Personalized treatment for longitudinal data using unspecified random-effects model

Cho, Hyunkeun; Wang, Peng; Qu, Annie

doi:10.5705/ss.202015.0120

Cited by 12 publications

(13 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Under the nonignorable missing data framework, the consistency property holds as long as either the SPM or the CMAR assumption is satisfied. The proof is quite similar to Cho, Wang and Qu (2016), and is omitted here. One notable condition is the L 2 -mixingale condition (McLeish (1975)) that controls the serial correlation Cor(y i |b i ) to achieve consistency, Cor(y it , y i,t+s ) should be sufficiently small with an increase of s.…”

Section: Asymptotic Propertiesmentioning

confidence: 85%

“…Remark 1. Given β 0 or its consistent estimatorβ, the penalized random-effects estimatorb is consistent as the cluster size T goes to infinity, as discussed in Cho, Wang and Qu (2016), given that regularity conditions are satisfied. Under the nonignorable missing data framework, the consistency property holds as long as either the SPM or the CMAR assumption is satisfied.…”

Section: Asymptotic Propertiesmentioning

confidence: 99%

See 1 more Smart Citation

A mixed-effects estimating equation approach to nonignorable missing longitudinal data with refreshment samples

2018

STAT SINICA

Self Cite

View full text Add to dashboard Cite

Nonignorable missing data occur frequently in longitudinal studies and can cause biased estimations. Refreshment samples which draw new subjects randomly in subsequent waves from the original population could mitigate the bias. In this paper, we introduce a mixed-effects estimating equation approach that enables one to incorporate refreshment samples and recover informative missing information from the measurement process. We show that the proposed method achieves consistency and asymptotic normality for fixed-effect estimation under shared-parameter models, and we extend it to a more general nonignorable-missing framework. Our finite sample simulation studies show the effectiveness and robustness of the proposed method under different missing mechanisms. In addition, we apply our method to election poll longitudinal survey data with refreshment samples from the 2007-2008 Associated Press-Yahoo! News.

show abstract

Section: Asymptotic Propertiesmentioning

confidence: 85%

Section: Asymptotic Propertiesmentioning

confidence: 99%

A mixed-effects estimating equation approach to nonignorable missing longitudinal data with refreshment samples

2018

STAT SINICA

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, their method takes serial correlation into account only for the fixed-effects parameter estimations. Cho et al [15] indicate that incorporating serial correlation is also crucial for random-effects estimation, especially if the random-effects prediction is the main focus. To allocate accurate dosage for each individual, it is important to obtain accurate estimations for both fixed and random effects.…”

Section: Estimation Of Population Parameters On Training Samplementioning

confidence: 99%

“…The reason we include (6) is to control the variance and ensure the identifiability of the random-effects estimation, and therefore, the iterative algorithm converges. Cho et al [15] show that the choice of 2 is not sensitive for parameter estimation and can be fixed as 2 = log(N), while 1 can be selected through cross-validation. Here, we fix 1 = log(n 0 ) and 2 = log(N) for simplification, which works well in simulation studies.…”

Section: Estimation Of Population Parameters On Training Samplementioning

confidence: 99%

Individualizing drug dosage with longitudinal data

Zhu

2016

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

We propose a two-step procedure to personalize drug dosage over time under the framework of a log-linear mixed-effect model. We model patients' heterogeneity using subject-specific random effects, which are treated as the realizations of an unspecified stochastic process. We extend the conditional quadratic inference function to estimate both fixed-effect coefficients and individual random effects on a longitudinal training data sample in the first step and propose an adaptive procedure to estimate new patients' random effects and provide dosage recommendations for new patients in the second step. An advantage of our approach is that we do not impose any distribution assumption on estimating random effects. Moreover, the new approach can accommodate more general time-varying covariates corresponding to random effects. We show in theory and numerical studies that the proposed method is more efficient compared with existing approaches, especially when covariates are time varying. In addition, a real data example of a clozapine study confirms that our two-step procedure leads to more accurate drug dosage recommendations. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract

“…Diaz et al, adopted a random intercept linear model for the log of trough‐plasma‐concentration to determine the optimal dosage. Cho et al estimated unobserved subject‐specific treatment effects through conditional random‐effects modeling and applied the random forest algorithm to allocate effective treatments for individuals. Zhu and Qu personalized drug dosage over time under the framework of a log‐linear mixed‐effect model.…”

Section: Introductionmentioning

confidence: 99%

Subgroup identification via homogeneity pursuit for dense longitudinal/spatial data

Zhang

2019

Statistics in Medicine

View full text Add to dashboard Cite

In the clinical trial community, it is usually not easy to find a treatment that benefits all patients since the reaction to treatment may differ substantially across different patient subgroups. The heterogeneity of treatment effect plays an essential role in personalized medicine. To facilitate the development of tailored therapies and improve the treatment efficacy, it is important to identify subgroups that exhibit different treatment effects. We consider a very general framework for subgroup identification via the homogeneity pursuit methods usually employed in econometric time series analysis. The change point detection algorithm in our procedure is most suitable for analyzing dense longitudinal or spatial data which are quite common for biomedical studies these days.We demonstrate that our proposed method is fast and accurate through extensive numerical studies. In particular, our method is illustrated by analyzing a diffusion tensor imaging data set. KEYWORDS binary segmentation, change point detection, dense longitudinal data, homogeneity pursuit, personalized medicine, treatment recommendation 3256

show abstract

Personalized treatment for longitudinal data using unspecified random-effects model

Cited by 12 publications

References 32 publications

A mixed-effects estimating equation approach to nonignorable missing longitudinal data with refreshment samples

A mixed-effects estimating equation approach to nonignorable missing longitudinal data with refreshment samples

Individualizing drug dosage with longitudinal data

Subgroup identification via homogeneity pursuit for dense longitudinal/spatial data

Contact Info

Product

Resources

About