Bounding Causal Effects Using Data from a Contaminated Natural Experiment: Analysing the Effects of Teenage Childbearing

Political scientists often attempt to exploit natural experiments to estimate causal effects. We explore how variation in geography can be exploited as a natural experiment and review several assumptions under which geographic natural experiments yield valid causal estimates. In particular, we focus on cases where a geographic or administrative boundary splits units into treated and control areas. The different identification assumptions we consider suggest testable implications, which we use to establish their plausibility. Our methods are illustrated with an original study of whether ballot initiatives increase turnout in Wisconsin and Ohio, which illustrates the strengths and weaknesses of causal inferences based on geographic natural experiments.

Download Full-text

The Impact of the Internet on Information Search for Automobiles

Journal of Marketing Research ◽

10.1509/jmkr.40.2.193.19221 ◽

2003 ◽

Vol 40 (2) ◽

pp. 193-209 ◽

Cited By ~ 172

Author(s):

Brian T. Ratchford ◽

Myung-Soo Lee ◽

Debabrata Talukdar

Keyword(s):

Information Search ◽

Natural Experiment ◽

The Internet ◽

Search Effort ◽

Use Of The Internet ◽

Using Data ◽

The Impact ◽

Source Of Information

Using data from surveys of automobile buyers collected in 1990 and 2000 in a natural experiment setting, the authors study the determinants of use of the Internet as a source of information on automobiles, its impact on the use of other sources, and its impact on total search effort. The results indicate that the Internet draws attention in approximately the same proportion from other sources. The results also show that those who use the Internet to search for automobiles are younger and more educated and search more in general. However, the analysis also indicates that they would have searched even more if the Internet had not been present.

Download Full-text

A Discordance Weighting Approach Estimating Occupational and Income Returns to Education

Twin Research and Human Genetics ◽

10.1017/thg.2018.20 ◽

2018 ◽

Vol 21 (3) ◽

pp. 191-202

Author(s):

Matthew A. Andersson

Keyword(s):

Natural Experiment ◽

Returns To Education ◽

Twin Pair ◽

Identical Twins ◽

Causal Effects ◽

Predictive Analysis ◽

Twin Data ◽

Random Nature

Schooling differences between identical twins are often utilized as a natural experiment to estimate returns to education. Despite longstanding doubts about the truly random nature of within-twin-pair schooling discordance, such discordance has not yet been understood comprehensively, in terms of diverse between- and within-family peer, academic, familial, social, and health exposures. Here, a predictive analysis using national U.S. midlife twin data shows that within-pair schooling differences are endogenous to a variety of childhood exposures. Using discordance propensities, returns to education under a true natural experiment are simulated. Results for midlife occupation and income reveal differences in estimated returns to education that are statistically insignificant, suggesting that twin-based estimates of causal effects are robust. Moreover, identical and fraternal twins show similar levels of discordance endogeneity and similar responses to propensity weighting, suggesting that the identical twins may not provide demonstrably better leverage in the causal identification of educational returns.

Download Full-text

Comparing Disciplinary Infraction Rates of North Carolina Fair Sentencing and Structured Sentencing Inmates: A Natural Experiment

The Prison Journal ◽

10.1177/0032885599079001004 ◽

1999 ◽

Vol 79 (1) ◽

pp. 45-71 ◽

Cited By ~ 9

Author(s):

JOHN M. MEMORY ◽

GUANG GUO ◽

KEN PARKER ◽

TOM SUTTON

Keyword(s):

North Carolina ◽

Natural Experiment ◽

Negative Binomial ◽

Cox Regression ◽

Negative Binomial Regression ◽

Research Literature ◽

Prison Inmates ◽

Binomial Regression ◽

Truth In Sentencing ◽

Using Data

Using data collected from June 1, 1995, to August 30, 1996, the researchers compared the disciplinary conviction rates of North Carolina prison inmates admitted during the study period before the truth-in-sentencing law and inmates admitted during that period under the truth-in-sentencing law. Based on deterrence theory, the researchers hypothesized that pre-truth-in-sentencing inmates, who could lose time off for good behavior and parole as results of a disciplinary conviction, would have higher disciplinary conviction rates than truth-in-sentencing inmates. Truth-in-sentencing inmates, with shorter sentences, could lose neither time off for good behavior nor parole as a result of disciplinary conviction. Cox regression and negative binomial regression procedures using control variables identified in the research literature generally supported the research hypotheses.

Download Full-text

The Socioeconomic Consequences of Teenage Childbearing: Findings from a Natural Experiment

Family Planning Perspectives ◽

10.2307/2135923 ◽

1993 ◽

Vol 25 (4) ◽

pp. 156 ◽

Cited By ~ 58

Author(s):

Jeff Grogger ◽

Stephen Bronars

Keyword(s):

Natural Experiment ◽

Teenage Childbearing ◽

Socioeconomic Consequences

Download Full-text

The role of pawnshops in risk coping in early twentieth-century Japan

Financial History Review ◽

10.1017/s0968565021000111 ◽

2021 ◽

pp. 1-25

Author(s):

Tatsuki Inoue

Keyword(s):

Twentieth Century ◽

Low Income ◽

Natural Experiment ◽

Financial Institution ◽

Influenza Pandemic ◽

The Poor ◽

Early Twentieth Century ◽

Using Data ◽

Risk Coping

This study examines the role of pawnshops as a risk-coping device in Japan in the early twentieth century, when the poor were very vulnerable to unexpected shocks such as illness. In contrast to European countries, Japanese pawnshops were the primary financial institution for low-income people up to the 1920s. Using data on pawnshop loans for more than 250 municipalities and exploiting the 1918–20 influenza pandemic as a natural experiment, we find that the adverse health shock increased the total amount of loans from pawnshops. This is because those who regularly relied on pawnshops borrowed more money from them than usual, and not because the number of people who used pawnshops increased. Our estimation results indicate that pawnshop loan amounts increased by approximately 7–10 percent due to the pandemic. These findings suggest that pawnshop loans were widely used as a risk-coping strategy.

Download Full-text

The Effects of Pre-Trial Detention on Conviction, Future Crime, and Employment: Evidence from Randomly Assigned Judges

The American Economic Review ◽

10.1257/aer.20161503 ◽

2018 ◽

Vol 108 (2) ◽

pp. 201-240 ◽

Cited By ~ 66

Author(s):

Will Dobbie ◽

Jacob Goldin ◽

Crystal S. Yang

Keyword(s):

The United States ◽

Causal Effects ◽

Jail Inmates ◽

Formal Sector ◽

Criminal Conviction ◽

Pretrial Detention ◽

Using Data ◽

The Impact ◽

Government Benefits ◽

Bargaining Positions

Over 20 percent of prison and jail inmates in the United States are currently awaiting trial, but little is known about the impact of pretrial detention on defendants. This paper uses the detention tendencies of quasi-randomly assigned bail judges to estimate the causal effects of pretrial detention on subsequent defendant outcomes. Using data from administrative court and tax records, we find that pretrial detention significantly increases the probability of conviction, primarily through an increase in guilty pleas. Pretrial detention has no net effect on future crime, but decreases formal sector employment and the receipt of employment- and tax-related government benefits. These results are consistent with (i) pretrial detention weakening defendants' bargaining positions during plea negotiations and (ii) a criminal conviction lowering defendants' prospects in the formal labor market. (JEL J23, J31, J65, K41, K42)

Download Full-text