The primary aim of the study was to determine if the propensity score data analytic procedure was sufficient to remove the sampling bias that was thought to be present in a large multiple-year smoking prevalence survey. The survey under examination was the Adult Tobacco Survey (ATS) administered in the state of Arizona in 1996, 1999, and 2002 by the Tobacco Education and Prevention Program. Information provided by the ATS is used to obtain estimates of smoking prevalence and determine attitudes and beliefs about smoking. In an attempt to obtain more relevant information, the ATS was revised between the 1999 and 2002 survey administrations; questions were added or removed, the order in which questions were presented was modified, and question wording was altered. In addition, slight changes in research protocol throughout the years had resulted in different sampling procedures and inclusion/exclusion criteria. It was suspected that these differences between the survey years had resulted in sampling bias or selection error. In an attempt to control for the sampling bias, two propensity score analyses were conducted that examine differences between survey years as well as differences due to variations in the surveys. It was anticipated that examining participants that had been stratified and matched using the calculated propensity scores would facilitate the comparison of groups that were originally nonequivalent. After stratifying and matching the participants, the two propensity analyses resulted in statewide prevalence estimates that were similar for the three years and revealed a steady decline in smoking prevalence. Based upon the results obtained with this investigation, it was concluded that the propensity score performs adequately to remove sampling bias in large multiple-year surveys.

The present study extends the previous one-way ANOVA multiple-comparison findings of Meyers and Beretvas (2003) to interaction comparisons in factorial ANOVA designs, one-factor MANOVA comparisons, and tests of partial regression coefficients in multiple regression, in specific regard to the practical utility of modified (sequential) Scheffe-based procedures. Researchers who are concerned with maintaining familywise Type I error rates while increasing statistical power are encouraged to consider these improved multiple-comparison methods.

The construct of alexithymia was examined using factor analyses and a modified Crovitz-Robinson autobiographical memory technique. Results indicated a two-factor solution to the Toronto Alexithymia Scale. Subjects high in alexithymic characteristics were actually faster at recalling emotional events. They also reported more intense emotional experience at time of encoding but not at time of recall, showed a more complex emotional profile for their memories, but a greater number of response failures. When factor scores from principal components analyses were used to predict the above variables opposite results were obtained. Factor 1 and factor 2 scores showed very different patterns of relationships with the variables. It is proposed that the first factor found contains the "core" alexithymia characteristics. The breakdown of alexithymic characteristics and their differential relationship to the present cognitive task are discussed.

Objective. The diagnostic interview for borderline personality disorder (DIB) requires a long duration of administration (45 minutes). This led to the development of a briefer (10 minutes), and therefore more feasible, version of the DIB named the DIB-Ab. It is the aim of this study to test the validity and reliability of the DIB-Ab. Method. Forty-seven previously suicidal adolescents, aged 14--21 years, participated in this study. The DIB-Ab and DIB-R were administered during a battery of tests separated by 130 minutes of unrelated measures. Results. The Pearson correlation coefficient of the DIB-Ab with respect to the DIB-R ranged from .52--.80 with respect to the total scores on three sections (i.e. affect, cognition, and impulse/action). The correlation coefficient of the DIB-Ab ranged from .43--.91 for the total section scores and the same section scores. The standardized alpha for internal consistency of the DIB-Ab ranged from .54--.83 for the total scores and for cognition and impulse/action section scores. Conclusion. The preliminary data analysis revealed that the DIB-Ab is a valid and reliable instrument, and it could replace the parent version in certain research and clinical paradigms.

The purpose of this project was to develop a reliable and valid battery for the assessment of spatial orientation skills (SOS) in persons with Alzheimer's disease (AD). The battery, comprised of 13 subtests, was administered to 97 normal control subjects, 25 subjects with early AD and 10 with late AD. The test-retest reliability of the battery was based on the test results of 33 normal control subjects and 25 early AD subjects. Inter-rater reliability was determined using four trained raters who evaluated 27 normal control subjects and the same 25 early AD subjects. Content validity was established using a panel of six experts and construct validity was determined by comparing the performance of the normal control and early AD groups. To establish criterion validity, the Global Deterioration Scale (GDS) was used as the criterion. For the AD group, eight subtests demonstrated acceptable test-retest and inter-rater reliability coefficients (ICC $ ge$.70). For the control group, three subtests had acceptable test-retest coefficients and four had acceptable inter-rater coefficients. The internal consistency of the battery was acceptable as shown by overall Cronbach's alpha of.86 for AD subjects and.72 for control subjects, and was further analyzed using factor analysis which yielded five factors. Logistic regression provided evidence for good construct validity. Scores on the SOS subtests were able to differentiate the three groups of subjects established on the basis of the GDS scores (GDS 1 and 2, GDS 3 and 4, and GDS 5). A preliminary shortened version of the battery was developed using six subtests which demonstrated high test-retest and inter-rater reliability. The performance of subjects with AD on the battery is discussed with respect to its implications for the theoretical basis and clinical assessment of spatial orientation in AD.

