A continuous-time version of the Markowitz mean-variance portfolio selection model is proposed and analyzed for a market consisting one bank account multiple stocks. The parameters, including interest rate appreciation volatility rates stocks, depend on mode that switches among finite number states. random regime switching assumed to be independent underlying Brownian motion. This essentially renders incomplete. Markov chain modulated diffusion formulation employed problem. Using techniques...

This study investigated the time-varying effects of vaccines and oral antiviral drugs in preventing severe COVID-19 complications mortality Hong Kong. Utilizing data from hospitalized patients diagnosed with SARS-CoV-2 between March 15, 2022, November 30, employed Andersen-Gill model time-dependent explanatory variables to address immortal time bias. Results demonstrate that both antivirals offered protection, showing significant waning after fourth dose. Oral were most effective if...

Abstract ErbB2 overexpression in breast tumors results increased metastasis and angiogenesis reduced survival. To study signaling mechanisms angiogenesis, we did a spontaneous assay using MDA-MB-435 human cancer cells stably transfected with constitutively active kinase (V659E), kinase-dead mutant of (K753M), or vector control (neo). Mice injected V659E had incidence tumor microvessel density than mice K753M control. Increased vivo from the transfectants paralleled angiogenic potential...

Objective: This matched cohort study used data from a large dental HMO in the Pacific Northwest to evaluate degree which pulpal involvement and subsequent endodontic therapy affects tooth survival. Root canal filled (RCF) teeth were as an indicator of involvement. Our hypothesis was that RCF would be extracted sooner than non-RCF within subjects, controlling for tooth-level variables interest. Methods: The HMO's treatment databases chart audit identify 202 eligible each whom had one...

The continual reassessment method (CRM) is a popular dose-finding design for phase I clinical trials. This requires that practitioners prespecify the toxicity probability at each dose. Such prespecification can be arbitrary, and different specifications of probabilities may lead to very properties. To overcome arbitrariness further enhance robustness design, we propose using multiple parallel CRM models, with set prespecified probabilities. In Bayesian paradigm, assign discrete mass model as...

Summary Treating patients with a combination of agents is becoming commonplace in cancer clinical trials, biochemical synergism often the primary focus. In typical drug trial, toxicity profile each individual has already been thoroughly studied single-agent which naturally offers rich prior information. We propose Bayesian adaptive design for dose finding that based on copula-type model to account synergistic effect two or more drugs combination. To search maximum tolerated combination, we...

To compare the characteristics of deregulation HER receptors and their ligands between primary tumor corresponding brain metastases non-small cell lung carcinoma (NSCLC).Fifty-five NSCLC tumors specimens were examined for immunohistochemical expression epidermal growth factor receptor (EGFR), phosphorylated EGFR, Her2, Her3, EGF, transforming factor-alpha, amphiregulin, epiregulin, betacellulin, heparin-binding EGFR-like factor, neuregulin (NRG) 1, NRG2. Analysis EGFR copy number using...

Graph-based methods have been extensively applied to whole slide histopathology image (WSI) analysis due the advantage of modeling spatial relationships among different entities. However, most existing focus on WSIs with homogeneous graphs (e.g., node type). Despite their successes, these works are incapable mining complex structural relations between biological entities diverse interaction cell types) in WSI. We propose a novel heterogeneous graph-based framework leverage...

The authors propose a novel class of cure rate models for right-censored failure time data. is formulated through transformation on the unknown population survival function. It includes mixture model and promotion as two special cases. general form covariate structure which automatically satisfies an inherent parameter constraint corresponding binomial exponential structures in main formulations models. proposed provides natural link between models, it offers wide variety new modelling well....

Summary A Bayesian adaptive design is proposed for dose‐finding in phase I/II clinical trials to incorporate the bivariate outcomes, toxicity and efficacy, of a new treatment. Without specifying any parametric functional form drug dose–response curve, we jointly model binary data account correlation between efficacy. After observing all responses each cohort patients, dosage next escalated, deescalated, or unchanged according odds ratio criteria constructed from posterior efficacy...

A single-institution Phase I clinical trial was conducted to determine the maximum tolerated dose (MTD) and define safety profile of temozolomide capecitabine when used in combination treat brain metastases from breast cancer.Patients were eligible if they had bidimensionally measurable supratentorial or infratentorial metastasis histologically confirmed carcinoma. Patients could have received up 3 prior chemotherapy regimens. Temozolomide administered concomitantly 4 sequential cohorts at...

