A5046198636- Advanced Causal Inference Techniques
- Statistical Methods and Bayesian Inference
- Statistical Methods in Clinical Trials
- Statistical Methods and Inference
- Parkinson's Disease Mechanisms and Treatments
- COVID-19 Pandemic Impacts
- COVID-19 epidemiological studies
- Health Systems, Economic Evaluations, Quality of Life
- Mobile Health and mHealth Applications
- Cerebral Palsy and Movement Disorders
- Data Analysis with R
- Cancer survivorship and care
- Allergic Rhinitis and Sensitization
- Balance, Gait, and Falls Prevention
- Inhalation and Respiratory Drug Delivery
- Clostridium difficile and Clostridium perfringens research
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Public Relations and Crisis Communication
- Asthma and respiratory diseases
- Statistics Education and Methodologies
- Media Influence and Politics
- Gastrointestinal motility and disorders
Bucknell University
2022
Simmons University
2018-2022
FOM University of Applied Sciences for Economics and Management
2022
Randomized clinical trials are ideal for estimating causal effects, because the distributions of background covariates similar in expectation across treatment groups. When effects using observational data, matching is a commonly used method to replicate covariate balance achieved randomized trial. Matching algorithms have rich history dating back mid‐1900s but been mostly estimate between two there more than treatments, requires additional assumptions and techniques. We propose several novel...
Abstract Several inefficiencies in drug development trial implementation may be improved by moving data collection from the clinic to mobile, allowing for more frequent measurements and therefore increased statistical power while aligning a patient‐centric approach design. Sensor‐based digital health technologies such as mobile spirometry (mSpirometry) are comparable capturing outcomes, forced expiratory volume 1 s (FEV1); however, impact of remote on detection treatment effect has not been...
Matching estimators for average treatment effects are widely used in the binary setting, which missing potential outcomes imputed as of observed all matches each unit. With more than two groups, however, estimation using matching requires additional techniques. In this paper, we propose a nearest-neighbors estimator use with multiple, nominal treatments, and simulations to show that method is precise has coverage levels close nominal. addition, implement proposed inference methods examine...
Introduction Parkinson's Disease affects over 8.5 million people and there are currently no medications approved to treat underlying disease. Clinical trials for disease modifying therapies (DMT) hampered by a lack of sufficiently sensitive measures detect treatment effect. Reliable digital assessments motor function allow frequent at-home measurements that may be able sensitively progression. Methods Here, we estimate the test-retest reliability suite derived from raw triaxial accelerometry...
592 Background: There is an unmet need for measures that predict adverse events during cancer therapy. Previous studies have demonstrated feasibility and value of collecting physical activity (PA) data from patients undergoing curative-intent chemoradiotherapy using a commercial fitness tracker. Here, we compare the predictive objective PA versus standard clinical information assess whether additional beyond daily step count help hospitalization treatment. Methods: Cancer enrolled in...
Randomized clinical trials are considered as the gold standard for estimating causal effects. Nevertheless, in studies that aimed at examining adverse effects of interventions, randomized often impractical because ethical and financial considerations. In observational studies, matching on generalized propensity scores was proposed a possible solution to estimate treatment multiple interventions. However, derivation point interval estimates these procedures can become complex with...
A modern statistics or data science course aims to equip students with both conceptual and computing skills. This is a challenging task as instructors do not want increase students’ cognitive load new tools technical details have balance limited teaching time help in achieving the learning outcomes of content tool use. Interactive tutorials, built R package learnr, can support student progressive reveal content, interactive code exercises, quizzes automatic feedback, an interface potential...
Introduction: Fecal microbiota transplantation (FMT) has emerged as a definitive treatment option for recurrent Clostridium difficile infection (CDI). Post-infection Irritable Bowel Syndrome (IBS) is common complication after infectious gastroenteritis and frequently observed CDI. We aimed to examine the prevalence of IBS symptoms FMT CDI in patients with without prior diagnosis. Methods: Patients who had between August 2011 October 2017 at The Miriam Hospital (TMH) Brigham Woman’s (BWH)...
Randomized clinical trials (RCTs) are ideal for estimating causal effects, because the distributions of background covariates similar in expectation across treatment groups. When effects using observational data, matching is a commonly used method to replicate covariate balance achieved RCT. Matching algorithms have rich history dating back mid-1900s, but been mostly estimate between two there more than treatments, requires additional assumptions and techniques. We propose that address...
Matching estimators for average treatment effects are widely used in the binary setting, which missing potential outcomes imputed as of observed all matches each unit. With more than two groups, however, estimation using matching requires additional techniques. In this paper, we propose a nearest-neighbors estimator use with multiple, nominal treatments, and simulations to show that method is precise has coverage levels close nominal. addition, implement proposed inference methods examine...
Randomized clinical trials are considered the gold standard for estimating causal effects. Nevertheless, in studies that aimed at examining adverse effects of interventions, such often impractical because ethical and financial considerations. In observational studies, matching on generalized propensity scores was proposed as a possible solution to estimate treatment multiple interventions. However, derivation point interval estimates these procedures can become complex with non-continuous or...
This paper segments the 50 American states by COVID-19 vaccination rates, Big Five personality traits, religiosity, and 2020 presidential election voting patterns to understand as with unique characteristics that make them receptive persuasive appeals. We collected data state of average information, percentage vote for Biden, governors' political affiliation. Next, we deployed a two-step cluster analysis method where first used distance measure separate groups then probabilistic approach...