Replication Data *Corresponding author.
Bankers, Bureaucrats, and Central Bank Politics: The Myth of Neutrality, Cambridge University Press, 2013.
Version 0.1, May 2013
Note: This entry will eventually contain complete replication data for all chapters of BBC. For the moment, replication data and notes are only available for the second part of Chapter 4 (regression models of FOMC members’ dissenting votes and ideal interest rates). If you have urgent need of data for other chapters, please contact me.
Allocation of Authority in European Health Policy, Social Science and Medicine, 2012, Vol. 75(9): 1595–1603.
Version 1.0, August 2012 (publication version)
Adolph, Greer, and Massard (2012; hereinafter agm) comprehensively account for the allocation of authority for various areas and instruments of health policy to different levels of government, and use a Bayesian multilevel multinomial logit model to explore how economic and political forces shape these allocations of authority (see Adolph, Greer, and Massard 2012 for further details). The agm data is available here , and a codebook is forthcoming. The complete replication code, including all R and WinBUGS helper files and intermediate estimation results, is available here . Replicators should begin by exploring the aahp.r command script.
Getting Ahead in the Communist Party: Explaining the Advancement of Central Committee Members in China, American Political Science Review, 2012, