Joseph T Ornstein
Biographic Data
| ID | 1162364 |
|---|---|
| NAME | Joseph T Ornstein |
| GIVEN NAMES | Joseph T |
| FAMILY NAME | Ornstein |
| SIGNATURE | ORNSTEIN J T |
| AFFILIATIONS | University of Georgia |
| ORCID | 0000-0002-5704-2098 |
| VERIFIED | Yes |
| TOTAL WORKS | 13 |
| TOTAL CITATIONS | 30 |
| AUTHOR COUNT | 13 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 2014 |
| LATEST PUBLICATION YEAR | 2026 |
| H-INDEX | 3 |
Survey Quality and Acquiescence Bias: A Cautionary Tale
In this note, we offer a cautionary tale on the dangers of drawing inferences from low-quality online survey datasets. We reanalyze and replicate a survey experiment studying the effect of acquiescence bias on estimates of conspiratorial beliefs and political misinformation. Correcting a minor data coding error yields a puzzling result: respondents with a postgraduate education appear to be the most prone to acquiescence bias. We conduct two prer…
Probabilistic Record Linkage Using Pretrained Text Embeddings
Pretrained text embeddings are a fast and scalable method for determining whether two texts have similar meaning, capturing not only lexical similarity, but semantic similarity as well. In this article, I show how to incorporate these measures into a probabilistic record linkage procedure that yields considerable improvements in both precision and recall over existing methods. The procedure even allows researchers to link datasets across differen…
How to train your stochastic parrot: Large Language Models for Political Texts
We demonstrate how few-shot prompts to large language models (LLMs) can be effectively applied to a wide range of text-as-data tasks in political science—including sentiment analysis, document scaling, and topic modeling. In a series of pre-registered analyses, this approach outperforms conventional supervised learning methods without the need for extensive data pre-processing or large sets of labeled training data. Performance is comparable to e…
Hometown Advantage: Voter Preferences for Community Embeddedness in Local Contests
Every year, Americans elect hundreds of thousands of candidates to local public office, typically in low-attention, nonpartisan races. How do voters evaluate candidates in these sorts of elections? Previous research suggests that, absent party cues, voters rely on a set of heuristic shortcuts – including the candidate’s name, profession, and interest group endorsements – to decide whom to support. In this paper, we suggest that community embedded…
How the Trump Administration's Quota Policy Transformed Immigration Judging
The Trump administration implemented a controversial performance quota policy for immigration judges in October 2018. The policy's political motivations were clear: to pressure immigration judges to order more immigration removals and deportations as quickly as possible. Previous attempts by U.S. presidents to control immigration judges were ineffective, but this quota policy was different because it credibly threatened judges' job security and p…
Who Represents the Renters
Owning a home profoundly shapes Americans’ economic and political lives and preferences. A wide body of housing policy research suggests that homeowners receive favorable treatment from public policy at all levels of government. We know virtually nothing, however, about the descriptive representation of renters and homeowners. This paper combines a novel data set of over 10,000 local, state, and federal officials with administrative data on prope…
Zone defense: Why liberal cities build too few homes
In this article, I investigate a puzzling feature of American urban politics: cities with more liberal residents tend to enact more restrictive zoning policies and permit fewer new housing units each year than similar conservative cities. To help explain this puzzle, I develop a formal model in which local governments regulate the size of their population to balance the benefits of agglomeration with the costs of congestion. To defend against con…
Draining the tobacco swamps: Shaping the built environment to reduce tobacco retailer proximity to residents in 30 big US cities
Combining geospatial data on residential and tobacco retailer density in 30 big US cities, we find that a large majority of urban residents live in tobacco swamps - neighborhoods where there is a glut of tobacco retailers. In this study, we simulate the effects of tobacco retail reduction policies and compare probable changes in resident-to-retailer proximity and retailer density for each city. While measures of proximity and density at baseline …
An application of agent-based modeling to explore the impact of decreasing incarceration rates and increasing drug treatment access on sero-discordant partnerships among people who inject drugs
Moving From Metrics to Mechanisms to Evaluate Tobacco Retailer Policies: Importance of Retail Policy in Tobacco Control
