On Association Coefficients for 2×2 Tables and Properties That Do Not Depend on the Marginal Distributions

We discuss properties that association coefficients may have in general, e.g., zero value under statistical independence, and we examine coefficients for 2×2 tables with respect to these properties. Furthermore, we study a family of coefficients that are linear transformations of the observed proportion of agreement given the marginal probabilities. This family includes the phi coefficient and Cohen’s kappa. The main result is that the linear transformations that set the value under independence at zero and the maximum value at unity, transform all coefficients in this family into the same underlying coefficient. This coefficient happens to be Loevinger’s H.     

A note to Bollen's alternative fit measure

The problem of dependence of the nonnormed fit index on sample size in covariance structure analysis is discussed. Contrary to Bollen (1986) we show that the mean of the nonnormed fit index is independent of sample size for true and almost true models whereas Bollen's alternative index does depend on sample size.     

Accuracy of parents' reports of height and weight

The accuracy of parents' reports of their own height and weight and the height and weight of their obese children, who were about to enter a weight control program, was assessed. Measured height and weights of 146 mothers, 55 fathers, and 150 children who attended a screening session were compared to the heights and weights they had previously reported on a demographic questionnaire. Eighty-four percent of the reported weights were accurate within ±5 lbs.; 71% of the reported heights were accurate within ±1 in. Parents' reports of weight tended to underestimate actual weights, with the magnitude of underestimation greater for mothers than for fathers, while reported heights overestimated actual height, with the magnitude of overestimation greatest for fathers. Errors in the parents' reports of children's weight were related to the child's actual weight and body mass index (BMI), with substantial underestimation of actual weight in the heaviest decile of children in the sample.Preparation of this paper was supported in part by Grant HDMH12520-01 from the National Institute of Child Health and Human Development and Mental Health. Reprints can be obtained from Rena R. Wing, Western Psychiatric Institute and Clinic, 3811 O'Hara Street, Pittsburgh, PA 15261.     

Male physical attractiveness in Britain and Malaysia: A cross-cultural study

Three purported cues to perceived male physical attractiveness are the waist-to-chest ratio (WCR), body mass index (BMI) and the waist-to-hip ratio (WHR). This study examined the relative contribution of each cue in several socio-economically distinct populations. Ninety-five female participants from Britain and Malaysia were asked to rate a set of images of real men with known WCR, BMI and WHR. The results showed clear differences along a gradient of socio-economic development. In urban settings, WCR was the primary component of attractiveness ratings, with BMI playing a smaller role and WHR not reaching significance. In the rural setting, BMI was the primary predictor of attractiveness, with WCR playing a more minor role and WHR not reaching significance. In general, urban participants were more reliant on body shape and chose a relatively slim figure with an ‘inverted triangle’ shape; rural participants were more reliant on body weight and chose a heavier figure with a less triangular shape. These findings are discussed in terms of evolutionary psychological explanations of mate selection and sociological theories that emphasise the effect of resource scarcity on preferences for body shapes and sizes.     

汉字笔迹与个性测评研究

本文采用汉字笔迹测量法和80－8神经类型量表法对大、中、小学生共计2153人进行了团体测验,各项测量指标所得到的数据,经统计检验,其主要结论如下：1．笔迹特征表现为年龄越小,以直笔、重笔、慢速、光边占的比例越大,13岁以后,笔迹特征出现明显分化,这表明,个性在13、14岁年龄阶段开始加速形成与发展．2．笔迹书写形式、书写速度、书写压力及稳定性等心理特征指标与其神经类型特征有密切的关系．3．根据笔迹书写形式、速度、压力及稳定性等基本特征指标的不同组合,划分为8种气质类型,并在实际应用中获得较为满意的效果．     

城市老年人社会支持网络与生活满意度的研究

本研究采用自编的社会支持网络调查表对上海市96位老人进行了调查，试图了解城市老年人社会支持的基本情况及其对生活满意度的影响。结果表明：（1）城市老年人社会支持网络得分为85．87±8．56（x±s）；（2）社会支持网络得分与生活满意度之间存在极其显著的正相关；（3）在各因素水平中，社会机构的支持对老年人生活满意度的影响最大，子女支持的影响次之，配偶支持的影响最小；情感支持的影响作用大于认知支持和行为支持。     

Extension of caution indices to mixed-format tests

Tatsuoka suggested several extended caution indices and their standardized versions, and these have been used as person-fit statistics by various researchers. However, these indices are only defined for tests with dichotomous items. This paper extends two of the popular standardized extended caution indices for use with polytomous items and mixed-format tests. Two additional new person-fit statistics are obtained by applying the asymptotic standardization of person-fit statistics for mixed-format tests. Detailed simulations are then performed to compute the Type I error rate and power of the four new person-fit statistics. Two real data illustrations follow. The new person-fit statistics appear to be satisfactory tools for assessing person fit for polytomous items and mixed-format tests.     

测量等价性的概念及其判定条件

测量等价性指的是,应用量表进行测量时,当观测变量和潜在特质之间的关系在相比较的各个组之间等同时,就称该量表具备测量等价性。特别地,来自不同群体但在潜在特质上得分相等的个体,他们观测变量的得分也应该相等。测量工具满足测量等价性的要求是进行组间差异比较的前提条件。该文首先明确了测量等价性的概念及其研究历史,然后阐述了测量等价性的重要性以及对测量等价性分析的必要性,进而讨论了在结构方程模型中测量等价性所要满足的5个条件,最后列举了模型优劣判定的拟合度指数     

Remarkable properties for diagnostics and inference of ranking data modelling

The Plackett-Luce model (PL) for ranked data assumes the forward order of the ranking process. This hypothesis postulates that the ranking process of the items is carried out by sequentially assigning the positions from the top (most liked) to the bottom (least liked) alternative. This assumption has been recently relaxed with the Extended Plackett-Luce model (EPL) through the introduction of the discrete reference order parameter, describing the rank attribution path. By starting from two formal properties of the EPL, the former related to the inverse ordering of the item probabilities at the first and last stage of the ranking process and the latter well-known as independence of irrelevant alternatives (or Luce's choice axiom), we derive novel diagnostic tools for testing the appropriateness of the EPL assumption as the actual sampling distribution of the observed rankings. These diagnostic tools can help uncovering possible idiosyncratic paths in the sequential choice process. Besides contributing to fill the gap of goodness-of-fit methods for the family of multistage models, we also show how one of the two statistics can be conveniently exploited to construct a heuristic method, that surrogates the maximum likelihood approach for inferring the underlying reference order parameter. The relative performance of the proposals, compared with more conventional approaches, is illustrated by means of extensive simulation studies.     

Poverty,ethnicity, and risk of obesity among low birth weight infants

The independent and joint effects of family and neighborhood poverty and ethnicity upon weight trajectories from age two to six-and-a-half were examined using data from the Infant Health and Development Program (N = 985), an early intervention program for low birth weight children and families. At age two, family poverty was associated with higher body mass index (BMI), whereas neighborhood poverty and ethnicity were not. Over time, the BMI of toddlers from poor and near poor neighborhoods increased nonlinearly, while those from nonpoor neighborhoods remained stable. BMIs of Hispanic-American toddlers increased steadily over time, unlike African-American and Anglo-American toddlers. Although initially similar, over time African-American toddlers' BMIs increased more rapidly than Anglo-American toddlers. Family and neighborhood poverty and ethnicity were associated with BMI. More work is needed on how poverty and ethnicity contribute to differences in early weight gain in conjunction with sociocultural and environmental factors in the home and community.