Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This paper presents an econometric mediation analysis. It considers identification of production functions and the sources of output effects (treatment effects) from experimental interventions when some inputs are mismeasured and others are entirely omitted.

Zonder onderwerpscode: economie

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This paper presents a new monotonicity condition for unordered discrete choice models with multiple treatments. Unlike a less general version of mono-tonicity in binary and ordered choice models, monotonicity in unordered discrete choice models along with other standard assumptions does not necessarily identify causal effects defined by variation in instruments, although in some cases it does. Our condition implies and is implied by additive separability of the choice equations in terms of observables and unobservables. These results follow from properties of binary matrices developed in this paper. We investigate conditions under which Unordered Monotonicity arises as a consequence of choice behavior. We represent IV estimators of counterfactuals as solutions to discrete mixture problems.

Zonder onderwerpscode: economie

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This paper considers the problem of making inferences about the effects of a program on multiple outcomes when the assignment of treatment status is imperfectly randomized. By imperfect randomization we mean that treatment status is reassigned after an initial randomization on the basis of characteristics that may be observed or unobserved by the analyst. We develop a partial identification approach to this problem that makes use of information limiting the extent to which randomization is imperfect to show that it is still possible to make nontrivial inferences about the effects of the program in such settings. We consider a family of null hypotheses in which each null hypothesis specifies that the program has no effect on one of several outcomes of interest. Under weak assumptions, we construct a procedure for testing this family of null hypotheses in a way that controls the familywise error rate -- the probability of even one false rejection -- in finite samples. We develop our methodology in the context of a reanalysis of the HighScope Perry Preschool program. We find statistically significant effects of the program on a number of different outcomes of interest, including outcomes related to criminal activity for males and females, even after accounting for the imperfectness of the randomization and the multiplicity of null hypotheses.

Zonder onderwerpscode: economie

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

It is often the case that an endogenous treatment variable causally affects an intermediate variable that in turn causally affects a final outcome. Using an Instrumental Variable (IV) identifies the causal effect of the endogenous treatment on both the intermediate and the final outcome variable, but not the extent to which the intermediate variable affects the final outcome. We present a new testable framework in which a single IV suffices to also estimate the causal effect of the intermediate variable on the final outcome. We use this framework to investigate to what extent German voters responded to the labor market turmoil caused by increasing trade with low-wage manufacturing countries. We first establish that import competition increased voters' support for only extreme (right) parties. We then decompose this populist 'total effect' into a 'mediated effect' running through labor market adjustments and a 'direct effect' of trade exposure on voting behavior. We find the total consists of a large populist effect driven by labor markets and a relatively smaller but moderating direct effect. Our approach provides a template that may be useful in a broad range of empirical applications studying causal mechanisms in observational data.

Zonder onderwerpscode: economie

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This paper defines and analyzes a new monotonicity condition for the identification of counterfactuals and treatment effects in unordered discrete choice models with multiple treatments, heterogenous agents and discrete-valued instruments. Unordered monotonicity implies and is implied by additive separability of choice of treatment equations in terms of observed and unobserved variables. These results follow from properties of binary matrices developed in this paper. We investigate conditions under which unordered monotonicity arises as a consequence of choice behavior. We characterize IV estimators of counterfactuals as solutions to discrete mixture problems.