PM effect size estimation for mediation analysis: a cautionary note,alternate strategy,and real data illustration

As research on mediation has grown, so too has interest in identifying ways to assess the size of indirect effects in a mediation analysis. One such estimate – the ratio of the indirect effect to the total effect (P_M) – was tested in a sample of 21,297 children from the Early Childhood Developmental Study. Results showed that the two independent variables – low self-control and externalizing behavior – correlated equally well with a common mediator (mathematical thinking). Moreover, the two pathways shared the same mediator and dependent variable (subsequent externalizing behavior). Despite this, P_M was three times larger in the self-control-initiated pathway than in the externalizing-initiated pathway, based on a stronger correlation between prior and subsequent externalizing behavior than between low self-control and externalizing behavior. The comparison pathways approach, where pathways mediated by mathematical reasoning are contrasted with pathways mediated by a control variable (general knowledge), is offered as an alternative to effect size measurement in mediation research.     

The Consequences of Objective and Subjective Status Inconsistency*

The phenomenon of status inconsisitency, while having rich potential as an explanatory variable, has been beset with methodological problems and conflicting findings. Nelson has argued that the use of objective and subjective components of status inconsistency will allow for a more accurate test of its usefulness (1973). The present study, using a sample of 1971 male college graduates interviewed in 1974, analyzed the attitudinal and behavioral consequences of one type of status inconsistency (under-rewarded) incorporating objective and subjective techniques. The tentative conclusions were: (1) the use of subjective measures of inconsistency validates this phenomenon as an explanatory variable; (2) the use of subjective measures minimizes the methodological criticisms of the objective approach; and (3) both objective and subjective measures of status inconsistency should be incorporated in future research.     

The Wider Benefits of Adult Learning: An Illustration of the Advantages of Multi‐method Research

This study presents a technique for enhancing causal validity in in‐depth interview research. The technique is based on the logic of control, as applied in various research contexts such as experiments and statistical analyses. According to this logic, to detect the real effect of an independent variable on a dependent variable, all other variables must be held constant. By using interview control questions (ICQs), this study applies this principle in in‐depth interviewing. An ICQ is a probe question that controls an independent variable in the participant’s thinking. Two modes are presented: simple control (neutralizing an independent variable to examine whether it is a necessary condition for an outcome) and parallel control (isolating an independent variable to examine whether it is a sufficient condition for an outcome). In both modes, the method allows for additional independent variables to surface. Applications in in‐depth interviews exploring attitudes toward victimless deviance are presented.     

Marital Quality and Personal Well‐Being: A Meta‐Analysis

This study examines the association between marital quality and personal well‐being using meta‐analytic techniques. Effects from 93 studies were analyzed. The average weighted effect size r was .37 for cross‐sectional and .25 for longitudinal effects. Results indicate that several variables moderate the association between marital quality and personal well‐being, including gender, participants’ marital duration, source of measurement, data collection year, and dependent variable. These results suggest that longitudinal effects are more likely to be uncovered when using standard measurement and that future research should use samples homogenous in marital length. The longitudinal finding that the strength of the association is stronger when personal well‐being is treated as the dependent variable supports previous theorizing.     

Independent,Autonomous, and Permissive: Examining the Links Between Self-Construal and Sexual Permissiveness

Much of the research on sexual attitudes has focused on biological sex as a predictor variable. This work has consistently demonstrated that men are more permissive in attitudes toward casual sex than are women. Less is known, however, about how other individual difference variables may shape sexual attitudes. In this research, we considered whether self-construal (whether one believes that others are or are not part of their self-concept) influences people’s attitudes toward casual sex. Specifically, we posited that an independent self-construal is positively related to, and an interdependent self-construal is negatively related to, sexual permissiveness. Two cross-sectional studies (ns = 517 and 212) yielded support for these hypotheses. We further considered autonomy as a potential process variable. A mediation analysis revealed that self-construal was related to autonomy, which in turn positively predicted sexual attitudes and drove this association. We integrate these findings into the literature on sexual attitudes and discuss theoretical insights derived from our findings.     

Re-examining a Landmark Research Study: A Teaching Editorial

A landmark research study from the 1950s was reanalyzed. Part of the study's results were confirmed, but other parts were found to have been incompletely analyzed and therefore incorrectly reported. Subsequent scholars who reviewed the study often did not distinguish between the accurate and inaccurate parts of the study. Furthermore, two of the main hypotheses of the study were that one variable (A) was not related to another variable (B) and that variable B was not related to another variable (C). In fact, both null hypotheses, insofar as data could be reconstructed from the original study, could be rejected. A reanalysis is presented here to encourage students in the family field to be bold and not accept published reports “just because” but to evaluate them carefully, perhaps even reanalyzing the data when available. It is hoped that scholars who submit reviews of the literature to Marriage and Family Review will use similar care and attention to assessing the scholarly literature in their particular areas of interest.     

