Better experimental design by hybridizing binary matching with imbalance optimization

We present a new experimental design procedure that divides a set of experimental units into two groups in order to minimize error in estimating a treatment effect. One concern is the elimination of large covariate imbalance between the two groups before the experiment begins. Another concern is robustness of the design to misspecification in response models. We address both concerns in our proposed design: we first place subjects into pairs using optimal nonbipartite matching, making our estimator robust to complicated nonlinear response models. Our innovation is to keep the matched pairs extant, take differences of the covariate values within each matched pair, and then use the greedy switching heuristic of Krieger et al. (2019) or rerandomization on these differences. This latter step greatly reduces covariate imbalance. Furthermore, our resultant designs are shown to be nearly as random as matching, which is robust to unobserved covariates. When compared to previous designs, our approach exhibits significant improvement in the mean squared error of the treatment effect estimator when the response model is nonlinear and performs at least as well when the response model is linear. Our design procedure can be found as a method in the open source R package available on CRAN called GreedyExperimentalDesign .     

Admissibility in Games1

Suppose that each player in a game is rational, each player thinks the other players are rational, and so on. Also, suppose that rationality is taken to incorporate an admissibility requirement—that is, the avoidance of weakly dominated strategies. Which strategies can be played? We provide an epistemic framework in which to address this question. Specifically, we formulate conditions of rationality and mth‐order assumption of rationality (RmAR) and rationality and common assumption of rationality (RCAR). We show that (i) RCAR is characterized by a solution concept we call a “self‐admissible set”; (ii) in a “complete” type structure, RmAR is characterized by the set of strategies that survive m+1 rounds of elimination of inadmissible strategies; (iii) under certain conditions, RCAR is impossible in a complete structure.     

A parametric analysis of prospect theory’s functionals for the general population

This article presents the results of an experiment that completely measures the utility function and probability weighting function for different positive and negative monetary outcomes, using a representative sample of N = 1,935 from the general public. The results confirm earlier findings in the lab, suggesting that utility is less pronounced than what is found in classical measurements where expected utility is assumed. Utility for losses is found to be convex, consistent with diminishing sensitivity, and the obtained loss-aversion coefficient of 1.6 is moderate but in agreement with contemporary evidence. The estimated probability weighting functions have an inverse-S shape and they imply pessimism in both domains. These results show that probability weighting is also an important phenomenon in the general population. Women and lower educated individuals are found to be more risk averse, in agreement with common findings. In contrast to previous studies that ascribed gender differences in risk attitudes solely to differences in the degree utility curvature, however, our results show that this finding is primarily driven by loss aversion and, for women, also by a more pessimistic psychological response toward the probability of obtaining the best possible outcome.     

A Comprehensive Model for Measuring the Potential Impact of Information Technology on Organizational Strategic Variables*

The existing literature on the impact of information technology (IT) does not include rigorous theory building or empirical studies. This research seems to be the first comprehensive investigation towards the development of an empirically validated comprehensive model for understanding the potential impact of IT on organizational strategic variables. More specifically, organizational and industrial variables that appeared to be affected by IT are identified, measured, and operationalized in the form of a comprehensive model. This study is based on structured interviews with a carefully selected sample of 31 strategic managers who had experience using IT for strategic decisions. In addition, the variables included in the model are well grounded in the information systems literature. The variables are then empirically validated and their reliabilities critically tested. A comprehensive model is derived from these validated variables. The model is a first step towards measuring the overall potential impact of IT on an organization. The model can also be used to gauge IT's potential impact on individual strategic variables. A set of hypotheses is also presented for future research. The hypotheses primarily relate to the impact of IT on organizational strategic performance. The model provides an empirically validated foundation for testing of such hypotheses.     

