A simulation comparison of estimators for a regression coefficient under differential non-response

We consider the estimation of a regression coefficient in a linear regression when observations are missing due to nonresponse. Response is assumed to be determined by a nonobservable variable which is linearly related to an observable variable. The values of the observable variable are assumed to be available for the whole sample but the variable is not includsd in the regression relationship of interest . Several alternative estimators have been proposed for this situation under various simplifying assumptions. A sampling theory approach provides three alternative estimatrs by considering the observatins as obtained from a sub-sample, selected on the basis of the fully observable variable , as formulated by Nathan and Holt (1980). Under an econometric approach, Heckman (1979) proposed a two-stage (probit and OLS) estimator which is consistent under specificconditions. A simulation comparison of the four estimators and the ordinary least squares estimator , under multivariate normality of all the variables involved, indicates that the econometric approach estimator is not robust to departures from the conditions underlying its derivation, while two of the other estimators exhibit a similar degree of stable performance over a wide range of conditions. Simulations for a non-normal distribution show that gains in performance can be obtained if observations on the independent variable are available for the whole population.     

THE EFFECTS OF RECREATIONAL MARIJUANA LEGALIZATION AND DISPENSING ON OPIOID MORTALITY

This study documents how the changing legal status of marijuana has impacted mortality in the United States over the past two decades. We use a difference-in-difference approach to estimate the effect of medical marijuana laws (MML) and recreational marijuana laws (RML) on fatalities from opioid overdoses, and we find that marijuana access induces sharp reductions in opioid mortality rates. Our research corroborates prior findings on MMLs and offers the first causal estimates of RML impacts on opioid mortality to date, the latter of which is particularly important given that RMLs are far more expansive in scope and reach than MMLs. In our preferred econometric specification, we estimate that RMLs reduce annual opioid mortality in the range of 20%–35%, with particularly pronounced effects for synthetic opioids. In further analysis, we demonstrate how RML impacts vary among demographic groups, shedding light on the distributional consequences of these laws. Our findings are especially important and timely given the scale of the opioid crisis in the United States and simultaneously evolving attitudes and regulations on marijuana use. (JEL I18, K32, H75)     

Effects of wearing a pressure redistribution belt while lying in a hospital bed

Bedsores (ulcers) are caused by multiple factors which include, but are not limited to; pressure, shear force, friction, temperature, age and medication. Specialised support services, such as specialised mattresses, sheepskin coverings etc., are thought to decrease or relieve pressure, resulting in a lowering of pressure ulcer incidence [3]. The primary aim of this study was to compare the upper/central body pressure distribution between normal lying in a hospital bed versus the use of a pressure redistribution belt. The study involved 16 healthy voluntary subjects lying on a hospital bed with and without wearing the belt. Results showed that the use of a pressure redistribution belt results in reduced pressure peaks and prevents the pressure from increasing over time.     

Exploring Trajectories of Pornography Use Through Adolescence and Emerging Adulthood

While the scholarly literature on pornography use is growing, much of this literature has examined pornography use as a static feature that does not change. Despite this trend, pornography use, like most sexual behaviors, is likely best viewed as a dynamic feature that may shift across the developmental life span. Using a sample of 908 adults from the United States, retrospective data on pornography use through adolescence and emerging adulthood were gathered to explore trajectories of pornography use across these developmental periods. Latent mixture models suggested the presence of common patterns of use across both developmental periods. Adolescence patterns appeared to largely be distinguished by those who either engaged or did not engage with pornography, while emerging adulthood data revealed the presence of a group of experimenters who engaged in pornography through adolescence but then decreased use through their 20s. Men were found to be more likely to have consistent profiles of pornography use, while single adults were likely to have delayed entry into pornography use. Associations with adult mental health and pornography use were found, suggesting that early exposure to pornography was related to elevated current pornography use patterns and, to a lesser extent, dysfunctional pornography use. Trajectories also had a weak association with life satisfaction, with individuals reporting trajectories involving consistent pornography use reporting lower life satisfaction after controls.     

Spatial Statistics for Dyadic Data: Analyzing the Relationship Landscape

Spatial statistics has a rich tradition in earth, economic, and epidemiological sciences and has potential to affect the study of couples as well. When applied to couple data, spatial statistics can model within‐ and between‐couple differences with results that are readily accessible for researchers and clinicians. This article offers a primer in using spatial statistics as a methodological tool for analyzing dyadic data. The article will introduce spatial approaches, review data structure required for spatial analysis, available software, and examples of data output.     

High and low levels of adolescent peer status are associated longitudinally with socioevaluative concern

This study examined linear and curvilinear longitudinal associations between peer status (i.e., likeability and popularity) and socioevaluative concern, a socio-cognitive feature characterized by attunement to judgment from peers. A sample of 716 adolescents (M_age = 16.01, SD = 1.25; 54% female; 46.5% White; 69.5% reduced-price lunch) was assessed twice annually. Likeability and popularity were assessed with peer nominations at Time 1. Measures of general (rejection sensitivity, peer importance) and online (digital status seeking, online status importance) socioevaluative concern were obtained at Times 1 and 2. High and low levels of likeability were longitudinally associated with increased peer importance, while high and low levels of popularity were associated with increased digital status seeking, and decreased online status importance for girls.