SPSS Statistics Premium

Linear models

• Statistics Premium includes generalized linear mixed models (GLMM) for use with hierarchical data.
• This software has general linear models (GLM) and mixed models procedures.
• It includes generalized linear models (GENLIN), including widely used statistical models such as linear regression for normally distributed responses, logistic models for binary data, and loglinear models for count data. GENLIN also offers many useful statistical models through its very general model formulation.
• Generalized estimating equations (GEE) procedures extend generalized linear models to accommodate correlated longitudinal data and clustered data.

Nonlinear models

• Multinomial logistic regression (MLR) predicts categorical outcomes with more than two categories.
• Binary logistic regression classifies data into two groups.
• Nonlinear regression (NLR) and constrained nonlinear regression (CNLR) estimate parameters of nonlinear models.
• Probit analysis evaluates the value of stimuli using a logit or probit transformation of the proportion responding

Customized tables

• Means or proportions are compared for demographic groups, customer segments, time periods or other categorical variables when including inferential statistics.
• The software creates summary statistics - from simple counts for categorical variables to measures of dispersion – and sorts categories by any summary statistic used.
• It includes three significance tests: Chi-square test of independence, comparison of column means (t test), or comparison of column proportions (z test).
• An interactive table builder provides drag and drop capabilities for creating pivot tables.
• It excludes specific categories and enables missing value cells to be displayed and subtotals to be added to tables.
• Tables can be previewed in real time and modified as they are created. They are exportable to Microsoft Word, Excel, PowerPoint or HTML for use in reports.

Data preparation

• Statistics Premium identifies suspicious or invalid cases, variables and data values.
• The software lets you view patterns of missing data and summarize variable distributions.
• Optimal Binning finds the best possible outcome for algorithms designed for nominal attributes.
• The Automated Data Preparation (ADP) tool detects and corrects quality errors and imputes missing values in one efficient step.
• Recommendations and visualizations help you determine which data to use.

Data validity and missing values

• Statistics Premium examines data from several different angles using one of six diagnostic reports, then estimates summary statistics and imputes missing values.
• The software can diagnose serious missing data imputation problems quickly.
• It lets you replace missing values with estimates.
• It displays a snapshot of each type of missing value and any extreme values for each case.
• Hidden bias is removed by replacing missing values with estimates to include all groups – even those with poor responsiveness.

Categorical and numeric data

• This software discovers underlying relationships through perceptual maps, bi plots and tri plots.
• It uses procedures similar to conventional regression, principal components and canonical correlation to predict outcomes and reveal relationships – helping you work with and understand nominal (e.g. salary) and ordinal (e.g. education level) data.
• Statistics Premium lets you visually interpret datasets and see how rows and columns relate in large tables of scores, counts, ratings, rankings or similarities.
• The software handles non-normal residuals in numeric data or nonlinear relationships between predictor variables (e.g. customer or product attributes) and the outcome variable (e.g. purchase/non-purchase).
• Techniques include Ridge Regression, the Lasso, the Elastic Net, variable selection and model selection for both numeric and categorical data.

Decision trees

• Statistics Premium visually determines how your model flows, so you can find specific subgroups and relationships.
• The software creates classification trees directly within IBM SPSS Statistics so you can use results to segment and group cases directly within the data.
• It includes four established tree-growing algorithms:
  • CHAID – A fast, statistical, multi-way tree algorithm that explores data quickly and efficiently, and builds segments and profiles with respect to the desired outcome.
  • Exhaustive CHAID – A modification of CHAID, which examines all possible splits for each predictor.
  • Classification and regression trees (C&RT) – A complete binary tree algorithm, which partitions data and produces accurate homogeneous subsets.
  • QUEST – A statistical algorithm that selects variables without bias and builds accurate binary trees quickly and efficiently.
• Selection or classification/prediction rules are generated in IBM SPSS Statistics syntax, SQL statements or simple text (through syntax).

Forecasting

• Statistics Premium enables you to deliver information in ways that your organization’s decision-makers can understand and use.
• It automatically determines the best-fitting ARIMA or exponential smoothing model to analyze your historic data.
• Hundreds of different time series can be modeled at once, rather than one variable at a time.
• Models are saved to a central file so that forecasts can be updated when data changes, without having to re-set parameters or re-estimate models.
• Scripts can be written to update models with new data automatically.

Structural equation modeling

• Statistics Premium tests hypotheses and confirms relationships among observed and latent variables – moving beyond regression to gain additional insight.
• It lets you builds models that more realistically reflect complex relationships because any numeric variable, whether observed (such as non-experimental data from a survey) or latent (such as satisfaction and loyalty) can be used to predict any other numeric variable.
• The software’s visual framework compares, confirms and refines models.
• Multivariate analysis encompasses and extends standard methods – including regression, factor analysis, correlation and analysis of variance.
• This product includes three data imputation methods: regression, stochastic regression and Bayesian.

Bootstrapping

• Statistics Premium estimates the sampling distribution of an estimator by re-sampling with replacement from the original sample.
• It estimates the standard errors and confidence intervals of a population parameter such as the mean, median, proportion, odds ratio, correlation coefficient, regression coefficient and many others.
• The software lets you create thousands of alternate versions of your datasets for more accurate analysis.

Advanced sampling assessment and testing

• Statistics Premium provides the specialized planning tools and statistics needed to work with complex sample designs, such as stratified, clustered or multistage sampling.
• It helps you achieve better results because it incorporates the sample design into survey analysis.
• Users can more accurately work with numerical and categorical outcomes in complex sample designs using algorithms for analysis and prediction, including predicting time to an event.
• Wizards make it easy to create plans, analyze data and interpret results.

Direct marketing and product decision-making tools

• Statistics Premium segments customers or contacts by creating clusters of those who are like each other, and distinctly different from others.
• The software profiles customers or contacts with shared characteristics to improve the targeting of marketing offers and campaigns.
• It develops propensity scores to identify those who are most likely to purchase.
• Test package performance can be compared to control packages.
• Responses to campaigns are identified by postal code.
• Campaign response data integrates with Salesforce.com to track leads and report on sales pipeline.

High-end charts and graphs

• Statistics Premium has dozens of built-in visualization templates to communicate analytic results.
• "Drag-and-drop" graph creation eliminates the need for programming skills.
• Style sheets and graph templates can be customized to set new graphic standards across your enterprise or match branding.
• Graphs are deployed in operational systems using IBM SPSS Collaboration and Deployment Services, IBM SPSS Statistics and IBM SPSS Modeler.
• The software supports a wide array of data sources, including delimiter-separated, IBM SPSS Statistics data files and common database sources such as DB2, SQL Server, Oracle and Sybase.