When can information from ordinal scale variables be integrated?

Many theoretical constructs of interest to psychologists are multidimensional and derive from the integration of several input variables. We show that input variables that are measured on ordinal scales cannot be combined to produce a stable weakly ordered output variable that allows trading off the input variables. Instead a partial order is obtained in which the amount of ordering depends on the number and nature of the input variables and the relationship between them. However, if trade-offs are excluded, it is still possible to obtain a weak order using lexicographic ordering of the input variables. An implication is that psychological processes that integrate information from different input variables and that produce consistent output require that the input variables be measured on more than ordinal scales. A further implication is that the level of measurement of the input variables affects the kind of psychological model that can be applied to the process.     

Implicit theories about interrelations of anger components in 25 countries

We were interested in the cross-cultural comparison of implicit theories of the interrelations of eight anger components (antecedents, body sensations, cognitive reactions, verbal expressions, nonverbal expressions, interpersonal responses, and primary and secondary self-control). Self-report scales of each of these components were administered to a total of 5,006 college students in 25 countries. Equivalence of the scales was supported in that scales showed acceptable congruence coefficients in almost all comparisons. A multigroup confirmatory factor model with three latent variables (labeled internal processes, behavioral outcomes, and self-control mechanisms) could well account for the interrelations of the eight observed variables; measurement and structural weights were invariant. Behavioral outcomes and self-control mechanisms were only associated through their common dependence on internal processes. Verbal expressions and cognitive reactions showed the largest cross-cultural differences in means, whereas self-control mechanisms scales showed the smallest differences. Yet, cultural differences between the countries were small. It is concluded that anger, as measured by these scales, shows more pronounced cross-cultural similarities than differences in terms of both interrelations and mean score levels.     

Normative versus ipsative configural frequency analysis in personality research—their use discussed in a reanalysis of data on situation-bound anxiety

Configural frequency analysis (CFA) tests whether certain individual patterns in different variables are observed more frequently in a sample than expected by chance. In normative CFA, these patterns are derived from the subject's specific position in relation to sample characteristics such as the median or the mean. In ipsative CFA, patterns are defined within an individual reference system, e.g. relative to the subject's median of different variable scores. Normative CFA examines dimensionality of scales and is comparable to factor analysis in this respect. Ipsative CFA rather yields information about location of scores in different variables, in a similar way to ANOVA or Friedman testing. However, both normative and ipsative CFA may supply information not obtainable by means of the aforementioned methods. This is illustrated in a reanalysis of data in four scales of an anxiety inventory. © 1997 John Wiley & Sons, Ltd.     

MMPI Supplemental Scale Performance of Mexican Americans and Level of Acculturation

Mexican American and Anglo American's performance on the Wiggins Content Scales, Harris-Lingoes subscales, and Serkownek subscales was assessed in a college student population, Level of acculturation (Mexican vs. Anglo orientation), age, and social class were statistically controlled, The results showed statistically significant differences between means of Anglo and Mexican Americans on most of the supplemental scales assessed. These differences were more numerous before scale validity criteria were applied. The number of statistically significant differences were further reduced when level of acculturation and age were statistically controlled, The results showed that level of acculturation is a highly important variable which moderates interpretation of the MMPI scale elevations we measured. Acculturation far outweighted the influence of the well established MMPI moderator variables of age and social class.     

Principal self-efficacy: relations with burnout, job satisfaction and motivation to quit

The purpose of this study was to explore relations between principals?? self-efficacy, burnout, job satisfaction and principals?? motivation to quit. Principal self-efficacy was measured by a recently developed multidimensional scale called the Norwegian Principal Self-Efficacy Scale. Burnout was measured by a modified version of the Maslach Burnout Inventory. Job satisfaction and motivation to quit were measured by two scales developed for the purpose of this study, respectively. Participant in the study were 1,818 principals from the population of Norwegian principals. Data was collected by means of an electronic questionnaire. Two structural equation models were tested which specified principal self-efficacy as an exogenous variable and burnout, job satisfaction and motivation to quit as endogenous variables. The data was analyzed by means of SEM analysis for latent variables using the AMOS 18 program. Both models had acceptable fit to data. The results revealed that principal self-efficacy was positively related to job satisfaction and motivation to quit and negatively related to burnout. Burnout and job satisfaction were negatively related. Burnout was positively related to motivation to quit whereas job satisfaction was negatively related. The study highlights important relations between self-efficacy, burnout, job satisfaction and motivation to quit and extends the literature on principal self-efficacy and its relation to other concepts. The results of the study are discussed together with limitations and suggestions for further research.     

SUBJECTIVE SCALING BASED ON THRESHOLD MEASUREMENTS

B acklund , F. A., and B ergström , S.-S. Subjective scaling based on threshold measurements. Scand. J. Psychol ., 1961, 2, 88–92. A method of establishing subjective scales by means of absolute threshold measurements is reported. The method is successfully applied to data from the perception of motion and time.     

Acquiescent Responding in Balanced Multidimensional Scales and Exploratory Factor Analysis

Personality tests often consist of a set of dichotomous or Likert items. These response formats are known to be susceptible to an agreeing-response bias called acquiescence. The common assumption in balanced scales is that the sum of appropriately reversed responses should be reasonably free of acquiescence. However, inter-item correlation (or covariance) matrices can still be affected by the presence of variance due to acquiescence. To analyse these correlation matrices, we propose a method that is based on an unrestricted factor analysis and can be applied to multidimensional scales. This method obtains a factor solution in which acquiescence response variance is isolated in an independent factor. It is therefore possible, without the potentially confounding effect of acquiescence, to: (a) examine the dominant factors related to content latent variables; and (b) estimate participants’ factor scores on content latent variables. This method, which is illustrated by two empirical data examples, has proved to be useful for improving the simplicity of the factor structure. This research was partially supported by a grant from the Spanish Ministry of Science and Technology (SEJ2005-09170-C04-04/PSIC), and a grant from the Catalan Ministry of Universities, the Research and Information Society (2005SGR00017). The authors are obliged to the team of reviewers for helpful comments on an earlier version of this paper.     

Assimilation resistance and affective response in problem solving

In a problem solving experiment, predictions were based upon a theory of motivation and action, the scheme theory, and a psychometric model for the component analysis of rating data, the sector model (Eckblad, 1981; 1980). Pattern guessing tasks were presented to 32 students, 8 to each subject, in individual sessions lasting more than one hour. Number of errors, rated attractiveness, and guessing latencies (the process variables) were recorded during each task. After completion of each task, the affective reaction to it was assessed by means of ratings on six scales, including the scales Pleasant, Interesting, and Complex. On the basis of the sector model, an index of assimilation resistance was computed from the ratings of each task/subject unit, and the index was used to predict mean values and gradients for the process variables. Results show that the sector structure is clearly present in the rating data, that the process variables fit into the structure in the predicted manner, and that mean values and gradients for the process variables differ highly significantly and as predicted among tasks of different levels of assimilation resistance.     

Multivariate modelling and personality organization: A comparative study of the Defense Mechanism Test and linguistic expressions

The main aim of the study is to establish an empirical connection between perceptual defences as measured by the Defense Mechanism Test (DMT)–a projective percept-genetic method–and manifest linguistic expressions based on word pattern analyses. The subjects were 25 psychiatric patients with the diagnoses neurotic personality organization (NPO), borderline personality organization (BPO) and psychotic personality organization (PPO) in accordance with Kernberg's theory. A set of 130 DMT variables and 40 linguistic variables were analyzed by means of partial least squares (PLS) discriminant analysis separately and then pooled together. The overall hypothesis was that it would be possible to define the personality organization of the patients in terms of an amalgam of perceptual defences and word patterns, and that these two kinds of data would confirm each other. The result of the combined PLS analysis revealed a very good separation between the diagnostic groups as measured by the pooled variable sets. Among other things, it was shown that NPO patients are principally characterized by linguistic variables, whereas BPO and PPO patients are better defined by perceptual defences as measured by the DMT method.     

