What’s new in IBM SPSS Statistics Version 26

IBM SPSS Statistics Version 26 includes new statistical tests, enhancements to existing statistics and scripting procedures, and new production facility capabilities.

New and Advanced Statistics

Quantile Regression (SPSS Statistics Regression Module): This module models the relationship between a set of predictor variables and specific percentiles of a target variable, most often the median.

- Improves results when data contains outliers
- Measures the effect of the predictors on the response variable

ROC Analysis (SPSS Statistics Base): AUC (Area Under The Curve) ROC (Receiver Operating Characteristics) curve is one of the most important evaluation metrics for visualising and checking the performance of classification models. This feature supports the inference regarding a single AUC, precision-recall curves, and provides options for comparing two ROC curves that are generated from either independent groups or paired subjects.

- Visually measure the performance of classification models
- Compare classification models

Procedure & Scripting Advancements

Version 26 has brought new enhancements to existing statistical procedures within the SPSS Statistics Base and SPSS Advanced Statistics modules.

Enhanced Bayesian Statistics (Advanced Statistics Module)

One-way Repeated Measures ANOVA: This new procedure measures one factor from the same subject at each distinct time point or condition, and allows subjects to be crossed within the levels.

One Sample Binomial enhancements: This procedure provides options for executing Bayesian one-sample inference on Binomial distribution.

One Sample Poisson enhancements: This procedure provides options for executing Bayesian one-sample inference on Poisson distribution

Reliability Analysis (SPSS Statistics Base)

Fleiss Multiple Rater Kappa enhancements: This procedure has been updated to provide options for Fleiss’ Multiple Rater Kappa statistics that assess the interrater agreement to determine the reliability among the various raters. A higher agreement provides more confidence in the ratings reflecting the true circumstance. Reliability analysis is used in survey research and as psychometrics.

Scripting Commands

MIXED scripting enhancements (Advanced Statistics Module) – DFMETHOD keyword, KRONECKER keyword, Covariance types UN_AR1, UN_CS, UN_UN options
GENLINMIXED scripting enhancements (Advanced Statistics Module) – Covariance type structures ARH1 & CSH, random effects, repeated effects; Kenward – Roger Degree of Freedom method; Kronecker Covariance types and the KRONECKER_MEASURES keyword
MATRIX scripting enhancements (SPSS Statistics Base) – Support for long variable names to name a matrix or vector name; long variable names in GET and SAVE commands; support for statistical functions that were previously only supported by the COMPUTE command (eg. IDF.CHISQ, CDF.NORMAL etc.)

Productivity Enhancements

Production Facility Updates (SPSS Statistics Base)

Use the INSERT HIDDEN feature in the Production Facility command line interface to submit jobs to the SPSS Statistics Server
When the Production Facility command line interface is used in conjunction with the Microsoft Windows Task Scheduler/MAC OS Automator for scheduling jobs; you can effectively replace Collaboration and Deployment Services for processing SPSS Statistics jobs.