Selecting Appropriate Statistical Methods for Small-Sample Continuous Measurement Data: A Comprehensive Review of Classical and Modern Approaches
Author (s)
Israa Abdulameer Resen
Abstract
In the fields of engineering and medical sciences, continuous measurement data based on small samples appear as a major problem, leading to the need for efficient and effective statistical tools. The problem of analysing data on the basis of small samples encourages the present review of the methods and ways for coordination of numerous statistical methods for analysis of small samples. The reviewed methodologies include all the ways from traditional statistical methods to advanced statistical techniques based on the developments of computing and artificial intelligence. T-test and Analysis of Variance (ANOVA) are among the most important methods of analysis of small samples. However, t-test and ANOVA and other traditional statistical techniques imply restrictive assumptions about normality and homogeneity of variances. It is well known that very often the previously mentioned assumptions do not hold in practice. Hence, statisticians had to find alternatives to the described traditional methods of analysing data, and nonparametric tests have become popular because of their effectiveness under the conditions when the basic assumptions of parametric methods do not hold true. The purpose of the research is to analyse the developing field of statistical techniques for small samples. Also, it is intended to describe the intersection, strengths and weaknesses of both traditional and modern techniques. With the help of computing and machine learning, modern statistical methods based on artificial intelligence have become powerful alternatives to traditional statistical techniques, especially for small samples. The scope of this paper is not limited to finding the best statistical techniques for small samples. It also reveals certain research gaps and the integration between the two techniques in this area.
Key words: Small-Sample, Resampling Techniques, Outlier Detection, ANOVA, Normality Assessment, Bootstrapping, Bayesian Inference, Deep and Machine Learning.
| Title: | Selecting Appropriate Statistical Methods for Small-Sample Continuous Measurement Data: A Comprehensive Review of Classical and Modern Approaches |
|---|---|
| Author: | Israa Abdulameer Resen |
| Journal Name: | Journal of Scientific Reports |
| Website: | http://ijsab.com/jsr |
| ISSN: | ISSN: 2708-7085 (Online), ISSN: 3079-9317 (Print) |
| Publisher | IJSAB International |
| DOI: | https://doi.org/10.58970/JSR.1240 |
| Media: | Online |
| Volume: | 15 |
| Issue: | 1 |
| Acceptance Date: | 14/09/2026 |
| Date of Publication: | 21/09/2026 |
| PDF URL: | http://ijsab.com/wp-content/uploads/1240.pdf |
| Free download: | Available |
| Page: | 68-80 |
| First Page: | 52 |
| Last Page: | 67 |
| Paper Type: | Review paper |
| Current Status: | Published |
Cite This Article:
Resen, I. A. (2026). Selecting Appropriate Statistical Methods for Small-Sample Continuous Measurement Data: A Comprehensive Review of Classical and Modern Approaches, Journal of Scientific Reports, 15(1), 68-80. DOI: https://doi.org/10.58970/JSR.1240
About Author (s)
Israa Abdulameer Resen, Department of Mobile communications and Computing Engineering, College of Engineering, University of Information Technology and Communications (UoITC), Baghdad, Iraq. ORCID: https://orcid.org/0009-0004-5590-010X
DOI: https://doi.org/10.58970/JSR.1240
This Post Has Been Viewed 1,894 Times
Summarize this article with:
