Machine learning of large-scale spatial distributions of wild turkeys with high-dimensional environmental data.

Species distribution modeling often involves high-dimensional environmental data. Large amounts of data and multicollinearity among covariates impose challenges to statistical models in variable selection for reliable inferences of the effects of environmental factors on the spatial distribution of species. Few studies have evaluated and compared the performance of multiple machine learning (ML) models in handling multicollinearity. Here, we assessed the effectiveness of removal of correlated covariates and regularization to cope with multicollinearity in ML models for habitat suitability. Three machine learning algorithms maximum entropy (MaxEnt), random forests (RFs), and support vector machines (SVMs) were applied to the original data (OD) of 27 landscape variables, reduced data (RD) with 14 highly correlated covariates being removed, and 15 principal components (PC) of the OD accounting for 90% of the original variability. The performance of the three ML models was measured with the area under the curve and continuous Boyce index. We collected 663 nonduplicated presence locations of Eastern wild turkeys (Meleagris gallopavo silvestris) across the state of Mississippi, United States. Of the total locations, 453 locations separated by a distance of ≥2 km were used to train the three ML algorithms on the OD, RD, and PC data, respectively. The remaining 210 locations were used to validate the trained ML models to measure ML performance. Three ML models had excellent performance on the RD and PC data. MaxEnt and SVMs had good performance on the OD data, indicating the adequacy of regularization of the default setting for multicollinearity. Weak learning of RFs through bagging appeared to alleviate multicollinearity and resulted in excellent performance on the OD data. Regularization of ML algorithms may help exploratory studies of the effects of environmental factors on the spatial distribution and habitat suitability of wildlife.

Academic demands are associated with reduced alcohol consumption by college students: evidence from a daily analysis.

There is little empirical evidence linking academic demands or rigor to alcohol consumption by college students. In a 3-week daily study of full-time college students at a public, residential campus in the United States, both current day and next day's academic demands were negatively related to alcohol consumption, and these relationships were mediated by daily academic effort. Academic demands on the previous day were not related to alcohol consumption, indicating that students do not engage in compensatory or celebratory drinking when demands end. The results suggest that enhancing academic expectations and rigor may be an appropriate intervention target to reduce student drinking.

College student employment and drinking: a daily study of work stressors, alcohol expectancies, and alcohol consumption.

We examined the within-person relationships between daily work stressors and alcohol consumption over 14 consecutive days in a sample of 106 employed college students. Using a tension reduction theoretical framework, we predicted that exposure to work stressors would increase alcohol consumption by employed college students, particularly for men and those with stronger daily expectancies about the tension reducing properties of alcohol. After controlling for day of the week, we found that hours worked were positively related to number of drinks consumed. Workload was unrelated to alcohol consumption, and work-school conflict was negatively related to consumption, particularly when students expressed strong beliefs in the tension reducing properties of alcohol. There was no evidence that the effects of work stressors were moderated by sex. The results illustrate that employment during the academic year plays a significant role in college student drinking and suggest that the employment context may be an appropriate intervention site to address the problem of student drinking.

Job characteristics and college performance and attitudes: a model of work-school conflict and facilitation.

The processes linking job characteristics to school performance and satisfaction in a sample of 253 full-time college students were examined from 2 role theory perspectives, 1 of which emphasized resource scarcity and the other resource expansion. Model tests using structural equation modeling showed that 2 resource-enriching job characteristics, job-school congruence and job control, were positively related to work-school facilitation (WSF). Two resource-depleting job characteristics, job demands and work hours, were positively related to work-school conflict (WSC), and job control was negatively related to WSC. In turn, WSF was positively related to school performance and satisfaction, and WSC was negatively related to school performance. Both WSF and WSC mediated the relationship between the job characteristics and school outcomes. There was no evidence of interactive effects between enriching and depleting job characteristics on interrole processes.

The impact of job characteristics on work-to-family facilitation: testing a theory and distinguishing a construct.

This study used objective measures of job characteristics appended to the National Survey of Midlife Development in the United States (MIDUS), self-reported job characteristics, and an individual resource characteristic (orientation toward personal growth) to test a theory of work-family facilitation. Results indicated that resource-rich jobs enable work-to-family facilitation. A higher level of work-to-family facilitation was reported by individuals in jobs with more autonomy and variety and whose jobs required greater substantive complexity and social skill. There was no support for the hypotheses that these effects would be more pronounced for individuals with higher levels of personal growth. The authors found significant differences in the strength of the associations of job characteristics with work-to-family facilitation and work-tofamily conflict, suggesting they are different constructs with distinct antecedents.