The effect of skew on the standardized item alpha, an estimate of internal consistency closely related to Cronbach's coefficient alpha, was examined through Monte Carlo techniques. First, situations in which skew may exist were described, then attempts to address problems created by skew were discussed. Next, the logical relations among split-half reliability, Cronbach's coefficient alpha, and the standardized item alpha were examined and shown to be equivalent when all item variances are equal. Finally, results from Monte Carlo simulations were presented which compared alpha computed from standard normal variables to alpha computed from the same samples but where skew was induced by the lognormal transformation and finally to alpha computed from the ranks of the lognormal values. Both the extent and direction of skew were systematically varied as was the size of the population interitem correlation--rho. Since factorial complexity and the average interitem correlation have been shown to be related to alpha, the effect of skew on both of these was also examined. Results indicated that skew increases factorial complexity, decreases the average interitem correlations, and decreases alpha. These results were especially pronounced when rho was small. Transforming the values with a natural log transformation, which produces results equivalent to bivariate normal values, and ranking the lognormal values eliminated the skew as well as the liabilities associated with skew. However, ranking resulted in a slight decrease in the standardized item alpha compared to standard normal values / acase@tulane.edu

This study investigated (1) the tenability of the assumptions underlying human resource utility analysis models, (2) methods of operationalizing these models, and (3) manager's perceptions of the accuracy of results from these models. The investigation was conducted using several behavioral and sales performance measures from 434 sales-representatives who attended a product information and sales strategy training program. Low positive relationships were observed between behavioral performance and the value of performance, demonstrating that it is tenable to assume a linear (but not a perfect) relationship between behavioral performance and the value of performance. Such linear relationships, however, were not uniformly observed, which suggests that the tenability of this assumption may be moderated by the latent behavioral and economic domains as well as the operationalizations of the utilized measures. Alternative methods of operationalizing the utility model's components, including the effect size (i.e., d) as well as alternative methods of calculating and summarizing variability in the value of employee performance (i.e., $\sigma\sb{y}$ (sometimes referred to as SDy), A$\nu y,$ and A$\sigma\sb{\rm R}),$ yielded results with different levels of accuracy: some components were quite accurate (overestimating the parameter by 2.3 percent) and others were quite inaccurate (overestimating the parameter by 107.2 percent). These levels of accuracy were perceived to be significantly different by human resource and training department managers in a Fortune 500 company. These managers' ratings, on average, indicated that some methods of estimating utility components are accurate enough for decision making purposes. Implications for utility analysis research, performance measurement research, and the use of utility models for applied human resource decision making are discussed / acase@tulane.edu

Trimming and Winsorization are methods for dealing with the problem of outliers. This study investigated the robustness of these two procedures when there was skew in the underlying distributions. Sample data were first generated from a population with a normal distribution, and were then transformed into two skewed distributions, the lognormal and the power distributions. Trimming and Winsorization were performed on both the normal samples and transformed samples. Both Type I and Type II errors of two sample t tests and confidence intervals were investigated for evidence of robustness and power. The study found that trimmed and Winsorized means, as defined by Tukey and McLaughlin (1963) and Dixon and Tukey (1968), were not very efficient estimates of population means when the underlying distributions were skewed. While student's t test was too conservative for skewed distributions, moderately Winsorized t, as defined by Fung and Rahman (1980), was found to bring the Type I error closer to their stated levels. Furthermore, Winsorized t was found more powerful than student's t when the underlying distributions were skewed, especially when the skew was heavy, and it performed better than trimming in most cases in this study. The study suggested that these two procedures should only be used with great caution, and Winsorizing only one data point from each side of a sample was recommended with heavily skewed distributions / acase@tulane.edu

Latent class analysis was originally introduced by Lazarsfeld to analyze categorical latent variables from a set of categorical manifest variables. Several test statistics have been previously proposed for evaluating the goodness of fit of latent class model. They provide the means to test whether a latent factor explains the observed associations. So far, however, little is known about the sensitivity of latent class analysis to detect the true latent structure (convergent) or to discriminate an inappropriate model from the true model (discriminant). This study provides some strategies for researchers to assess both convergent and discriminant sensitivity of latent class analysis using simulation methods The impact of several factors on convergent sensitivity of latent class analysis were investigated. These factors include (1) sample size, (2) nearness of unconditional probabilities to 0.5, (3) nearness of conditional probabilities to one or zero, (4) strength of association between latent and manifest variables and (5) nearness of the pair of conditional probabilities among all latent classes for any manifest variable. Factors (1), (2) and (3) address the sample size issue. Factors (4) and (5) address the strength of association. Results confirm that convergent sensitivity is globally improved by increasing either the sample size or the strength of association It was also found that the discriminatory power of latent class analysis to distinguish an inappropriate model from the true latent structure is significantly high. Based on the findings of this study, we believe researchers can significantly improve their study designs / acase@tulane.edu

