100.0We can see from the above results of descriptive statistics that except age no other interval scale variable is normally distributed.Construct a couple of scatterplots looking at the relationships among some of the interval variables that interest you. What if anything do you discover this way?There is positive correlation between age and salary and correlation is strong, but there is poor and negative correlation between salary and teacher’s rating.Set up a regression model to predict salary (DV) from teaching ratings (IV). Be sure to request appropriate residuals plots. What are your results? What do you learn from the residuals plots? [HINT: here is a good guide on interpreting residuals plots.]ANOVAbModelSum of SquaresdfMean SquareFSig.1Regression1.596E1011.596E1017.197.000aResidual5.725E116179.279E8Total5.885E11618a. Predictors: (Constant), tch_ratingb. Dependent Variable: salaryCoefficientsaModelUnstandardized CoefficientsStandardized CoefficientstSig.BStd. ErrorBeta1(Constant)136254.16517958.0427.587.000tch_rating-7628.8261839.609-.165-4.147.000a. Dependent Variable: salaryThe regression model is significant at 5% level because the p-value of ANOVA table is less than 0.05. Both, interceptor and scale are significant at 5% level because their corresponding p-values are less than 0.05. The R-square value is 0.027 which means that this model explains only 2% of the variation in dependent variable. The normal probability plot tells us that the residuals are not normally distributed because the points are not on a straight line. The model and coefficient are significant due to the large number of observations in the dataset. Since neither salary nor teaching ratings is particularly normally distributed (i.e., both are skewed), we might do better with the log transforms of these data (if you're not familiar with log transforms of data, here is a good general guide to the subject (Hopkins). Try your regression model with these transformed variables. Any better? How do you know?ANOVAbModelSum of SquaresdfMean SquareFSig.1Regression2.48312.48314.902.000aResidual102.792617.167Total105.274618a. Predictors: (Constant), log_ratingb. Dependent Variable: log_salaryCoefficientsaModelUnstandardized CoefficientsStandardized CoefficientstSig.BStd. ErrorBeta1(Constant)12.842.49326.041.000log_rating-.837.217-.154-3.860.000a. Dependent Variable: log_salaryThe regression model is significant at 5% level because the p-value of ANOVA table is less than 0.05. Both, interceptor and scale are significant at 5% level because their corresponding p-values are less than 0.05. The R-square value is 0.024 which means that this model explains only 2% of the variation in dependent variable. The normal probability plot tells us that the residuals are not normally distributed because the points are not on a straight line. The model and coefficient are significant due to the large number of observations in the dataset. Both the models are giving the same results.Now let’s try a multiple predictor model. Use salary as DV, and Age, Years in dept, Sex, level, tch_rating, minority, admin_resp, Science, degree_tier, and pub_prestige as IV’s. How good is your prediction now/? What are the best predictors? Anything in the residuals?ANOVAbModelSum of SquaresdfMean SquareFSig.1Regression4.549E11104.549E10207.083.000aResidual1.336E116082.197E8Total5.885E11618a. Predictors: (Constant), pub_prestige, tch_rating, minority, Sex, degree_tier, Science, Age, admin_resp, level, Yearsindeptb. Dependent Variable: salaryCoefficientsaModelUnstandardized CoefficientsStandardized CoefficientstSig.BStd. ErrorBeta1(Constant)55618.41210063.4625.527.000Age-53.673113.521-.015-.473.637Yearsindept77.973139.666.020.558.577Sex-1929.0211236.022-.031-1.561.119level13213.781838.391.45915.761.000tch_rating-7016.031902.403-.151-7.775.000minority7428.0591447.509.1045.132.000admin_resp-3864.5621632.358-.055-2.367.018Science-932.6511412.487-.014-.660.509degree_tier10797.6541576.196.1476.850.000pub_prestige14475.222717.333.53320.179.000a. Dependent Variable: salaryThe regression model is