Work Sample Testing

The general evidence supporting the use of work sample tests (good criterion — related validity, positive applicant reaction and job preview capability) is reviewed, limitations are also noted. The extent to which work sample tests may be used to limit adverse impact in selection is reviewed and the extent to which work sample tests may be used to complement other selection instruments, in particular, cognitive ability tests, is discussed. Work sample tests are based on attempts to embody key tasks within the job in a selection instrument. Five distinctive (though not mutually exclusive) types of work sample tests are identified and validity evidence is reviewed. Key dimensions (bandwidth, fidelity, task specificity, necessary experience, type of tasks and mode of presentation and response) are identified and used to compare different types of work sample tests.     

Sample selection and inductive generalization

In two experiments with adults (N=126), we examined the influence of sampling procedure on inductive generalization. In predicate sampling, participants learned the category identity of individuals known to possess some property. In subject sampling, individuals selected for category identity were discovered to possess a novel property. In both experiments, sampling procedure influenced induction. Predicate sampling resulted in very narrow generalization, whereas subject sampling yielded a fairly high and constant rate of projection. Differences in confidence of generalizations were also observed. Conditions in which evidence was described as randomly sampled from a collection of animals yielded a consistent decrease in projections as predicted by similarity-based models. The results are presented as support for an evidence-based view of induction.     

Sample size and correlational inference

In 4 studies, the authors examined the hypothesis that the structure of the informational environment makes small samples more informative than large ones for drawing inferences about population correlations. The specific purpose of the studies was to test predictions arising from the signal detection simulations of R. B. Anderson, M. E. Doherty, N. D. Berg, and J. C. Friedrich (2005). The results of a simulation study in the present article confirmed and extended previous theoretical claims (R. B. Anderson et al., 2005) that in a yes/no correlation detection task, small-sample advantages should occur but should be restricted to particular decision conditions. In 3 behavioral studies, participants viewed larger or smaller samples of data pairs and judged whether each sample had been drawn from a population characterized by a zero correlation or from one characterized by a greater-than-zero correlation. Consistent with traditional statistical theory, accuracy tended to be greater for larger than for smaller samples, though there was a small-sample advantage in 1 experimental condition. The results are discussed in relation to alternative theoretical and behavioral paradigms such as those of Y. Kareev (e.g., 2005) and K. Fiedler and Y. Kareev (2006).     

Sample size and multiple regression analysis

Despite the development of procedures for calculating sample size as a function of relevant effect size parameters, rules of thumb tend to persist in designs of multiple regression studies. One explanation for their persistence may be the difficulty in formulating a reasonable a priori value of an effect size to be detected. This article presents methods for calculating effect sizes in multiple regression from a variety of perspectives and also introduces a new method based on an exchangeability structure among predictor variables. No single method is deemed superior, but rather examples show that a combination of methods is likely to be most valuable in many situations. A simulation provides a 2nd explanation for why rules of thumb for choosing sample size have persisted but also shows that the outcome of such underpowered studies will be a literature consisting of seemingly contradictory results.     

Psychological Distress in a Sample of Teachers

This article describes a cross-sectional study of the links between job-related stressors and depressive and psychophysiologic symptoms and morale in 67 New York City teachers. The teachers' mean score on the Center for Epidemiologic Studies Depression Scale (CES-D; M = 13.03) was higher than might be expected from average community residents. The teachers also tended to express dissatisfaction with their jobs. The CES-D and the Psychophysiologic Symptom Scale were correlated as highly as their reliabilities would permit, a finding consistent with the view that the CES-D and the Psycho physiologic Symptom Scale measure the same construct, nonspecific psychological distress. The correlational findings suggest that distress is distinct from job-related morale, which was indexed by measures of motivation to continue teaching and job satisfaction. The results of regression analyses, which controlled for sociodemographic factors, indicated that the level of job strain (frequency of ongoing stressors) is more closely related to psychological distress and low morale than episodic stressors, including crimes in which the teacher was victim. The regression analyses also indicated that colleague support was related to lower symptom levels and higher morale.     

Suicidality in a Sample of Arctic Households

We investigated the association of suicidal ideation and behavior with depression, anxiety, and alcohol abuse in a Canadian Arctic Inuit community. Inuit (N = 111) from a random sample of households completed assessments of anxiety and depression, alcohol abuse, and suicidality. High rates of suicidal ideation within the past week (43.6%), and suicide attempts within last 6 months (30%), were reported. Ideation was more frequent among younger persons, whereas those favoring local native language were less likely to report a wish to die. Higher overall suicidality scores were associated with higher anxiety, and alcohol abuse, but not with depression or gender. Implications for future research are discussed.     

