Williams, Jones, and Tukey (1999) showed that a sequential approach to controlling the false discovery rate in multiple comparisons, due to Benjamini and Hochberg (1995), yields much greater power than the widely used Bonferroni technique that limits the familywise Type I error rate. The Benjamini-Hochberg (B-H) procedure has since been adopted for use in reporting results from the National Assessment of Educational Progress (NAEP), as well as in other research applications. This short note illustrates that the B-H procedure is extremely simple to implement using widely available spreadsheet software. Given its easy implementation, it is feasible to include the B-H procedure in introductory instruction in inferential statistics, augmenting or replacing the Bonferroni technique.

The purpose of this investigation was to develop a self-administered questionnaire to measure sexual desire. In the development phase, items were generated and pilot-tested with 24 subjects. Based on these data, items were deleted, added, or modified. Next, in Study One, the Sexual Desire Inventory (SDI) was administered to 197 females and 117 males. Factor analyses revealed that the SDI was multifactorial; however, none of the generated factor solutions up to five factors yielded a good fit. Interpretation of the factors led to revisions of the SDI. It was hypothesized that sexual desire might consist of two related dimensions; dyadic sexual desire and solitary sexual desire. Items on the SDI were modified to measure these two dimensions, and the revised SDI was administered to 249 females and 131 males. Factor analysis supported the presence of these two dimensions. Internal consistency estimates using Cronbach's alpha revealed coefficients of .86 for dyadic sexual desire and .96 for solitary sexual desire, providing preliminary evidence for the reliability of the SDI. The implications of these findings are discussed.

No abstract

item response theory, test theory, logistic models,

The Barratt Impulsivity Scale (BIS), a 30-item self-report measure, is one of the most commonly used scales for the assessment of the personality construct of impulsiveness. It has recently marked 50 years of use in research and clinical settings. The current BIS-11 is held to measure 3 theoretical subtraits, namely, attentional, motor, and non-planning impulsiveness. We evaluated the factor structure of the BIS using full information item bifactor analysis for Likert-type items. We found no evidence supporting the 3-factor model. In fact, half of the items do not share any relation with other items and do not form any factor. In light of this, we introduce a unidimensional Barratt Impulsiveness Scale-Brief (BIS-Brief) that includes 8 of the original BIS-11 items. Next, we present evidence of construct validity comparing scores obtained with the BIS-Brief against the original BIS total scores using data from (a) a community sample of borderline personality patients and normal controls, (b) a forensic sample, and (c) an inpatient sample of young adults and adolescents. We demonstrated similar indices of construct validity that is observed for the BIS-11 total score with the BIS-Brief score. Use of the BIS-Brief in clinical assessment settings and large epidemiological studies of psychiatric disorders will reduce the burden on respondents without loss of information.

Although item bias has received increased attention in the literature on the measurement of ability and achievement, comparatively little work on the detection of item bias has been done in the attitudepersonality assessment domain. The present article describes item bias analysis in attitude and personality measurement using the techniques of item response theory. A psychological inventory intended to measure a construct called "sex guilt" provides a focus to illustrate the procedures developed to distinguish true group differences on a psychologically meaningful construct from artifactual differences due to some aspect of the test construction process.The concept of item bias has recently received increased attention in the ability-and achievement-testing literature (e.g.,

It is not always convenient or appropriate to construct tests in which individual items are fungible. There are situations in which small clusters of items (testlets) are the units that are assembled to create a test. Using data from a test of reading comprehension constructed of four passages with several questions following each passage, we show that local independence fails at the level of the individual questions. The questions following each passage, however, constitute a testlet. We discuss the application to testlet scoring of some multiplecategory models originally developed for individual items, In the example examined, the concurrent validity of the testlet scoring equaled or exceeded that of individual-item-level scoring.

No abstract