Related Experiment Video
Updated: Aug 5, 2026
05:47
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
Statistical Consistency in Artificial Intelligence-Assisted Computations: A Comparison of SPSS 31.0 and GPT-5.5
Frederick F Strale1, Rachael M German1, VeraLucia Mendes-Kramer2
1Eugene Applebaum College of Pharmacy and Health Sciences/Applied Health Sciences, Wayne State University, Detroit, USA.
Cureus
|July 28, 2026
Summary
Large language models (LLMs) like GPT-5.5 show statistical consistency with SPSS for common analyses, but advanced procedures require caution and verification.
Area of Science:
- * Computational statistics and artificial intelligence applications in scientific research.
- * Evaluation of large language models (LLMs) for statistical analysis.
- * Reproducibility and reliability in data analysis.
Background:
- * Artificial intelligence (AI), including large language models (LLMs), is increasingly used for statistical interpretation and research support.
- * Traditional software like IBM SPSS is the standard for transparent and reproducible analyses.
- * Concerns exist regarding the accuracy and consistency of LLM-generated statistical outputs, necessitating replication studies.
Purpose of the Study:
- * To evaluate the statistical reliability and alignment of newer LLMs with established analytic standards.
- * To compare the statistical outputs of GPT-5.5 with IBM SPSS 31.0.
- * To assess the consistency of LLM-generated statistical results across various procedures.
Main Methods:
- * 14 statistical procedures were applied to real datasets from peer-reviewed articles (2012-2023).
- * Analyses included descriptive statistics, correlations, t-tests, ANOVA, and MANOVA.
- * GPT-5.5 and SPSS 31.0 were used, with prompts and variable names copied directly.
Main Results:
- * GPT-5.5 showed concordance with SPSS 31.0 for descriptive statistics, correlations, t-tests, regression, and one-way ANOVA.
- * Discrepancies were noted in nonparametric tests, factorial ANOVA, MANOVA, and repeated-measures ANOVA.
- * Substantive interpretations were largely consistent, but not perfectly identical, between the two platforms.
Conclusions:
- * GPT-5.5 demonstrated considerable agreement with SPSS 31.0 for many common statistical procedures.
- * More complex analyses like factorial ANOVA, MANOVA, and repeated-measures ANOVA showed notable discrepancies.
- * LLM outputs can be a useful adjunct for exploratory research but require caution and verification with validated software for confirmatory analyses.
Related Concept Videos
01:22Statistical Package for the Social Sciences (SPSS)
The Statistical Package for the Social Sciences, or SPSS, is a data management and analysis software suite. Developed by SPSS Inc. in 1968 and acquired by IBM in 2009, this tool was initially designed for social science data analysis, evolving to serve a wider range of disciplines. It was later renamed to Statistical Product and Service Solutions.
SPSS streamlines the process from data preparation to analysis and reporting. It is characterized by its user-friendly interface, which conceals...
SPSS streamlines the process from data preparation to analysis and reporting. It is characterized by its user-friendly interface, which conceals...
01:10Statgraphics
Statgraphics is a comprehensive statistical software suite designed for both basic and advanced data analysis. Originating in 1980 at Princeton University under Dr. Neil W. Polhemus, it was one of the pioneering tools for statistical computing on personal computers, with its public release in 1982 marking an early milestone in data science software. Over the years, it has evolved into a robust platform for data science, offering tools for regression analysis, ANOVA, multivariate statistics,...
01:16Statistical Inference Techniques in Hypothesis Testing: Parametric Versus Nonparametric Data
Statistical inference techniques, paramount in hypothesis testing, differentiate into two broad categories: parametric and nonparametric statistics.
Parametric statistics, as the name suggests, assumes that data follow a specific distribution, often a normal distribution. This assumption enables robust hypothesis testing and estimation. Parametric methods, like the Student's t-test or Goodness-of-fit test, are frequently employed in biostatistics due to their robustness. For instance, comparing...
Parametric statistics, as the name suggests, assumes that data follow a specific distribution, often a normal distribution. This assumption enables robust hypothesis testing and estimation. Parametric methods, like the Student's t-test or Goodness-of-fit test, are frequently employed in biostatistics due to their robustness. For instance, comparing...
01:16Statistical Hypothesis Testing
Hypothesis testing is a critical statistical procedure facilitating informed, evidence-based decisions. It begins with a hypothesis, which is a tentative explanation, or a prediction about a population parameter. This hypothesis can be either a null hypothesis (H0), indicating no effect or difference, or an alternative hypothesis (Ha), suggesting an effect or difference.
Statistical significance measures the probability that an observed result occurred by chance. If this probability, known as...
Statistical significance measures the probability that an observed result occurred by chance. If this probability, known as...
01:11Statistical Analysis: Overview
When we take repeated measurements on the same or replicated samples, we will observe inconsistencies in the magnitude. These inconsistencies are called errors. To categorize and characterize these results and their errors, the researcher can use statistical analysis to determine the quality of the measurements and/or suitability of the methods.
One of the most commonly used statistical quantifiers is the mean, which is the ratio between the sum of the numerical values of all results and the...
One of the most commonly used statistical quantifiers is the mean, which is the ratio between the sum of the numerical values of all results and the...
01:09Statistical Methods to Analyze Parametric Data: Student t-Test and Goodness-of-Fit Test
In parametric statistics, two fundamental tests stand out for their utility and wide application: the Student's t-test and goodness-of-fit tests. These tests provide researchers with a robust method for drawing insights from data, testing hypotheses, and making informed decisions based on their findings.
The Student's t-test is a statistical test that examines if there is a statistically significant difference between the means of two groups. This test is instrumental when dealing with data...
The Student's t-test is a statistical test that examines if there is a statistically significant difference between the means of two groups. This test is instrumental when dealing with data...