Sample Size Determination for Rasch Model Tests

This paper is concerned with supplementing statistical tests for the Rasch model so that additionally to the probability of the error of the first kind (Type I probability) the probability of the error of the second kind (Type II probability) can be controlled at a predetermined level by basing the test on the appropriate number of observations. An approach to determining a practically meaningful extent of model deviation is proposed, and the approximate distribution of the Wald test is derived under the extent of model deviation of interest.     

Beliefs About Aggression in an Indian Sample

Studies of Western samples have shown that men tend to view aggression as an instrumental act, whereas women view it in expressive terms. The present Study investigated aggression in two studies. In Study 1 sample of 400 (both sexes, ages 16 and 26 years) young adults from the Indian state of Mizoram. Consistent with western findings, men showed higher instrumental and physical aggression than women, but they also showed higher expressive beliefs, contrary to previous findings. Both instrumental beliefs and physical aggression were higher at 16 than at 26 years of age. Since reliabilities of the scales were low, the questionnaires were translated into Mizo and presented to another similar sample of 201 participants (101 males; the same age groups as in Study 1). The pattern of mean differences and correlations were similar to Study 1, although the reliabilities increased only slightly. Overall, there were some similarities with western samples regarding beliefs about aggression, and sex and age differences in aggression, although the structures of responses appeared more complex.     

Exploratory Factor Analysis With Small Sample Sizes

Exploratory factor analysis (EFA) is generally regarded as a technique for large sample sizes (N), with N = 50 as a reasonable absolute minimum. This study offers a comprehensive overview of the conditions in which EFA can yield good quality results for N below 50. Simulations were carried out to estimate the minimum required N for different levels of loadings (λ), number of factors (f), and number of variables (p) and to examine the extent to which a small N solution can sustain the presence of small distortions such as interfactor correlations, model error, secondary loadings, unequal loadings, and unequal p/f. Factor recovery was assessed in terms of pattern congruence coefficients, factor score correlations, Heywood cases, and the gap size between eigenvalues. A subsampling study was also conducted on a psychological dataset of individuals who filled in a Big Five Inventory via the Internet. Results showed that when data are well conditioned (i.e., high λ, low f, high p), EFA can yield reliable results for N well below 50, even in the presence of small distortions. Such conditions may be uncommon but should certainly not be ruled out in behavioral research data.     

Further Evidence for Reliability and Validity of the Triarchic Psychopathy Measure in a Forensic Sample and a Community Sample

Psychopathy is often described as a constellation of personality characteristics encompassing features such as impulsivity and antisociality, and a lack of empathy and guilt. Although the use of self-reports to assess psychopathy is still debated, there are distinct advantages to such measures and recent research suggests that they may not be as problematic as previously thought. This study further examined the reliability and validity of the Triarchic Psychopathy Measure (TriPM) in a community sample (N = 496) and forensic psychiatric patient sample (N = 217). Results indicated excellent internal consistencies. Additionally, the TriPM total and subscale scores related as expected to different subscales of the Psychopathic Personality Inventory –Revised (PPI-R) and to the Reactive and Proactive Aggression Questionnaire, reflecting good construct validity. Most importantly, ROC curve analyses showed that the TriPM evidenced better discrimination between the community sample and forensic psychiatric patients than the PPI-R. The current study extends the existent evidence demonstrating that the TriPM can be used as an efficient self-report instrument.     

Minimum Sample Size Recommendations for Conducting Factor Analyses

There is no shortage of recommendations regarding the appropriate sample size to use when conducting a factor analysis. Suggested minimums for sample size include from 3 to 20 times the number of variables and absolute ranges from 100 to over 1,000. For the most part, there is little empirical evidence to support these recommendations. This simulation study addressed minimum sample size requirements for 180 different population conditions that varied in the number of factors, the number of variables per factor, and the level of communality. Congruence coefficients were calculated to assess the agreement between population solutions and sample solutions generated from the various population conditions. Although absolute minimums are not presented, it was found that, in general, minimum sample sizes appear to be smaller for higher levels of communality; minimum sample sizes appear to be smaller for higher ratios of the number of variables to the number of factors; and when the variables-to-factors ratio exceeds 6, the minimum sample size begins to stabilize regardless of the number of factors or the level of communality.     

