Leroy Wolins

Fabric Hand: Tactile Sensory Assessment

The assessment of fabric hand involves two major classes of variables: fabrics as stimuli with certain physical properties, and people as judges with certain traits. This research investigated the tactile sensory assessment of selected fabrics that varied in specified physical dimensions—namely : stiffness, roughness, and thickness—replicated in two fiber contents: cotton and polyester. In the analysis- of-variance design, physical dimensions of fabrics were taken as fixed, rather than random, variables, and judges as blocks. The subjective-hand properties were measured by polar adjectives using a 99-point certainty scale, transformed to normal deviates. Sensory responses of judges to the nine pairs of polar adjectives differed significantly with respect to all four main effects: fiber content, stiffness, roughness, and thickness. The sensitivity of the 99-point certainty scale resulted in a wide range of F values; various interactions were clarified by graphic analysis. Editing of data for suspected errors in responses caused few changes in the ANOVA results.

A Procedure for Estimation of Trait, Method, and Error Variance Attributable to a Measure

IN order to delineate the problem considered in this paper, and the rationale upon which the solution is based, the following definitions mill be adhered to. A trait is defined as any potentially measureable attribute of the subject whose responses are observed, e.g., anxiety, neuroticism, morale, etc. A method refers to the means used to ob: -ewe or assess the trait, e.g. peer ratings, psychologist’s ratings, questionnaires, etc. The measure refers to the particular trait-method combination administered to a subject to obtain an observation. The multitrait-multimethod matrix is comprised of correlations between measures which use a number of methods to assess each member of the same set of traits. The procedure described in this paper is based on explicit models for multitrait-multimethod data. The formal models are related to models implicit in the classical Campbell and Fiske (1959) presentation. The procedure is based also on previous research conducted by Wolins (1964) and by Stanley (1961). Another

Alternative Methods of Analysis: Multitrait-Multimethod Data

THE following definitions, taken from Thurstone (1947) and from Campbell and Fiske (1959), will be employed to characterize the measurement system considered in this paper. A subject is generally the person whose responses are observed. A trait is defined as any potentially observable attribute of the subj ect. A method refers to the means used to observe or assess the trait. A measure refers to the trait-method combination used to obtain an observation on the subject. The observations yielded by a measure are treated as if they vary on an interval scale. Consider, for example, the traits called manager human relations

Transformations to Improve Reliability and/or Validity for Affective Scales

THE psychological literature is rich with studies demonstrating that collecting responses to affective stimuli using a large number of ordered categories is not effective when compared with using some smaller number (e.g., Matell and Jacoby, 1971; Komorita and Graham, 1965). Thus, a 20-point scale is no better, and perhaps worse, in terms of reliability and validity than, say, a 5-point scale. However, these studies uniformly rank the categories and analyze these ranks. There is a small, circumscribed body of literature (Liu, 1971 ; Warren, Klonglan, and Sabri, 1969) which indicates that the use of normalized ranks or, in the case of large numbers of categories, normal deviates results in an increasing, monotonic relationship between reliability and number of categories. Such transformations weight highly response differences in the ends of the scale

Perceived Fashion Risk and Self-Esteem of Males and Females

An instrument was developed to examine a persons perception of fashion risk in clothing, relative to his or her self-esteem. Fashion risk is the uncertainty a consumer perceives when making a choice involving a fashion good, in addition to the uncertainty perceived when a good is not subject to fashion. Items were written or adapted to represent self-esteem, self- esteem related to clothing, perceived fashion risk, and economic, social, psychological, and performance risks related to clothing. Approximately 400 university students, half males and half females, responded to the instrument. Response patterns of males and females differed; therefore data were factor analyzed separately for each sex. Eleven factors were derived for females, eight for males. Factor content was similar, but fac tor structure was different. For females, factors representing fashion interest formed one cluster and factors representing self-esteem and social approval a separate cluster, the two clusters being completely uncorrelated. For males, factors did not cluster. Fashion risk seems to be a part of other types of risk rather than a distinct type of risk. Also, perception of fashion risk seems not to be linearly related to self-esteem.

