Search

Causal inference in psychological research is typically hampered by unobserved confounding. A copula-based method can be used to statistically control for this problem without the need for instruments or covariates, given relatively lenient distributional assumptions on independent variables and error terms. The current study aims to: (a) provide a user-friendly introduction to the copula method for psychology researchers, and (b) examine the degree of non-normality in the independent variables required for satisfactory performance. A Monte Carlo simulation study was used to assess the behavior of the copula method under various combinations of conditions (sample size, skewness of independent variables, effect size, and magnitude of confounding). In addition, an applied example from research on the effects of parental rearing on adult personality and life satisfaction was used to illustrate the method. Simulations revealed that the copula method performed better at higher levels of skewness in the independent variables, and that the impacts of lower skewness can be offset to some extent by larger sample size. When skewness and/or sample size is too small, the copula method is biased toward the uncorrected model. In the applied example, parental rejection/punishment predicted less adaptive personality and life satisfaction, with no evidence of confounding. For parental control/overprotection, there was evidence that confounding attenuated the estimated relationship with personality/life satisfaction. Copula adjustment is a promising method for handling unobserved confounding. The discussion focuses on how to proceed when assumptions are not quite met, and outlines potential avenues for future research. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

In this paper, we examine the problem of endogeneity in the context of operations management research. Whereas the extant literature has focused primarily on the statistical aspect of the problem, a comprehensive treatment requires an examination of theoretical and pragmatic considerations as complements. The prevailing problem with the focus on statistical techniques is that the standards tend to be derived from idealizations: the correlation between a regressor and a disturbance term must be exactly zero, or the analysis will be invalid. In actual empirical research settings, such a knife-edge assumption can never be satisfied, indeed it cannot even be directly tested. Idealizations are useful in helping us understand what it would take to eliminate endogeneity, but when applied directly and unconditionally, they lead to unreasonable standards that may unnecessarily stifle substantive inquiry. We believe that it is far more productive and meaningful to ask: “What can we realistically expect empirical scientists to be able to achieve?” To this end, we cover and revisit some of the general technical material on endogeneity, paying special attention to the idiosyncrasies of operations management research and what could constitute reasonable criteria for addressing endogeneity in empirical operations management studies.

This chapter provides a cost-benefit analysis of developmental crime prevention. From a life-course perspective, developmental prevention offers an intriguing solution to address growing concerns regarding current criminal justice practices, given the growing body of research that suggests that this type of intervention is both results-oriented and fiscally responsible. To this end, this chapter lays out the case for the economics of developmental crime prevention. It next provides an overview of the methodological basis, and related considerations, of a cost-benefit analysis, which assigns monetary values to program outcomes relative to program costs so as to provide an estimate of the financial return on investment. The chapter then reviews the leading cost-benefit analysis studies in developmental crime prevention today and offers a glimpse at the future of such research.

Several calls have been made for replacing coefficient α with more contemporary model-based reliability coefficients in psychological research. Under the assumption of unidimensional measurement scales and independent measurement errors, two leading alternatives are composite reliability and maximal reliability. Of these two, the maximal reliability statistic, or equivalently Hancock's H, has received a significant amount of attention in recent years. The difference between composite reliability and maximal reliability is that the former is a reliability index for a scale mean (or unweighted sum), whereas the latter estimates the reliability of a scale score where indicators are weighted differently based on their estimated reliabilities. The formula for the maximal reliability weights has been derived using population quantities; however, their finite-sample behavior has not been extensively examined. Particularly, there are two types of bias when the maximal reliability statistic is calculated from sample data: (a) the sample maximal reliability estimator is a positively biased estimator of population maximal reliability, and (b) the true reliability of composites formed with maximal reliability weights calculated from sample data is on average less than the population reliability. Both effects are more pronounced in small-sample scenarios (e.g.

A recent article by Krause (Qual Quant, doi: 10.1007/s11135-012-9712-5 , Krause (2012)) maintains that: (1) it is untenable to characterize the error term in multiple regression as simply an extraneous random influence on the outcome variable, because any amount of error implies the possibility of one or more omitted, relevant explanatory variables; and (2) the only way to guarantee the prevention of omitted variable bias and thereby justify causal interpretations of estimated coefficients is to construct fully specified models that completely eliminate the error term. The present commentary argues that such an extreme position is impractical and unnecessary, given the availability of specialized techniques for dealing with the primary statistical consequence of omitted variables, namely endogeneity, or the existence of correlations between included explanatory variables and the error term. In particular, the current article discusses the method of instrumental variable estimation, which can resolve the endogeneity problem in causal models where one or more relevant explanatory variables are excluded, thus allowing for accurate estimation of effects. An overview of recent methodological resources and software for conducting instrumental variables estimation is provided, with the aim of helping to place this crucial technique squarely in the statistical toolkit of applied researchers.

