Drug Demand Forecasting
Drug Demand Forecasting
Cumulative Dose
Drug Dispensing Model Fitting
Drug Dispensing Data Simulation
Drug Dispensing Data Simulation for One Iteration
Drug Dispensing Visit Dates Simulation for One Iteration
Dosing Date Imputation for New Patients
Observed Drug Dispensing Data Summary
Dosing Date Imputation for Ongoing Patients
Drug Demand Per Protocol
Drug Demand Forecasting
Model Fitting for Dispensed Doses
Model Fitting for Number of Skipped Visits
Model Fitting for Dispensing Delay After Randomization
Model Fitting for Gap Times
Observed Dosing for Ongoing and New Subjects
Random Number Generator for the Dirichlet Distribution
Performs drug demand forecasting by modeling drug dispensing data while taking into account predicted enrollment and treatment discontinuation dates. The gap time between randomization and the first drug dispensing visit is modeled using interval-censored exponential, Weibull, log-logistic, or log-normal distributions (Anderson-Bergman (2017) <doi:10.18637/jss.v081.i12>). The number of skipped visits is modeled using Poisson, zero-inflated Poisson, or negative binomial distributions (Zeileis, Kleiber & Jackman (2008) <doi:10.18637/jss.v027.i08>). The gap time between two consecutive drug dispensing visits given the number of skipped visits is modeled using linear regression based on least squares or least absolute deviations (Birkes & Dodge (1993, ISBN:0-471-56881-3)). The number of dispensed doses is modeled using linear or linear mixed-effects models (McCulloch & Searle (2001, ISBN:0-471-19364-X)).