Improved Regression Estimation of A Multivariate Relationship with Population Data on the Bivariate Relationship

Regression coefficients specify the partial effect of a regressor on the dependent variable. Sometimes the bivariate or limited multivariate relationship of that regressor variable with the dependent variable is known from population‐level data. We show here that such population‐level data can be used to reduce variance and bias about estimates of those regression coefficients from sample survey data. The method of constrained MLE is used to achieve these improvements. Its statistical properties are first described. The method constrains the weighted sum of all the covariate‐specific associations (partial effects) of the regressors on the dependent variable to equal the overall association of one or more regressors, where the latter is known exactly from the population data. We refer to those regressors whose bivariate or limited multivariate relationships with the dependent variable are constrained by population data as being "directly constrained." Our study investigates the improvements in the estimation of directly constrained variables as well as the improvements in the estimation of other regressor variables that may be correlated with the directly constrained variables, and thus "indirectly constrained" by the population data. The example application is to the marital fertility of black versus white women. The difference between white and black women's rates of marital fertility, available from population‐level data, gives the overall association of race with fertility. We show that the constrained MLE technique both provides a far more powerful statistical test of the partial effect of being black and purges the test of a bias that would otherwise distort the estimated magnitude of this effect. We find only trivial reductions, however, in the standard errors of the parameters for indirectly constrained regressors.     

The Family and Juvenile Delinquency*

This paper examines the effect of various “family variables” on the etiology of juvenile delinquency. These self-report data are unique in that they are from reports by parents of their child's behavior, the nature of the child's life at home, and parental perceptions of their relationship with the child. How the family and delinquency literature fit into control theory's conceptualization of the importance of a child's attachment to the family as a determinant of delinquency is evaluated. Variables measuring (1) family structure, (2) poor parental characteristics, (3) household characteristics, and (4) parent-child relationships are examined. The attachment variable was found to be the strongest predictor of delinquency and helps to “interpret” the effects of other variables that are significantly related to delinquency. The variables that predict male delinquency were found to be different from those that predict female delinquency. Characteristics of the parents' marriage play an important role for boys, while misbehavior of girls is more strongly predicted by variables measuring parent-child interaction and parental control.     

Why are mediation effects so small?

Identifying mediators in variable chains as part of a causal mediation analysis can shed light on issues of causation, assessment, and intervention. However, coefficients and effect sizes in a causal mediation analysis are nearly always small. This can lead those less familiar with the approach to reject the results of causal mediation analysis. The current paper highlights five factors that contribute to small path coefficients in mediation research: loss of information when measuring relationships across time, controlling for prior levels of a predicted variable, adding control variables to the analysis, ignoring measurement error in one’s variables, and using multiple mediators. It is argued that these issues are best handled by increasing the statistical power of the analysis, identifying the optimal temporal interval between variables, using bootstrapped confidence intervals to analyze the results, and finding alternate ways of assessing the meaningfulness of the indirect effect.     

Gender,Social Bond,and Academic Cheating in Japan*

There is evidence that females are less likely to cheat than males on college campuses. A frequently offered but still untested explanation is that females, with a stronger sense of responsibility for the maintenance of social relationships, tend to develop a stronger bond to a conventional society—a key explanatory concept in Hirschi’s (1969) social control theory. With academic cheating as the dependent variable, we test the hypotheses that the four elements of social bond are the intervening variables linking gender to such dishonesty among Japanese students who, due to their stronger orientation toward masculinity on Hofstede’s (1980) scale of gender role separation, are subject to more gender distinct socialization, leading to greater gender differences in the strength of social bond than those previously reported in the United States. The analysis provides rather limited support for the theory, most of which is due to the stronger belief in the legitimacy of societal rules among the females.     

