Results 41 to 50 of about 1,618 (122)

Mediated probabilities of causation

Journal of Causal Inference
We propose a set of causal estimands that we call “the mediated probabilities of causation.” These estimands quantify the probabilities that an observed negative outcome was induced via a mediating pathway versus a direct pathway in a stylized setting ...
Rubinstein Max, Cuellar Maria, Malinsky Daniel   +2 more
doaj   +1 more source

Optimal learning with $Q$-aggregation

, 2014
We consider a general supervised learning problem with strongly convex and Lipschitz loss and study the problem of model selection aggregation. In particular, given a finite dictionary functions (learners) together with the prior, we generalize the ...
Lecué, Guillaume, Rigollet, Philippe
core   +1 more source

Causal additive models with smooth backfitting

Journal of Causal Inference
A fully nonparametric approach to learning causal structures from observational data is proposed. The method is described in the setting of additive structural equation models with a link to causal inference.
Morville Asger B., Park Byeong U.
doaj   +1 more source

Nonparametric estimation in a semimartingale regression model. Part 2. Robust asymptotic efficiency [PDF]

, 2009
In this paper we prove the asymptotic efficiency of the model selection procedure proposed by the authors in the first part. To this end we introduce the robust risk as the least upper bound of the quadratical risk over a broad class of observation ...
Konev, Victor, Pergamenchtchikov, Serguei   +1 more
core   +3 more sources

Targeted maximum likelihood based estimation for longitudinal mediation analysis

Journal of Causal Inference
Causal mediation analysis with random interventions has become an area of significant interest for understanding time-varying effects with longitudinal and survival outcomes.
Wang Zeyi, Laan Lars van der, Petersen Maya, Gerds Thomas, Kvist Kajsa, Laan Mark van der   +5 more
doaj   +1 more source

Pharmacokinetics and Pharmacodynamics Models of Tumor Growth and Anticancer Effects in Discrete Time

Computational and Mathematical Biophysics, 2020
We study the h-discrete and h-discrete fractional representation of a pharmacokinetics-pharmacodynamics (PK-PD) model describing tumor growth and anticancer effects in continuous time considering a time scale h𝕅0, where h > 0.
Atıcı Ferhan M., Nguyen Ngoc, Dadashova Kamala, Pedersen Sarah E., Koch Gilbert   +4 more
doaj   +1 more source

Selection of tuning parameters in bridge regression models via Bayesian information criterion

, 2012
We consider the bridge linear regression modeling, which can produce a sparse or non-sparse model. A crucial point in the model building process is the selection of adjusted parameters including a regularization parameter and a tuning parameter in bridge
A Antoniadis, AE Hoerl, C Park, C-H Zhang, CM Hurvich, CM Hurvich, G McDonald, G Schwarz, H Zou, H Zou, J Fan, J Fan, J Huang, J Huang, J Lv, JE Frank, K Knight, L Tierney, M Ishiguro, M Yuan, N Sugiura, P Bühlmann, P Craven, PHC Eilers, R Tibshirani, S Konishi, Shuichi Kawano, T Shimamura, WJ Fu, Y Liu   +29 more
core   +1 more source

Solution of linear ill-posed problems using random dictionaries

, 2017
In the present paper we consider application of overcomplete dictionaries to solution of general ill-posed linear inverse problems. In the context of regression problems, there has been enormous amount of effort to recover an unknown function using such ...
Gupta, Pawan, Pensky, Marianna
core   +1 more source

Strong convergence for weighted sums of (α, β)-mixing random variables and application to simple linear EV regression model

Open Mathematics
In this article, the complete convergence and the Kolmogorov strong law of large numbers for weighted sums of (α,β)\left(\alpha ,\beta )-mixing random variables are presented.
Hu Wenjing, Wang Wei, Wu Yi
doaj   +1 more source

Simulation analysis of non-respondent information in context of small domain

Heliyon
In the real-world, there are various situations when all units are not accessible of the respondent called unit non-response. The effect of unit non-response is a tricky matter for estimating the total number of unit.
Ashutosh Ashutosh, Marius Stefan, Piyush Kant Rai, Walid Emam, Soofia Iftikhar, Malik Muhammad Anas   +5 more
doaj   +1 more source