An empirical study of Hedge's homogeneity test.

The behavior of the L. V. Hedges's (see record 1983-00213-001) Q test for the fixed-effects meta-analytic model was investigated for small and unequal study sample sizes paired with larger numbers of studies, nonnormal score distributions, and unequal variances. The results of a Monte Carlo study indicate that the hypothesis of equal effect sizes tends to be rejected less than expected if smaller study sample sizes are paired with larger numbers of studies; pairing smaller variances with larger sample sizes (or vice versa) leads to this hypothesis being rejected more than expected. The power of the Q test is also less than expected when small study sample sizes are paired with larger numbers of studies. These findings suggest conditions for which the Q test should be used cautiously. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Implications of empirical Bayes meta-analysis for test validation.

Empirical Bayes meta-analysis provides a useful framework for examining test validation. The fixed-effects case in which ρ has a single value corresponds to the inference that the situational specificity hypothesis can be rejected in a validity generalization study. A Bayesian analysis of such a case provides a simple and powerful test of ρ?=?0; such a test has practical implications for significance testing in test validation. The random-effects case in which ?2 ρ ?>?0 provides an explicit method with which to assess the relative importance of local validity studies and previous meta-analyses. Simulated data are used to illustrate both cases. Results of published meta-analyses are used to show that local validation becomes increasingly important as ?2 ρ increases. The meaning of the term validity generalization is explored, and the problem of what can be inferred about test transportability in the random-effects case is described. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Allowing for correlations between correlations in random-effects meta-analysis of correlation matrices.

Practical meta-analysis of correlation matrices generally ignores covariances (and hence correlations) between correlation estimates. The authors consider various methods for allowing for covariances, including generalized least squares, maximum marginal likelihood, and Bayesian approaches, illustrated using a 6-dimensional response in a series of psychological studies concerning prediction of exercise behavior change. Quantities of interest include the overall population mean correlation matrix, the contrast between the mean correlations, the predicted correlation matrix in a new study, and the conflict between the existing studies and a new correlation matrix. The authors conclude that accounting for correlations between correlations is unnecessary when interested in individual correlations but potentially important if concerned with a composite measure involving 2 or more correlations. A simulation study indicates the asymptotic normal assumption appears reasonable. Because of potential instability in the generalized least squares methods, they recommend a model-based approach, either the maximum marginal likelihood approach or a full Bayesian analysis. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Varieties of psychological test homogeneity.

Lists 5 steps in the historical development of the psychological test item: Blin's concept of a scale; Alfred Binet's use of simple tests as components of a scale; the development of key-scored tests; the Army Alpha with its new item types; and the proliferation of objective testing in the 1920s. 3 concepts of homogeneity are appropriate for test items: (a) factorial (items exhibit a rank 1 matrix of correlations); (b) scalar (successive items exhibit increase in factorial complexity as in a Guttman scale); and (c) criterial (such unity as the items may have comes from their being predictors of a unified external criterion). Test construction goals can be clarified by observing the distinctions. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The interaction model of anxiety: An empirical test in an examination situation.

Tested the interaction model of anxiety in an examination situation. 56 undergraduates completed the self-report Behavioral Reactions Questionnaire (BRQ), a measure of A-state, and measured their pulse rates prior to an important psychology exam. Under nonstressful conditions 2 wks later, Ss again completed the BRQ and measured their pulse rate. In addition they completed the S–R Inventory of General Trait Anxiousness (S–R GTA), a measure of A-trait. The differential hypothesis of the interaction model of anxiety predicted a significant interaction between interpersonal (ego-threatening) A-trait (high vs low) and the ego-threatening situation (exam), in affecting A-state arousal, but no significant interaction between the other facets of A-trait (physical danger, ambiguous, and innocuous) and the threatening exam situation. When pulse rate was used as the dependent variable, the congruent Interpersonal A-Trait?×?ego-stress exam situation interaction was significant. None of the remaining 6 noncongruent person-by-situation interactions was significant except for the Physical Danger A-Trait?×?Situation interaction for BRQ scores. The pulse rates results confirmed the differential predictions of the interaction model of anxiety. Ss responded differentially to the 4 situations of the GTA, and in general the results provide confirmation for the multidimensionality of A-trait. (French summary) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A conceptual and empirical examination of justifications for dichotomization.