significant at 5% level because the p-value of ANOVA table is less than 0.05. The variables which have p-values are less than 0.05 are significant at 5% level. The R-square value is 0.773 which means that this model explains 77.3% of the variation in dependent variable. The normal probability plot tells us that the residuals are normally distributed because the points are on a straight line. The model and coefficient are significant due to the large number of observations in the dataset. Your prediction is good, but it’s too complicated. See if you can reduce it some by using a stepwise procedure on the same model. What is the efficiency of prediction of your final model here? What predictors are left? Which have been excluded? Of those left, which are best? Anything in the residuals? Any overall comments or observations here?Model SummarygModelRR SquareAdjusted R SquareStd. Error of the Estimatedimension01.769a.591.59019755.5812.843b.711.71016607.2163.858c.736.73415904.2274.871d.758.75615235.7255.877e.770.76814863.3776.878f.772.77014814.515a. Predictors: (Constant), pub_prestigeb. Predictors: (Constant), pub_prestige, levelc. Predictors: (Constant), pub_prestige, level, tch_ratingd. Predictors: (Constant), pub_prestige, level, tch_rating, degree_tiere. Predictors: (Constant), pub_prestige, level, tch_rating, degree_tier, minorityf. Predictors: (Constant), pub_prestige, level, tch_rating, degree_tier, minority, admin_respg. Dependent Variable: salaryANOVAgModelSum of SquaresdfMean SquareFSig.1Regression3.477E1113.477E11890.807.000aResidual2.408E116173.903E8Total5.885E116182Regression4.186E1122.093E11758.846.000bResidual1.699E116162.758E8Total5.885E116183Regression4.329E1131.443E11570.495.000cResidual1.556E116152.529E8Total5.885E116184Regression4.459E1141.115E11480.281.000dResidual1.425E116142.321E8Total5.885E116185Regression4.530E1159.061E10410.146.000eResidual1.354E116132.209E8Total5.885E116186Regression4.542E1167.569E10344.889.000fResidual1.343E116122.195E8Total5.885E11618a. Predictors: (Constant), pub_prestigeb. Predictors: (Constant), pub_prestige, levelc. Predictors: (Constant), pub_prestige, level, tch_ratingd. Predictors: (Constant), pub_prestige, level, tch_rating, degree_tiere. Predictors: (Constant), pub_prestige, level, tch_rating, degree_tier, minorityf. Predictors: (Constant), pub_prestige, level, tch_rating, degree_tier, minority, admin_respg. Dependent Variable: salaryCoefficientsaModelUnstandardized CoefficientsStandardized CoefficientstSig.BStd. ErrorBeta1(Constant)-7092.4592445.930-2.900.004pub_prestige20857.341698.823.76929.846.0002(Constant)-11155.9552071.690-5.385.000pub_prestige15622.185672.084.57623.244.000level11436.257713.216.39716.035.0003(Constant)59404.0279581.5876.200.000pub_prestige15586.934643.651.57424.216.000level11421.488683.028.39716.722.000tch_rating-7230.154960.530-.156-7.527.0004(Constant)56891.6089184.9666.194.000pub_prestige14213.666643.254.52422.097.000level13154.225693.974.45718.955.000tch_rating-7110.893920.294-.153-7.727.000degree_tier11741.5051566.885.1597.494.0005(Constant)51183.3939016.8725.676.000pub_prestige14065.630628.076.51822.395.000level13179.534677.028.45819.467.000tch_rating-7062.405897.843-.152-7.866.000degree_tier10639.1671540.905.1446.904.000minority7908.2831394.769.1115.670.0006(Constant)51213.0298987.2395.698.000pub_prestige14628.716674.293.53921.695.000level13470.290687.094.46819.605.000tch_rating-6992.587895.431-.151-7.809.000degree_tier10928.6401541.232.1487.091.000minority7288.1341417.307.1025.142.000admin_resp-3657.8111627.647-.052-2.247.025a. Dependent Variable: salaryExcluded VariablesgModelBeta IntSig.Partial CorrelationCollinearity