Nonparametric identification of dynamic decision processes with discrete and continuous choices

Blevins, Jason R.

doi:10.3982/qe117

Cited by 40 publications

(39 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6 Rust (1994) shows that an important class of these models is nonparametrically non-identified. 7 Blevins (2014) shows how adding continuous state variables aids in securing nonparametric identification.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic treatment effects

Heckman

Humphries

Veramendi

2016

Journal of Econometrics

101

View full text Add to dashboard Cite

This paper develops robust models for estimating and interpreting treatment effects arising from both ordered and unordered multistage decision problems. Identification is secured through instrumental variables and/or conditional independence (matching) assumptions. We decompose treatment effects into direct effects and continuation values associated with moving to the next stage of a decision problem. Using our framework, we decompose the IV estimator, showing that IV generally does not estimate economically interpretable or policy relevant parameters in prototypical dynamic discrete choice models, unless policy variables are instruments. Continuation values are an empirically important component of estimated total treatment effects of education. We use our analysis to estimate the components of what LATE estimates in a dynamic discrete choice model.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Conditional independence assumptions are used extensively in the dynamic discrete choice literature (see, e.g., Rust, 1994 and Blevins, 2014) and the matching literature (see, e.g., Rosenbaum and Rubin, 1983). They are especially well motivated if analysts have rich data on the determinants of choices.…”

Section: Introductionmentioning

confidence: 99%

Dynamic treatment effects

Heckman

Humphries

Veramendi

2016

Journal of Econometrics

101

View full text Add to dashboard Cite

show abstract

“…We state the necessary and sufficient conditions for identification of 7 See Heckman and Vytlacil (2007b) and Blevins (2014). 8 Continuity of instruments and full support produce identifiability in our model, but are not required.…”

mentioning

confidence: 99%

Unordered Monotonicity

Heckman¹,

Pinto²

2017

View full text Add to dashboard Cite

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.

show abstract

“…In this paper, we derive sufficient conditions for identification when continuous observed state variables are available. Our study is also related to a recent paper of Blevins (2014), who considered structural dynamic models that admit both discrete and continuous choices. When the joint distribution of shocks of the discrete choices is unknown, he adopted the exclusion restriction strategy and provided identification results in the setting where the agent's discrete action is in fact binary.…”

Section: Introductionmentioning

confidence: 97%

Identification of Discrete Choice Dynamic Programming Models With Nonparametric Distribution of Unobservables

Chen

2016

Econom. Theory

View full text Add to dashboard Cite

This paper presents semiparametric identification results for the Rust (1994) class of discrete choice dynamic programming (DCDP) models. We develop sufficient conditions for identification of the deep structural parameters for the case where the per-period utility function ascribed to one choice in the model is parametric but the distribution of unobserved state variables is nonparametric. The proposed identification strategy does not rely on availability of the terminal period data and can therefore be applied to infinite horizon structural dynamic models. Identifying power comes from assuming that the agent's per-period utilities admit continuous choice-specific state variables that are observed with sufficient variation and satisfy certain conditional independence assumptions on the joint time series of observables. These conditions allow us to formulate exclusion restrictions for identifying the primitive structural functions of the model.

show abstract

Nonparametric identification of dynamic decision processes with discrete and continuous choices

Cited by 40 publications

References 50 publications

Dynamic treatment effects

Dynamic treatment effects

Unordered Monotonicity

Identification of Discrete Choice Dynamic Programming Models With Nonparametric Distribution of Unobservables

Contact Info

Product

Resources

About