Considering that causal mechanisms unfold over time, it is important to investigate the mechanisms over time, taking into account the time-varying features of treatments and mediators. However, identification of the average causal mediation effect in the presence of time-varying treatments and mediators is often complicated by time-varying confounding. This article aims to provide a novel approach to uncovering causal mechanisms in time-varying treatments and mediators in the presence of time-varying confounding. We provide different strategies for identification and sensitivity analysis under homogeneous and heterogeneous effects. Homogeneous effects are those in which each individual experiences the same effect, and heterogeneous effects are those in which the effects vary over individuals. Most importantly, we provide an alternative definition of average causal mediation effects that evaluates a partial mediation effect; the effect that is mediated by paths other than through an intermediate confounding variable. We argue that this alternative definition allows us to better assess at least a part of the mediated effect and provides meaningful and unique interpretations. A case study using ECLS-K data that evaluates kindergarten retention policy is offered to illustrate our proposed approach.

Kernel regularized least squares (KRLS) is a popular method for flexibly estimating models that may have complex relationships between variables. However, its usefulness to many researchers is limited for two reasons. First, existing approaches are inflexible and do not allow KRLS to be combined with theoretically motivated extensions such as random effects, unregularized fixed effects, or non-Gaussian outcomes. Second, estimation is extremely computationally intensive for even modestly sized datasets. Our paper addresses both concerns by introducing generalized KRLS (gKRLS). We note that KRLS can be re-formulated as a hierarchical model thereby allowing easy inference and modular model construction where KRLS can be used alongside random effects, splines, and unregularized fixed effects. Computationally, we also implement random sketching to dramatically accelerate estimation while incurring a limited penalty in estimation quality. We demonstrate that gKRLS can be fit on datasets with tens of thousands of observations in under 1 min. Further, state-of-the-art techniques that require fitting the model over a dozen times (e.g., meta-learners) can be estimated quickly.

Small family farms account for 72% of the farms in the world. Most of these farms, in developing countries, face labor productivity gaps. One of the strategies to increase agricultural productivity focuses on implementing technical assistance programs. Using agriculture microdata, we estimate the marginal treatment effect of receiving technical assistance services. We find that technical assistance generates heterogeneous effects. On average, agricultural units receiving technical assistance increased their agricultural production by 50.4%. However, there is important heterogeneity of technical assistance’s effects across the production units’ unobserved and observed characteristics.

Conjoint experiments are quickly gaining popularity as a vehicle for studying multidimensional political preferences. A common way to explore heterogeneity of preferences estimated with conjoint experiments is by estimating average marginal component effects across subgroups. However, this method does not give the researcher the full access to the variation of preferences in the studied populations, as that would require estimating effects on the individual level. Currently, there is no accepted technique to obtain estimates of individual-level preferences from conjoint experiments. The present paper addresses this gap by proposing a procedure to estimate individual preferences as respondent-specific marginal component effects. The proposed strategy does not require any additional assumptions compared to the standard conjoint analysis, although some changes to the task design are recommended. Methods to account for uncertainty in resulting estimates are also discussed. Using the proposed procedure, I partially replicate a conjoint experiment on immigrant admission with recommended design adjustments. Then, I demonstrate how individual marginal component effects can be used to explore distributions of preferences, intercorrelations between different preference dimensions, and relationships of preferences to other variables of interest.

Experiments should be designed to facilitate the detection of experimental measurement error. To this end, we advocate the implementation of identical experimental protocols employing diverse experimental modes. We suggest iterative nonparametric estimation techniques for assessing the magnitude of heterogeneous treatment effects across these modes. And we propose two diagnostic strategies—measurement metrics embedded in experiments, and measurement experiments—that help assess whether any observed heterogeneity reflects experimental measurement error. To illustrate our argument, first we conduct and analyze results from four identical interactive experiments: in the lab; online with subjects from the CESS lab subject pool; online with an online subject pool; and online with MTurk workers. Second, we implement a measurement experiment in India with CESS Online subjects and MTurk workers.

Classical generalized linear models assume that marginal effects are homogeneous in the population given the observed covariates. Researchers can never be sure a priori if that assumption is adequate. Recent literature in statistics and political science have proposed models that use Dirichlet process priors to deal with the possibility of latent heterogeneity in the covariate effects. In this paper, we extend and generalize those approaches and propose a hierarchical Dirichlet process of generalized linear models in which the latent heterogeneity can depend on context-level features. Such a model is important in comparative analyses when the data comes from different countries and the latent heterogeneity can be a function of country-level features. We provide a Gibbs sampler for the general model, a special Gibbs sampler for gaussian outcome variables, and a Hamiltonian Monte Carlo within Gibbs to handle discrete outcome variables. We demonstrate the importance of accounting for latent heterogeneity with a Monte Carlo exercise and with two applications that replicate recent scholarly work. We show how Simpson’s paradox can emerge in the empirical analysis if latent heterogeneity is ignored and how the proposed model can be used to estimate heterogeneity in the effect of covariates.