Adding Insult to Injury: Sex,Sexual Orientation,and Juror Decision-Making in a Case of Intimate Partner Violence

Societal definitions of intimate partner violence (IPV) are highly gendered and heteronormative, resulting in dissonance regarding cases of same-sex IPV. This study explored perceptions of IPV when the context of the case is inconsistent with societal norms regarding sex and sexuality. Mock jurors read a vignette describing a case of alleged IPV in which the sex and sexual orientation of the defendant were manipulated. Participants (N = 415) rendered a verdict and provided ratings of the defendant, victim, and case. Results suggest participants were more confident in a guilty verdict when the defendant was male, compared to female. Further, male defendants were perceived as more morally responsible, but only when the victim was female. Perceptions regarding the crime suggest violence perpetrated by a man against a woman is viewed more adversely than any other condition. Data are discussed in terms of implications for legal decision-makers and public policy.     

Impact of a sleep course on sleep,mood and anxiety symptoms in college students: A pilot study

Objective: To examine the impact of a sleep course on sleep-related behaviors, mood, and anxiety in college students. Participants: Participants were 145 students enrolled in either the sleep course (n = 70) or a psychology course (n = 75); data were collected in September 2014, November 2014, and February 2015. Methods: Sleep characteristics and symptoms of depression and anxiety were assessed using validated questionnaires and sleep logs. Linear, logistic and proportional odds regression models were used to test course effects. Results: In November, sleep course students reported significant differences in sleep hygiene (SHI; p < .001), perceived sleep latency (PSQI; p < .05), and circadian sleep phase (MEQ; p < .05), compared to controls. In February, the sleep course students maintained most of the aforementioned gains and reported fewer symptoms of depression (CES-D; p = .05) and anxiety (BAI; p < .05). Conclusions: These positive preliminary results indicate that focused education has the potential to improve sleep among college students.     

Earning Gaps for Chinese Immigrants in Canada and the United States

This study compares the US and Canada on the gap in earnings between Chinese immigrants and native‐born whites. Canada and the US are arguably more alike than most possible country pairings, yet they differ in significant ways in their approaches to immigration and integration. The primary difference between Canada and the US regarding immigration policy is that Canada selects a larger proportion of economic immigrants – that is, those admitted based on their ability to contribute to the economy – than the US's focus on family reunification. Canadian immigration and multicultural integration policy does not appear to improve Chinese immigrant earnings in the way that might be predicted from Canada's skilled‐based immigrant selection policy and welcoming social context. In spite of a more laissez‐faire approach to immigrant integration and a less skill‐selective immigration policy, we show that Chinese immigrants are earning relatively more in the US than in Canada.     

The Stratification of Attendance at Cultural Activities in Canada

Scholars have debated the relative applicability of homology and omnivorousness, two theories of cultural stratification, for explaining links between socioeconomic position and cultural repertoires. However, the discussion has mostly focused on musical tastes rather than attendance at cultural activities. Using data from the 2010 Canadian General Social Survey on Time Use, I examine how measures of socioeconomic position predict attendance at 12 different kinds of cultural activities. I apply three analytical techniques to this data set: (1) binary logistic regressions to investigate the socioeconomic bases of attendance at each cultural activity; (2) ordered logistic regression to assess the nature of the relationship between socioeconomic position and omnivorous attendance; and (3) latent class analysis to identify clusters of attendance and the socioeconomic bases thereof. Controlling for demographic factors, I find that education and income are positively associated with attendance at each activity and with omnivorous cultural engagement. The latent class model reveals four distinct groups: highbrow omnivores, selective omnivores, univores, and inactive people. Education and income predict membership in the omnivorous groups, with stronger effects for highbrow omnivores. I confirm that omnivorousness is associated with cultural and economic elites, but also reveal different gradations of omnivorousness, thus suggesting that the two theoretical frameworks are to a degree entangled with one another.     

Optimal global rates of convergence for nonparametric regression with unbounded data

Estimation of regression functions from independent and identically distributed data is considered. The _L2$L_2$ error with integration with respect to the design measure is used as an error criterion. Usually in the analysis of the rate of convergence of estimates a boundedness assumption on the explanatory variable X$X$ is made besides smoothness assumptions on the regression function and moment conditions on the response variable Y$Y$. In this article we consider the kernel estimate and show that by replacing the boundedness assumption on X$X$ by a proper moment condition the same (optimal) rate of convergence can be shown as for bounded data. This answers Question 1 in Stone [1982. Optimal global rates of convergence for nonparametric regression. Ann. Statist., 10, 1040–1053].