This special issue focuses on a phenomenon studied by only a handful of organised crime scholars to date – criminal group mobility. The contributions in this issue evolved out of discussion papers commissioned by the Department of Public Safety Canada in 2010 for the 12th National and 15th International Metropolis conferences, and cover a wide variety of economic, social, and law enforcement issues related to the mobility of criminal groups. In this introductory article, we provide the general background and context for the collection, as well as a brief overview of each of the four papers. It is our hope that this special issue will inspire further rigorous research on this important topic, as well as help contribute toward the development of effective strategies for preventing the spread of organised crime.

The present study used Canadian National Longitudinal data to examine a model of the mechanisms through which the effects of neighborhood socioeconomic conditions impact young children's verbal and behavioral outcomes (N= 3,528; M age = 5.05 years, SD= 0.86). Integrating elements of social disorganization theory and family stress models, and results from structural equation models suggest that both neighborhood and family mechanisms played an important role in the transmission of neighborhood socioeconomic effects. Neighborhood disadvantage manifested its effect via lower neighborhood cohesion, which was associated with maternal depression and family dysfunction. These processes were, in turn, related to less consistent, less stimulating, and more punitive parenting behaviors, and ultimately, poorer child outcomes.

With seemingly few exceptions, current practice in structural equation modelling (SEM) aims at establishing close rather than exact fit between hypothetical models and observed data. This orientation has gone without serious challenge until the appearance of a sharp critique by Barrett (2007) , who suggests discontinuing the use of approximate fit indices (AFIs) in SEM. The present article provides a commentary and elaboration on the key aspects of Barrett’s position, and also supplies further practical guidance and methodological references to applied researchers, who may be motivated to significantly alter their modelling practices in order to address the issues he raises. I strongly support his calls for performing more detailed diagnostic examinations of model misfit when confronted with a significant chi-square ( χ 2 ) test statistic, rather than simply deferring to AFIs. However, I do not second the recommendation that assessments of a model’s predictive accuracy (e.g., R 2 values) can supplant a focused search for the reasons underlying significant global misfit. Accordingly, some misconceptions about the relationship between global model fit and predictive accuracy are pointed out, and modified advice is given to practitioners. Issues surrounding how to properly appraise a model yielding a non-significant χ 2 are also discussed, as are concerns raised by Barrett about small sample size and power in SEM. It is concluded that AFIs offer little value-added in SEM practice, given the wide variety of available methods for performing detailed model assessments. However, I leave the issue of whether AFIs should be completely abandoned to future research.

The partial least squares technique (PLS) has been touted as a viable alternative to latent variable structural equation modeling (SEM) for evaluating theoretical models in the differential psychology domain. We bring some balance to the discussion by reviewing the broader methodological literature to highlight: (1) the misleading characterization of PLS as an SEM method; (2) limitations of PLS for global model testing; (3) problems in testing the significance of path coefficients; (4) extremely high false positive rates when using empirical confidence intervals in conjunction with a new “sign-change correction” for path coefficients; (5) misconceptions surrounding the supposedly superior ability of PLS to handle small sample sizes and non-normality; and (6) conceptual and statistical problems with formative measurement and the application of PLS to such models. Additionally, we also reanalyze the dataset provided by Willaby et al. (2015; http://dx.doi.org/10.1016/j.paid.2014.09.008 ) to highlight the limitations of PLS. Our broader review and analysis of the available evidence makes it clear that PLS is not useful for statistical estimation and testing.