AbstractWe propose a class of transformation models for survival data with cure fraction. The is motivated by biological considerations and includes both the proportional hazards odds as two special cases. An efficient recursive algorithm proposed to calculate maximum likelihood estimators (MLEs). Furthermore, MLEs regression coefficients are shown be consistent asymptotically normal, their asymptotic variances attain semiparametric efficiency bound. Simulation studies conducted examine...

We study quantile regression (QR) for longitudinal measurements with nonignorable intermittent missing data and dropout. Compared to conventional mean regression, can characterize the entire conditional distribution of outcome variable, is more robust outliers misspecification error distribution. account within-subject correlation by introducing a l(2) penalty in usual QR check function shrink subject-specific intercepts slopes toward common population values. The informative are assumed be...

Background Non-small cell lung cancer (NSCLC) represents the majority (85%) of cancers and is comprised mainly adenocarcinomas squamous carcinomas (SCCs). The sequential pathogenesis SCCs occurs through dissimilar phases as former tumors typically arise in periphery whereas latter normally near central airway. Methodology/Principal Findings We assessed expression SOX2, an embryonic stem transcriptional factor that also plays important roles proliferation basal tracheal cells whose restricted...

Two-agent combination trials have recently attracted enormous attention in oncology research. There are several strong motivations for combining different agents a treatment: to induce the synergistic treatment effect, increase dose intensity with nonoverlapping toxicities, and target tumor cell susceptibilities. To accommodate this growing trend clinical trials, we propose Bayesian adaptive design finding based on latent 2 x tables. In search maximum tolerated combination, continuously...

Summary In traditional phase I and II clinical trial designs, toxicity efficacy are often modelled as binary outcomes. Such methods ignore information on when the outcome event occurs, such experiencing or achieving cure remission. They also have difficulty accommodating a high accrual rate under which outcomes cannot be observed in timely manner, thus delay treatment assignment. To address these issues, we propose Bayesian adaptive I–II design that jointly models time-to-event At each...

Previous studies have evaluated 3-week and weekly docetaxel schedules in patients with metastatic breast cancer (MBC). The varying efficacy results toxicity profiles noted these earlier led to a comparison of the determine which was safer more efficacious.A phase 3 clinical trial conducted MBC who were treated either every weeks or once compare response rate duration, time disease progression, progression-free survival (PFS), overall (OS), toxicity. Patients randomized receive at starting...

In multiple change-point problems, different data segments often follow distributions, for which the changes may occur in mean, scale or entire distribution from one segment to another. Without need know number of change-points advance, we propose a nonparametric maximum likelihood approach detecting change-points. Our method does not impose any parametric assumption on underlying distributions sequence, is thus suitable detection distributions. The determined by Bayesian information...

Interval designs have recently attracted enormous attention due to their simplicity and desirable properties. We develop a Bayesian optimal interval design for dose finding in drug-combination trials. To determine the next combination based on cumulative data, we propose an allocation rule by maximizing posterior probability that toxicity rate of falls inside prespecified interval. The entire dose-finding procedure is nonparametric (model-free), which thus robust also does not require...

To accommodate the heterogeneity that is often present in ultrahigh-dimensional data, we propose a conditional quantile screening method, which enables us to select features contribute of response given covariates. The method can naturally handle censored data by incorporating weighting scheme through redistribution mass right; moreover, it invariant monotone transformation and requires substantially weaker conditions than do alternative methods. We establish sure independent properties for...

Summary We propose a randomized phase II clinical trial design based on Bayesian adaptive randomization and predictive probability monitoring. Adaptive assigns more patients to efficacious treatment arm by comparing the posterior probabilities of efficacy between different arms. continuously monitor using probability. The is terminated early when it shown that one overwhelmingly superior others or all treatments are equivalent. develop two methods compute considering uncertainty sample size...

Journal Article Outlier detection for high-dimensional data Get access Kwangil Ro, Ro Institute of Statistics, Nankai University, Tianjin 300071, China, rokwangil@yahoo.com.cnzjwang@nankai.edu.cn nk.chlzou@gmail.com Search other works by this author on: Oxford Academic Google Scholar Changliang Zou, Zou Zhaojun Wang, Wang Guosheng Yin Department Statistics and Actuarial Science, The University Hong Kong, Pokfulam Road, gyin@hku.hk Biometrika, Volume 102, Issue 3, September 2015, Pages...

ardiovascular trials often use the time to a clinical event as primary end point when evaluating new treatment, versus control, via and statistical significance criteria.For past 50 years, hazard ratio (HR) has been routinely used for quantifying treatment effect.However, it is difficult interpret using measure, such HR, there no reference available from control arm.Moreover, valid HR analysis requires proportional hazards (PH) assumption: that of curves constant over time.This assumption...