A5043693138- Statistical Methods and Bayesian Inference
- Statistical Methods in Clinical Trials
- Bayesian Methods and Mixture Models
- Statistical Distribution Estimation and Applications
- Statistical Methods and Inference
- Optimal Experimental Design Methods
- Chronic Lymphocytic Leukemia Research
- Aortic Disease and Treatment Approaches
- Chronic Myeloid Leukemia Treatments
- Aortic aneurysm repair treatments
- Health Systems, Economic Evaluations, Quality of Life
- Lymphoma Diagnosis and Treatment
- Cardiac, Anesthesia and Surgical Outcomes
Bristol-Myers Squibb (Switzerland)
2024
Seoul National University
2021
Hasselt University
2013-2017
Since the seminal paper by Cook and Weisberg [9 R.D. S. Weisberg, Residuals Influence in Regression, Chapman & Hall, London, 1982. [Google Scholar]], local influence, next to case deletion, has gained popularity as a tool detect influential subjects measurements for variety of statistical models. For linear mixed model approach leads easily interpretable computationally convenient expressions, not only highlighting subjects, but also which aspect their profile undue influence on model's fit...
We consider models for hierarchical count data, subject to overdispersion and/or excess zeros. Molenberghs et al. () and extend the Poisson-normal generalized linear-mixed model by including gamma random effects accommodate overdispersion. Excess zeros are handled using either a zero-inflation or hurdle component. These were studied Kassahun (). While flexible, they quite elaborate in parametric specification therefore assessment is imperative. derive local influence measures detect examine...
Objective We investigated the survival of patients who had undergone elective reconstruction ascending aorta for degenerative aneurysms. The long-term was compared to an age- and sex-matched case-control population. An analysis risk factors, infl uencing made.Methods results From May 1998 to-01-2012, 72 underwent disease at department Cardiothoracic Surgery Jessa Hospital, Hasselt, Belgium. Sixty were treated with Bentall procedures, whereas 12 received valve-sparing procedures. average age...
We develop local influence diagnostics to detect influential subjects when generalized linear mixed models are fitted incomplete longitudinal overdispersed count data. The focus is on the stemming from dropout model specification. In particular, effect of small perturbations around an MAR specification examined. method applied data a clinical trial in epileptic patients. allowing for overdispersion contrasted with that do not.
Competing risks data usually arise when an occurrence of event precludes other types events from being observed. Such are often encountered in a clustered clinical study such as multi‐center trial. For the competing‐risks which correlated within cluster, models allowing for frailty terms have been recently studied. To best our knowledge, however, there is no literature on variable selection methods cause‐specific hazard models. In this article, we propose procedure fixed effects competing...
7026 Background: Liso-cel is an autologous, CD19-directed, 4-1BB CAR T cell product indicated for the treatment of adults with R/R LBCL. NCP defined as any wherein one or both CD8 CD4 components did not meet ≥ 1 commercial release specifications but met EAP criteria and was considered appropriate infusion. Methods: This a prospective, multicenter study pts LBCL intended to receive liso-cel were treated due manufacturing outcomes. Data from United States are reported here. The comprised...
The main objective of this paper is to evaluate the influence individual subjects exerted on a random-effects model for repeated measures, where random effects follow mixture distribution. diagnostic tool based local with perturbation scheme that explicitly targets influences resulting from perturbing component probabilities. Bruckers, Molenberghs, Verbeke, and Geys (2016) considered similar model, but focused stemming subject's likelihood contributions as whole. We also compare two types...