Humor styles and personality: A meta‐analysis of the relation between humor styles and the Big Five personality traits

This research summarizes the knowledge generated in social psychology and positive psychology about the relationship between humor styles, personality and wellbeing. Specifically, a meta‐analysis was performed with the results of 15 studies on humor styles measured by the Humor Styles Questionnaire (Martin, Puhlik‐Doris, Larsen, Gray & Weir, 2003) in correlation with the personality traits measured by the Big Five Personality model (measured with different scales). Following the steps presented by Rosenthal (1991) for meta‐analysis in the case of correlational research, we calculated the total mean r as an indicator of effect size. Results show that affiliative humor has a strong and homogeneous relation to neuroticism and extraversion. The homogeneity and heterogeneity found between variables and possible explanations are discussed in the conclusion.     

A critique of the usefulness of inferential statistics in applied behavior analysis

Researchers continue to recommend that applied behavior analysts use inferential statistics in making decisions about effects of independent variables on dependent variables. In many other approaches to behavioral science, inferential statistics are the primary means for deciding the importance of effects. Several possible uses of inferential statistics are considered. Rather than being an objective means for making decisions about effects, as is often claimed, inferential statistics are shown to be subjective. It is argued that the use of inferential statistics adds nothing to the complex and admittedly subjective nonstatistical methods that are often employed in applied behavior analysis. Attacks on inferential statistics that are being made, perhaps with increasing frequency, by those who are not behavior analysts, are discussed. These attackers are calling for banning the use of inferential statistics in research publications and commonly recommend that behavioral scientists should switch to using statistics aimed at interval estimation or the method of confidence intervals. Interval estimation is shown to be contrary to the fundamental assumption of behavior analysis that only individuals behave. It is recommended that authors who wish to publish the results of inferential statistics be asked to justify them as a means for helping us to identify any ways in which they may be useful.     

Zur rückfallprognostischen Bedeutung des Tatverhaltens bei Sexualdelinquenz

The study examined the possibility of predicting sexual recidivism within a period of 5 years in a sample of 612 male sex offenders by means of behavioural crime scene variables. A total of 20 variables were selected based on a significant bivariate correlation with sexual recidivism. Multivariate analysis was conducted to determine combined predictive accuracy. Step-wise reverse logistic regression extracted 12 variables explaining 22% of total variance in sexual recidivism. The unweighted sum score of these variables showed considerable predictive power (AUC?=?0.76; r?=?0.34). Findings were robust not only for different subgroups of sexual offenders, but also when cross-validated on an independent sample. In addition, the unweighted sum score showed significant incremental validity above and beyond common risk measures [Static99, Sexual Violence Risk- (SVR-)20], both in the original and the cross-validation sample. Thus, the potential of crime scene analysis in predicting sexual recidivism has been clearly demonstrated. Future research should provide a more accurate access to psychologically meaningful interpretations of the risk immanent in crime scene actions by adapting risk scales to certain subgroups of perpetrators.     

Psychological measures as predictors of military training performance

The predictive validity of 7 ability tests, the Big Five, and the Rorschach method administered to 71 male applicants at the Naval Special Forces (NSF) of Norway was evaluated based on pass/fail results in training. The findings showed: (a) small correlations between the ability tests, the Big Five scales, and the success criterion; (b) Rorschach variables measuring stress tolerance, reality testing, cognition, and social adjustment correlated significantly (r =.25 to.48) with pass/fail results in training, and (c) logistic regression analysis revealed that 3 of the Rorschach variables accumulated incrementally in the prediction of training completion when entered after the ability tests and the Big Five scales, thus supporting the merit of using Rorschach variables for predicting NSF training performance     