<p>Personality-type measures should be viable tools to use for selection. They have incremental validity over cognitive measures and they add this incremental validity while decreasing adverse impact (Hough, 1998; Ones, Viswesvaran &amp; Schmidt, 1993; Ones &amp; Viswesvaran, 1998a). However, personality measures are susceptible to faking; individual's instructed to fake on personality measures are able to increase their scores (Barrick &amp; Mount, 1996; Ellingson, Sackett &amp; Hough, 1999; Hough, Eaton, Dunnette, Kamp, &amp; McCloy, 1990). Further, personality measures often reveal less than optimal validity estimates as research continually finds meta-analytic coefficients near .2 (e.g., Morgeson, Campion, Dipboye, Hollenbeck, Murphy, &amp; Schmitt, 2007). Some researchers have suggested that these two problems are linked as faking on personality measure may reduce their ability to predict job performance (e.g., Tett &amp; Christansen, 2007). Empirically keyed instruments traditionally enhance prediction and have been found to mitigate the effects of faking (Kluger, Reilly &amp; Russell, 1991; Scott &amp; Sinar, 2011). Recently suggested as a means to key to personality measures (e.g., Tawney &amp; Mead, In Prep), this dissertation further investigates empirical keying methods as a means to both mitigate faking effects and as a means to increase validity of personality-type measures. A Monte Carlo methodology is used due to the difficulties in obtaining accurate measures of faking. As such, this dissertation investigates faking issues under controlled and known parameters, allowing for more robust conclusions as compared to prior faking research. </p>

<p> This study assessed the extent to which multiple administrations of an intensity scale; in this case, the Simulator Sickness Questionnaire (SSQ), influences participant responding on subsequent administrations of the same scale. The first experiment sought to determine this by using a laboratory task in which one group of participants were asked to watch a number of identical videos depicting a simulated drive from the driver's point of view, and fill out an SSQ and Center for Epidemiological Studies Depression Scale (CES-D) between viewings of the videos. Another group of participants were asked to view the videos, but were only asked to fill out the SSQ and CES-D once before the first video and once after the last video. Overall, it was found that multiple administrations of the SSQ and CES-D do not substantially influence subsequent responding on both scales. The second experiment sought to replicate the findings from the first experiment online by using Amazon's Mechanical Turk service. Here, the same pattern of responding to the SSQ was found. Together, these findings suggest that additional administrations of an intensity scale; in this case, the SSQ, do not substantially influence participant responding on subsequent administrations.</p>

<p> The goal of this research was to study differences in cognitive performance on verbal and quantitative measures among subjects of different ages. Data was gathered on subjects ranging in age from 16 to 80 years of age from birth-cohorts from 1927 to 1990. In addition to year of birth, personal characteristics of gender, race/ethnicity and undergraduate area of study were obtained. Multilevel models were built that predict cognitive performance as a function of age, cohort and other non-independent personal characteristics . Verbal performance rises as the age of the test-taker rises; quantitative performance declines as the age of the test-taker rises. After controlling for the race/ethnicity and gender of the test-taker, there are both age and cohort effects for verbal and quantitative models. On the verbal measure, the cohort effect favors those test-takers born at an earlier time. There is an interaction between age and cohort on the quantitative measure. This data is secondary analysis and the records are from those test-takers who choose to take a consequential assessment. When the multilevel models are produced independently for those test-takers ages 20-39 and those ages 40-64, different results are seen between the two age groups. There is little difference in performance for 20-39 year olds on the verbal measure other than a positive effect for age at time of test. For the test-taker aged 40-64, there is a positive effect due to age, a positive cohort effect and a negative interaction effect between age and science study. Comparing the 20-39 year olds with the 40-64 year olds on the quantitative measure, the decline in performance for the older group is one-fourth the rate of decline in the younger group. For the quantitative measure, after controlling for age, there is a positive cohort effect for both age groups. </p>

<p> The purpose of the current study was to assess a model of college completion at a 2-year community college based on Tinto's Theory of Student Drop Out and current factors known to impact college completion. A freshman cohort (<i>n</i> = 2,846) that attended a large-urban community college was assessed. Logistic regression analysis found student age and math proficiency when entering college were significant factors in the model. The older the student was when first enrolling, the lower their likelihood of completing college. The more remediation a student needed in math skills, then the less likely she or he was in completing college. Placement into developmental (remedial) English writing courses did not seem to suppress completion, and was a non-significant finding in the model. Reading proficiency and participation in a student success course (first-year seminar) were not significant factors in the model, though estimated coefficients aligned with research literature.</p>

The main objective of this research was to determine whether differences between group and individual accuracy on behavioral rating tasks are due to differences in memory sensitivity or to systematic differences in the type of decision criterion adopted. Group vs. individual differences in evaluative judgment and in confidence levels, and the effects of a five-day delay were also investigated. Lastly the relationship between response bias and prior evaluative judgment was explored. The results revealed a group memory superiority but also demonstrated that groups adopt a too-liberal decision criterion when rating the occurrence of effective behaviors. In addition, in the delayed rating condition, groups were found to be more confident in their correct responses than individual subjects. And finally, for individual subjects, prior evaluative decisions were positively related to response bias in the rating of effective behaviors and negatively related to response bias in the rating of ineffective behaviors.