Model selection criteria for dual-inflated data

ABSTRACT

Inflated data are prevalent in many situations and a variety of inflated models with extensions have been derived to fit data with excessive counts of some particular responses. The family of information criteria (IC) has been used to compare the fit of models for selection purposes. Yet despite the common use in statistical applications, there are not too many studies evaluating the performance of IC in inflated models. In this study, we studied the performance of IC for data with dual-inflated data. The new zero- and K-inflated Poisson (ZKIP) regression model and conventional inflated models including Poisson regression and zero-inflated Poisson (ZIP) regression were fitted for dual-inflated data and the performance of IC were compared. The effect of sample sizes and the proportions of inflated observations towards selection performance were also examined. The results suggest that the Bayesian information criterion (BIC) and consistent Akaike information criterion (CAIC) are more accurate than the Akaike information criterion (AIC) in terms of model selection when the true model is simple (i.e. Poisson regression (POI)). For more complex models, such as ZIP and ZKIP, the AIC was consistently better than the BIC and CAIC, although it did not reach high levels of accuracy when sample size and the proportion of zero observations were small. The AIC tended to over-fit the data for the POI, whereas the BIC and CAIC tended to under-parameterize the data for ZIP and ZKIP. Therefore, it is desirable to study other model selection criteria for dual-inflated data with small sample size.     

Minimum Scoring Rule Inference

Proper scoring rules are devices for encouraging honest assessment of probability distributions. Just like log‐likelihood, which is a special case, a proper scoring rule can be applied to supply an unbiased estimating equation for any statistical model, and the theory of such equations can be applied to understand the properties of the associated estimator. In this paper, we discuss some novel applications of scoring rules to parametric inference. In particular, we focus on scoring rule test statistics, and we propose suitable adjustments to allow reference to the usual asymptotic chi‐squared distribution. We further explore robustness and interval estimation properties, by both theory and simulations.     

大学生学习环境乐趣量表编制:方法与原则

本研究依据工作场所乐趣的相关理论,研拟讨论问题,透过大学生深入访谈,厘清大学生学习环境乐趣量表的各个因素与问题,并针对大学生问卷调查进行探索性因素分析与二阶验证性因素分析.研究结果表明,大学生学习环境乐趣量表可分三大因素:同侪互动、环境乐趣营造、学习气氛,量表具有良好的结构效度和效标关联效度,各项指针显示具有较好的稳定性和一致性.     

Responsive Listening in Long-Married Couples: A Psycholinguistic Perspective

Positive and responsive listening behavior benefits marital satisfaction, but previous reports have examined emotionally positive behavior confounded with responsive behavior, and focused primarily on younger marriages. Psycholinguistic views of listening suggest that responsive listening is distinct from emotionally positive listening. The former may change with an aging relationship, while the latter is unlikely to do so. Long-married couples share extensive common ground about recurrent conflicts, reducing the need for some listening behaviors. We observed 79 younger and older married couples, happily and unhappily married, discussing conflicts. We coded listening behaviors indicative of attention and comprehension (responsiveness) as well as those expressing emotions. We expected that older married couples would display lower frequencies of responsive listening behaviors than middle-aged couples. Results provide conditional support for this hypothesis. Implications for research on marital communication and aging are discussed.     

“We're Not Old!”: Older Women's Negotiation of Aging and Oldness

This article is based on participant observation research at a seniors' center in central Canada in which the writer sought to acquire an understanding of how older adults define, interpret, and negotiate their realities and identities. Through activity and group membership, the center members — the majority of whom are single, older women between the ages of 50 and 90 — seek to distance themselves from the category of “old” and the accompanying ageist stereotypes. Striving to establish and preserve their precarious membership in the “not old”, center members struggle to reconcile their belief and experience of older adulthood as a time of activity, health, and happiness with their ever-present fear of declining health and the realities of widowhood and the loss of youthful attractiveness.     

Why Do the Privileged Resort to Oppression? A Look at Some Intragroup Factors

This article shows that (intergroup) oppression can be strategically motivated by (intragroup) processes. It is often assumed that high-status groups oppress when their social position is declining (relative deprivation). Counterintuitively, research shows that oppression also occurs when their position is improving (gratification): a curvilinear relationship referred to as "the v-curve effect." We test the hypothesis that this relationship is due to intragroup processes within the high-status group: individuals respond strategically to elite norms. Two experiments manipulated participants' future prospects: to join the nation's elite in future (relative gratification), social stasis, or status decline (relative deprivation, Study 2). Elite norms toward immigrants (positive, negative) were manipulated independently. The curvilinear relationship was only found when norms were negative. In other words, those who anticipate joining the elite tailor their actions to the norms of their prospective in-group.     

Rewards and Costs in Adolescent Other-sex Friendships: Comparisons to Same-sex Friendships and Romantic Relationships

This study used a social exchange framework to examine the features of non-romantic other-sex (OS) friendships compared with same-sex (SS) friendships and romantic relationships. High school seniors (N  =  141) completed open-ended interviews about the benefits and costs of having OS friendships, SS friendships, and romantic relationships in general. As expected, perspective taking, learning about the other sex, and meeting the other sex were seen as rewards of OS friendships more often than for SS friendships and romantic relationships. Confusion about the nature of the relationship was seen as a cost of OS friendships more often than of SS friendships and romantic relationships. Intimacy, support, and companionship were mentioned less often as rewards of OS friendships than romantic relationships. Adolescents also completed questionnaires about their own specific relationships of each type. Their OS friendships were perceived as less supportive than their other two relationships; OS friendships were also seen as having fewer negative interactions than romantic relationships. Our findings expand the application of social exchange theory and lend empirical support to prior speculations about OS friendships and their importance in adolescents' social worlds.     

An Observational Investigation of Poker Style and the Five-Factor Personality Model

Little empirical investigation has been made of the relationship between personality and gambling play style. In an observation of on-table poker behavior, this study classified 44 players competing in an amateur league (43 male; mean age 32) according to two main dimensions of play style; tight or loose and aggressive or passive. Superstitious beliefs towards the game were additionally measured. The NEO-PI-R questionnaire (Costa and McCrae, Revised NEO personality inventory (NEO-PI-R) and NEO-five factor inventory (NEO-FFI) professional manual, 1992) was used to measure personality according to the five-factor model. Results showed players with superstitious beliefs to be significantly higher in neuroticism and lower in conscientiousness and than those with no superstitious beliefs. Results approaching significance showed players adopting an aggressive style to be higher in extraversion than passive players and superstitious players to be lower in extraversion than non-superstitious players. Analysis of play style according to age of player revealed a significantly higher mean age among loose compared to tight players. Implications of results concerning validity of these style classifications and potential development in future work are discussed.     

Minimum winning versus oversized coalitions in public finance: the role of uncertainty

This paper extends Persson et al.’s (J Polit Econ 108:1121–1161, 2000) simple legislature in the context of public finance with certainty to uncertainty. In our uncertain world, oversized coalitions (OSCs) as well as minimum winning coalitions (MWCs) may arise in equilibrium, and the agenda setter’s proposed policy may fail to receive a majority support. This is in marked contrast to the certain world, in which only MWCs can arise in equilibrium and the agenda setter’s proposal never fails to pass. When OSCs arise, we show that both public good provision and redistribution are likely to achieve their first-best solution, even if the legislature is simple.