IBM SPSS Statistics
IBM SPSS Statistics is an integrated family of products that addresses the entire analytical process, from planning to data collection to analysis, reporting and deployment. With more than a dozen fully integrated modules to choose from, you can find the specialised capabilities you need to increase revenue, outperform competitors, conduct research and make better decisions.
IBM SPSS Statistics is a modular product and available in three pre-packaged editions. Which edition is best for you depends on the type of analysis you’re doing. If you’d like advice on this just get in touch and we will be happy to help.
Fundamental analytical capabilities for a wide variety of business and research questions.
Additional capabilities to address issues of data quality, data complexity, automation and forecasting.
A full range of analytical techniques plus structural equation modeling (SEM). In-depth sampling assessment and testing, and procedures for direct marketing.
IBM SPSS Statistics Modules
SPSS Statistics is a modular product. You can select the combination of modules that best meet your requirements.
Std Modules included in IBM SPSS Standard
Pro Modules included in IBM SPSS Professional
Prem Modules included in IBM SPSS Premium
IBM SPSS Statistics Base Std
Forms the foundation for many types of statistical analyses, allowing a quick look at data and its easy preparation for analysis. Easily build charts with sophisticated reporting capabilities, formulate hypotheses for additional testing, clarify relationships between variables, create clusters, identify trends and make predictions.
The following modules can be added to IBM SPSS Statistics Base.
These are the most popular modules bought together with IBM SPSS Statistics Base:
Dive deeper into your data, analyse variances and the complex relationships of real world data to draw more dependable conclusions.
When your data does not conform to the assumptions required by standard analytical procedures, apply more sophisticated univariate and multivariate analytical techniques.
When there is no clear distinction between independent or dependent variables, loglinear and hierarchical loglinear analysis can be used for modelling multiway tables of count data.
Examine the expected duration of time until one or more events happen, such as death in biological organisms and failure in mechanical systems with state-of-the-art survival procedures; Kaplan-Meier and Cox regression.
Predict nonlinear outcomes, such as ordinal values or what product a customer is likely to buy, by using generalized linear mixed models (GLMM).
Model means, variances and covariances in your data using the general linear models (GLM). Describe the relationship between a dependent variable and a set of independent variables. Build flexible models including linear regression, ANOVA, ANCOVA, MANOVA, and MANCOVA. GLM also includes capabilities for repeated measures, mixed models, post hoc tests and post hoc tests for repeated measures, four types of sums of squares, and pairwise comparisons of expected marginal means, as well as the sophisticated handling of missing cells, and the option to save design matrices and effect files.
Use generalised linear models (GENLIN) and accommodate correlated longitudinal data and clustered data with generalised estimating equations (GEE).
Advanced Statistics techniques are commonly used to:
- Identify product interest levels and the impact of customer satisfaction.
- Analyse different medications and their effectiveness.
- Determine ways to repair processes or make improvements to existing processes.
Use Decision Trees for better profiling and targeting. Identify groups, discover relationships between them and predict future events.
Using the comprehensive interface, you can easily build highly visual classification trees to uncover relationships, segments and patterns.
Present groupings in a highly visual and intuitive manner, perfect for non-technical audiences. Display tree diagrams, tree maps, bar graphs and data tables. Choose which statistics, charts and rules to include.
Prune your tree and refine your model, by collapsing and expanding branches.
Dig deeper into your data as visual results can help you find specific subgroups and relationships that you might not uncover using more traditional statistics. Run further analysis on these subgroups and save information from trees as new variables for deeper insights.
Choose from four tree-growing algorithms – CHAID, Exhaustive CHAID, C&RT and QUEST, to find the best fit for your data.
Evaluate your model by using the gains summary tables and gains chart to identify segments by highest (and lowest) contribution.
Directly select cases or assign predictions in your data from the model results, or export rules for later use.
Classification and decision trees are commonly used for:
- Data reduction and variable screening
- Interaction identification
- Category merging
- Discretizing continuous variables
Summarise data and display your analyses as presentation-quality, production ready tables.
