Treatment Effect Estimation Using Nonlinear Two‐Stage Instrumental Variable Estimators: Another Cautionary Note

Chapman, Cole G.; Brooks, John M.

doi:10.1111/1475-6773.12463

Cited by 23 publications

(47 citation statements)

References 48 publications

(104 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results from this study conform with the simulation results of Chapman and Brooks (), who compared 2SLS and nonlinear 2SRI with raw residuals in simulation models with binary treatment, binary outcome, and continuous instruments to find that 2SLS produced consistent estimates for the IV effect whereas 2SRI did not reliably estimate either the ATE or the IV effect. However, their study did not examine models with binary instruments, vary rarity of treatment or outcome from approximately 0.5, examine alternative forms of 2SRI residuals, or report coverage probabilities of estimates.…”

Section: Discussionsupporting

confidence: 83%

“…However, 2SRI estimates of ATE were also generally biased, with the level of bias varying by residual form and outcome rarity. General conclusions from results of these simulation models are consistent with those of the more limited scenarios considered by Chapman and Brooks (). Among 2SRI models, those using generalized residuals were most often least biased in estimating ATE, though 2SRI with Anscombe residuals generated less biased estimates in scenarios with very rare outcomes (<5%).…”

Section: Introductionsupporting

confidence: 84%

“…We expect that for a binary treatment in the first stage, a linear approximation of the conditional mean is likely to be most appropriate when the mean treatment is close to 50%. Chapman and Brooks () simulation results showed that 2SLS methods produced unbiased estimates of the IV effect (i.e., weighted average of LATEs defined by the continuous IVs that they use) in models with treatment rates near 50% but did not consider binary instruments.…”

Section: Econometric Theory and Methodsmentioning

confidence: 99%

See 2 more Smart Citations

2SLS versus 2SRI: Appropriate methods for rare outcomes and/or rare exposures

2018

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionsupporting

confidence: 83%

Section: Introductionsupporting

confidence: 84%

Section: Econometric Theory and Methodsmentioning

confidence: 99%

See 1 more Smart Citation

2SLS versus 2SRI: Appropriate methods for rare outcomes and/or rare exposures

2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…Proper generalization of estimates of ATT or LATE for the outcome of interest to the untreated patients in a study population requires the assumption that treatments were not chosen based on expected treatment benefit, i.e. no ‘sorting on the gain’ or essential heterogeneity [18, 51]. It has also been shown that different IVs affect the treatment choices of a different subset of patients in the same study, producing different but valid estimates of LATE [18–21].…”

Section: Discussionmentioning

confidence: 99%

Understanding Treatment Effect Estimates When Treatment Effects Are Heterogeneous for More Than One Outcome

Brooks

Chapman

Schroeder

2018

Appl Health Econ Health Policy

Self Cite

View full text Add to dashboard Cite

show abstract

“…69 Linear 2-stage least squares (2SLS) IV estimators were used (Data S4). 29,[70][71][72][73][74][75][76][77][78][79][80] In this study 2SLS yields estimates of the absolute average effect of ACEI/ARBs for the patients whose ACEI/ARB choice was sensitive to local area practice styles 71,80 or what is known as the local average treatment effect. Our large sample size ensures that our 2SLS estimates will be distributed normally via the central limit theorem.…”

Section: Discussionmentioning

confidence: 99%

Use of Angiotensin‐Converting Enzyme Inhibitors and Angiotensin Receptor Blockers for Geriatric Ischemic Stroke Patients: Are the Rates Right?

Brooks

Chapman

Suneja

et al. 2018

JAHA

Self Cite

View full text Add to dashboard Cite

BackgroundOur objective is to estimate the effects associated with higher rates of renin‐angiotensin system antagonists, angiotensin‐converting enzyme inhibitors and angiotensin receptor blockers (ACEI/ARBs), in secondary prevention for geriatric (aged >65 years) patients with new ischemic strokes by chronic kidney disease (CKD) status.Methods and ResultsThe effects of ACEI/ARBs on survival and renal risk were estimated by CKD status using an instrumental variable (IV) estimator. Instruments were based on local area variation in ACEI/ARB use. Data abstracted from charts were used to assess the assumptions underlying the instrumental estimator. ACEI/ARBs were used after stroke by 45.9% and 45.2% of CKD and non‐CKD patients, respectively. ACEI/ARB rate differences across local areas grouped by practice styles were nearly identical for CKD and non‐CKD patients. Higher ACEI/ARB use rates for non‐CKD patients were associated with higher 2‐year survival rates, whereas higher ACEI/ARB use rates for patients with CKD were associated with lower 2‐year survival rates. While the negative survival estimates for patients with CKD were not statistically different from zero, they were statistically lower than the estimates for non‐CKD patients. Confounders abstracted from charts were not associated with the instrumental variable used.ConclusionsHigher ACEI/ARB use rates had different survival implications for older ischemic stroke patients with and without CKD. ACEI/ARBs appear underused in ischemic stroke patients without CKD as higher use rates were associated with higher 2‐year survival rates. This conclusion is not generalizable to the ischemic stroke patients with CKD, as higher ACEI/ARBS use rates were associated with lower 2‐year survival rates that were statistically lower than the estimates for non‐CKD patients.

show abstract

Treatment Effect Estimation Using Nonlinear Two‐Stage Instrumental Variable Estimators: Another Cautionary Note

Cited by 23 publications

References 48 publications

2SLS versus 2SRI: Appropriate methods for rare outcomes and/or rare exposures

2SLS versus 2SRI: Appropriate methods for rare outcomes and/or rare exposures

Understanding Treatment Effect Estimates When Treatment Effects Are Heterogeneous for More Than One Outcome

Use of Angiotensin‐Converting Enzyme Inhibitors and Angiotensin Receptor Blockers for Geriatric Ischemic Stroke Patients: Are the Rates Right?

Contact Info

Product

Resources

About