%0 Journal Article
%J Health Economics
%D Forthcoming
%T 2SLS vs 2SRI: Appropriate methods for rare outcomes and/or rare exposures
%A Basu, Anirban
%A Norma Coe
%K Health Care Outcomes
%K Monte-Carlo Simulations
%X Using Monte-Carlo simulations, we compare the two-stage least-squares estimator with two-stage residual inclusion estimators, with varying forms of residuals, to estimate the local average treatment effect parameter for a binary outcome and endogenous binary treatment model in the presence of binary covariates and a binary instrumental variable. We vary the rarity of both the outcome and the treatment and find different estimators to produce the least bias in different settings. We develop guidance for applied researchers and illustrate the utility of this guidance with estimating the effects of long-term care insurance on a variety of binary health care use outcomes among the near-elderly using the Health and Retirement Study.
%B Health Economics
%8 Jan-01-2017
%G eng
%U http://doi.wiley.com/10.1002/hec.3490http://onlinelibrary.wiley.com/wol1/doi/10.1002/hec.3490/fullpdfhttps://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1002%2Fhec.3490
%! Health Econ.
%R 10.1002/hec.3490
%0 Journal Article
%J Health Services Research
%D Forthcoming
%T Medicare expenditures attributable to dementia.
%A White, Lindsay
%A Fishman, Paul
%A Basu, Anirban
%A Crane, Paul K.
%A Eric B Larson
%A Norma Coe
%K Cognition & Reasoning
%K Dementia
%K Medicare linkage
%K Medicare/Medicaid/Health Insurance
%X **OBJECTIVE: **To estimate dementia's incremental cost to the traditional Medicare program.

**DATA SOURCES: **Health and Retirement Study (HRS) survey-linked Medicare part A and B claims from 1991 to 2012.

**STUDY DESIGN: **We compared Medicare expenditures for 60 months following a claims-based dementia diagnosis to those for a randomly selected, matched comparison group.

**DATA COLLECTION/EXTRACTION METHODS: **We used a cost estimator that accounts for differential survival between individuals with and without dementia and decomposes incremental costs into survival and cost intensity components.

**PRINCIPAL FINDINGS: **Dementia's five-year incremental cost to the traditional Medicare program is approximately $15 700 per patient, nearly half of which is incurred in the first year after diagnosis. Shorter survival with dementia mitigates the incremental cost by about $2650. Increased costs for individuals with dementia were driven by more intensive use of Medicare part A covered services. The incremental cost of dementia was about $7850 higher for females than for males because of sex-specific differential mortality associated with dementia.

**CONCLUSIONS: **Dementia's cost to the traditional Medicare program is significant. Interventions that target early identification of dementia and preventable inpatient and post-acute care services could produce substantial savings.

%B Health Services Research
%G eng
%1 http://www.ncbi.nlm.nih.gov/pubmed/30868557?dopt=Abstract
%R 10.1111/1475-6773.13134
%0 Journal Article
%J Health Economics
%D 2018
%T 2SLS versus 2SRI: Appropriate methods for rare outcomes and/or rare exposures
%A Basu, Anirban
%A Norma Coe
%A Cole G. Chapman
%K Clinical trials
%K Health Care Outcomes
%K Insurance
%K Monte-Carlo Simulations
%X This study used Monte Carlo simulations to examine the ability of the two‐stage least squares (2SLS) estimator and two‐stage residual inclusion (2SRI) estimators with varying forms of residuals to estimate the local average and population average treatment effect parameters in models with binary outcome, endogenous binary treatment, and single binary instrument. The rarity of the outcome and the treatment was varied across simulation scenarios. Results showed that 2SLS generated consistent estimates of the local average treatment effects (LATE) and biased estimates of the average treatment effects (ATE) across all scenarios. 2SRI approaches, in general, produced biased estimates of both LATE and ATE under all scenarios. 2SRI using generalized residuals minimized the bias in ATE estimates. Use of 2SLS and 2SRI is illustrated in an empirical application estimating the effects of long‐term care insurance on a variety of binary health care utilization outcomes among the near‐elderly using the Health and Retirement Study.
%B Health Economics
%V 27
%P 937 - 955
%8 Jan-06-2018
%G eng
%U http://doi.wiley.com/10.1002/hec.v27.6http://doi.wiley.com/10.1002/hec.3647http://onlinelibrary.wiley.com/wol1/doi/10.1002/hec.3647/fullpdfhttps://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1002%2Fhec.3647
%N 6
%! Health Economics
%R 10.1002/hec.v27.610.1002/hec.3647
%0 Report
%D 2017
%T Comparing 2SLS vs 2SRI for Binary Outcomes and Binary Exposures
%A Basu, Anirban
%A Norma Coe
%A Cole G. Chapman
%K Economics
%K Health Services Utilization
%K Long-term Care
%X This study uses Monte Carlo simulations to examine the ability of the two-stage least-squares (2SLS) estimator and two-stage residual inclusion (2SRI) estimators with varying forms of residuals to estimate the local average and population average treatment effect parameters in models with binary outcome, endogenous binary treatment, and single binary instrument. The rarity of the outcome and the treatment are varied across simulation scenarios. Results show that 2SLS generated consistent estimates of the LATE and biased estimates of the ATE across all scenarios. 2SRI approaches, in general, produce biased estimates of both LATE and ATE under all scenarios. 2SRI using generalized residuals minimizes the bias in ATE estimates. Use of 2SLS and 2SRI is illustrated in an empirical application estimating the effects of long-term care insurance on a variety of binary healthcare utilization outcomes among the near-elderly using the Health and Retirement Study.
%B NBER Working Paper Series
%I National Bureau of Economic Research
%C Cambridge, MA
%8 09/2017
%G eng
%U http://www.nber.org/papers/w23840.pdf
%R 10.3386/w23840