Carl F. Falk

Assessing Mediational Models: Testing and Interval Estimation for Indirect Effects

Theoretical models specifying indirect or mediated effects are common in the social sciences. An indirect effect exists when an independent variables influence on the dependent variable is mediated through an intervening variable. Classic approaches to assessing such mediational hypotheses (Baron & Kenny, 1986; Sobel, 1982) have in recent years been supplemented by computationally intensive methods such as bootstrapping, the distribution of the product methods, and hierarchical Bayesian Markov chain Monte Carlo (MCMC) methods. These different approaches for assessing mediation are illustrated using data from Dunn, Biesanz, Human, and Finn (2007). However, little is known about how these methods perform relative to each other, particularly in more challenging situations, such as with data that are incomplete and/or nonnormal. This article presents an extensive Monte Carlo simulation evaluating a host of approaches for assessing mediation. We examine Type I error rates, power, and coverage. We study normal and nonnormal data as well as complete and incomplete data. In addition, we adapt a method, recently proposed in statistical literature, that does not rely on confidence intervals (CIs) to test the null hypothesis of no indirect effect. The results suggest that the new inferential method—the partial posterior p value—slightly outperforms existing ones in terms of maintaining Type I error rates while maximizing power, especially with incomplete data. Among confidence interval approaches, the bias-corrected accelerated (BC a ) bootstrapping approach often has inflated Type I error rates and inconsistent coverage and is not recommended; In contrast, the bootstrapped percentile confidence interval and the hierarchical Bayesian MCMC method perform best overall, maintaining Type I error rates, exhibiting reasonable power, and producing stable and accurate coverage rates.

For Whom Is Parting With Possessions More Painful? Cultural Differences in the Endowment Effect

The endowment effect—the tendency for owners (potential sellers) to value objects more than potential buyers do—is among the most widely studied judgment and decision-making phenomena. However, the current research is the first to explore whether the effect varies across cultures. Given previously demonstrated cultural differences in self-construals and self-enhancement, we predicted a smaller endowment effect for East Asians compared with Westerners. Two studies involving buyers and sellers of a coffee mug (Study 1a) and a box of chocolates (Study 1b) supported this prediction. Study 2 conceptually replicated this cultural difference by experimentally manipulating independent and interdependent self-construals. Finally, Study 3 provided evidence for an underlying self-enhancement mechanism: Cultural differences emerged when self-object associations were made salient, but disappeared when self-object associations were minimized. Thus, the endowment effect may be influenced by the degree to which independence and self-enhancement (vs. interdependence and self-criticism) are culturally valued or normative.

Why do Westerners self-enhance more than East Asians?

Much research finds that Westerners self‐enhance more than East Asians, with the exception of studies using the implicit associations test for self‐esteem (IATSE). We contrasted Japanese and Canadians on a new measure of self‐enhancement under low‐ and high‐attentional load to assess whether cultural differences vary across controlled and automatic processes. Participants also completed measures of relational mobility and the IATSE. Results indicated that Japanese and Asian‐Canadians were more self‐critical than Euro‐Canadians, both under high‐ and low‐attentional load. This cultural difference was partially mediated by relational mobility. The IATSE showed no cultural differences, but this measure did not positively correlate with any of the other measures in the study, suggesting that it is not a valid measure of ‘true’ self‐feelings. Copyright

Not all collectivisms are equal: opposing preferences for ideal affect between East Asians and Mexicans.

Previous research has revealed differences in how people value and pursue positive affect in individualistic and collectivistic cultural contexts. Whereas Euro-Americans place greater value on high activation positive affect (HAP; e.g., excitement, enthusiasm, elation) than do Asian Americans and Hong Kong Chinese, the opposite is true for low activation positive affect (LAP; e.g., calmness, serenity, tranquility). Although the form of collectivism present in East Asia dictates that individuals control and subdue their emotional expressions so as to maintain harmonious relationships, the opposite norm emerges in Mexico and other Latin American countries, in that the cultural script of simpatía promotes harmony through the open and vibrant expression of positive emotion. Across two studies, we found that Mexicans display a pattern of HAP/LAP preference different from those from East Asian collectivistic cultures, endorsing HAP over LAP.

A flexible full-information approach to the modeling of response styles.

We present a flexible full-information approach to modeling multiple user-defined response styles across multiple constructs of interest. The model is based on a novel parameterization of the multidimensional nominal response model that separates estimation of overall item slopes from the scoring functions (indicating the order of categories) for each item and latent trait. This feature allows the definition of response styles to vary across items as well as overall item slopes that vary across items for both substantive and response style dimensions. We compared the model with similar approaches using examples from the smoking initiative of the Patient-Reported Outcomes Measurement Information System. A small set of simulations showed that the estimation approach is able to recover model parameters, factor scores, and reasonable estimates of standard errors. Furthermore, these simulations suggest that failing to include response style factors (when present in the data generating model) has adverse consequences for substantive trait factor score recovery. (PsycINFO Database Record

Two Cross-Platform Programs for Inferences and Interval Estimation About Indirect Effects in Mediational Models

In this article, we describe two new programs that compute both p-values and confidence intervals (CI) for the indirect effect in mediational models, including (a) a p-value based on the partial posterior method, which we refer to as p3 computed across the posterior distribution of the regression coefficients; (b) a variant of p3 that uses a normal approximation for the posterior distributions, p3N; (c) Hierarchical Bayesian CIs (CIHB) based on the posterior distributions of the regression coefficients; and (d) CIs based on the Monte Carlo method (CIMC). These programs do not require access to raw data as do resampling methods. Similar to Sobel’s test, p3 and p3N constitute a single p-value for the indirect effect while performing substantially better in terms of Type I and II error rates. Furthermore, we include a memory efficient computational algorithm for CIHB and CIMC that allows for precision beyond that in existing alternative implementations. The underlying programs can utilize multicore processors, and their performance is tested through a simulation study. Finally, the use of these programs is illustrated with an empirical example.