A social psychological approach to driving violations in two Chinese cities

A questionnaire study conducted in two Chinese cities investigated the determinants of the respondents’ aberrant driving behaviours. The Chinese Driving Questionnaire (CDQ) was developed and a version of the Manchester Driver Behaviour Questionnaire (DBQ) containing an extended set of driving violations particularly relevant in China was also included. Factor analysis of the DBQ revealed four factors with Alpha values over .60, two of them violations and the other two lapses and errors. Factor analysis of the CDQ items also revealed four factors with Alpha values over .60, namely the sense of social hierarchy, potential road safety countermeasure, belief in interpersonal network, and challenging legitimate authority. The result of a correlation analysis of the DBQ and CDQ scales showed that while the two violation scales were significantly and positively correlated with the social hierarchy and interpersonal network scale, the two lapse and error scales basically were not. When the DBQ scales were regressed on demographic variables and CDQ scales, the results of the hierarchical regressions showed that the prediction of self-reported driving violations had been significantly improved by the addition of culture relevant factors measured in the CDQ, while there was no major change in the prediction of lapses and errors. Logistic regression analysis showed that aggressive violations made a significant contribution to traffic accident involvement, independent of the demographic variables. The present study also identified some potential road safety countermeasures, and suggested young female drivers, and drivers at their early thirties should be especially targeted in road safety campaign.     

Brief Report: Some Possible Uses Of Factor Analysis In Multivariate Studies

Factor analysis is used in item selection in the hopes of producing a small number of factors each of which will represent a unidimensional sub- scale. If item analysis has been successful in producing truly independent subscales, it might be hoped that the number of factors would equal the number of subscales and that each factor would be highly defined by a single subscale. Factor analysis when used in studies of organization, is not assumed to produce factors that represent unidimensional scales. Rather, factor analysis is used to reveal various substructures that exist within an organization. If several variables are loaded on a single factor, the variables can be regarded as nodes of interaction between measured dimensions of organization.     

The application of an action system model to destructive behaviour: the examples of arson and terrorism.

This article argues that criminal and deviant behaviour can be productively viewed through an action system framework. The idea is developed by considering two forms of destructive behaviour: arson and barricade-hostage terrorist incidents. Two studies are presented. The first study tests the hypothesis that different forms of arson will reflect the four dominant states that an action system can take; integrative, expressive, conservative, and adaptive. A smallest space analysis was performed on 46 variables describing 230 cases of arson and the results identified the four themes of action system functioning. An examination of the personal characteristics of the arsonists also produced four variable groupings and a combined analysis of the four action scales and four characteristics scales also supported the structural hypothesis of the action system model. The second study applied the action system model to the study acts of terrorist barricade-hostage incidents. A smallest space analysis of 44 variables coded from 41 incidents again revealed four distinct forms of activity, which were psychologically similar to the four modes of arson identified in study one. Overall, these two studies provide support for the appropriateness of the action system framework as a way of classifying different forms of deviant behaviour.     

The principal components of mixed measurement level multivariate data: An alternating least squares method with optimal scaling features

A method is discussed which extends principal components analysis to the situation where the variables may be measured at a variety of scale levels (nominal, ordinal or interval), and where they may be either continuous or discrete. There are no restrictions on the mix of measurement characteristics and there may be any pattern of missing observations. The method scales the observations on each variable within the restrictions imposed by the variable's measurement characteristics, so that the deviation from the principal components model for a specified number of components is minimized in the least squares sense. An alternating least squares algorithm is discussed. An illustrative example is given.Copies of this paper and of the associated PRINCIPALS program may be obtained by writing to Forrest W. Young, Psychometric Laboratory, Davie Hall 013-A, Chapel Hill, NC 27514.     

Adolescent attitudes toward body image and anorexic behavior

This study explored the relationship between anorexic behavior and selected dimensions of body image. Anorexic behavior was assessed by two scales, the Eating Attitudes Test (EAT 26) (Garner, Olmstead, Bohr, & Garfinkel, 1982) and the Eating Disorders Inventory (EDI) (Garner, Olmstead, & Polivy, 1983). Predictor variables, selected dimensions of body image, physical attractiveness, self-esteem, and physical effectiveness, were measured by scales adapted by Lerner and Karabenick (1974) and Lerner, Orlos, and Knapp (1976). Multiple regression techniques were used to determine how much of the tendency toward anorexic behavior can be predicted by selected dimensions of body image. The major focus of the analysis was to explore the contributions of each of the dimensions of body image to predicting tendencies toward anorexic behavior in adolescents. The research sample consisted of 169 high school students, aged 15 to 18, who were enrolled in health, physical education, or psychology classes in the spring of 1983. Results indicated that the dimension of self-esteem was the major factor in the prediction of anorexic behaviors as measured by the Eating Disorders Inventory.