Spiritual Development Across the Adult Life Course: Findings from a Longitudinal Study

Longitudinal data spanning early (30s) and older (late 60s/mid-70s) adulthood were used to study spiritual development across the adult life course in a sample of men and women belonging to a younger (born 1928/29) and an older (born 1920/21) age cohort. All participants, irrespective of gender and cohort, increased significantly in spirituality between late middle (mid-50s/early 60s) and older adulthood. Members of the younger cohort increased in spirituality throughout the adult life cycle. In the second half of adulthood, women increased more rapidly in spirituality than men. Spiritual involvement in older age was predicted by religious involvement and personality characteristics in early adulthood and subsequent experiences of negative life events.     

Perceived product instrumentality: the process of scale purification and validation

Perceived product instrumentality (PPI) is a new construct that is proposed as a key process component of a general model of family purchasing behaviour. PPI reflects the degree to which consumers, apprehended as actors of social roles, deem a product to be helpful, facilitative of role performance, compatible with role identity and congruent with the self‐concept. The objective of this paper is threefold: (1) assess the PPI unidimensionality and reliability; (2) purify the PPI scale, and (3) assess its validity. First, a pilot survey was administered to a convenience sample of men and women, who filled in four identical lists of 33 items tapping their attitudes towards durables, and exploratory factor analysis was conducted on each set to explore the overall pattern of the items relationships. Five try‐out pools of different sizes (33, 28, 15, 13 and 9 items) were involved in the analysis. The 15‐item scale was retained. Secondly, a large‐scale survey was administered to 500 couples as part of an extensive research involving comprehensive model testing. Exploratory factor analysis was conducted on the whole sample for reliability and unidimensionality assessment. At times, the analysis is done on men's and women's sub‐samples separately in order to account for eventual differences among both populations. Thirdly, confirmatory factor was conducted, splitting the sample into two random halves: the generation sample and the validation sample. The first half served for the PPI scales purification. In this case, PPI was posited as the latent variable and the scale items were posited as the manifest ones. The second served to validate the PPI theory in a system's framework: PPI was posited as a latent dependent variable while other role orientations variables were posited as latent independent variables. Copyright © 2002 Henry Stewart Publications.     

潜变量交互效应分析方法

简要回顾了分析显变量交互效应的常用方法。详细讨论了目前分析潜变量交互效应的主要方法,包括用潜变量的因子得分做回归分析、分组线性结构方程模型分析、加入乘积项的结构方程模型分析和两步最小二乘回归分析,并比较和评价了这些方法的优缺点。最后归纳了潜变量交互效应分析方法的研究趋势,并介绍了新近进展(包括LMS方法和GAPI方法)。     

Why is support for Jamesian actual–ideal discrepancy model so elusive? A latent-variable approach

We investigate the Actual–Ideal Discrepancy (AID) model of self-esteem determination dating back to James (1890/1963). Although intuitively appealing, this model received weak support from rigorous empirical research. We propose a multiple-item latent difference approach to AID as applied to a range of self-concept domains and sub-domains in young adolescents from two different countries (UK: N = 402; Italy: N = 250). The effects of the AID remained elusive for most domains and sub-domains; indeed, the effects of the specific AIDs were generally trivial and only appearance-AID became significant in the combined sample. Also AIDs did not substantially explain the more general self-concepts beyond what was explained by the actual domains. Even if they had been significant, AID effects would have been, at best, trivially small and detectable only using appropriate latent-variable methodologies coupled with large sample sizes; thus undermining the psychological meaning of the AID model.     

Efficient nonparametric approaches for estimating the operating characteristics of discrete item responses

Rationale and the actual procedures of two nonparametric approaches, called Bivariate P.D.F. Approach and Conditional P.D.F. Approach, for estimating the operating characteristic of a discrete item response, or the conditional probability, given latent trait, that the examinee's response be that specific response, are introduced and discussed. These methods are featured by the facts that: (a) estimation is made without assuming any mathematical forms, and (b) it is based upon a relatively small sample of several hundred to a few thousand examinees.Some examples of the results obtained by the Simple Sum Procedure and the Differential Weight Procedure of the Conditional P.D.F. Approach are given, using simulated data. The usefulness of these nonparametric methods is also discussed.This research was mostly supported by the Office of Naval Research (N00014-77-C-0360, N00014-81-C-0569, N00014-87-K-0320, N00014-90-J-1456).     

Regression Mixture Models: Does Modeling the Covariance Between Independent Variables and Latent Classes Improve the Results?

Regression mixture models are increasingly used as an exploratory approach to identify heterogeneity in the effects of a predictor on an outcome. In this simulation study, we tested the effects of violating an implicit assumption often made in these models; that is, independent variables in the model are not directly related to latent classes. Results indicate that the major risk of failing to model the relationship between predictor and latent class was an increase in the probability of selecting additional latent classes and biased class proportions. In addition, we tested whether regression mixture models can detect a piecewise relationship between a predictor and outcome. Results suggest that these models are able to detect piecewise relations but only when the relationship between the latent class and the predictor is included in model estimation. We illustrate the implications of making this assumption through a reanalysis of applied data examining heterogeneity in the effects of family resources on academic achievement. We compare previous results (which assumed no relation between independent variables and latent class) to the model where this assumption is lifted. Implications and analytic suggestions for conducting regression mixture based on these findings are noted.