• Crosstabulations - Counts, percentages, residuals, marginals, tests of independence, test of linear association, measure of linear association, ordinal data measures, nominal by interval measures, measure of agreement, relative risk estimates for case control and cohort studies.
• Frequencies - Counts, percentages, valid and cumulative percentages; central tendency, dispersion, distribution and percentile values.
• Descriptives - Central tendency, dispersion, distribution and Z scores.
• Descriptive ratio statistics - Coefficient of dispersion, coefficient of variation, price-related differential and average absolute deviance.
• Compare means - Choose whether to use harmonic or geometric means; test linearity; compare via independent sample statistics, paired sample statistics or one-sample t test.
• ANOVA and ANCOVA - Conduct contrast, range and post hoc tests; analyze fixed-effects and random-effects measures; group descriptive statistics; choose your model based on four types of the sum-of-squares procedure; perform lack-of-fit tests; choose balanced or unbalanced design; and analyze covariance with up to 10 methods.
• Correlation - Test for bivariate or partial correlation, or for distances indicating similarity or dissimilarity between measures.
• Nonparametric tests - Chi-square, Binomial, Runs, one-sample, two independent samples, k-independent samples, two related samples, k-related samples.
• Explore - Confidence intervals for means; M-estimators; identification of outliers; plotting of findings.

Tests to Predict Numerical Outcomes and Identify Groups:

IBM SPSS Statistics Base contains procedures for the projects you are working on now and any new ones to come. You can be confident that you’ll always have the analytic tools you need to get the job done quickly and effectively.

• Factor Analysis - Used to identify the underlying variables, or factors, that explain the pattern of correlations within a set of observed variables. In IBM SPSS Statistics Base, the factor analysis procedure provides a high degree of flexibility, offering:
  • Seven methods of factor extraction
  • Five methods of rotation, including direct oblimin and promax for nonorthogonal rotations
  • Three methods of computing factor scores. Also, scores can be saved as variables for further analysis
• K-means Cluster Analysis - Used to identify relatively homogeneous groups of cases based on selected characteristics, using an algorithm that can handle large numbers of cases but which requires you to specify the number of clusters. Select one of two methods for classifying cases, either updating cluster centers iteratively or classifying only.
• Hierarchical Cluster Analysis - Used to identify relatively homogeneous groups of cases (or variables) based on selected characteristics, using an algorithm that starts with each case in a separate cluster and combines clusters until only one is left. Analyze raw variables or choose from a variety of standardizing transformations. Distance or similarity measures are generated by the Proximities procedure. Statistics are displayed at each stage to help you select the best solution.
• TwoStep Cluster Analysis - Group observations into clusters based on nearness criterion, with either categorical or continuous level data; specify the number of clusters or let the number be chosen automatically.
• Discriminant - Offers a choice of variable selection methods, statistics at each step and in a final summary; output is displayed at each step and/or in final form.
• Linear Regression - Choose from six methods: backwards elimination, forced entry, forced removal, forward entry, forward stepwise selection and R2 change/test of significance; produces numerous descriptive and equation statistics.
• Ordinal regression—PLUM - Choose from seven options to control the iterative algorithm used for estimation, to specify numerical tolerance for checking singularity, and to customize output; five link functions can be used to specify the model.
• Nearest Neighbor analysis - Use for prediction (with a specified outcome) or for classification (with no outcome specified); specify the distance metric used to measure the similarity of cases; and control whether missing values or categorical variables are treated as valid values.

What's New in IBM SPSS Base 20