Sample Heterogeneity and the Measurement Structure of the Multidimensional Students’ Life Satisfaction Scale

Several measurement assumptions were examined with the goal of assessing the validity of the Multidimensional Students’ Life Satisfaction Scale (MSLSS), a measure of adolescents’ satisfaction with their family, friends, living environment, school, self, and general quality of life. The data were obtained via a cross-sectional survey of 8,225 adolescents in British Columbia, Canada. Confirmatory factor and factor mixture analyses of ordinal data were used to examine the measurement assumptions. The adolescents did not respond to all the MSLSS items in a psychometrically equivalent manner. A correlated five-factor model for an abridged version of the MSLSS resulted in good fit when all negatively worded items and several positively worded items (the least invariant) were excluded. The abridged 18-item version of the MSLSS provides a promising alternative for the measurement of five life domains that are pertinent to adolescents’ quality of life.     

Ethnicity,Modern Prejudice and the Quality of Life

The aim of this investigation was to measure levels of ethnic or cultural background diversity, social cohesion and modern prejudice, and the impact of such diversity, cohesion and prejudice on the quality of life. Using a sample of 743 residents of Prince George, British Columbia, we identified diverse ethnic or cultural groups, and created several indexes of heterogeneous social networks and a measure of modern prejudice. Dividing the total sample into three roughly distinct groups containing, respectively, respondents self-reporting an ethnic or cultural background that was aboriginal, non-aboriginal visible minority or anything else, we discovered that all significant comparisons indicated that people with aboriginal backgrounds reported a generally lower quality of life than those in the other two groups. The quality of life scores of the other two groups were practically indistinguishable. Given the demographic structure of our sample, the revealed differences could not be attributed to differences in socio-economic classes. Members of the largest group of respondents tended to be most prejudiced and optimistic, people with aboriginal backgrounds tended to be least prejudiced and optimistic and people with visible minority backgrounds tended to be between the other two groups. Regressions revealed that a variety of ethnic/culture-related phenomena could only explain 8%, 9% and 10%, respectively, of the variation in scores for happiness, life satisfaction and satisfaction with the overall quality of life. When domain satisfaction scores were added to the set of predictors, we were able to explain 48%, 69% and 54%, respectively, of the variation in scores for happiness, life satisfaction and satisfaction with the overall quality of life. In the presence of the domain satisfaction scores, the scores on the ethnic/cultural related phenomena added only one percentage point of explanatory power for happiness and life satisfaction, and three percentage points for satisfaction with the overall quality of life. All things considered, then, it is fair to say that this project showed that ethnic or cultural background diversity, social cohesion and modern prejudice had relatively very little impact on the quality of life of our sample of respondents.     

Access to Health Care: Social Determinants of Preventive Cancer Screening Use in Northern British Columbia

The purpose of this study was to examine theextent to which social factors are influentialin determining women's access to cancerscreening services in Prince George, BritishColumbia. Specifically, this study evaluatedthe association of age, income, education, workstatus, disability, marital status, andimmigrant status with previous use of screeningmammography and Pap tests. Data was obtainedfrom the 1994 National Population HealthSurvey, which contains a sample of 416 womenfrom the Prince George area. A series oflogistic regression analyses were used todistinguish ever versus never beenscreened as well as recency of previousscreening. Participation rates in screeningmammography in Prince George are comparativelyhigh; however, no association was found betweensocial factors and previous mammography use.This suggests women in Prince George areparticipating in mammography servicesregardless of social background. Participationrates in Pap test screening in Prince Georgeare high and are similar to provincialaverages; however, while a large percentage ofwomen have been screened, this percentagevaries across social groups. Immigrant women,single women, and women with less education areover represented among women who have never hada Pap test. In addition, older women are lesslikely to obtain a recent Pap test whencompared to younger women. This study suggeststhat certain groups of women in northernBritish Columbia experience low participationin health services, resulting in a higher riskfor poor health and a poor quality of life.     

A Statistical Examination of the Health Utility Index-Mark III as a Summary Measure of Health Status for a General Population Health Survey

The purpose of this study was to examine the abilityof the Health Utility Index-Mark III (HUI-Mark III) toprovide a summary measure of the physical, mental andsocial dimensions of health assessed in the 1994/5National Population Health Survey (NPHS). The sampleconsisted of 838 (402 male, 436 female) randomlyselected residents of Prince George, British Columbia.An exploratory factor analysis was conducted using themeasures of physical, psychological and social healthincluded in the NPHS. The HUI-Mark III scores werethen regressed on to the factors in an attempt todetermine the proportion of variance in factor scoresaccounted for by the HUI-Mark III. The results suggestthat the HUI-Mark III is primarily a measure ofphysical impairment that does not adequately representthe physical, mental and social dimensions of healthas measured in the NPHS.     