The Custom Tables module allows you to build tables and charts in a succinct and clear way with full control over what goes into your reports and how they’re styled. Advanced analytical features allow you to learn from your data and build tables that are easy to read and interpret.
Preview tables as you build them with the drag-and-drop functionality and make changes in real-time.
Include multiple variables and describe your data in multiple structures, cross tabulation and pivot table options as well as additional descriptive statistics.
Present table results using nesting, stacking and multiple response categories as well as continuous measurement fields.
Customise layout and format by collapsing categories, swapping row and column variables, and editing labels directly on the table.
Identify differences, changes or trends in the data by running more than 160 summary statistics, subtotals and displaying missing value cells. Calculate statistics for each cell, row, column, subgroup or table, and highlight cells with significance test results.
Create new fields directly in output tables to perform calculations on output categories and build bar charts using the values produced within the tables.
Protect respondents’ identities by hiding cells or excluding categories.
Automate frequent tasks to automatically produce similar tables with new data.
Custom Tables are used for:
- Easily creating visually appealing tables.
- Presenting and sharing complex information in a clear and succinct format.
- Saving time by automating frequent tables.
- Producing tables for publication/reports.
Watch our IBM SPSS Custom Tables video series to learn how you can save time, reduce your workload and improve your reporting capabilities.
Predict categorical outcomes and apply various nonlinear regression procedures where ordinary regression techniques are limiting or inappropriate.
Free yourself from constraints such as yes/no answers with Multinomial Logistic Regression (MLR). Model which factors predict if customers buy product A, product B or product C.
Easily classify your data into two groups such as buy or not buy or vote or not vote using Binary Logistic Regression. Select the main and interaction effects that best predict your response variable with stepwise methods.
When your data does not meet the statistical assumptions for ordinary least squares, give more weight to measurements within a series by using weighted least squares (WLS) or two-stage least squares (2SLS) to control for correlations between predictor variables and error terms that often occur with time-based data.
Have more control over your model by using constrained and unconstrained nonlinear regression procedures.
Analyse the potency of responses to stimuli, such as medicine doses, prices or incentives with probit and logit response modelling.
Choose from four methods of selecting predictors: forward entry, backward elimination, forward stepwise and backward stepwise.
Regression techniques are commonly used for:
- Investigating consumer buying habits
- Credit risk analysis
- Supply and demand impact analysis
Other IBM SPSS Modules
Gives analysts advanced techniques to streamline the data preparation stage of the analytical process, prior to analysis. While basic data preparation tools are included in IBM SPSS Statistics Base, IBM SPSS Data Preparation provides specialized techniques to prepare your data for more accurate analyzes and results
Finds relationships between any missing values in your data and other variables. Missing data can seriously affect your models—and your results. Used by survey researchers, social scientists, data miners and market researchers to validate data.
Enables analysts to predict trends and develop forecasts quickly and easily—without being an expert statistician. IBM SPSS Forecasting has the advanced statistical techniques needed to work with time-series data regardless of your level of expertise.
Provides tools to obtain clear insight into complex categorical, numerical and high-dimensional data. Understand which characteristics consumers relate most closely to your brand, or determine customer perception of your products compared to others.
Makes testing the stability and reliability of your models easy.
Incorporates complex sample designs into data analysis, with specialized planning tools and statistics, reducing the risk of reaching incorrect or misleading inferences for stratified, clustered or multistage sampling. This module is indispensable for survey and market researchers, public opinion researchers or social scientists seeking to reach more accurate conclusions when working with sample survey methodology.
Helps market researchers develop successful products, giving a realistic way to measure how individual attributes affect people’s preferences. When used with competitive product market research for your new products, you are less likely to overlook product dimensions that are important to your customers or constituents, and more likely to successfully meet their needs.
Helps marketers perform various kinds of analyses easily, without requiring a detailed understanding of statistics. Understand your customers in greater depth, improve your marketing campaigns and maximize the ROI of your marketing budget.