StatisticsTolerance1Age.210a7.397.000.286.755Yearsindept.277a9.338.000.352.662Sex-.071a-2.732.006-.109.974level.397a16.035.000.543.764tch_rating-.157a-6.286.000-.2461.000minority.112a4.395.000.174.996admin_resp.002a.068.946.003.756Science-.025a-.959.338-.039.969degree_tier.027a1.057.291.043.9822Age.022b.780.436.031.579Yearsindept.065b2.063.040.083.468Sex-.035b-1.587.113-.064.964tch_rating-.156b-7.527.000-.2901.000minority.130b6.162.000.241.993admin_resp-.071b-2.815.005-.113.732Science.032b1.429.154.058.944degree_tier.162b7.288.000.282.8733Age.005c.201.841.008.575Yearsindept.040c1.313.190.053.462Sex-.039c-1.852.065-.075.963minority.128c6.357.000.248.993admin_resp-.065c-2.676.008-.107.731Science.027c1.256.210.051.943degree_tier.159c7.494.000.289.8734Age-.005d-.207.836-.008.573Yearsindept.003d.091.927.004.449Sex-.032d-1.577.115-.064.961minority.111d5.670.000.223.977admin_resp-.075d-3.245.001-.130.729Science.009d.429.668.017.9305Age-.004e-.162.871-.007.573Yearsindept.011e.363.717.015.448Sex-.029e-1.486.138-.060.960admin_resp-.052e-2.247.025-.090.701Science-.014e-.705.481-.028.8936Age-.004f-.176.860-.007.573Yearsindept.012f.420.675.017.448Sex-.032f-1.626.104-.066.957Science-.015f-.757.449-.031.893a. Predictors in the Model: (Constant), pub_prestigeb. Predictors in the Model: (Constant), pub_prestige, levelc. Predictors in the Model: (Constant), pub_prestige, level, tch_ratingd. Predictors in the Model: (Constant), pub_prestige, level, tch_rating, degree_tiere. Predictors in the Model: (Constant), pub_prestige, level, tch_rating, degree_tier, minorityf. Predictors in the Model: (Constant), pub_prestige, level, tch_rating, degree_tier, minority, admin_respg. Dependent Variable: salaryThe final model left with (Constant), pub_prestige, level, tch_rating, degree_tier, minority, and admin_resp. The regression model is significant at 5% level because the p-value of ANOVA table is less than 0.05. These all variables have p-values less than 0.05 so these are significant at 5% level. The adjusted R-square value is 0.77 which means that this model explains 77.3% of the variation in dependent variable. The normal probability plot tells us that the residuals are normally distributed because the points are on a straight line. Actually, including LEVEL as an interval variable in this last analysis is somewhat suspect, since while it has some ordinal properties it’s really more of a categorical variable. So let’s try another approach – separate regressions for each level. Use DATA | SPLIT FILE | COMPARE GROUPS | based on LEVEL to divide the sample into the four levels; then run the same regression (of course, without level as a predictor now. Compare the results you get for each level. Any differences in accounting for salary based on these factors between the different levels – i.e., are assistant professors’ salaries set using different criteria from those used for full or chaired professors? Test and comment.ANOVAe,flevelModelSum of SquaresdfMean SquareFSig.11Regression1.190E1191.323E10231.535.000aResidual1.771E103105.712E7Total1.367E1131921Regression2.107E1092.341E9533.789.000bResidual5.659E81294386535.249Total2.164E1013831Regression3.667E975.239E816.495.000cResidual2.287E9723.176E7Total5.954E97941Regression7.037E1071.005E10821.919.000dResidual8.806E8721.223E7Total7.125E1079a. Predictors: (Constant), pub_prestige, tch_rating, minority, Sex, degree_tier, Science, Age, admin_resp, Yearsindeptb. Predictors: (Constant), pub_prestige, tch_rating, minority, Sex, Age, Science, degree_tier, admin_resp, Yearsindeptc. Predictors: (Constant), pub_prestige, Science, tch_rating, Sex, minority, Age, Yearsindeptd. Predictors: (Constant), pub_prestige, tch_rating, Sex, degree_tier, Science, Age, Yearsindepte. There are no valid cases in one or more split files. Statistics cannot be computed.f. Dependent Variable: salaryCoefficientsa,blevelModelUnstandardized CoefficientsStandardized