Semiparametric Theory for Causal Mediation Analysis: efficiency bounds, multiple robustness, and sensitivity analysis

Whilst estimation of the marginal (total) causal effect of a point exposure on an outcome is arguably the most common objective of experimental and observational studies in the health and social sciences, in recent years, investigators have also become increasingly interested in mediation analysis. Specifically, upon establishing a non-null total effect of the exposure, investigators routinely wish to make inferences about the direct (indirect) pathway of the effect of the exposure not through (through) a mediator variable that occurs subsequently to the exposure and prior to the outcome. Although powerful semiparametric methodologies have been developed to analyze observational studies, that produce double robust and highly efficient estimates of the marginal total causal effect, similar methods for mediation analysis are currently lacking. Thus, this paper develops a general semiparametric framework for obtaining inferences about so-called marginal natural direct and indirect causal effects, while appropriately accounting for a large number of pre-exposure confounding factors for the exposure and the mediator variables. Our analytic framework is particularly appealing, because it gives new insights on issues of efficiency and robustness in the context of mediation analysis. In particular, we propose new multiply robust locally efficient estimators of the marginal natural indirect and direct causal effects, and develop a novel double robust sensitivity analysis framework for the assumption of ignorability of the mediator variable.

On Causal Mediation Analysis with a Survival Outcome

Suppose that having established a marginal total effect of a point exposure on a time-to-event outcome, an investigator wishes to decompose this effect into its direct and indirect pathways, also know as natural direct and indirect effects, mediated by a variable known to occur after the exposure and prior to the outcome. This paper proposes a theory of estimation of natural direct and indirect effects in two important semiparametric models for a failure time outcome. The underlying survival model for the marginal total effect and thus for the direct and indirect effects, can either be a marginal structural Cox proportional hazards model, or a marginal structural additive hazards model. The proposed theory delivers new estimators for mediation analysis in each of these models, with appealing robustness properties. Specifically, in order to guarantee ignorability with respect to the exposure and mediator variables, the approach, which is multiply robust, allows the investigator to use several flexible working models to adjust for confounding by a large number of pre-exposure variables. Multiple robustness is appealing because it only requires a subset of working models to be correct for consistency; furthermore, the analyst need not know which subset of working models is in fact correct to report valid inferences. Finally, a novel semiparametric sensitivity analysis technique is developed for each of these models, to assess the impact on inference, of a violation of the assumption of ignorability of the mediator.

ON THE MERITS OF VOXEL-BASED MORPHOMETRIC PATH-ANALYSIS FOR INVESTIGATING VOLUMETRIC MEDIATION OF A TOXICANT'S INFLUENCE ON COGNITIVE FUNCTION

We previously showed that lifetime cumulative lead dose, measured as lead concentration in the tibia bone by X-ray fluorescence, was associated with persistent and progressive declines in cognitive function and with decreases in MRI-based brain volumes in former lead workers. Moreover, larger region-specific brain volumes were associated with better cognitive function. These findings motivated us to explore a novel application of path analysis to evaluate effect mediation. Voxel-wise path analysis, at face value, represents the natural evolution of voxel-based morphometry methods to answer questions of mediation. Application of these methods to the former lead worker data demonstrated potential limitations in this approach where there was a tendency for results to be strongly biased towards the null hypothesis (lack of mediation). Moreover, a complimentary analysis using anatomically-derived regions of interest volumes yielded opposing results, suggesting evidence of mediation. Specifically, in the ROI-based approach, there was evidence that the association of tibia lead with function in three cognitive domains was mediated through the volumes of total brain, frontal gray matter, and/or possibly cingulate. A simulation study was conducted to investigate whether the voxel-wise results arose from an absence of localized mediation, or more subtle defects in the methodology. The simulation results showed the same null bias evidenced as seen in the lead workers data. Both the lead worker data results and the simulation study suggest that a null-bias in voxel-wise path analysis limits its inferential utility for producing confirmatory results.

Preparing writing centers and tutors for literacy mediation for working class campus-staff

Writing centers work with writers; traditionally services have been focused on undergraduates taking composition classes. More recently, centers have started to attract a wider client base including: students taking labs that require writing; graduate students; and ESL students learning the conventions of U.S. communication. There are very few centers, however, which identify themselves as open to working with all members of the campus-community. Michigan Technological University has one such center. In the Michigan Tech writing center, doors are open to “all students, faculty and staff.” While graduate students, post docs, and professors preparing articles for publication have used the center, for the first time in the collective memory of the center UAW staff members requested center appointments in the summer of 2008. These working class employees were in the process of filling out a work related document, the UAW Position Audit, an approximately seven-page form. This form was their one avenue for requesting a review of the job they were doing; the review was the first step in requesting a raise in job level and pay. This study grew out of the realization that implicit literacy expectations between working class United Auto Workers (UAW) staff and professional class staff were complicating the filling out and filing of the position audit form. Professional class supervisors had designed the form as a measure of fairness, in that each UAW employee on campus was responding to the same set of questions about their work. However, the implicit literacy expectations of supervisors were different from those of many of the employees who were to fill out the form. As a result, questions that were meant to be straightforward to answer were in the eyes of the employees filling out the form, complex. Before coming to the writing center UAW staff had spent months writing out responses to the form; they expressed concerns that their responses still would not meet audience expectations. These writers recognized that they did not yet know exactly what the audience was expecting. The results of this study include a framework for planning writing center sessions that facilitate the acquisition of literacy practices which are new to the user. One important realization from this dissertation is that the social nature of literacy must be kept in the forefront when both planning sessions and when educating tutors to lead these sessions. Literacy scholars such as James Paul Gee, Brian Street, and Shirley Brice Heath are used to show that a person can only know those literacy practices that they have previously acquired. In order to acquire new literacy practices, a person must have social opportunities for hands-on practice and mentoring from someone with experience. The writing center can adapt theory and practices from this dissertation that will facilitate sessions for a range of writers wishing to learn “new” literacy practices. This study also calls for specific changes to writing center tutor education.

Some considerations on the potential contributions of intercultural social work...

Social work at global levels, and across international and intercultural divides, is probably more important now than ever before in our history. It may be that the very form our ideas about intercultural work take need to be re-examined in the light of recent global changes and uncertainties. In this short position paper I wish to offer some considerations about how we might approach the field of intercultural social work in order to gain new insights about how we practise at both local and global levels. For me, much of the promise of an intercultural social work (and for the purposes of this paper I see aspects of international social work in much the same light) lies in its focus on the way we categorise ourselves, our ideas and experiences in relation to others. The very notion of intercultural or international social work is based on assumptions about boundaries, differences, ways of differentiating and defining sets of experiences. Whether these are deemed "cultural" or "national" is of less importance. Once we are forced to examine these assumptions, about how and why we categorise ourselves in relation to other people in particular ways, the way is opened up for us to be much more critical about the bases of our own, often very deep-seated, thinking. This understanding, about how and why notions of "difference" operate in the way they do, can potentially open our understanding to all the other ways, besides cultural or national labelling, in which we categorise and create differences between ourselves and others. Intercultural social work, taken as a potential site for understanding the creation of difference then, has the potential to help us critically examine the bases of much of our practice in any setting, since most practice involves some kind of categorisation of phenomena.