An Exploration of the Independent Contributions of Genetics, Shared Environment, Specific Environment, and Adult Roles and Statuses on Perceived Control

Perceived-control 'describes individuals'generalized beliefs about their abilities to influence their life courses and circumstances. Most research concerning this construct has viewed perceived control as a developmentally acquired, stable personality characteristic. Others argue that perceived control is determined by current social status, with more privileged social positions contributing to increased control over life circumstances.
This study analyzes data from the Virginia Twin Registry to determine the independent contributions of genetics, shared environment, and nonshared environment, including adult roles and statuses, on women's perceived control. Findings from latent variable twin models suggest that there are modest but significant effects of shared environment and genetics on perceived control but that the majority of individual variation in perceived control is due to nonshared environmental factors on perceived control among adult women. Analyses of measured individual-level variables indicate significant effects from education, income, earnings, marital quality, age, and single-parent status.     

Multivariate analysis of qualitative data*

Cette dissertation présente une technique pour I'analyse de données qualitatives qui fournit des coefficients d'association multiple, partielle, d'ordre-zéro et d'interaction. La technique se sert de la contre-classification de la variable dépendante avec des variables indipendantes, séparément et par ensembles. II s'accomplit un partage de la variation dans la variable dépendante, qui est comparable à celui obtenu par la régression multiple et par l'analyse de variance pour les données quantitatives. On démontre les effets de contraintes de distribution marginale sur les coefficients. Ensuite on développe des procédés pour les contrôer qui permettent aux chercheurs de rapporter des relations entre variables non contaminées par les contraintes marginales. La supériorité de ces procédés est montrée si l'on compare leur efficacité avec celle des méthodes d'analyse conventionnelles et log-linéaires. This paper presents a technique for the analysis of qualitative data which provides zero-order, multiple, partial, and interaction association coefficients. The technique uses cross-classification of the dependent variable with independent variables singly and in sets. A partitioning of the variation in the dependent variable is accomplished which is comparable to that obtained through multiple regression and analysis of variance for quantitative data. The effects of marginal distribution constraints on the coefficients are demonstrated. Procedures for their control are developed which permit researchers to report relationships among variables uncontaminated by marginal constraints. The superiority of the present procedures is shown through comparing their effectiveness to conventional and log-linear methods of analysis.     

Investigating non-gamblers: another step toward identifying potential protective factors against problem gambling

In this article it is argued that knowing more about non-gamblers could help researchers discover novel protective factors against problem gambling. The purpose of this study was to therefore to identify the sociodemographic, psychological and behavioural characteristics that are more prevalent among non-gamblers than among gamblers. Results from a logistic regression analysis with a representative sample of adults in the province of Quebec (Canada) revealed 12 significant predictors of non-gambling status. Among these predictors, seven were sociodemographic variables (i.e. birthplace, mother tongue, childhood religion, civil status, education, family income and family history of gambling problems), four were psychological variables (i.e. perception of one's financial situation relative to others, optimism concerning one's financial situation, beliefs concerning chances of winning, and suicidal ideation) and one variable was behavioural (i.e. church attendance). Further research including different types of variables and a common operational definition of non-gamblers is necessary to better understand this subgroup and its potential for possessing protective factors against gambling problems.     

Is the web a promising tool for data collection in developing countries? An analysis of the sample bias of 10 web and face-to-face surveys from Africa,Asia, and South America

Whereas the sample composition biases of web surveys have been discussed extensively for developed countries, studies for developing countries are scarce. This article helps to fill that gap by comparing similar non-probability-based web surveys (WEB) and probability-based face-to-face (F2F) surveys both to each other and to the labor force. An analysis of WageIndicator data on work and wages derived from surveys held in 2009–2013 in 10 developing countries (WEB-sample N = 9135; F2F-sample N = 14,659), shows that F2F samples resemble the labor force to a larger extent than web samples do. In both cases, individuals in their 20s and early 30s are overrepresented, and younger and older respondents are underrepresented. This trend is more pronounced in WEB than in F2F samples. However, the differences converge in countries with higher Internet usage. A comparison of the WEB and F2F samples shows that compositions differ greatly, with web respondents being younger, more often male, more often living alone, and higher educated, although these differences are smaller in countries with higher Internet usage. Given the cost differences between the two survey modes, one should nevertheless consider the potential of web surveys as an instrument to gain explorative insights, specifically when searching for individuals with particular characteristics.     

Regression Models With Parametrically Weighted Explanatory Variables

This paper describes linear regression models with parametrically weighted explanatory variables and related logistic regression models that estimate parameters characterizing (1) the effects of weighted variables on the dependent variable and (2) weights for the components of weighted variables. The models also characterize parsimoniously the interaction effects between weighted variables and covariates on the dependent variable by the use of various constraints on parameters. In particular, the models are concerned with testing the significance of variation with covariates in the weights of weighted variables separately from the significance of variation with those covariates in the effects of weighted variables.
The usefulness of these models in sociological research is demonstrated by an illustrative analysis of the class identifications of married working women using education, occupational prestige, and income as three variables weighted between own and spousal attributes, and using year, age, race, part–time–full–time distinction, and employment status as covariates.     

