Robustness of T-test Based on Skewness and Kurtosis
Steven T. Garren, Kate McGann Osborne
Journal of Advances in Mathematics and Computer Science · pp. 102–110 · Published 7 Apr 2021
10.9734/jamcs/2021/v36i230342Abstract
Coverage probabilities of the two-sided one-sample t-test are simulated for some symmetric and right-skewed distributions. The symmetric distributions analyzed are Normal, Uniform, Laplace, and student-t with 5, 7, and 10 degrees of freedom. The right-skewed distributions analyzed are Exponential and Chi-square with 1, 2, and 3 degrees of freedom. Left-skewed distributions were not analyzed without loss of generality. The coverage probabilities for the symmetric distributions tend to achieve or just barely exceed the nominal values. The coverage probabilities for the skewed distributions tend to be too low, indicating high Type I error rates. Percentiles for the skewness and kurtosis statistics are simulated using Normal data. For sample sizes of 5, 10, 15 and 20 the skewness statistic does an excellent job of detecting non-Normal data, except for Uniform data. The kurtosis statistic also does an excellent job of detecting non-Normal data, including Uniform data. Examined herein are Type I error rates, but not power calculations. We nd that sample skewness is unhelpful when determining whether or not the t-test should be used, but low sample kurtosis is reason to avoid using the t-test.
References (9)
- 1 The Importance of the Normality Assumption in Large Public Health Data Sets [DOI]
- 2 T test as a parametric statistic [DOI]
- 3 Univariate and multivariate skewness and kurtosis for measuring nonnormality: Prevalence, influence and estimation [DOI]
- 4 Why Psychologists Should by Default Use Welch’s t-test Instead of Student’s t-test [DOI]
- 5 Descriptive Statistics for Modern Test Score Distributions [DOI]
- 6 Robustness and Accuracy of Methods for High Dimensional Data Analysis Based on Student’st-Statistic [DOI]
- 7 Forecasting stock market volatility: Do realized skewness and kurtosis help? [DOI]
- 8 Skewness-based projection pursuit: A computational approach [DOI]
- 9 Estimation and hypothesis testing in multivariate linear regression models under non normality [DOI]
Cited by 37
Carmen L. Rivera-Medina, David Corbera Batlló, A. Inda · Educación y Educadores · 2024
Adnan Elahi, Danilo Comminiello, S. Marceglia · 2024 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) · 2024
Benjamin Mwakyeja, H. Kimario · Management Matters · 2024
Shuang Hao, Nalini Arumugam, Wenlin Li · International Journal of Religion · 2024
Meltem Saygılı, Miraç Ataseven, Büşra Yıldırım · Hacettepe sağlık idaresi dergisi · 2023
V. Gebski, S. M. Silva, K. Byth · Bioinformatics Advances · 2023
H. Kimario, L. Mwagike · Benchmarking : An International Journal · 2023
Kizito Mukuni, Doris Kincade, Xu-Qing Wang · Quarterly review of distance education · 2022
S. Garren, G. Davenport · Current Journal of Applied Science and Technology · 2022
R. Truzoli, P. Reed, L. Osborne · Frontiers in Medicine · 2021
Showing 22 of 37 known citations — external sources report more than can currently be individually listed.
Related research
- A Diagnostic Study on Managing Packaging Weight Variability in Chilli Powder Manufacturing Using Statistical Process Control — shares topic coverage
- Evaluation of Superior Cross Combinations and Identification of Better Parental Stocks from Early Clonal Trials in Sugarcane — shares topic coverage
- New Critical Values for the Winsorized t-Test — shares topic coverage
- Optimization in Breast Lesions Detection via Integrated Statistical Approach — shares topic coverage
- Determinants of Instruction Mode Choice in TVET: A Conditional Logit Analysis of Instructor Assessment Competence, Class Size and Institutional Capacity — shares topic coverage
Article metrics
Real usage data collected on this platform.
66
Page views
0
PDF downloads
12
Outbound clicks
37
Citations
Views over time
Views by country
Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".
Traffic sources
Referring site, by host.
Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.