Discussion Paper No. 424
September 11, 2023
Abadie's Kappa and Weighting Estimators of the Local Average Treatment Effect
Author:
Abstract:
In this paper we study the finite sample and asymptotic properties of various weighting estimators of the local average treatment effect (LATE), several of which are based on Abadie's (2003) kappa theorem. Our framework presumes a binary treatment and a binary instrument, which may only be valid after conditioning on additional covariates. We argue that one of the Abadie estimators, which is weight normalized, is preferable in many contexts. Several other estimators, which are unnormalized, do not generally satisfy the properties of scale invariance with respect to the natural logarithm and translation invariance, thereby exhibiting sensitivity to the units of measurement when estimating the LATE in logs and the centering of the outcome variable more generally. On the other hand, when noncompliance is one-sided, certain unnormalized estimators have the advantage of being based on a denominator that is bounded away from zero. To reconcile these findings, we demonstrate that when the instrument propensity score is estimated using an appropriate covariate balancing approach, the resulting normalized estimator also shares this advantage. We use a simulation study and three empirical applications to illustrate our findings. In two cases, the unnormalized estimates are clearly unreasonable, with ``incorrect'' signs, magnitudes, or both.
Keywords:
JEL-Classification:
Download:
Discussion Paper No. 423
Peer Effects Heterogeneity and Social Networks in Education
Author:
Abstract:
This study focuses on the role of heterogeneity in network peer effects by accounting for network-specific factors and different driving mechanisms of peer behavior. We propose a novel Multivariate Instrumental Variable (MVIV) estimator which is consistent for a large number of networks keeping the individual network size bounded. We apply this approach to estimate peer effects on school achievement exploiting the network structure of friendships within classrooms. The empirical evidence presented is based on a unique network dataset from German upper secondary schools. We show that accounting for heterogeneity is not only crucial from a statistical perspective, but also yields new structural insights into how class size and gender composition affect school achievement through peer behavior.
Keywords:
network heterogeneity; peer effects; multivariate instrumental variables; minimum distance estimation; school achievement;
JEL-Classification:
D85; L14; I21; C30; C36;
Download:
Discussion Paper No. 386
February 27, 2023
Measuring Preferences Over Intertemporal Profiles
Author:
Abstract:
Growing evidence indicates that utility over time is different from utility under risk. Hence, measuring intertemporal preferences (discounting and utility) exclusively from intertemporal choices is desirable. We develop a simple method for measuring intertemporal preferences. It is parameter-free in both discounting and utility, and allows a wider range of models to be measured than preceding methods. It is easy to implement, clear to subjects, incentive compatible, and does not require more measurements than existing methods if identical assumptions are imposed. In an experiment, we illustrate how the method can be used to test recent models with unconventional assumptions non-parametrically.
Keywords:
measuring time preferences; intertemporal profile; parameter-free;
JEL-Classification:
C91; D12; D91;
Download:
Discussion Paper No. 381
February 8, 2023
Cognitive Ability and Perceived Disagreement in Learning
Author:
Abstract:
Do agents believe to be agreeing more with others in the long-run? This paper designs an experiment to study how cognitive abilities affect actual and perceived disagreement in a standard sequential belief updating task with public signals. We document a persistent gap in the perception of disagreement as a function of cognitive ability. Higher cognitive ability is associated with less perceived disagreement, although the average subject underestimates the extent of actual disagreement regardless of cognitive ability. Learning about the state of the world has little effect on the evolution of perceived disagreement when controlling for cognitive ability. Providing subjects with information about their partner’s cognitive ability affects perceived disagreement only when the partner is less cognitively able.
Keywords:
cognitive ability; disagreement; learning;
JEL-Classification:
C90; D83; D89;
Download:
Discussion Paper No. 333
August 15, 2022
The Dynamics of Behavioral Responses During a Crisis
Author:
Abstract:
This paper investigates the dynamics of behavioral changes during a crisis. We study this in the context of the first year of the Covid-19 pandemic, where behavioral responses were important in mitigating the costs of the pandemic. To identify behavioral responses to unanticipated and transient health risk shocks, we combine high-frequency cellphone mobility data with detailed incidence data in Germany. Using an event-study design on local outbreaks, we find that county-level mobility immediately and significantly decreased by about 2.5% in response to an outbreak independent of non-pharmaceutical interventions. We also find that the reproduction rate decreased by about 17% in response to a local outbreak. Both behavioral responses are quite persistent even after the relative health risk has dissipated. By the time of the second wave, the behavioral response to a second or third shock is small or negligible. Our results demonstrate the importance of (1) integrating behavioral persistence in models used to study behavior and policies that change behavior, (2) the effectiveness of policies that provide high-frequency localized information on health risks, and (3) the potential persistence of behavioral changes after the Covid-19 pandemic has passed.
