Attached files contain the estimation code for the paper: "The Commercial Contribution of Clinical Studies for Pharmaceutical Drugs." It contains the following files with R-code. 1) Simulated_Data.R: This contains the simulated data to test the model we use in the paper. 2) HB_Linear_Model.R: This contains the estimation code for a hierarchical Bayesian linear model with a Metropolis-Hastings step. 3) GIRFs.R: This files contains the code to calculate level impulse response functions for the endogenous variables (and the clinical study metrics) based on Wieringa and Horvath (2005). The first two files are adapted from the bayesm package in R and see Rossi (2012) for more documentation on Bayesian estimation in R. References: Rossi, P. (2012). Bayesm: Bayesian inference for marketing/micro-econometrics. R package version 2.2.4. Wieringa, J. E., & Horváth, C. (2005). Computing level-impulse responses of log-specified VAR systems. International Journal of Forecasting, 21(2), 279-289.
Oxford Bulletin of Economics and Statistics (2022)
Matsuoka Hideaki