Višeparametarska linearna regresija te povezanost zakona o prekidu trudnoće i stope kriminaliteta u SAD

master's thesis

• Author: Dario Ćosić
• Mentor: Siniša Slijepčević (mentor)
• Committee member: Siniša Slijepčević (predsjednik povjerenstva)
• Committee member: Vanja Wagner (član povjerenstva)
• Committee member: Matko Ljulj (član povjerenstva)
• Committee member: Nela Bosner (član povjerenstva)
• Granter: University of Zagreb; Faculty of Science; (Department of Mathematics); Zagreb
• Defense date and country: 2025-02-28, Croatia
• Scientific / art field, discipline and subdiscipline: NATURAL SCIENCES; Mathematics

Abstract

Ovaj diplomski rad istražuje primjenu višeparametarske linearne regresije u analizi povezanosti zakona o prekidu trudnoće sa stopama kriminaliteta u Sjedinjenim Američkim Državama. Rad se temelji na utjecajnom članku The Impact of Legalized Abortion on Crime over the Last Two Decades [13] iz 2020. autora Donohuea i Levitta. Uvodna poglavlja pružaju uvid u osnovne pojmove iz vjerojatnosti i statistike, nakon čega slijedi detaljna analiza modela višeparametarske linearne regresije, uključujući točkovnu i intervalnu procjenu parametara te testiranje hipoteza o modelu. Na temelju ovih teorijskih spoznaja, rad primjenjuje regresijski model za proučavanje dugoročnih učinaka legalizacije pobačaja na stope nasilnog i imovinskog kriminala. Analizom podataka koji obuhvaćaju nekoliko desetljeća, studija pokazuje kako je legalizacija pobačaja značajno doprinijela smanjenju kriminaliteta u SAD-u, posebice kroz smanjenje broja neželjenih trudnoća. Analiza uključuje detaljne procjene utjecaja pobačaja na nasilne zločine, imovinske zločine i ubojstva, uz kontrolu za druge utjecajne čimbenike. Rezultati analize su relativno jak statistički argument u korist hipoteze da je legalizacija pobačaja bila ključni čimbenik u smanjenju kriminaliteta, u skladu s nalazima Donohuea i Levitta. Osim toga, rad naglašava šire implikacije politika planiranja obitelji na društvene ishode, ističući kako poboljšani pristup reproduktivnoj zdravstvenoj skrbi može pozitivno utjecati na opće društveno blagostanje.

Abstract (english)

This thesis explores the application of multivariate linear regression in analyzing the relationship between abortion legislation and crime rates in the United States. The work is based on the influential article The Impact of Legalized Abortion on Crime over the Last Two Decades [13] from 2020, by Donohue and Levitt. The introductory chapters provide a foundation in probability and statistical concepts, followed by an in-depth examination of multivariate linear regression, including point and interval estimation of parameters and hypothesis testing about the model. Building on these theoretical insights, the thesis applies the regression model to study the long-term effects of legalized abortion on violent and property crime rates. By analyzing data spanning multiple decades, the study demonstrates how the legalization of abortion has contributed significantly to the decline in crime rates in the U.S., particularly by reducing unwanted births. The analysis incorporates detailed regression estimates to evaluate the specific impact of abortion on violent crimes, property crimes, and homicides, while controlling for other influential factors. The results of the analysis provide a relatively strong statistical argument in favor of the hypothesis that the legalization of abortion was a key factor in the reduction of crime, consistent with the findings of Donohue and Levitt. Furthermore, the paper highlights the broader implications of family planning policies on societal outcomes, emphasizing how improved access to reproductive healthcare can positively influence overall social well-being.

• Keywords: Višeparametarska linearna regresija; zakona o prekidu trudnoće; stopa kriminaliteta
• Keywords (english): multivariate linear regression; abortion legislation; crime rates
• Language: croatian
• URN:NBN: urn:nbn:hr:217:365810
• Study programme: Title: Financial and Business Mathematics; Study programme type: university; Study level: graduate; Academic / professional title: sveučilišni magistar matematike (sveučilišni magistar matematike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2025-02-11 16:37:31