Log-Paradox: Necessary and sufficient conditions for confounding statistically significant pattern reversal under the log-transform
The log-transform is a common tool in statistical analysis, reducing the impact of extreme values, compressing the range of reported values for improved visualization, enabling the usage of parametric statistical tests requiring normally distributed data, or enabling linear models on non-linear data...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2023-02 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Cardoen, Ben Hanene Ben Yedder Lee, Sieun Nabi, Ivan Robert Hamarneh, Ghassan |
description | The log-transform is a common tool in statistical analysis, reducing the impact of extreme values, compressing the range of reported values for improved visualization, enabling the usage of parametric statistical tests requiring normally distributed data, or enabling linear models on non-linear data. Practitioners are rarely aware that log-transformed results can reverse findings: a hypothesis test without the transform can show a negative trend, while with the log-transform, it can show a positive trend, both statistically significant. We derive necessary and sufficient conditions underlying this paradoxical pattern reversal using finite difference notation. We show that biomedical image quantification is very susceptible to these conditions. Using a novel heuristic maximizing the reversal, we show that statistical significance of the paradoxical pattern reversal can be easily induced by changing as little as 5% of a dataset. We illustrate how quantifying the sizes of objects in proportional data, especially where object sizes capture underlying creation and destruction dynamics, satisfies the precondition for the paradox. We discuss recommendations on proper use of the log-transform, discuss methods to explore the underlying patterns robustly, and emphasize that any transformed result should always be accompanied by its non-transformed source equivalent to exclude accidental confounded findings. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2775126791</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2775126791</sourcerecordid><originalsourceid>FETCH-proquest_journals_27751267913</originalsourceid><addsrcrecordid>eNqNjkFLA0EMhYeC0KL9DwHPC7uzXbd6LRUPIh68l7CbWaeMmTbJij37xx3BH-Ap5L335WXhVr5tm2q78X7p1qrHuq79Xe-7rl257-c8Va8oOOavB3ihgVRRLoA8gs4hxCESGwyZx2gxs0LI8ruGPBeJJ1BDi2pxwJQuoHHiWCgs0AnNSBiEPkkUExSCBOydIJVWE2Qt1z5u3FXApLT-m9fu9nH_tnuqTpLPM6kdjnkWLtbB933XlOfvm_Z_qR8jjFOu</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2775126791</pqid></control><display><type>article</type><title>Log-Paradox: Necessary and sufficient conditions for confounding statistically significant pattern reversal under the log-transform</title><source>Free E- Journals</source><creator>Cardoen, Ben ; Hanene Ben Yedder ; Lee, Sieun ; Nabi, Ivan Robert ; Hamarneh, Ghassan</creator><creatorcontrib>Cardoen, Ben ; Hanene Ben Yedder ; Lee, Sieun ; Nabi, Ivan Robert ; Hamarneh, Ghassan</creatorcontrib><description>The log-transform is a common tool in statistical analysis, reducing the impact of extreme values, compressing the range of reported values for improved visualization, enabling the usage of parametric statistical tests requiring normally distributed data, or enabling linear models on non-linear data. Practitioners are rarely aware that log-transformed results can reverse findings: a hypothesis test without the transform can show a negative trend, while with the log-transform, it can show a positive trend, both statistically significant. We derive necessary and sufficient conditions underlying this paradoxical pattern reversal using finite difference notation. We show that biomedical image quantification is very susceptible to these conditions. Using a novel heuristic maximizing the reversal, we show that statistical significance of the paradoxical pattern reversal can be easily induced by changing as little as 5% of a dataset. We illustrate how quantifying the sizes of objects in proportional data, especially where object sizes capture underlying creation and destruction dynamics, satisfies the precondition for the paradox. We discuss recommendations on proper use of the log-transform, discuss methods to explore the underlying patterns robustly, and emphasize that any transformed result should always be accompanied by its non-transformed source equivalent to exclude accidental confounded findings.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Extreme values ; Finite difference method ; Impact analysis ; Medical imaging ; Paradoxes ; Statistical analysis ; Statistical significance ; Statistical tests</subject><ispartof>arXiv.org, 2023-02</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Cardoen, Ben</creatorcontrib><creatorcontrib>Hanene Ben Yedder</creatorcontrib><creatorcontrib>Lee, Sieun</creatorcontrib><creatorcontrib>Nabi, Ivan Robert</creatorcontrib><creatorcontrib>Hamarneh, Ghassan</creatorcontrib><title>Log-Paradox: Necessary and sufficient conditions for confounding statistically significant pattern reversal under the log-transform</title><title>arXiv.org</title><description>The log-transform is a common tool in statistical analysis, reducing the impact of extreme values, compressing the range of reported values for improved visualization, enabling the usage of parametric statistical tests requiring normally distributed data, or enabling linear models on non-linear data. Practitioners are rarely aware that log-transformed results can reverse findings: a hypothesis test without