Evidential Analysis: An Alternative to Hypothesis Testing in Normal Linear Models

Statistical hypothesis testing, as formalized by 20th century statisticians and taught in college statistics courses, has been a cornerstone of 100 years of scientific progress. Nevertheless, the methodology is increasingly questioned in many scientific disciplines. We demonstrate in this paper how...

Full description

Saved in:
Bibliographic Details
Main Authors: Brian Dennis, Mark L. Taper, José M. Ponciano
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Entropy
Subjects:
Online Access:https://www.mdpi.com/1099-4300/26/11/964
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846153611872043008
author Brian Dennis
Mark L. Taper
José M. Ponciano
author_facet Brian Dennis
Mark L. Taper
José M. Ponciano
author_sort Brian Dennis
collection DOAJ
description Statistical hypothesis testing, as formalized by 20th century statisticians and taught in college statistics courses, has been a cornerstone of 100 years of scientific progress. Nevertheless, the methodology is increasingly questioned in many scientific disciplines. We demonstrate in this paper how many of the worrisome aspects of statistical hypothesis testing can be ameliorated with concepts and methods from evidential analysis. The model family we treat is the familiar normal linear model with fixed effects, embracing multiple regression and analysis of variance, a warhorse of everyday science in labs and field stations. Questions about study design, the applicability of the null hypothesis, the effect size, error probabilities, evidence strength, and model misspecification become more naturally housed in an evidential setting. We provide a completely worked example featuring a two-way analysis of variance.
format Article
id doaj-art-b6c43a378e0e4da9a1e89a89764aab07
institution Kabale University
issn 1099-4300
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Entropy
spelling doaj-art-b6c43a378e0e4da9a1e89a89764aab072024-11-26T18:03:14ZengMDPI AGEntropy1099-43002024-11-01261196410.3390/e26110964Evidential Analysis: An Alternative to Hypothesis Testing in Normal Linear ModelsBrian Dennis0Mark L. Taper1José M. Ponciano2Department of Fish and Wildlife Sciences, University of Idaho, Moscow, ID 83844, USADepartment of Ecology, Montana State University, Bozeman, MT 59717, USADepartment of Biology, University of Florida, Gainesville, FL 32611, USAStatistical hypothesis testing, as formalized by 20th century statisticians and taught in college statistics courses, has been a cornerstone of 100 years of scientific progress. Nevertheless, the methodology is increasingly questioned in many scientific disciplines. We demonstrate in this paper how many of the worrisome aspects of statistical hypothesis testing can be ameliorated with concepts and methods from evidential analysis. The model family we treat is the familiar normal linear model with fixed effects, embracing multiple regression and analysis of variance, a warhorse of everyday science in labs and field stations. Questions about study design, the applicability of the null hypothesis, the effect size, error probabilities, evidence strength, and model misspecification become more naturally housed in an evidential setting. We provide a completely worked example featuring a two-way analysis of variance.https://www.mdpi.com/1099-4300/26/11/964evidenceevidence functionslinear modelsNeyman–Pearsonhypothesis testingKullback–Leibler
spellingShingle Brian Dennis
Mark L. Taper
José M. Ponciano
Evidential Analysis: An Alternative to Hypothesis Testing in Normal Linear Models
Entropy
evidence
evidence functions
linear models
Neyman–Pearson
hypothesis testing
Kullback–Leibler
title Evidential Analysis: An Alternative to Hypothesis Testing in Normal Linear Models
title_full Evidential Analysis: An Alternative to Hypothesis Testing in Normal Linear Models
title_fullStr Evidential Analysis: An Alternative to Hypothesis Testing in Normal Linear Models
title_full_unstemmed Evidential Analysis: An Alternative to Hypothesis Testing in Normal Linear Models
title_short Evidential Analysis: An Alternative to Hypothesis Testing in Normal Linear Models
title_sort evidential analysis an alternative to hypothesis testing in normal linear models
topic evidence
evidence functions
linear models
Neyman–Pearson
hypothesis testing
Kullback–Leibler
url https://www.mdpi.com/1099-4300/26/11/964
work_keys_str_mv AT briandennis evidentialanalysisanalternativetohypothesistestinginnormallinearmodels
AT markltaper evidentialanalysisanalternativetohypothesistestinginnormallinearmodels
AT josemponciano evidentialanalysisanalternativetohypothesistestinginnormallinearmodels