AffiliationsDouglas A. Luke, Joseph T. Ornstein, and Todd B. Combs are with the Center for Public Health Systems Science, Brown School, Washington University, St. Louis, MO. Lisa Henriksen is with the Stanford Prevention Research Center, School of Medicine, Stanford University, Stanford, CA. Maggie Mahoney is a tobacco policy and legal consultant in Minneapolis, MN
Stacked Regression and Poststratification
I develop a procedure for estimating local-area public opinion called stacked regression and poststratification (SRP), a generalization of classical multilevel regression and poststratification (MRP). This procedure employs a diverse ensemble of predictive models—including multilevel regression, LASSO, k-nearest neighbors, random forest, and gradient boosting—to improve the cross-validated fit of the first-stage predictions. In a Monte Carlo simu…
Modelling the impact of menthol sales restrictions and retailer density reduction policies: Insights from tobacco town Minnesota
Our simulations revealed the importance of context, for example, lower income communities in urban areas begin with higher retailer density and may need stronger policies to show impact, as well as the need to focus on differential effects for priority populations, for example, combinations of policies may equalise the average distance travelled to purchase. Adapting and combining policies could enhance the sustainability of policy effects and re…
Frequency of monotonicity failure under Instant Runoff Voting: Estimates based on a spatial model of elections
How to train your stochastic parrot: Large Language Models for Political Texts
We demonstrate how few-shot prompts to large language models (LLMs) can be effectively applied to a wide range of text-as-data tasks in political science—including sentiment analysis, document scaling, and topic modeling. In a series of pre-registered analyses, this approach outperforms conventional supervised learning methods without the need for extensive data pre-processing or large sets of labeled training data. Performance is comparable to e…
Frequency of monotonicity failure under Instant Runoff Voting: Estimates based on a spatial model of elections
Stacked Regression and Poststratification
I develop a procedure for estimating local-area public opinion called stacked regression and poststratification (SRP), a generalization of classical multilevel regression and poststratification (MRP). This procedure employs a diverse ensemble of predictive models—including multilevel regression, LASSO, k-nearest neighbors, random forest, and gradient boosting—to improve the cross-validated fit of the first-stage predictions. In a Monte Carlo simu…
How the Trump Administration's Quota Policy Transformed Immigration Judging
The Trump administration implemented a controversial performance quota policy for immigration judges in October 2018. The policy's political motivations were clear: to pressure immigration judges to order more immigration removals and deportations as quickly as possible. Previous attempts by U.S. presidents to control immigration judges were ineffective, but this quota policy was different because it credibly threatened judges' job security and p…
Hometown Advantage: Voter Preferences for Community Embeddedness in Local Contests
Every year, Americans elect hundreds of thousands of candidates to local public office, typically in low-attention, nonpartisan races. How do voters evaluate candidates in these sorts of elections? Previous research suggests that, absent party cues, voters rely on a set of heuristic shortcuts – including the candidate’s name, profession, and interest group endorsements – to decide whom to support. In this paper, we suggest that community embedded…
Frequency of monotonicity failure under Instant Runoff Voting: Estimates based on a spatial model of elections
Modelling the impact of menthol sales restrictions and retailer density reduction policies: Insights from tobacco town Minnesota
Our simulations revealed the importance of context, for example, lower income communities in urban areas begin with higher retailer density and may need stronger policies to show impact, as well as the need to focus on differential effects for priority populations, for example, combinations of policies may equalise the average distance travelled to purchase. Adapting and combining policies could enhance the sustainability of policy effects and re…
Moving From Metrics to Mechanisms to Evaluate Tobacco Retailer Policies: Importance of Retail Policy in Tobacco Control
AffiliationsDouglas A. Luke, Joseph T. Ornstein, and Todd B. Combs are with the Center for Public Health Systems Science, Brown School, Washington University, St. Louis, MO. Lisa Henriksen is with the Stanford Prevention Research Center, School of Medicine, Stanford University, Stanford, CA. Maggie Mahoney is a tobacco policy and legal consultant in Minneapolis, MN
Stacked Regression and Poststratification