Despite many articles reporting the problems of dichotomizing continuous measures, researchers still commonly use this practice. The authors’ purpose in this article was to understand the reasons that people still dichotomize and to determine whether any of these reasons are valid. They contacted 66 researchers who had published articles using dichotomized variables and obtained their justifications for dichotomization. They also contacted 53 authors of articles published in Psychological Methods and asked them to identify any situations in which they believed dichotomized indicators could perform better. Justifications provided by these two groups fell into three broad categories, which the authors explored both logically and with Monte Carlo simulations. Continuous indicators were superior in the majority of circumstances and never performed substantially worse than the dichotomized indicators, but the simulations did reveal specific situations in which dichotomized indicators performed as well as or better than the original continuous indictors. The authors also considered several justifications for dichotomization that did not lend themselves to simulation, but in each case they found compelling arguments to address these situations using techniques other than dichotomization. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Associative homogeneity may affect the persistence of illusory correlations but does not account for their occurrence.

Discusses G. M. Rosen's (see record 1975-31957-001) suggestion that associative homogeneity, as described by L. J. and J. P. Chapman (see record 1969-13004-001), may influence the persistence of illusory correlations. It is pointed out, however, that Rosen's suggestion should not be confused with issues of causality raised in the Chapmans' article. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Theoretical and empirical examination of cognitive resource theory.

Two assumptions and seven hypotheses defining F. E. Fiedler and J. E. Garcia's (1987) cognitive resource theory are critiqued and examined with data from 48 four-man groups. Information for leaders and subordinates was available on the dimensions of IQ, directiveness, group atmosphere, rank, and group performance on seven tasks. Results yielded support for Hypothesis 2 of the theory (i.e., leader intelligence was more strongly correlated with group performance for highly directive leaders, relative to nondirective leaders). Problems with the theory associated with (a) the definition of intelligence, (b) the undervalued importance of specific task demands and the combinations of tasks, and (c) the role of stress are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A test of two refinements in procedures for meta-analysis.

This study used Monte Carlo simulation to examine the increase in accuracy resulting from 2 statistical refinements of the interactive Schmidt-Hunter procedures for meta-analysis: the use of the mean correlation instead of individual correlations in the estimation of sampling error variance, and a procedure that takes into account the nonlinear nature of the range-restriction correction. In all of the cases examined, these refinements increased the accuracy of the interactive procedure in estimating the variance of population correlations and resulted in more accuracy than other procedures examined. The use of the mean correlation in the sampling error variance formula also increased the accuracy of variance estimates for the multiplicative and Taylor Series procedures. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Personality and organizations: A test of the homogeneity of personality hypothesis.

A central proposition of attraction-selection-attrition theory (B. Schneider, 1987) and of the literature on organizational socialization was tested. Support for the hypothesis that organizations are relatively homogeneous with respect to the personality attributes of their managers was found. A multivariate analysis of variance (MANOVA) conducted on a sample of approximately 13,000 managers from 142 organizations representing a broad cross-sample of U.S. industries revealed a significant effect for organizational membership on the personality characteristics of managers. Results of a 2nd MANOVA, nesting organizations within industries, revealed a significant effect for both organization and industry on the personality characteristics of managers. Some implications of these findings are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A multidimensional meta-analysis of treatments for depression, panic, and generalized anxiety disorder: An empirical examination of the status of empirically supported therapies.

The authors report a meta-analysis of high-quality studies published from 1990-1998 on the efficacy of manualized psychotherapies for depression, panic disorder, and generalized anxiety disorder (GAD) that bear on the clinical utility and external validity of empirically supported therapies. The results suggest that a substantial proportion of patients with panic improve and remain improved; that treatments for depression and GAD produce impressive short-term effects; that most patients in treatment for depression and GAD do not improve and remain improved at clinically meaningful follow-up intervals; and that screening procedures used in many studies raise questions about generalizability, particularly in light of a systematic relation across studies between exclusion rates and outcome. The data suggest the importance of reporting, in both clinical trials and meta-analyses, a range of outcome indices that provide a more comprehensive, multidimensional portrait of treatment effects and their generalizability. These include exclusion rates, percent improved, percent recovered, percent who remained improved or recovered at follow-up, percent seeking additional treatment at follow-up, and data on both completer and intent-to-treat samples. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Statistical definitions of test validity for minority groups.

Considers the problem of deciding when a selection test is invalid for members of a minority group. There is both a strong empirical and theoretical basis for rejecting the choice of zero correlation between test and criterion as an appropriate null hypothesis. The choice typically requires that the population value of the correlation be higher in the minority group than in the majority group. The direct comparison of correlations in minority and majority samples is recommended. Only when the minority correlation is significantly lower and the confidence limits around that correlation include no useful levels of the relationship, should the correlation be considered essentially zero. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

An empirical test of the female castration complex.

