结构方程模型检验：拟合指数与卡方准则

讨论了Hu和Bentler（1998,1999）推荐的检验结构方程模型的7个拟合指数准则,对这7个指数的历史、特点和表现做了比较详细的述评。指出了他们基于这7个指数的单指数准则和2-指数准则的不足之处。提出了超低显著性水平下的卡方准则,并部分重复他们的模拟例子,将卡方准则与这7个指数准则比较,结果说明新的卡方准则优于其中的6个,与另一个相当。最后简要说明了应当如何检视拟合指数进行模型检验和模型比较。     

Religious Fundamentalism and Gender Differences

The role of religious fundamentalism and its relationship to shame and guilt was evaluated in 107 students who attend a church-sponsored university. A number of personality measures were given and gender differences were analyzed. The role of externalization was similar for males in this sample to that of earlier studies. However, it was found that females showed positive correlations between externalization and both shame and guilt. For females, more fundamentalistic religious training may help to contribute to an external orientation at the expense of identifying with a personal religion, and appropriate guilt.     

Emergent patterns of feedback strategies in performing a closed motor skill.

This sturdy identified self-chosen patterns of feedback usage and how they influenced accuracy and consistency in performing a closed motor skill. Learners completed 100 practice trials with 25 opportunities to receive knowledge of results (KR), the timing of which was self-chosen, followed by 25 no KR retention trials. The study identified two patterns of self-chosen KR, namely, a faded frequency pattern and a reversed faded frequency pattern. Analyses of variance indicated a significant trial block effect for accuracy in acquisition and no significant main effects or interactions associated with self-chosen patterns of KR. Quantification of regularity of KR patterns yielded correlations indicating that less regularity was associated with greater accuracy in performing the task. These results were congruent with previous research on self chosen feedback.     

The Portrayal of Men's Family Roles in Television Commercials

This study examines the portrayal of men infamily roles, as fathers and husbands, on televisioncommercials. A content analysis of commercials airedduring football, daytime, and prime time is carried out. The sample size of characters is 944, mostof whom are middle-class, non-Hispanic whites. Men withchildren but no spouse are more likely to be shownduring football than are women with children but no spouse. Advertisements for computers andelectronics are more likely to include men with childrenbut no spouse than women with children but no spouse.Men appearing alone with children are more likely to be shown outside than women alone withchildren. Men are less likely to be portrayed cooking,cleaning, washing dishes, and shopping than women. Menwithout spouses are more likely to be shown with boys and less likely to be shown with infants thanwomen without spouses. Men are infrequently shown takingcare of a child and are never shown caring for girls.However, men are often shown teaching, reading, talking, eating, and playing with children. Tothe extent that men are shown as more involved in familylife, they still tend to depend largely on knowledge andactivities that are stereotypically male.     

CHRISTIAN REALISM AND AUGUSTINIAN (?) LIBERALISM

Augustine's ontology, ecclesiology, and soteriology have recently been mined to help Christian realists and liberals respond to the problems that pluralism and conflict create for democratic societies. The results challenge those secularists who object to the late antique prelate's “moralizing” as well as others who insist that “public reason”—not religious traditions—makes for more meaningful political conversations and for collaboration “across differences.” But the results also raise the question whether Augustine would have gone along with the realists and liberals he has inspired and outfitted.     

Women helping chewers: partner support and smokeless tobacco cessation.

Data from 363 male smokeless tobacco users and their romantic partners were analyzed to discern the role of support in cessation. Women reported playing a part in enrollment (71%), and more than half examined program materials or discussed cessation activities with the chewers. Women's reports of delivered support correlated substantially with men's experience of received support. Men's received positive support predicted abstinence at 6-month follow-up (odds ratio = 1.29, confidence interval = 1.03-1.61) and more than 24 hr of abstinence for those still using tobacco at 6 months (odds ratio = 1.75, confidence interval = 1.30-2.36) and moderated the effect of baseline depression and addiction on abstinence. Women played a major role through all stages of cessation.     

Navigating joint projects with dialogue

Dialogue has its origins in joint activities, which it serves to coordinate. Joint activities, in turn, usually emerge in hierarchically nested projects and subprojects. We propose that participants use dialogue to coordinate two kinds of transitions in these joint projects: vertical transitions, or entering and exiting joint projects; and horizontal transitions, or continuing within joint projects. The participants help signal these transitions with project markers, words such as uh‐huh, m‐hm, yeah, okay, or all right. These words have been studied mainly as signals of listener feedback (back‐channel signals) or turn‐taking devices (acknowledgment tokens). We present evidence from several types of well‐defined tasks that they are also part of a system of contrasts specialized for navigating joint projects. Uh‐huh, m‐hm and yeah are used for horizontal transitions, and okay and all right for vertical transitions.     

Testing for DIF in a model with single peaked item characteristic curves: The parella model

The PARELLA model is a probabilistic parallelogram model that can be used for the measurement of latent attitudes or latent preferences. The data analyzed are the dichotomous responses of persons to items, with a one (zero) indicating agreement (disagreement) with the content of the item. The model provides a unidimensional representation of persons and items. The response probabilities are a function of the distance between person and item: the smaller the distance, the larger the probability that a person will agree with the content of the item. This paper discusses how the approach to differential item functioning presented by Thissen, Steinberg, and Wainer can be implemented for the PARELLA model. Requests for the PARELLA software should be sent to Iec Progamma PO Box 841, 9700 AV Groningen, The Netherlands.