Statistics

This folder commits to the application of biostatistics knowledge on clinical, randomized trials and observational studies. Goals include:

• write a good statistical analysis plan
• understand the obstacles when dealing real-world data
• apply biomedical/research statistical analyses
• excel various analytical models

Code and raw datasets are placed in this Github repository

• Logistic Regression:
  • analytics: logistic regression model, build & interpretation
  • data source: Framingham longitudinal heart study
  • research question: Does quitting smoking reduce the likelihood of incident cardiovascular disease?
• Survey Analysis:
  • analytics: survey data analysis with weights
  • data source: National Health and Nutrition Examination Survey (NHANES) 2017-2018 data
  • research question: Is vaping associated with increased blood lead levels? Is there effect modification by age or gender?
• Longitudinal Analysis:
  • analytics: longitudinal data analysis & missing data imputation
  • data source: longitudinal data from study “A Phase 3 placebo-controlled, double-blind, multi-site trial of the alpha-2-adrenergic agonist, lofexidine, for opioid withdrawal”
  • research question:
    • Is there group difference between the treatment group and placebo group with respect to MHOWS (parallel group response profiles)?
    • Is there any time effect?
• Propesity Score Matching Analysis:
  • analytics: propensity score matching and outcome analysis
  • data source: National Health and Nutrition Examination Survey Data I Epidemiologic Follow Up Study (NHEFS) 1971&1982 follow-up data
  • research question: Is there an effect of smoking cessation on weight gain?
• Survival Analysis:
  • analytics: survival analysis, Cox proportional hazards model
  • data source: simulated Ebola epidemic data
  • research question: is gender, age a risk factor for Ebola survivability?