Ethnic intermarriage among immigrants: human capital and assortative mating

This paper analyzes the determinants of interethnic marriages by immigrants in the United States. The dependent variable is intermarriage across ethnic groups (on the basis of ancestry and country of birth) and the inclusion of the explanatory variables is justified by a simple rational choice economic model. A binomial logistic regression is estimated using data from the 1980 US Census, the last Census where post-migration marriages can be identified. Results show that the probability of intermarriage increases the longer a migrant resides in the U.S. and the younger the age at arrival. Both relationships can be attributable to the accumulation of US-specific human capital and an erosion of ethnic-specific human capital. Inter-ethnic marriages are more likely between individuals with similar education levels, providing evidence of positive assortative mating by education for immigrants. The construction of the “availability ratio” for potential spouses from one’s own group and group size where one lives using data from several Censuses provides a the measure of the marriage market. Intermarriage is lower the greater the availability ratio and the larger the size of one’s own group. Linguistic distance of the immigrant’s mother tongue from English indirectly measures the effect of English language proficiency at arrival and is found to be a significant negative predictor of intermarriage. Those who report multiple ancestries and who were previously married are more likely to intermarry.     

Rural population density: its impact on social and demographic aspects of rural communities

Using the settled areas of South Australia as a case study, this paper seeks to demonstrate the specific importance of rural population and settlement density as an important variable in understanding the social, population and settlement geography of sparsely settled rural regions, where sparse and falling density presents both practical and conceptual problems for rural planners. After a review of the literature on population density, the case is argued for the use of net rural rather than gross density in the analysis of settlement patterns. The paper then tests a series of hypotheses on the empirical relationship between rural density as independent variable and selected demographic and socio-economic indicators as dependent variables, at two specific points in time. For the same region, points in time and set of indicators, it goes on to compare the predictive power of rural density as an independent variable with that of three other important qualities of rural settlement patterns (remoteness, settlement size and urban concentration). Rural density is found to be a significant explanatory variable, both in its own right and in comparison with the three other variables tested. In conclusion, the findings are related to policy development measures for rural Australia.     

Understanding Unique Effects of Parental Incarceration on Children: Challenges,Progress, and Recommendations

Growth in U.S. incarceration rates during the 1980s and 1990s prompted a body of research focused on understanding the diverse effects of incarceration on individuals, families, and communities. An area of particular interest has been how the incarceration of a parent may affect child well‐being. Despite what appears to be converging evidence that parental incarceration poses a significant threat to child development, this area of inquiry has yet to overcome important methodological and conceptual challenges related to selection bias. It is therefore unclear whether the difficulties that have been observed among children whose parents are incarcerated are due to the incarceration itself or to other adversities that children have experienced. The purpose of this article is to draw attention to these issues, to summarize empirical and conceptual progress in overcoming these challenges, and to suggest directions for future research.     

Systemic requisites of communal groups

Functional analysis, which deals specifically with the systemic needs of social organizations, is utilized here to specify the structural necessities of communal groups. The adaptive and goal attainment functions of social systems are the principal foci of this research. The present research is based on a content analysis of literature dealing with the communal movement in America. A snowball sampling technique yielded 58 communes for which data on the variables of interest could be obtained. Two organizational features, financial situation at the time of a commune's formation and type of social organization, were selected as independent variables and were examined in order to ascertain their effects on the duration of communal groups, the dependent variable. Both gamma and chisquare indicate that financial situation and type of social organization significantly influence the duration of communal groups. Sufficient finances for the stabilization and maintenance of the communal organization, and a type of social organization which adequately coordinates the activities of the group, seem to be systemic problems with which communal groups must deal in order to endure for an extended length of time.     

Women’s Sexual Communication with Their Peers and Its Association with Sexual Wellbeing

Abstract

Communication about sex is an important variable in sexual well-being, but sex remains a taboo topic, particularly for women. This study explores women’s peer sexual communication, and its association with their sexual well-being. A survey (N?=?617) showed that women tend to solicit expressive, rather than instrumental, sexual communication from other women. Regression analyses revealed that peer sexual communication is associated with higher sexual self-efficacy, and sexual self-esteem, but also higher risky sexual norms perceptions. Peer sexual communication appears to be a potential vehicle for disseminating sexual information, as long as women have accurate and empowering information to start with.