Fashion Preference: Drawings versus Photographs

Are consumer preferences for fashions affected by whether styles are presented in photographs or drawings? Does mode of presentation of stimuli influence responses obtained in research? These were questions addressed in this experiment. Stimuli were photographs of five styles of evening wear and drawings of the same styles. Female university students responded to each stimulus on 19 pairs of polar adjectives; preferences were expressed in full forced-choice paired comparisons. Mode of presentation made no difference in preferences for the five styles. Responses to specific styles differed between photographs and drawings for five of the 19 pairs of polar adjectives, but the quantitative effect of mode of presentation was very small. Order of preference for the styles was most closely linked with the word pairs dated-current and ugly-beautiful.

Disordered eating and weight control behaviors among male and female university students

The purposes of this study were to develop an instrument capable of assessing factors potentially related to disordered eating and weight control behaviors among university students and then to compare male and female students on these factors. A 90 item instrument was developed. Sixty-four items were written by these authors, such that eight items would assess each of eight identified factors related to disordered eating. Additionally, all 26 items from the Eating Attitudes Test (EAT-26) were included and interspersed within the instrument. The instrument was administered to 502 female university students and their responses were factor analyzed. Ten factors were identified. The instrument was then administered to 94 female and 76 male university students. Results indicate that compared to males, females report a greater desire to be thin, less tolerance for cold, more frequent use of laxatives, and a greater occurrence of eating in response to internal and external cues. There were no other sex differences. The students in this study appeared to be engaging in appropriate health practices.

The Use of Multiple Regression Procedures When the Predictor Variables are Psychological Tests

MODERN textbooks on statistical methods uniformly caution the reader that regression procedures are based on the assumption that the predictor variables are not subject to error. However, vhen the predictor variables are psychological tests, this assumption is seldom, if ever, approximated. On the other hand, some of the implications of statistical theory clearly point to procedures for hypothesis testing and estimation when the predictor variables are subject to error that are superior to usual procedures dictated by the inappropriate statistical model. This statistical theory more or less (rather than precisely) defines the kind of inferences one can and cannot make from regression analysis based on such predictor variables and suggests a n alternative cross-validation design. The purpose of this paper is to expound rather than derive these principles. This exposition is intended to alert the quantitatively Sophisticated reader to these principles and to provide the less quantitatively sophisticated reader with statistical tools more appropriate for psychological prediction than those offered in textbooks. These principles require a psychologist to expound them apparently because the statistician, by temperament, requires more precise statements than those offered here. However, it is anticipated that these principles mill be endorsed (more or less) by most statisticians. Principle 1. Inferences d r a m from estimates of and tests of hypotheses concerning partial regression coefficients have greater

A Monte Carlo Study of Constrained Factor Analysis Using Maximum Likelihood and Unweighted Least Squares

From each of 105 samples of 300 observations each and from each of 87 samples of 3,000 each, constrained factor analyses of 96 normally distributed variables arranged in a three-stage hierarchical structure were computed by maximum likelihood (ML) and unweighted least squares (ULS). It was evident that ULS not only takes less time and computer resources than does ML, but also leads to better estimates for small sample sizes. It was also evident that when a large number of variables are loaded highly on a factor, especially when those variables have high communalities, the adverse effects of small sample size are somewhat diminished. Finally, it was evident that the occurrence of a boundary problem does not necessarily detract from the overall validity of a solution.

COOPERATIVE-COMPETITIVE PREFERENCES AND BEHAVIORAL CORRELATES AS A FUNCTION OF SEX AND AGE OF SCHOOL-AGE CHILDREN

The objectives of the study were to: (1) develop a two-factor self-report preference measure of cooperation and competition; (2) explore the relationships between cooperative and competitive preferences, locus of control, social competence (parent rating), and school behaviors (teacher rating); (3) investigate sex and grade differences on the dependent measures. Factor analysis was employed on an 85-item inventory, administered to 120 children, resulting in the two expected factors plus two other factors. Another sample of 246 fourth-, fifth-, and sixth-grade children, their parents, and teachers was obtained. Correlational analysis indicated that childrens cooperative-competitive preferences were not related to behaviors rated by teachers or parents; however, childrens externality was related to competitive preferences and maladaptive behaviors at school. Analyses of variance showed girls indicated significantly more cooperative preferences than boys and girls remained uniformly cooperative over the three grade levels while males declined in cooperative preferences. Findings supported traditional sex differences as in the literature.