The current study examines the longitudinal relationship between dementia-related challenging behaviors (e.g., vocal disruption, physical aggression, repetitive behaviors, and restlessness) and cognitive functioning in the long-term care (LTC) context. A multivariate latent growth curve model within the structural equation modeling (SEM) framework was applied to data collected from 16,804 older adults upon admission to LTC and every 3 months for a period of 2.5 years. Increases in challenging behaviors were characterized by a significant positive linear and negative quadratic trend (i.e., a subtle leveling off at later assessment times), whereas increases in cognitive impairment were characterized by a positive linear trend. On average, individuals who were more cognitively impaired upon entry into LTC and who exhibited a steeper increase in cognitive impairment also exhibited more challenging behaviors at entry into LTC and a steeper increase in challenging behaviors, respectively. At the within-person level, individuals demonstrating an increase in cognitive impairment at a specific occasion were also more likely to demonstrate an increase in challenging behaviors at that same occasion; however, the magnitude of these effects was very small, suggesting limited practical implications. This study provides novel empirical evidence about the coevolution of cognitive impairment and challenging behaviors, going beyond prior research that has been either cross-sectional in nature, examined longitudinal change in only 1 variable, or simply looked at linear trends without attempting to explore the possibility of nonlinear change. Most importantly, this longitudinal examination of persons with dementia living in LTC has implications for how challenging behaviors can be better managed and for how new strategies can be implemented to prevent challenging behaviors.

Purpose To investigate the statistical fit of alternative higher order models for summarizing the health-related quality of life profile generated by the EORTC QLQ-C30 questionnaire. Methods A 50% random sample was drawn from a dataset of more than 9,000 pre-treatment QLQ-C30 v 3.0 questionnaires completed by cancer patients from 48 countries, differing in primary tumor site and disease stage. Building on a “standard” 14-dimensional QLQ-C30 model, confirmatory factor analysis was used to compare 6 higher order models, including a 1-dimensional (1D) model, a 2D “symptom burden and function” model, two 2D “mental/physical” models, and two models with a “formative” (or “causal”) formulation of “symptom burden,” and “function.” Results All of the models considered had at least an “adequate” fit to the data: the less restricted the model, the better the fit. The RMSEA fit indices for the various models ranged from 0.042 to 0.061, CFI’s 0.90–0.96, and TLI’s from 0.96 to 0.98. All chi-square tests were significant. One of the Physical/Mental models had fit indices superior to the other models considered. Conclusions The Physical/Mental health model had the best fit of the higher order models considered, and enjoys empirical and theoretical support in comparable instruments and applications.

The purpose of the present article is to take stock of a recent exchange in Organizational Research Methods between critics (Rönkkö & Evermann, 2013) and proponents (Henseler et al., 2014) of partial least squares path modeling (PLS-PM). The two target articles were centered around six principal issues, namely whether PLS-PM: (1) can be truly characterized as a technique for structural equation modeling (SEM); (2) is able to correct for measurement error; (3) can be used to validate measurement models; (4) accommodates small sample sizes; (5) is able to provide null hypothesis tests for path coefficients; and (6) can be employed in an exploratory, model-building fashion. We summarize and elaborate further on the key arguments underlying the exchange, drawing from the broader methodological and statistical literature in order to offer additional thoughts concerning the utility of PLS-PM and ways in which the technique might be improved. We conclude with recommendations as to whether and how PLS-PM serves as a viable contender to SEM approaches for estimating and evaluating theoretical models.

This study evaluated the factorial and convergent validity of theTemporal Satisfaction With Life Scale (TSWLS; Pavot, Diener andSuh, 1998), which was designed to measure past, present, andfuture life satisfaction. A sample of psychology undergraduates(N = 223) was administered a questionnaire containing the TSWLSand a global measure of past, present, and future subjectivewell-being (SWB), the Self-Anchoring Striving Scale (SASS;Kilpatrick and Cantril, 1960). Results of covariance structureanalyses supported a 3-factor model (past, present, and futurelife satisfaction as distinct, yet correlated, factors) for theTSWLS, demonstrated that item responding was only slightlycontaminated by an acquiescence bias, and showed that each of thepast, present, and future dimensions of the TSWLS was moststrongly related to its corresponding global SWB rating on theSASS. Theoretical and practical implications are discussed.

Purpose To analyze changes in life satisfaction (LS) scores over time in persons with spinal cord injury (SCI) and to interpret what these changes mean. Methods Multicenter, prospective cohort study of persons with SCI (n = 96) classified into 3 life satisfaction trajectories identified earlier. Assessment took place 6 times from the start of active rehabilitation up to 5 years after discharge. Three LS scores were compared: (1) LS ‘now’ score, (2) ‘comparison’ score between LS ‘now’ and LS ‘before the SCI’, and (3) retrospective score of LS ‘before the SCI’. Results Persons in the low LS trajectory showed increase in the LS ‘now’ score, but not in the LS ‘comparison’ score and retrospective score. Persons in the recovery trajectory showed increase in the LS ‘now’ and LS ‘comparison’ scores, but not in the retrospective score. Persons in the high LS trajectory showed increase in the ‘comparison’ LS score and decrease in the retrospective score, but no change in the LS ‘now’ score. Conclusions Diverging patterns of change were found and that were interpreted as adaptation or scale recalibration. Recalibration could also be considered healthy rebalancing after SCI. Being able to compare different LS ratings can facilitate the interpretation of change in and stability of LS.