Multivariate Analysis of Variance (MANOVA) is a commonly used statistical procedure for group comparison in behavioral research, however, the traditional parametric approach for MANOVA when there are more than two groups has Type I error rates that deviate from stated alpha (Olson, 1976) and may have poor power (Stevens, 1980). The approximate randomization test (ART), a nonparametric and computer intensive approach, has been recently recommended as a theoretically attractive alternative to parametric MANOVA (Edgington, 1987; Manly, 1991), but its performance relative to the parametric procedures has not been empirically investigated. The main purpose of this study is to evaluate the advantages, disadvantages, and feasibility of applying the ART for MANOVA using Monte Carlo methods. Results indicate that, contrary to the common belief, the ART in general yield Type I error rates similar in tendency and degree to that for parametric methods under assumption violations. Although the ART using composite z score as statistic recommended by Edgington (1987) is less biased compared to the parametric method under assumption violations, it may not test the same hypothesis tested by the parametric method. This study concludes that despite the theoretical attractiveness of the ART, none of the previously recommended statistics yields a satisfactory test for replacing the parametric MANOVA / acase@tulane.edu

This study assessed the relationship between second and fifth graders' strategy use and performance on the Digit Span subtest of the Wechsler Intelligence Scale for Children-Revised (Wechsler, 1974). Verbal reports and observations were used to assess each subject's cognitive processes on the Digit Span tasks and to relate each subject's metamemorial knowledge to task performance. In addition, the relationship between response latency (time used to begin recall of digit series and time used to recall digit series) and performance on Digits Backward was investigated Fifth graders reported using more complex strategies than second graders. Second graders were observed to use rehearsal more on Digits Backward. Grouping predicted the performance for second graders on the Digit Span tasks while rehearsal and grouping predicted the performance of fifth graders on Digit Span tasks. Response latency was related to performance on Digits Backward for both grades, with a longer recall time on latter trials positively predicting performance While not a major focus of study, there were gender differences in performance. Overall, females performed better than males on Digits Backward; and, they also had a higher mean Digit Span scaled score than males. Females were observed using rehearsal more often than males on Digits Backward / acase@tulane.edu

No description available.

The aim of this study was to argue for a new conception of subjective control and then to devise psychometric scales to test this new conception in the area of gambling behaviour. The 'Subjective Control'scales were constructed using Michell's (1994a, 1998) theory of the ordinal determinable. After extensive pilot testing, these scales were administered to a participant sample consisting of 57 students, 104 in situ club EGM players and 49 self-referred problem gamblers. The data collected consisted of paired comparisons judgements, ratings and rank orders. The limitations of the findings were discussed and suggestions for future research were made. / Doctor of Philosophy (PhD)

Thesis (Ph. D.)--University of Missouri-Columbia, 2007. / The entire dissertation/thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file (which also appears in the research.pdf); a non-technical general description, or public abstract, appears in the public.pdf file. Title from title screen of research.pdf file (viewed on December 17, 2007) Vita. Includes bibliographical references.

<p>Denna uppsats görs en utvärdering av Agerus PrestationsIndex, ett verktyg för att mäta prestation i organisationer utifrån empowerment. PrestationsIndex är ett självskattningstest och bygger på en modell för empowerment med fem psykologiska rekvisit för självgående. Testet prövas psykometriskt för reliabilitet och validitet. Därutöver testas två hypoteser, dels om PrestationsIndex kan predicera prestation och dels om ojämnhet mellan de psykologiska rekvisiten kan påverka prestationen negativt. Resultaten visar starkt stöd för den första teorin när det gäller att predicera individuell prestation, men kan inte belägga PrestationsIndex som en prediktor för gruppresstation, när man har rensat för miljöfaktorer såsom trivsel och lust till arbetet. Den andra hypotesen får inget stöd i uppsatsen. Utöver de testade hypoteserna fann författaren intressanta relationer mellan stöd i arbetsgruppen, lojalitet med arbetsgivaren och den individuella prestationen.</p>