BLP-Lasso for Aggregate Discrete Choice Models of Elections with Rich Demographic Covariates

Gillen, Ben; Montero, Sergio; Moon, Hyungsik Roger; Shum, Matthew

doi:10.2139/ssrn.2700775

Cited by 6 publications

(8 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once we consider as consisting of all main effects and two- and three-way interaction terms, even a modest number of variables can produce a large number of covariates (e.g., Gillen et al. 2016). In our application below, we consider data from a conjoint experiment, where main effects plus treatment covariate interactions generated 215 possible subgroup effects.…”

Section: Variable Selection and Shrinkagementioning

confidence: 99%

Sparse Estimation and Uncertainty with Application to Subgroup Analysis

Ratkovic¹,

Tingley²

2017

Polit. Anal.

View full text Add to dashboard Cite

We introduce a Bayesian method, LASSOplus, that unifies recent contributions in the sparse modeling literatures, while substantially extending pre-existing estimators in terms of both performance and flexibility. Unlike existing Bayesian variable selection methods, LASSOplus both selects and estimates effects while returning estimated confidence intervals for discovered effects. Furthermore, we show how LASSOplus easily extends to modeling repeated observations and permits a simple Bonferroni correction to control coverage on confidence intervals among discovered effects. We situate LASSOplus in the literature on how to estimate subgroup effects, a topic that often leads to a proliferation of estimation parameters. We also offer a simple preprocessing step that draws on recent theoretical work to estimate higher-order effects that can be interpreted independently of their lower-order terms. A simulation study illustrates the method’s performance relative to several existing variable selection methods. In addition, we apply LASSOplus to an existing study on public support for climate treaties to illustrate the method’s ability to discover substantive and relevant effects. Software implementing the method is publicly available in the R package sparsereg.

show abstract

Section: Variable Selection and Shrinkagementioning

confidence: 99%

Sparse Estimation and Uncertainty with Application to Subgroup Analysis

Ratkovic¹,

Tingley²

2017

Polit. Anal.

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Physician-Industry Interactions: Persuasion and Welfare

et al. 2018

View full text Add to dashboard Cite

“…In order to examine the interactions between market power and payments to physicians, we estimate a nested logit model of statin choice, integrating our demand estimation with the machine learning procedures from Belloni et al (2017), similar to Gillen et al (2015). 8 At least two other published studies we are aware of incorporate physician-level fixed effects: Mizik and Jacobson (2004) and Datta and Dave (2016).…”

Section: Introductionmentioning

confidence: 99%

Physician-Industry Interactions: Persuasion and Welfare

Grennan¹,

Myers²,

Swanson³

et al. 2018

View full text Add to dashboard Cite

In markets where consumers seek expert advice regarding purchases, firms seek to influence experts, raising concerns about biased advice. Assessing firm-expert interactions requires identifying their causal impact on demand, amidst frictions like market power. We study pharmaceutical firms' payments to physicians, leveraging instrumental variables based on regional spillovers from hospitals' conflict-of-interest policies and market shocks due to patent expiration. We find that the average payment increases prescribing of the focal drug by 73 percent. Our structural model estimates indicate that payments decrease total surplus, unless payments are sufficiently correlated with information (vs. persuasion) or clinical gains not captured in demand. AbstractIn markets where consumers seek expert advice regarding purchases, firms seek to influence experts, raising concerns about biased advice. Assessing firm-expert interactions requires identifying their causal impact on demand, amidst frictions like market power. We study pharmaceutical firms' payments to physicians, leveraging instrumental variables based on regional spillovers from hospitals' conflict-of-interest policies and market shocks due to patent expiration. We find that the average payment increases prescribing of the focal drug by 73 percent. Our structural model estimates indicate that payments decrease total surplus, unless payments are sufficiently correlated with information (vs. persuasion) or clinical gains not captured in demand.

show abstract

BLP-Lasso for Aggregate Discrete Choice Models of Elections with Rich Demographic Covariates

Cited by 6 publications

References 42 publications

Sparse Estimation and Uncertainty with Application to Subgroup Analysis

Sparse Estimation and Uncertainty with Application to Subgroup Analysis

Physician-Industry Interactions: Persuasion and Welfare

Physician-Industry Interactions: Persuasion and Welfare

Contact Info

Product

Resources

About