I develop a procedure for estimating local-area public opinion called stacked regression and poststratification (SRP), a generalization of classical multilevel regression and poststratification (MRP). This procedure employs a diverse ensemble of predictive models—including multilevel regression, LASSO, k-nearest neighbors, random forest, and gradient boosting—to improve the cross-validated fit of the first-stage predictions. In a Monte Carlo simu…
An application of agent-based modeling to explore the impact of decreasing incarceration rates and increasing drug treatment access on sero-discordant partnerships among people who inject drugs
Draining the tobacco swamps: Shaping the built environment to reduce tobacco retailer proximity to residents in 30 big US cities
Combining geospatial data on residential and tobacco retailer density in 30 big US cities, we find that a large majority of urban residents live in tobacco swamps - neighborhoods where there is a glut of tobacco retailers. In this study, we simulate the effects of tobacco retail reduction policies and compare probable changes in resident-to-retailer proximity and retailer density for each city. While measures of proximity and density at baseline …
Who Represents the Renters
Owning a home profoundly shapes Americans’ economic and political lives and preferences. A wide body of housing policy research suggests that homeowners receive favorable treatment from public policy at all levels of government. We know virtually nothing, however, about the descriptive representation of renters and homeowners. This paper combines a novel data set of over 10,000 local, state, and federal officials with administrative data on prope…
Zone defense: Why liberal cities build too few homes
In this article, I investigate a puzzling feature of American urban politics: cities with more liberal residents tend to enact more restrictive zoning policies and permit fewer new housing units each year than similar conservative cities. To help explain this puzzle, I develop a formal model in which local governments regulate the size of their population to balance the benefits of agglomeration with the costs of congestion. To defend against con…
Hometown Advantage: Voter Preferences for Community Embeddedness in Local Contests
Every year, Americans elect hundreds of thousands of candidates to local public office, typically in low-attention, nonpartisan races. How do voters evaluate candidates in these sorts of elections? Previous research suggests that, absent party cues, voters rely on a set of heuristic shortcuts – including the candidate’s name, profession, and interest group endorsements – to decide whom to support. In this paper, we suggest that community embedded…
How the Trump Administration's Quota Policy Transformed Immigration Judging
The Trump administration implemented a controversial performance quota policy for immigration judges in October 2018. The policy's political motivations were clear: to pressure immigration judges to order more immigration removals and deportations as quickly as possible. Previous attempts by U.S. presidents to control immigration judges were ineffective, but this quota policy was different because it credibly threatened judges' job security and p…
Probabilistic Record Linkage Using Pretrained Text Embeddings
Pretrained text embeddings are a fast and scalable method for determining whether two texts have similar meaning, capturing not only lexical similarity, but semantic similarity as well. In this article, I show how to incorporate these measures into a probabilistic record linkage procedure that yields considerable improvements in both precision and recall over existing methods. The procedure even allows researchers to link datasets across differen…
How to train your stochastic parrot: Large Language Models for Political Texts
We demonstrate how few-shot prompts to large language models (LLMs) can be effectively applied to a wide range of text-as-data tasks in political science—including sentiment analysis, document scaling, and topic modeling. In a series of pre-registered analyses, this approach outperforms conventional supervised learning methods without the need for extensive data pre-processing or large sets of labeled training data. Performance is comparable to e…
Survey Quality and Acquiescence Bias: A Cautionary Tale
In this note, we offer a cautionary tale on the dangers of drawing inferences from low-quality online survey datasets. We reanalyze and replicate a survey experiment studying the effect of acquiescence bias on estimates of conspiratorial beliefs and political misinformation. Correcting a minor data coding error yields a puzzling result: respondents with a postgraduate education appear to be the most prone to acquiescence bias. We conduct two prer…
Political science (9 works) · Law (8 works) · Economics (6 works) · Law (6 works) · Politics (5 works) · Business (4 works) · Computer Science (4 works) · Medicine (4 works) · Sociology (4 works) · Computational and Text Analysis Methods (3 works)