This study investigated the frequency of distortion that occurs when raw score patterns of Affinity 2.0, a viewing time measure designed to assess sexual interest, are converted to ipsative scores. Eighty-eight percent of a sample of ninety-nine non-pedophilic, exclusively heterosexual males' profiles sustained some degree of distortion. The study also applied Brown's (2005) approach to predicting distortion with this sample of males' responses. Brown's techniques were largely ineffective in predicting males' distortion scores.

Yes / A comprehensive meta‐analysis of two types of forced‐choice (FC) personality inventories (ipsative and quasi‐ipsative) across nine occupational groups (Clerical, Customer Service, Health Care, Managerial, Military, Police, Sales, Skilled Manual, and Supervisory) is reported. Quasi‐ipsative measures showed substantially higher operational validity coefficients and validity generalization across all occupations than ipsative measures. Results also showed that, compared with the findings of previous meta‐analyses, quasi‐ipsative personality inventories are better predictors of job performance than previously thought and that operational validities for ipsative measures are notably congruent with past findings. We conclude that quasi‐ipsative scale formats are superior for predicting job performance for all occupational groups. Theoretical and practical implications of these findings for personnel selection are discussed in 4.4. / Ministry of Economy and Competitiveness. Grant Number: PSI2011‐27943. Leverhulme Trust. Grant Number: IN‐2012‐095

The LOOK, an iOS app, is a viewing time measure used to assess sexual interest. The measure is based on the assumption that sexual interest can be assessed by the amount of time a participant spends looking at an image. The purpose of this study was to examine the ability of the LOOK, a newly developed viewing time instrument, to accurately screen and diagnose individuals with deviant sexual interest. The profiles of known sexual offenders were compared to norm-referenced profiles of an exclusively heterosexual, non-pedophilic, male, college student population. Researchers were not able to find a fair constant multiplier that would allow for a positive screen of our offender sample while not over identifying our non-offender sample. Instead a graph was generated which showed the trends of offenders were closely related to those of non-offenders using Fischer’s Chi-square model. Additionally, when looking at the predictive validity of being able to identify victim demographics of known perpetrators based on Fischer’s Chi Square residuals, only 15.9% were found to have offense histories that were consistent with their profiles on the LOOK. The LOOK, using Fischer’s Chi-square model does not seem to be able to differentiate offenders from non-offenders. Future studies may include looking at the predictive nature of ipsative data.

This study investigated distortion that occurs when raw scores are converted to ipsative scores on Affinity 2.0, a relatively new instrument for assessing sexual interest. Using a sample of 146 non-offending, heterosexual females, this study examined the characteristics of distorted ipsative score profiles and attempted to develop an algorithm to identify such distortions. A method was developed for defining distortion objectively. Of the 146 profiles,125 were found to contain some degree of distortion. Several hypotheses were formulated as to variables that might be related to distortion. These relationships were examined using Pearson Product Moment Correlations. Several statistically significant, but weak, correlations were found. An interaction effect was calculated for four of these variables, and was found to have a moderately strong correlation with distortion (r = .530, p <.01). An algorithm for identifying distortion was developed using this interaction effect. Several cut-off scores were tested. The most effective cut-off only correctly identified 42.9% of the significantly distorted profiles. Implications and limitations of the results are discussed, and directions for future research are provided.

The present study evaluates the factorial structure, in the leve! of the subscales, of the Survey of Interpersonal Values (SIV), and the relationships among them, in a sample of adolescents between 15 and 17 years old of both sexes and from a private and public school, representative of low and middle socioeconomic Ievels. Although the SIV has been a widely used too!, there is no report of ah analysis of its factorial structure in Latín-American samples. By means of the principal components analysis and the factorial analysis with a confirmatory approach, bipolar relationships have been identified between Independence and Benevolence, and Support and Conformity. The confirmation of the pattem of interpersonal values proposed by L. V. Gordon was also accomplished. An aspect considered in the analysis may have artificially influenced the pattern of correlations among the components, and the reliability: the ipsative method of the questions of the SIV. Finally, there is a discussion about the ipsative measurement and its consequences in the interpretation of the results. / El artículo evalúa la estructura factorial bajo los efectos del método ipsativo de respuesta, estudiados en el nivel de las subescalas del Cuestionario de Valores Interpersonales de Gordon (SIV), y las relaciones entre ellas, en una muestra de adolescentes entre 15 y 17 años de ambos sexos y procedentes de un colegio privado y estatal, representativos de los niveles socioeconómicos medio y bajo. Aunque el SIV ha sido una herramienta extensamente utilizada, no se reportado previamente un análisis de su estructura factorial en muestras Latinoamericanas. Mediante el análisis de componentes principales y el análisis factorial con un enfoque confirmatorio, se han identificado relaciones bipolares entre Independencia y Benevolencia, y Soporte y Conformidad. Se obtuvo también la confirmación del modelo de valores interpersonales propuesto por L. V. Gordon. En el análisis se consideró un aspecto que artificialmente puede haber influido en el patrón de correlaciones entre los componentes, esto es el método ipsativo de las preguntas del SIV. Finalmente, se discute sobre las medidas ipsativas y sus consecuencias en la interpretación de sus resultados.

Multidimensional forced-choice questionnaires can reduce the impact of numerous response biases typically associated with Likert scales. However, if scored with traditional methodology these instruments produce ipsative data, which has psychometric problems, such as constrained total test score and negative average scale inter-correlation. Ipsative scores distort scale relationships and reliability estimates, and make interpretation of scores problematic. This research demonstrates how Item Response Theory (IRT) modeling may be applied to overcome these problems. A multidimensional IRT model for forced-choice questionnaires is introduced, which is suitable for use with any forced-choice instrument composed of items fitting the dominance response model, with any number of measured traits, and any block sizes (i.e. pairs, triplets, quads etc.). The proposed model is based on Thurstone's framework for comparative data. Thurstonian IRT models are normal ogive models with structured factor loadings, structured uniquenesses, and structured local dependencies. These models can be straightforwardly estimated using structural equation modeling (SEM) software Mplus. Simulation studies show how the latent traits are recovered from the comparative binary data under different conditions. The Thurstonian IRT model is also tested with real participants in both research and occupational assessment settings. It is concluded that when the recommended design guidelines are met, scores estimated from forced-choice questionnaires with the proposed methodology reproduce the latent traits well.