MAPI Code Types in an Inpatient Crisis-Unit Sample

Limited data is available concerning the use of the Millon Adolescent Personality Inventory (MAPI; Millon, Green, & Meagher, 1982) and high-point code combinations of its personality style scales. Our study reports on the frequency of high-point codes in an inpatient crisis-unit sample. Data analyses comparing personality style codes using MAPI expressed concerns scale elevations and Rorschach data are reported. Results comparing the personality style codes and expressed concerns scales were consistent with the findings of Millon et al. (1982). Analyses comparing Rorschach and MAPI data revealed only the presence or absence of vista responses as having any appreciable relationship to MAPI codes or personality scales.     

Risk Factors for Misconduct in a Navy Sample

Understanding antisocial behavior and organizational misconduct is an important objective, because these maladaptive behaviors are disruptive and costly to organizations and to society as a whole. The objective of this study was to identify psychosocial risk factors for misconduct and antisocial behavior in a sample of Navy personnel. A group of sailors (n = 158) who had engaged in significant misconduct were compared with a demographically similar group of sailors (n = 288) who had not engaged in misconduct and who were in good standing with the Navy. The psychosocial variables that emerged as the most important risk factors for antisocial behavior were alcohol use (odds ratio [OR] = 2.42), high impulsivity (OR = 2.20), high trait hostility (OR = 1.79), and antisocial behavior of friends (OR = 1.65). The implications of these results for the military and for research on antisocial behavior are discussed.     

Sample size bias in the estimation of means

The present research concerns the hypothesis that intuitive estimates of the arithmetic mean of a sample of numbers tend to increase as a function of the sample size; that is, they reflect a systematic sample size bias. A similar bias has been observed when people judge the average member of a group of people on an inferred quantity (e.g., a disease risk; see Price, 2001; Price, Smith, & Lench, 2006). Until now, however, it has been unclear whether it would be observed when the stimuli were numbers, in which case the quantity need not be inferred, and “average” can be precisely defined as the arithmetic mean. In two experiments, participants estimated the arithmetic mean of 12 samples of numbers. In the first experiment, samples of from 5 to 20 numbers were presented simultaneously and participants quickly estimated their mean. In the second experiment, the numbers in each sample were presented sequentially. The results of both experiments confirmed the existence of a systematic sample size bias.     

Failure in Class-Inclusion Reasoning in a University Sample

Two studies were undertaken with the purpose of examining adult performance on tasks of class-inclusion reasoning. Both duration of visual presentation and instructions regarding speed of response were varied. In both studies overall performance was low (approximately 60% of items were answered correctly) but neither duration of visual presentation nor speed of responding were shown to be systematically related to errors. Even when participants were permitted unlimited time to view the visual display and put under no pressure to respond quickly performance only reached 80% correct. Significant improvement over trials was observed, which suggests that participants may not have initially understood the task. Results are discussed in terms of the adequacy of class-inclusion tasks as measures of competence in logical reasoning about classes.     

Empirically Derived Ability-Achievement Subtypes in a Clinical Sample

The purpose of the present study was to identify reliable and clinically meaningful patterns of ability and achievement using the WISC-III and WIAT. Cluster analysis was used to group the 182 WISC-III and WIAT profiles (10 WISC-III subtests and 4 WIAT subtests) of children between the ages of 9 and 14 years. Theoretical and empirical considerations were used to identify a cluster solution, which involved comparison of several five-, six- and eight-cluster solutions. A five-cluster solution was selected as being representative of the data, which was well replicated across three hierarchical clustering methods (i.e., complete linkage, average linkage-within groups, and average linkage-between groups (UPGMA)). The clusters were labeled based on their most salient characteristics, which included a group of predominantly low ability and achievement, a group demonstrating a pattern of verbal processing deficits, a group demonstrating a pattern of visual spatial/processing speed deficits, a group with low ability and achievement with average processing speed, and a group with deficits consistent with an ACID pattern. The external validity of the five subtypes was assessed through an evaluation of the relationship between cluster membership and neuropsychological test data. Most predictions regarding neuropsychological performance were supported by the data, providing further evidence of the validity of the five-cluster solution. Clinical implications of the ability-achievement typology and suggestions for future research are discussed.