the transform can show a negative trend, while with the log-transform, it can show a positive trend, both statistically significant. We derive necessary and sufficient conditions underlying this paradoxical pattern reversal using finite difference notation. We show that biomedical image quantification is very susceptible to these conditions. Using a novel heuristic maximizing the reversal, we show that statistical significance of the paradoxical pattern reversal can be easily induced by changing as little as 5% of a dataset. We illustrate how quantifying the sizes of objects in proportional data, especially where object sizes capture underlying creation and destruction dynamics, satisfies the precondition for the paradox. We discuss recommendations on proper use of the log-transform, discuss methods to explore the underlying patterns robustly, and emphasize that any transformed result should always be accompanied by its non-transformed source equivalent to exclude accidental confounded findings.</description><subject>Extreme values</subject><subject>Finite difference method</subject><subject>Impact analysis</subject><subject>Medical imaging</subject><subject>Paradoxes</subject><subject>Statistical analysis</subject><subject>Statistical significance</subject><subject>Statistical tests</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNjkFLA0EMhYeC0KL9DwHPC7uzXbd6LRUPIh68l7CbWaeMmTbJij37xx3BH-Ap5L335WXhVr5tm2q78X7p1qrHuq79Xe-7rl257-c8Va8oOOavB3ihgVRRLoA8gs4hxCESGwyZx2gxs0LI8ruGPBeJJ1BDi2pxwJQuoHHiWCgs0AnNSBiEPkkUExSCBOydIJVWE2Qt1z5u3FXApLT-m9fu9nH_tnuqTpLPM6kdjnkWLtbB933XlOfvm_Z_qR8jjFOu</recordid><startdate>20230209</startdate><enddate>20230209</enddate><creator>Cardoen, Ben</creator><creator>Hanene Ben Yedder</creator><creator>Lee, Sieun</creator><creator>Nabi, Ivan Robert</creator><creator>Hamarneh, Ghassan</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20230209</creationdate><title>Log-Paradox: Necessary and sufficient conditions for confounding statistically significant pattern reversal under the log-transform</title><author>Cardoen, Ben ; Hanene Ben Yedder ; Lee, Sieun ; Nabi, Ivan Robert ; Hamarneh, Ghassan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27751267913</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Extreme values</topic><topic>Finite difference method</topic><topic>Impact analysis</topic><topic>Medical imaging</topic><topic>Paradoxes</topic><topic>Statistical analysis</topic><topic>Statistical significance</topic><topic>Statistical tests</topic><toplevel>online_resources</toplevel><creatorcontrib>Cardoen, Ben</creatorcontrib><creatorcontrib>Hanene Ben Yedder</creatorcontrib><creatorcontrib>Lee, Sieun</creatorcontrib><creatorcontrib>Nabi, Ivan Robert</creatorcontrib><creatorcontrib>Hamarneh, Ghassan</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Cardoen, Ben</au><au>Hanene Ben Yedder</au><au>Lee, Sieun</au><au>Nabi, Ivan Robert</au><au>Hamarneh, Ghassan</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Log-Paradox: Necessary and sufficient conditions for confounding statistically significant pattern reversal under the log-transform</atitle><jtitle>arXiv.org</jtitle><date>2023-02-09</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>The log-transform is a common tool in statistical analysis, reducing the impact of extreme values, compressing the range of reported values for improved visualization, enabling the usage of parametric statistical tests requiring normally distributed data, or enabling linear models on non-linear data. Practitioners are rarely aware that log-transformed results can reverse findings: a hypothesis test without the transform can show a negative trend, while with the log-transform, it can show a positive trend, both statistically significant. We derive necessary and sufficient conditions underlying this paradoxical pattern reversal using finite difference notation. We show that biomedical image quantification is very susceptible to these conditions. Using a novel heuristic maximizing the reversal, we show that statistical significance of the paradoxical pattern reversal can be easily induced by changing as little as 5% of a dataset. We illustrate how quantifying the sizes of objects in proportional data, especially where object sizes capture underlying creation and destruction dynamics, satisfies the precondition for the paradox. We discuss recommendations on proper use of the log-transform, discuss methods to explore the underlying patterns robustly, and emphasize that any transformed result should always be accompanied by its non-transformed source equivalent to exclude accidental confounded findings.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2023-02 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2775126791 |
source | Free E- Journals |
subjects | Extreme values Finite difference method Impact analysis Medical imaging Paradoxes Statistical analysis Statistical significance Statistical tests |
title | Log-Paradox: Necessary and sufficient conditions for confounding statistically significant pattern reversal under the log-transform |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T03%3A02%3A42IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Log-Paradox:%20Necessary%20and%20sufficient%20conditions%20for%20confounding%20statistically%20significant%20pattern%20reversal%20under%20the%20log-transform&rft.jtitle=arXiv.org&rft.au=Cardoen,%20Ben&rft.date=2023-02-09&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2775126791%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2775126791&rft_id=info:pmid/&rfr_iscdi=true |