ON OPTIMIZING MULTI-LEVEL DESIGNS: POWER UNDER BUDGET CONSTRAINTS

This paper derives a procedure for efficiently allocating the number of units in multi‐level designs given prespecified power levels. The derivation of the procedure is based on a constrained optimization problem that maximizes a general form of a ratio of expected mean squares subject to a budget constraint. The procedure makes use of variance component estimates to optimize designs during the budget formulating stages. The method provides more general closed form solutions than other currently available formulae. As such, the proposed procedure allows for the determination of the optimal numbers of units for studies that involve more complex designs. A method is also described for optimizing designs when variance component estimates are not available. Case studies are provided to demonstrate the method.     

Index of Authors Volume 51

Authors Index

Index of Authors Volume 51     

Validity and the Consequences of Test Interpretation and Use

The vast majority of measures have, at their core, a purpose of personal and social change. If test developers and users want measures to have personal and social consequences and impact, then it is critical to consider the consequences and side effects of measurement in the validation process itself. The consequential basis of test interpretation and use, as introduced in Messick’s (Educational measurement, Macmillan, New York, pp. 13–103, 1989) progressive matrix model of unified validity theory, has been misunderstood by many measurement experts, test developers, researchers, and practitioners. The purposes of this paper were to (a) review Messick’s unified view of validity and clarify his consequential basis of test interpretation and use, (b) discuss the kinds of questions evoked by value implications and social consequences and their role in construct validity and score meaning, (c) present a reframing of Messick’s model and a new model of unified validity and validation, (d) bring the concept of multilevel measures under the same validation umbrella as individual differences measures, and (e) offer some thoughts and directions for more explicit consideration of value implications, intended social consequences, and unintended side effects of legitimate test interpretation and use. This paper has implications for the interpretation, use, and validation of both individual differences and multilevel measures in education, psychology, and health contexts.     

Assessing the Unidimensionality of Psychological Scales: Using Multiple Criteria from Factor Analysis

Whenever one uses a composite scale score from item responses, one is tacitly assuming that the scale is dominantly unidimensional. Investigating the unidimensionality of item response data is an essential component of construct validity. Yet, there is no universally accepted technique or set of rules to determine the number of factors to retain when assessing the dimensionality of item response data. Typically factor analysis is used with the eigenvalues-greater-than-one rule, the ratio of first-to-second eigenvalues, parallel analysis, root-mean-square-error-of-approximation, or hypothesis testing approaches involving chi-square tests from Maximum Likelihood or Generalized Least Squares estimation. The purpose of this study was to investigate how these various procedures perform individually, and in combination, when assessing the unidimensionality of item response data via a computer simulated design. Conditions such as sample size, magnitude of communality, distribution of item responses, proportion of communality on second factor, and the number of items with non-zero loadings on the second factor were varied. Results indicate that there was no one individual decision-making method that identified unidimensionality under all conditions manipulated. Given the low communalities, all individual decision-making methods failed to detect unidimensionality for the combination where sample size was small, magnitude of communality was low, and item distributions were skewed. A set of guidelines and a new statistical methodology are provided for researchers.     

A Method for Simulating Multivariate Non Normal Distributions with Specified Standardized Cumulants and Intraclass Correlation Coefficients

Intraclass correlation coefficients (ICCs) are commonly used indices in subject areas such as biometrics, longitudinal data analysis, measurement theory, quality control, and survey research. The properties of the ICCs most often used are derived under the assumption of normality. However, real-world data often violate the normality assumption. In view of this, a computationally efficient procedure is developed for simulating multivariate non normal continuous distributions with specified (a) standardized cumulants, (b) Pearson intercorrelations, and (c) ICCs. The linear model specified is a two-factor design with either fixed or random effects. A numerical example is worked and the results of a Monte Carlo simulation are provided to demonstrate and confirm the methodology.     

Opening Remarks to the Special Issue on Validity Theory and the Methods Used in Validation: Perspectives from the Social and Behavioral Sciences

Social Indicators Research -