Cargando…

From Regression Analysis to Deep Learning: Development of Improved Proxy Measures of State-Level Household Gun Ownership

In the absence of direct measurements of state-level household gun ownership (GO), the quality and accuracy of proxy measures for this variable are essential for firearm-related research and policy development. In this work, we develop two highly accurate proxy measures of GO using traditional regre...

Descripción completa

Detalles Bibliográficos
Autores principales: Gomez, David Benjamin, Xu, Zhaoyi, Saleh, Joseph Homer
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7733878/
https://www.ncbi.nlm.nih.gov/pubmed/33336203
http://dx.doi.org/10.1016/j.patter.2020.100154
_version_ 1783622354315771904
author Gomez, David Benjamin
Xu, Zhaoyi
Saleh, Joseph Homer
author_facet Gomez, David Benjamin
Xu, Zhaoyi
Saleh, Joseph Homer
author_sort Gomez, David Benjamin
collection PubMed
description In the absence of direct measurements of state-level household gun ownership (GO), the quality and accuracy of proxy measures for this variable are essential for firearm-related research and policy development. In this work, we develop two highly accurate proxy measures of GO using traditional regression analysis and deep learning, the former accounting for non-linearities in the covariates (portion of suicides committed with a firearm [FS/S] and hunting license rates) and their statistical interactions. We subject the proxies to extensive model diagnostics and validation. Both our regression-based and deep-learning proxy measures provide highly accurate models of GO with training R(2) of 96% and 98%, respectively, along with other desirable qualities—stark improvements over the prevalent FS/S proxy (R(2) = 0.68). Model diagnostics reveal this widely used FS/S proxy is highly biased and inadequate; we recommend that it no longer be used to represent state-level household gun ownership in firearm-related studies.
format Online
Article
Text
id pubmed-7733878
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-77338782020-12-16 From Regression Analysis to Deep Learning: Development of Improved Proxy Measures of State-Level Household Gun Ownership Gomez, David Benjamin Xu, Zhaoyi Saleh, Joseph Homer Patterns (N Y) Article In the absence of direct measurements of state-level household gun ownership (GO), the quality and accuracy of proxy measures for this variable are essential for firearm-related research and policy development. In this work, we develop two highly accurate proxy measures of GO using traditional regression analysis and deep learning, the former accounting for non-linearities in the covariates (portion of suicides committed with a firearm [FS/S] and hunting license rates) and their statistical interactions. We subject the proxies to extensive model diagnostics and validation. Both our regression-based and deep-learning proxy measures provide highly accurate models of GO with training R(2) of 96% and 98%, respectively, along with other desirable qualities—stark improvements over the prevalent FS/S proxy (R(2) = 0.68). Model diagnostics reveal this widely used FS/S proxy is highly biased and inadequate; we recommend that it no longer be used to represent state-level household gun ownership in firearm-related studies. Elsevier 2020-11-27 /pmc/articles/PMC7733878/ /pubmed/33336203 http://dx.doi.org/10.1016/j.patter.2020.100154 Text en © 2020 The Authors http://creativecommons.org/licenses/by-nc-nd/4.0/ This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Article
Gomez, David Benjamin
Xu, Zhaoyi
Saleh, Joseph Homer
From Regression Analysis to Deep Learning: Development of Improved Proxy Measures of State-Level Household Gun Ownership
title From Regression Analysis to Deep Learning: Development of Improved Proxy Measures of State-Level Household Gun Ownership
title_full From Regression Analysis to Deep Learning: Development of Improved Proxy Measures of State-Level Household Gun Ownership
title_fullStr From Regression Analysis to Deep Learning: Development of Improved Proxy Measures of State-Level Household Gun Ownership
title_full_unstemmed From Regression Analysis to Deep Learning: Development of Improved Proxy Measures of State-Level Household Gun Ownership
title_short From Regression Analysis to Deep Learning: Development of Improved Proxy Measures of State-Level Household Gun Ownership
title_sort from regression analysis to deep learning: development of improved proxy measures of state-level household gun ownership
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7733878/
https://www.ncbi.nlm.nih.gov/pubmed/33336203
http://dx.doi.org/10.1016/j.patter.2020.100154
work_keys_str_mv AT gomezdavidbenjamin fromregressionanalysistodeeplearningdevelopmentofimprovedproxymeasuresofstatelevelhouseholdgunownership
AT xuzhaoyi fromregressionanalysistodeeplearningdevelopmentofimprovedproxymeasuresofstatelevelhouseholdgunownership
AT salehjosephhomer fromregressionanalysistodeeplearningdevelopmentofimprovedproxymeasuresofstatelevelhouseholdgunownership