Keywords:
dynamics; behavioral response; crisis; covid-19;
JEL-Classification:
Download:
Discussion Paper No. 284
November 10, 2021
Preferences over Taxation of High-Income Individuals: Evidence from a Survey Experiment
Author:
Abstract:
Mobility of high-income individuals across borders puts pressure on governments to lower taxes. A central tenet of the corresponding textbook argument is that mobile individuals react to tax differentials through migra- tion, and in turn immobile individuals vote for lower taxes. We investigate to which extent this argument is complete. In particular, political ideology may influence voting on taxes. We vary mobility and foreign taxes in a survey experiment within the German Internet Panel (GIP), with more than 3,000 individuals participating. We find that while the treatment effects qualitatively confirm model predictions how voters take mobility of high-income earners into account when choosing domestic taxes, ideology matters: left-leaning high-income individuals choose higher taxes and emigrate less frequently than right-leaning ones. These findings are in line with the comparative- static predictions of a simple model of inequality aversion when the aversion parameters vary with ideology.
Keywords:
taxation; mobility; ideology; survey experiments;
JEL-Classification:
Download:
Discussion Paper No. 269
Signaling Motives in Lying Games
Author:
Abstract:
This paper studies the implications of agents signaling their moral type in a lying game. In the theoretical analysis, a signaling motive emerges where agents dislike being suspected of lying and where some types of liars are more stigmatized than others. The equilibrium prediction of the model can explain experimental data from previous studies, in particular on partial lying, where some agents dishonestly report a non payoff-maximizing report. I discuss the relationship with previous theoretical models of lying that conceptualize the image concern as an aversion to being suspected of lying. The second half of the paper tests the theoretical predictions in an experiment. In contrast to previous literature, the experimental results show no evidence that image concerns influence lying behavior in the laboratory.
Keywords:
lying; image concerns; honesty; experiment;
JEL-Classification:
Download:
Discussion Paper No. 253
November 9, 2021
Face Masks Increase Compliance with Physical Distancing Recommendations during the COVID-19 Pandemic
Author:
Abstract:
Governments across the world have implemented restrictive policies to slow the spread of COVID-19. Recommended face mask use has been a controversially discussed policy, among others, due to potential adverse effects on physical distancing. Using a randomized field experiment (N=300), we show that individuals keep a significantly larger distance from someone wearing a face mask than from an unmasked person. According to an additional survey experiment (N=456), masked individuals are not perceived as being more infectious than unmasked ones, but they are believed to prefer more distancing. This result suggests that, in times where mask use is voluntary, wearing a mask serves as a social signal for a preferred greater distance that is respected by others. Our findings provide strong evidence against the claim that mask use creates a false sense of security that would negatively affect physical distancing.
Keywords:
COVID-19; health policy; compliance; face masks; risk compensation; field experiment;
JEL-Classification:
Download:
Discussion Paper No. 239
Starke Erwartungsreaktionen auf Angela Merkels Covid-Erklärungen
Author:
Abstract:
Wir führen hochfrequente Befragungen der in Deutschland lebenden Personen durch und erheben die Erwartungen zur Dauer der Covid-bedingten Beschränkungen des öffentlichen Lebens. In einer ersten Analyse der Daten finden wir Hinweise, dass zwei in den Erhebungszeitraum fallenden öffentlichen Auftritte von Bundeskanzlerin Angela Merkel die Erwartungen stark beeinflussen. Insbesondere messen wir nach Merkels Pressekonferenz vom 15.4.2020 eine deutlich pessimistische Bewegung der Erwartungen und die beabsichtigten Konsumausgaben der Haushalte sinken zeitgleich. Die Ergebnisse legen nahe, dass die deutsche Politik über die Möglichkeit eines sehr wirksamen Erwartungsmanagements verfügt.
Keywords:
ökonomische Erwartungen; Covid-Shutdown;
JEL-Classification:
Download:
Discussion Paper No. 237
Second-Chance Offers and Buyer Reputation: Theory and Evidence on Auctions with Default
Author:
Abstract:
Winners in online auctions frequently fail to complete purchases. Major auction platforms therefore allow “second-chance” offers, where the runner-up bidder pays his own bid price, and they let sellers leave negative feedback on buyers who default. We show theoretically that (i) all else equal, the availability of second-chance offers reduces bids; (ii) sellers have no incentive to exclude bidders, even if they are nearly certain to default; (iii) buyer reputation systems reward bidders with a reputation for defaulting, counter to the idea of deterring such behavior. Our auction experiments support these predictions and provide insights on their practical relevance.
Keywords:
auctions; default; reputation; second-chance offers;
JEL-Classification: