Variable selection for longitudinal survey data

05/02/2021
by   Laura Dumitrescu, et al.
0

In this article we propose a new variable selection method for analyzing data collected from longitudinal sample surveys. The procedure is based on the survey-weighted quadratic inference function, which was recently introduced as an alternative to the survey-weighted generalized estimating function. Under the joint model-design framework, we introduce the penalized survey-weighted quadratic inference estimator and obtain sufficient conditions for the existence, weak consistency, sparsity and asymptotic normality. To illustrate the finite sample performance of the model selection procedure, we include a limited simulation study.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/03/2019

Robust Model Selection for Finite Mixture of Regression Models Through Trimming

In this article, we introduce a new variable selection technique through...
research
06/07/2023

Improving Survey Inference in Two-phase Designs Using Bayesian Machine Learning

The two-phase sampling design is a cost-effective sampling strategy that...
research
10/20/2021

Variable selection in doubly truncated regression

Doubly truncated data arise in many areas such as astronomy, econometric...
research
08/04/2022

Statistical Inference for Streamed Longitudinal Data

Modern longitudinal data, for example from wearable devices, measures bi...
research
06/24/2020

Bayesian Shrinkage for Functional Network Models with Intractable Normalizing Constants

Longitudinal network models are widely used to study the time-varying re...
research
07/18/2021

Sparse group variable selection for gene-environment interactions in the longitudinal study

Penalized variable selection for high dimensional longitudinal data has ...
research
06/08/2018

Estimation of marginal model with subgroup auxiliary information

Marginal model is a popular instrument for studying longitudinal data an...

Please sign up or login with your details

Forgot password? Click here to reset