Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Predicting Alcohol Use Behaviors in the United States: A Complex Survey Analysis

Minardi, Benjamin (2022) Predicting Alcohol Use Behaviors in the United States: A Complex Survey Analysis. Master's Thesis, University of Pittsburgh. (Unpublished)

[img]
Preview
PDF
Download (825kB) | Preview

Abstract

Introduction: Risky alcohol use behaviors create a heavy toll on the health of the United States population. While many studies have attempted to understand the true underpinnings of alcohol use, alcohol consumption and drinking behaviors are multifaceted issues that have both risk factors and consequences. This thesis intended to study the relationship between alcohol use behaviors and their potential predictors in order to answer the question: what influences best predict alcohol use behaviors in the general United States population?
Methods: Data from the National Health and Nutrition Examination Survey (2013-2018) were utilized to create and test models that predicted alcohol use behaviors. Logistic regression and classification and regression tree models were built with complex survey weighting to produce estimates generalizable to the population of the United States. Accuracy and receiver operating characteristic curves were used to assess prediction ability of the models.
Results: Age and sex were the strongest predictors of alcohol use behaviors. The final logistic regression model resulted in odds ratios of 0.971 per each one-year increase in age and 0.380 for females compared to males (p-value < 0.001 for each). Other statistically significant and marginally significant characteristics included being a college graduate, belonging to the Mexican American race/ethnicity group, living with a smoker, self-described health condition, score of a PHQ-9 depression screener, and marital status. Both the logistic regression and classification and regression tree models predicted alcohol use behaviors well with accuracies of 0.702 and 0.660, respectively.
Conclusions: Findings show that the covariates age, sex, education, race, smoking status, marital status, mental health, overall health, and living with a smoker are all important predictors of alcohol use behaviors. These results are generally consistent with the literature and provide evidence that advocates for further exploration of certain characteristics like living with a smoker.
Public Health Significance: Understanding these risk factors or potentially uncovering new risk factors holds a large public health impact. It would provide public health officials with intuition about where to direct research and where to apply interventions in attempt to reduce the burden of risky alcohol use behaviors on the health of the public.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Minardi, Benjaminbem118@pitt.edubem118
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Thesis AdvisorBuchanich, Jeaninejeanine@pitt.edujeanine
Committee MemberCarlson, Jennajnc35@pitt.edujnc35
Committee MemberYouk, Adaayouk@pitt.eduayouk
Committee MemberMair, Christinacmair@pitt.educmair
Date: 12 May 2022
Date Type: Publication
Defense Date: 25 April 2022
Approval Date: 12 May 2022
Submission Date: 29 April 2022
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Number of Pages: 72
Institution: University of Pittsburgh
Schools and Programs: Graduate School of Public Health > Biostatistics
Degree: MS - Master of Science
Thesis Type: Master's Thesis
Refereed: Yes
Uncontrolled Keywords: Complex Survey Analysis, Logistic Regression, CART, Alcohol Use
Date Deposited: 12 May 2022 13:33
Last Modified: 12 May 2022 13:33
URI: http://d-scholarship.pitt.edu/id/eprint/42910

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item