RÉSUMÉDans cette étude, nous avons examiné les relations longitudinales entre les cinq dimensions de soutien social et la détresse psychologique afin de déterminer si (1) le soutien social est lié à niveaux subséquentes de la détresse psychologique ; ou (2) si les niveaux de détresse psychologique ont été liés à des niveaux ultérieurs de soutien social ; ou (3) si la détresse et le soutien avaient une relation réciproque (bi-directionnel) à travers le temps. L’étude a examiné le rapport bidirectionnel longitudinal entre les dimensions différentes du soutien social et la détresse psychologique, en utilisant un modèle autorégressif de corrélation avec décalage pour cinq périodes de données. Nous avons trouvé des preuves (d’appui) de la relation réciproque entre le soutien affectueux et la détresse. L’augmentation de la détresse psychologique etait liée à des niveaux élevés de la suite des interactions sociales positives et significativement liée a un soutien par la suite plus émotionnel et informationnel. Aucune relation significative n’a été trouvée entre un soutien tangible et structurelle et la détresse psychologique. Cette étude démontre que les différents types de soutien sont associés avec la détresse psychologique d’une manière correspondante et que la détresse psychologique peut être important, deux ans plus tard, pour prévoir des niveaux de soutien social.

The Medical Outcomes Study (MOS) social support scale is a 19-item survey that measures four dimensions of functional support. The current study reports on the psychometric properties, factorial structure, and measurement invariance of the scale for a sample of English- and French-speaking Canadians aged 55 or older.The internal consistency and composite reliability for a congeneric measurement model of the dimensions of functional social support were examined. A confirmatory factor analysis and test of invariance across language (English = 2,642; French = 489) were also performed.Across both English- and French-speaking respondents, results indicated good internal consistency (Cronbach's alpha ranged from .90 to .97) and composite reliability (ranging from .93 to .97) for all dimensions of functional social support. The confirmatory factor analysis revealed acceptable fit indices for the 4-factor structure similar to the original one. The scale appears to function uniformly across both language groups.The MOS social support scale appears to be a psychometrically sound instrument for use in research on social support with samples of English- and French-speaking older adults.

Health-adjusted life expectancy is a summary measure of population health that combines mortality and morbidity data into a single index. This article profiles differences in health-adjusted life expectancy across income categories for a representative sample of the Canadian population.Mortality data were obtained from the 1991-2001 Canadian census mortality follow-up study, which linked a 15% sample of the 1991 adult non-institutional population with 11 years of death records from the Canadian Mortality Data Base. Information on morbidity was obtained from the Health Utilities Index Mark 3 instrument on the 2000/2001 Canadian Community Health Survey. The Sullivan method was used to compute health-adjusted life expectancy for national deciles of population ranked by income.For both sexes, and with few exceptions, a nearly linear gradient across income deciles emerged for health-adjusted life expectancy at age 25. Compared with people in higher-income deciles, those in lower-income deciles had fewer years of health-adjusted life expectancy. These disparities were substantially larger than those revealed by life expectancy alone.These findings highlight the generally worse health-related quality of life of lower-income groups. The results demonstrate that assessments of socio-economic disparities in health should include the effects of both mortality and morbidity.

A major objective of the Population Health Impact of Disease in Canada (PHI) research program was to obtain Canadian-specific preferences for health states associated with various diseases, in order to estimate the morbidity component of summary measures of population health embodying the Canadian experience of disease. In this study, preferences for health states were elicited from lay panels (N=146) in nine Canadian communities (Vancouver, Edmonton, Saskatoon, Toronto, Ottawa, Montréal, Québec, Moncton and Halifax); the study was conducted from January to June of 2003. Information on health states was presented to raters using the CLAssification and MEasurement System of Functional Health (CLAMES), which assesses functional capacity using 11 health status attributes, each with four to five levels ranging from normal to severely limited functioning. Preferences for 238 health states classified by CLAMES were elicited using the standard gamble (SG) technique in both individual and group exercises. Mean preferences for these health states were then used to estimate the parameters of a log-linear scoring function for CLAMES. The function provides a convenient method of computing preference scores for any health state classified by CLAMES, without the need for direct measurement in surveys. Further, the SG appears feasible in group settings.