Investigated the psychoanalytic hypothesis that intensity of the female castration complex (FCC) is greater in women with a masculine social role than in those with a feminine social role. Ss were normal, college-educated women, ages 30-55, divided into 2 groups: 26 career women, unmarried, and in masculine occupations; and 25 homemakers, married, with 2 or more children, and not employed outside the home. The career women scored significantly higher on an overall measure of the FCC based on the Rorschach, supporting the hypothesis. They also scored significantly higher on 3 of the 8 individual components of the FCC (penis envy, high activity, and high need for achievement). Some theoretical implications are discussed. (22 ref.) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Goal setting: A meta-analytic examination of the empirical evidence.

Conducted meta-analyses to estimate the amount of empirical support for the major postulates of the goal theory of E. A. Locke (see record 1968-11263-001) and Locke et al (see record 1981-27276-001). A technique similar to that described by J. E. Hunter et al (1982) was used to (a) accumulate effect sizes, (b) correct the mean and variance of those effect sizes for the effects of sampling error and attenuation, and (c) determine whether methodological characteristics of the studies have moderated the results. The results of well-controlled studies were generally supportive of the hypotheses. However, sources of variation in findings were discovered, including the setting in which the study took place and the manner in which goal setting factors were operationalized. (89 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

An empirical analysis of the correlations between leadership status and participation rates reported in the literature.

Many studies of small group leadership have reported a positive relationship between leadership status and the rate of verbal participation. The leadership/participation relationship has been attributed to (a) the performance of task leadership behaviors, (b) task skill and knowledge, (c) social status characteristics, and (d) the presence of observers. Hypotheses based on these 4 explanations were generated and tested using 72 correlations reported in the literature as data points. The relationship of a large number of situational variables to the leadership/participation rate relationship was also examined. In a multiple regression analysis, 4 variables accounted for 63% of the variance in the leadership/participation rate correlations. The 1st 3 explanations were supported. They can be integrated if the moderating effect of task competence and social status on the performance of task leadership behavior is recognized. (48 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

On the bias of Huffcutt and Arthur's (1995) procedure for identifying outliers in the meta-analysis of correlations.

This study documents how the use of A. I. Huffcutt & W. A. Arthur's (1995) sample adjusted meta-analytic deviancy (SAMD) statistic for identifying outliers in correlational meta-analyses results in inaccuracies in mean r. Monte Carlo simulations found that use of the SAMD resulted in the overidentification of small relative to large correlations as outliers. Furthermore, this tendency to overidentify small correlations was found to increase as the magnitude of the population correlation increased and resulted in mean rs that overestimated the population correlation. The implications for meta-analysts are discussed, and 2 possible solutions are offered. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

An empirical examination of the antecedents of commitment to difficult goals.

Goal commitment has been given a critical role in goal-setting theory, yet the factors associated with commitment to difficult goals have not often been studied. This study examined possible antecedents of commitment to difficult goals. Two sets of such variables were examined: situational (goal publicness and goal origin) and personal (need for achievement and locus of control) factors. Both sets of variables accounted for significant amounts of variance in goal commitment among 190 college students with academic goals. A Person?×?Situation interaction also accounted for a significant increment of variance. Specifically, commitment to difficult goals was higher when (a) goals were made public rather than private, (b) when locus of control was internal, and (c) when subjects were high in need for achievement, especially when goals were self-set as opposed to assigned. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

An empirical examination of Weiner's critique of attribution research.

Evaluates 3 of the allegations of error made by B. Weiner (see record 1983-32685-001) about methodological pitfalls in attributional research. The present authors (see record 1985-15804-001) contend that failure to confirm Weiner's predictions occurred because of theoretical shortcomings inherent in his model rather than because of procedural limitations in testing it. The path analysis of the cognitive model of achievement motivation study of the present authors (see record 1981-01260-001) was replicated using undergraduates dissatisfied by their midterm examinations. The time interval for retest was lengthened from 2 days to 3 wks. Results show that disconfirmation of Weiner's prediction occurred irrespective of which expectancy measure (expectancy or expectancy change) or which behavioral criterion was employed. Expansion of the cognitive model to include additional affective variables (humiliation, guilt, and shame reactions) were useful in understanding the role of effort cognitions in eliciting failure-induced affect. (46 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

光谱分析标准物质均匀性检验数据的EXCEL统计处理

依照方差分析法的原理,在Microsoft Excel中设计方差分析检验均匀性工作模板,并将该模板应用到钛合金光谱分析标准物质的均匀性检验中,取得了很好的效果,该模板也可用于其它标准物质的均匀性检验。