Enables you to use small samples and still feel confident about the results. With the money saved using smaller sample sizes, you can conduct surveys or test direct marketing programs more often. More than 30 exact tests, which cover the entire spectrum of nonparametric and categorical data problems for small or large datasets, are included.
Offers non-linear data modeling procedures that enable you to discover more complex relationships in your data. Choose from algorithms that can be used for classification (categorical outcomes) and prediction (numerical outcomes) to develop more accurate and effective predictive models that provide deeper insight and better decision-making.
IBM SPSS Statistics Features
SPSS Statistics is loaded with powerful analytic techniques and time-saving features to help you quickly and easily find new insights in your data, so you can make more accurate predictions and achieve better outcomes for your organization.
Here’s a look at the features and techniques you’ll find in the latest release. They’re designed to help you make data-driven decisions anytime, anywhere; build more accurate models for greater predictive insight, get analytical results faster and work more productively.
View interactive output on smart devices
Take your SPSS Statistics charts and tables wherever you go and make decisions anytime, anywhere. Now view output on the following platforms and devices without a dedicated SmartReader or other application:
- Windows, Mac and Linux desktop environments
- iPod, iPhone and iPad
- Android phones and tablets (versions 2.1 and above)
- Windows 8 devices
You can also export your SPSS Statistics output as .mht (Cognos Active Report) files, which can be opened using the IBM Cognos Mobile app (available on iPad only).
Generate presentation-ready output quickly and easily
Making your SPSS Statistics output ready for presentation is easier than ever.
- Select and modify objects within a table.
- Apply colors to columns or rows (including gradation across rows/columns) to emphasize key findings.
- Change the color, font, size, background color and other table text attributes.
- Use conditional styling to highlight selected cell(s) based on the value or significance values of tests.
- Index, hide, show or delete table objects.
- Apply a Table Look to a table.
Improve model building using Monte Carlo simulation
Monte Carlo simulation is enhanced to help you build more accurate predictive models when inputs are uncertain, including:
- Simulating strings – SPSS Statistics supports fitting a categorical distribution to a string field in the active dataset, enabling non-numeric variables to be used in simulations.
- Support for Automatic Linear Modeling (ALM) – Export a model from ALM and use it as the starting point for a simulation.
- Heat maps – Generate heat maps automatically when displaying scatterplots in which the target or the input, or both, are categorical.
- Association between categorical inputs– Automatically determine and use associations between categorical inputs when generating data for those inputs. Compute a multiway contingency table for all inputs that are fit to a categorical distribution and use that table when generating data for those inputs.
- Generating data in the absence of a predictive model – Specify which variables you want to simulate and either fit them to the active dataset or manually specify their distributions.
Get better performance and scalability using SPSS Statistics Server
SPSS Statistics Server includes SQL pushback to help you make the best use of your existing IT infrastructure. Now you can perform data transformations without moving data into and out of the proprietary format, helping you conserve resources, deliver results faster and reduce overall IT costs. Other SPSS Statistics Server updates include:
- Greater resilience of SPSS Statistics Server in the event of network failures
- Asynchronous reading of data to get data to the procedures faster
- Improvements to importing/exporting from/to database
- ODBC pooling for more reliable database connections
Simplify custom programming
We’ve added features to make programming in SPSS Statistics easier than ever:
- Install the Python plug-in as part of the main installation.
- Search for, download and install available extensions from within SPSS Statistics. You can also search for updates to installed extensions, and download and install the updated versions.
- Read and write case data faster from and to the active dataset.
Do more work in less time
SPSS Statistics 22 includes productivity enhancements to help you work faster and more efficiently:
- Use a simplified method to specify user-defined estimands in IBM SPSS Amos.
- Benefit from improved logging support for Enterprise Standard in the Platform Standards.
- Enable other applications to read/write encrypted SPSS Statistics data files with i/o dll.
- Generate pivot table output for non-parametric procedures.