Waiting times for medical services such as specialist visits and surgery continue to be an issue in most countries with publicly funded healthcare systems, particularly in Canada, where timely access to healthcare services is at the top of the health policy agenda (Romanow 2002). In this country, long waits are routinely identified as the leading barrier to care (Sanmartin et al. 2002). Waiting for care, however, is only problematic when patients consider their waiting times unacceptable (Martin et al. 2003). To address the issue of unacceptable waits for care, it is important to understand the factors contributing to patients’ assessment of the acceptability of their waiting times. Much of the evidence to date focuses on the duration of the waiting time as the principal determinant of wait time acceptability, often with little to no regard for other factors that may influence patients’ views on waiting times (Sanmartin 2001; Llewellyn-Thomas et al. 1998; Conner-Spady et al. 2004). In Ontario, Ho and colleagues (1994) asked patients who underwent knee replacement about the acceptability of their waiting times. Patients who considered their waiting times acceptable reported a median waiting time of 8 weeks from consultation to surgery as compared with the median of 32 weeks reported by those who considered their waits unacceptable (Ho et al. 1994). In a subsequent study, the duration of the wait was identified as a primary determinant of wait time acceptability (Coyte et al. 1994). A similar approach was used by Dunn and associates (1997) among cataract patients in Manitoba, where the majority of patients agreed that 3 months or less was a reasonable wait for surgery (Dunn et al. 1997). Recent results from a national study on access to care in Canada revealed that individuals who considered their waiting times unacceptable waited an average of between 9 weeks (for specialist visits) and 13 weeks (for non-emergency surgery) for specialized services, which was three to four times longer than the wait for those who did not consider their wait unacceptable (Figure ​(Figure1).1). These individuals were also more likely to report that waiting for care affected their lives (Sanmartin et al. 2004). FIGURE 1. Median waiting times for specialized services by reported acceptability, Canada, 2003 Although current evidence provides some insight regarding patients’ experiences waiting for care, considerably less information exists about other factors that may affect wait time acceptability, such as patient demographics and socio-economic status. The purpose of this study, therefore, was to analyze national data on waiting for care to identify the key determinants associated with unacceptable waiting times. Specifically, the study focuses on three specialized services: specialist visits, non-emergency (or elective) surgery and diagnostic tests.

Background The co-morbidity of health conditions is becoming a significant health issue, particularly as populations age, and presents important methodological challenges for population health research. For example, the calculation of summary measures of population health (SMPH) can be compromised if co-morbidity is not taken into account. One popular co-morbidity adjustment used in SMPH computations relies on a straightforward multiplicative combination of the severity weights for the individual conditions involved. While the convenience and simplicity of the multiplicative model are attractive, its appropriateness has yet to be formally tested. The primary objective of the current study was therefore to examine the empirical evidence in support of this approach. Methods The present study drew on information on the prevalence of chronic conditions and a utility-based measure of health-related quality of life (HRQoL), namely the Health Utilities Index Mark 3 (HUI3), available from Cycle 1.1 of the Canadian Community Health Survey (CCHS; 2000–01). Average HUI3 scores were computed for both single and co-morbid conditions, and were also purified by statistically removing the loss of functional health due to health problems other than the chronic conditions reported. The co-morbidity rule was specified as a multiplicative combination of the purified average observed HUI3 utility scores for the individual conditions involved, with the addition of a synergy coefficient s for capturing any interaction between the conditions not explained by the product of their utilities. The fit of the model to the purified average observed utilities for the co-morbid conditions was optimized using ordinary least squares regression to estimate s. Replicability of the results was assessed by applying the method to triple co-morbidities from the CCHS cycle 1.1 database, as well as to double and triple co-morbidities from cycle 2.1 of the CCHS (2003–04). Results Model fit was optimized at s = .99 (i.e., essentially a straightforward multiplicative model). These results were closely replicated with triple co-morbidities reported on CCHS 2000–01, as well as with double and triple co-morbidities reported on CCHS 2003–04. Conclusion The findings support the simple multiplicative model for computing utilities for co-morbid conditions from the utilities for the individual conditions involved. Future work using a wider variety of conditions and data sources could serve to further evaluate and refine the approach.