Selective Inference for Effect Modification: An Empirical Investigation

Zhao, Qingyuan; Panigrahi, Snigdha

doi:10.1353/obs.2019.0007

Cited by 6 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where plug-in estimates of the nuisance parameters m ( x ) and π ( x ) are obtained from some off-the-shelf machine learning methods, and the individualized treatment effects, Δ ( x ) , are estimated using penalized empirical loss minimization. These ideas were first conceptualized in the proposal of selecting inference for effect modifiers by Zhao et al 41,42 and further generalized in the R-learning method of Nie and Wager. 43…”

Section: Overview Of Hte Evaluation Methodsmentioning

confidence: 99%

“…where plug-in estimates of the nuisance parameters m(x) and p(x) are obtained from some off-the-shelf machine learning methods, and the individualized treatment effects, D(x), are estimated using penalized empirical loss minimization. These ideas were first conceptualized in the proposal of selecting inference for effect modifiers by Zhao et al 41,42 and further generalized in the R-learning method of Nie and Wager. 43 An important role in removing biases due to overfitting is played by cross-validated predictions of the nuisance function, that is, the plugged-in values mÀi (X i ) and pÀi (X i ) for the outcome and propensity functions, respectively.…”

Section: Global Outcome Modelingmentioning

confidence: 99%

See 1 more Smart Citation

Overview of modern approaches for identifying and evaluating heterogeneous treatment effects from clinical data

et al. 2023

View full text Add to dashboard Cite

There has been much interest in the evaluation of heterogeneous treatment effects (HTE) and multiple statistical methods have emerged under the heading of personalized/precision medicine combining ideas from hypothesis testing, causal inference, and machine learning over the past 10-15 years. We discuss new ideas and approaches for evaluating HTE in randomized clinical trials and observational studies using the features introduced earlier by Lipkovich, Dmitrienko, and D’Agostino that distinguish principled methods from simplistic approaches to data-driven subgroup identification and estimating individual treatment effects and use a case study to illustrate these approaches. We identified and provided a high-level overview of several classes of modern statistical approaches for personalized/precision medicine, elucidated the underlying principles and challenges, and compared findings for a case study across different methods. Different approaches to evaluating HTEs may produce (and actually produced) highly disparate results when applied to a specific data set. Evaluating HTE with machine learning methods presents special challenges since most of machine learning algorithms are optimized for prediction rather than for estimating causal effects. An additional challenge is in that the output of machine learning methods is typically a “black box” that needs to be transformed into interpretable personalized solutions in order to gain acceptance and usability.

show abstract

Section: Overview Of Hte Evaluation Methodsmentioning

confidence: 99%

Section: Global Outcome Modelingmentioning

confidence: 99%

Overview of modern approaches for identifying and evaluating heterogeneous treatment effects from clinical data

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Like for MCM, current implementations consider a linear working model for the IATE (Nie & Wager, 2017;Zhao, Small, & Ertefaie, 2017) and solve βRL = arg min…”

Section: R-learningmentioning

confidence: 99%

Machine Learning Estimation of Heterogeneous Causal Effects: Empirical Monte Carlo Evidence

Knaus,

Lechner,

Strittmatter

2018

Preprint

View full text Add to dashboard Cite

We investigate the finite sample performance of causal machine learning estimators for heterogeneous causal effects at different aggregation levels. We employ an Empirical Monte Carlo Study that relies on arguably realistic data generation processes (DGPs) based on actual data. We consider 24 different DGPs, eleven different causal machine learning estimators, and three aggregation levels of the estimated effects. In the main DGPs, we allow for selection into treatment based on a rich set of observable covariates. We provide evidence that the estimators can be categorized into three groups. The first group performs consistently well across all DGPs and aggregation levels. These estimators have multiple steps to account for the selection into the treatment and the outcome process. The second group shows competitive performance only for particular DGPs. The third group is clearly outperformed by the other estimators.

show abstract

“…For models chosen based on the LASSO solution, Lee et al (2016) developed the influential polyhedral method, reducing the selection event to a series of affine inequalities in the response variable. Many different model selection events for a Gaussian response variable have subsequently been developed using a similar set of constraints, yielding tractable conditional distributions that can be used for inference (Suzumura et al, 2017;Liu et al, 2018;Taylor and Tibshirani, 2018;Zhao and Panigrahi, 2019;Tanizaki et al, 2020, among others). Despite the convenience of the polyhedral method, the resulting confidence intervals can have infinite expected length under Gaussian regression, formally established by Kivaranovic and Leeb (2018).…”

Section: Introductionmentioning

confidence: 99%

Selective Inference for Sparse Multitask Regression with Applications in Neuroimaging

Panigrahi¹,

Stewart²,

Sripada³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Multi-task learning is frequently used to model a set of related response variables from the same set of features, improving predictive performance and modeling accuracy relative to methods that handle each response variable separately. Despite the potential of multi-task learning to yield more powerful inference than single-task alternatives, prior work in this area has largely omitted uncertainty quantification. Our focus in this paper is a common multi-task problem in neuroimaging, where the goal is to understand the relationship between multiple cognitive task scores (or other subject-level assessments) and brain connectome data collected from imaging. We propose a framework for selective inference to address this problem, with the flexibility to: (i) jointly identify the relevant covariates for each task through a sparsity-inducing penalty, and (ii) conduct valid inference in a model based on the estimated sparsity structure. Our framework offers a new conditional procedure for inference, based on a refinement of the selection event that yields a tractable selection-adjusted likelihood. This gives an approximate system of estimating equations for maximum likelihood inference, solvable via a single convex optimization problem, and enables us to efficiently form confidence intervals with approximately the correct coverage. Applied to both simulated data and data from the Adolescent Cognitive Brain Development (ABCD) study, our selective inference methods yield tighter confidence intervals than commonly used alternatives, such as data splitting. We also demonstrate through simulations that multi-task learning with selective inference can more accurately recover true signals than single-task methods.

show abstract

Selective Inference for Effect Modification: An Empirical Investigation

Cited by 6 publications

References 12 publications

Overview of modern approaches for identifying and evaluating heterogeneous treatment effects from clinical data

Overview of modern approaches for identifying and evaluating heterogeneous treatment effects from clinical data

Machine Learning Estimation of Heterogeneous Causal Effects: Empirical Monte Carlo Evidence

Selective Inference for Sparse Multitask Regression with Applications in Neuroimaging

Contact Info

Product

Resources

About