Multivariate Methods and Forecasting with Ibm(r) Spss(r) Statistics (Paperback)

1 Multivariate Regression 1.1 The assumption underlying regression 1.1.1 Multicollinearity 1.1.2 Homoscedasticity of residuals 1.1.3 Normality of residuals 1.1.4 Independence of residuals 1.2 Selecting the regression equation 1.3 Multivariate regression in IBM SPSS Statistics 1.4 The Cochrane-Orcutt procedure 2 Further Regression Models 2.1 Logistic regression 2.1.1 Logistic regression in IBM SPSS Statistics 2.1.2 Further comments about logistic regression 2.2 Multinomial logistic regression 2.3 Dummy regression 3 The Box-Jenkins Methodology 3.1 The property of stationarity 3.2 The ARIMA model 3.3 Autocorrelation 3.4 ARIMA models in IBM SPSS Statistics 4 Factor Analysis 4.1 The correlation matrix 4.2 The terminology and logic of factor analysis 4.3 Rotation and naming of factors 4.4 Factor scores in IBM SPSS Statistics 5 Discriminant Analysis 5.1 The Methodology of discriminant analysis 5.2 Discriminant analysis in IBM SPSS Statistics 5.3 Results of applying the SPSS discrimination procedure 6 Multidimensional Scaling 6.1 Multidimensional scaling models 6.2 Methods of obtaining proximities 6.3 Flying mileages in IBM SPSS Statistics 6.4 Methods of computing proximities 6.5 Weighted multidimensional scaling in IBM SPSS Statistics 7 Hierarchical Log-Linear Analysis 7.1 The logic and terminology of log-linear analysis 7.2 IBM SPSS Statistics commands for the saturated model 7.3 The independence model 7.4 Hierarchical model 7.5 Backward elimination