CoefficientstSig.BStd. ErrorBeta11(Constant)51290.9857039.9787.286.000Age-256.52984.502-.083-3.036.003Yearsindept278.448111.728.0742.492.013Sex1128.879894.325.0261.262.208tch_rating-4252.731620.142-.142-6.858.000minority1489.6601177.224.0281.265.207admin_resp-496.810954.738-.012-.520.603Science-1216.1471223.388-.022-.994.321degree_tier3298.2201026.772.0743.212.001pub_prestige15954.675457.570.88734.868.00021(Constant)-49748.9144449.582-11.181.000Age23.60934.775.011.679.498Yearsindept4533.720136.423.98033.233.000Sex343.666372.242.014.923.358tch_rating451.120324.475.0231.390.167minority-629.347426.139-.024-1.477.142admin_resp-1422.385560.880-.047-2.536.012Science-65.497411.277-.003-.159.874degree_tier2376.201527.312.0784.506.000pub_prestige453.700359.029.0381.264.20931(Constant)37487.46618958.5161.977.052Age156.098117.577.1271.328.188Yearsindept-148.857121.320-.124-1.227.224Sex-877.1371359.477-.050-.645.521tch_rating-7180.7371331.408-.400-5.393.000minority835.7461334.449.048.626.533Science-1077.0701349.991-.059-.798.428pub_prestige24903.8933144.827.6607.919.00041(Constant)15468.0848657.4751.787.078Age6.74974.626.001.090.928Yearsindept4713.799191.852.66724.570.000Sex-1370.722843.972-.022-1.624.109tch_rating-2938.994616.847-.076-4.765.000Science1527.692837.106.0251.825.072degree_tier31796.3382013.523.35215.791.000pub_prestige2148.265862.061.0412.492.015a. There are no valid cases in one or more split files. Statistics cannot be computed.b. Dependent Variable: salaryAll the models are significant but the first model with level 1 is significant and best because the residual are normally distributed in this case. But there does not seem any difference in other models.Try another couple of regression analyses, single or multiple, among variables of your choice. Explain why you set up the analyses you did, and what you found.ANOVAbModelSum of SquaresdfMean SquareFSig.1Regression3.920E1175.599E10174.090.000aResidual1.965E116113.216E8Total5.885E11618a. Predictors: (Constant), pub_prestige, tch_rating, degree_tier, Sex, Science, Age, Yearsindeptb. Dependent Variable: salaryCoefficientsaModelUnstandardized CoefficientsStandardized CoefficientstSig.BStd. ErrorBeta1(Constant)47536.94712110.6363.925.000Age241.983135.649.0671.784.075Yearsindept814.867157.575.2065.171.000Sex-3381.9671488.603-.054-2.272.023tch_rating-6388.3271089.713-.138-5.862.000Science-999.0321669.101-.014-.599.550degree_tier3044.6401775.698.0411.715.087pub_prestige16215.899799.327.59820.287.000a. Dependent Variable: salaryI have selected these variables such as pub_prestige, tch_rating, degree_tier, Sex, Science, Age and Yearsindept which can affect the dependent variable “Salary”. The regression model is significant at 5% level because the p-value of ANOVA table is less than 0.05. These all variables have p-values less than 0.05 so these are significant at 5% level. The adjusted R-square value is 0.662 which means that this model explains 66.2% of the variation in dependent variable. The normal probability plot tells us that the residuals are normally distributed because the points are on a straight line. Any overall comments on using regression techniques?We can see that the stepwise regression is the best technique which can identify the significance of variables and includes only those independent variables which are significant and able to predict the dependent variable.
Statistics Assignment

Statistics Assignment

Question # 00449681 Posted By: indiana317 Updated on: 12/26/2016 10:22 AM Due on: 12/27/2016
Subject Physics Topic General Physics Tutorials:
Question
Dot Image

Statistics

In this exercise, you are expected to continue using data from previous assignment (see attachment) in order to establish practical experience in and better understanding of meditation and moderation.

Select three interval variables from this data set (see attachment) where one of them should be a DV, one of them an IV and a third one a possible mediator or moderator.

1. Justify your selection of DV, IV, and Mediator or Moderator. Develop appropriate hypotheses.

2. Develop appropriate hypotheses.

3. Test your moderation hypothesis using SPSS.

4. Interpret the results.

Test your mediation analysis following Baron and Kenny procedure. Interpret the results. What would you do if you had to test moderated mediation relationship.

Dot Image
Attachments
statistic_assignment_1.docx (1886.83 KB)
Tutorials for this Question
  1. neil2103
    Tutorial # 00445473 Posted By: neil2103 Posted on: 12/26/2016 05:48 PM
    Puchased By: 3
    Tutorial Preview
    The solution of Statistics Assignment...
      Get the Solution
    Attachments
    Solution-00445473.zip (76 KB)
Whatsapp Lisa