The Relationship Between Unstandardized and Standardized Alpha, True Reliability, and the Underlying Measurement Model

Popular computer programs print 2 versions of Cronbachs alpha: unstandardized alpha, αΣ, based on the covariance matrix, and standardized alpha, α R , based on the correlation matrix. Sources that accurately describe the theoretical distinction between the 2 coefficients are lacking, which can lead to the misconception that the differences between α R and αΣ are unimportant and to the temptation to report the larger coefficient. We explore the relationship between α R and αΣ and the reliability of the standardized and unstandardized composite under 3 popular measurement models; we clarify the theoretical meaning of each coefficient and conclude that researchers should choose an appropriate reliability coefficient based on theoretical considerations. We also illustrate that α R and αΣ estimate the reliability of different composite scores, and in most cases cannot be substituted for one another.

What Is Implicit Self-Esteem, and Does it Vary Across Cultures?

Implicit self-esteem (ISE), which is often defined as automatic self-evaluations, fuses research on unconscious processes with that on self-esteem. As ISE is viewed as immune to explicit control, it affords the testing of theoretical questions such as whether cultures vary in self-enhancement motivations. We provide a critical review and integration of the work on (a) the operationalization of ISE and (b) possible cultural variation in self-enhancement motivations. Although ISE measures do not often vary across cultures, recent meta-analyses and empirical studies question the validity of the most common way of defining ISE. We revive an alternative conceptualization that defines ISE in terms of how positively people evaluate objects that reflect upon themselves. This conceptualization suggests that ISE research should target alternative phenomena (e.g., minimal group effect, similarity-attraction effect, endowment effect) and it allows for a host of previous cross-cultural findings to bear on the question of cultural variability in ISE.

Unpacking Cultural Differences in Alexithymia The Role of Cultural Values Among Euro-Canadian and Chinese-Canadian Students

The current study provides a cultural examination of alexithymia, a multifaceted personality construct that refers to a general deficit in the ability to identify and describe emotional states, and that has been linked to a number of psychiatric illnesses. Though this construct has been critiqued as heavily rooted in “Western” norms of emotional expression, it has not received much empirical attention from a cultural perspective. Recently, Ryder et al. (2008) found that higher levels of alexithymia among Chinese versus Euro-Canadian outpatients were explained by group differences in one component of alexithymia, externally oriented thinking (EOT); they proposed that Chinese cultural contexts may encourage EOT due to a greater emphasis on social relationships and interpersonal harmony rather than inner emotional experience. The current study examined the hypothesis that EOT is more strongly shaped by cultural values than are two other components of alexithymia, difficulty identifying feelings (DIF) and difficulty describing feelings (DDF). Euro-Canadian (n = 271) and Chinese-Canadian (n = 237) undergraduates completed measures of alexithymia and cultural values. Chinese-Canadians showed higher levels of EOT than Euro-Canadians (p < .001). EOT, and not DIF or DDF, was predicted by Modernization and Euro-American values in both groups. Furthermore, cultural values mediated the effect of group membership on levels of EOT. These results suggest that cultural differences in alexithymia may be explained by culturally based variations in the importance placed on emotions, rather than deficits in emotional processing. The study also raises questions about the measurement and meaning of EOT, particularly from a cross-cultural perspective.

Are Implicit Self‐Esteem Measures Valid for Assessing Individual and Cultural Differences?

OBJECTIVE Our research utilized two popular theoretical conceptualizations of implicit self-esteem: 1) implicit self-esteem as a global automatic reaction to the self; and 2) implicit self-esteem as a context/domain specific construct. Under this framework, we present an extensive search for implicit self-esteem measure validity among different cultural groups (Study 1) and under several experimental manipulations (Study 2). METHOD In Study 1, Euro-Canadians (N = 107), Asian-Canadians (N = 187), and Japanese (N = 112) completed a battery of implicit self-esteem, explicit self-esteem, and criterion measures. Included implicit self-esteem measures were either popular or provided methodological improvements upon older methods. Criterion measures were sampled from previous research on implicit self-esteem and included self-report and independent ratings. In Study 2, Americans (N = 582) completed a shorter battery of these same types of measures under either a control condition, an explicit prime meant to activate the self-concept in a particular context, or prime meant to activate self-competence related implicit attitudes. RESULTS Across both studies, explicit self-esteem measures far outperformed implicit self-esteem measures in all cultural groups and under all experimental manipulations. CONCLUSION Implicit self-esteem measures are not valid for individual or cross-cultural comparisons. We speculate that individuals may not form implicit associations with the self as an attitudinal object.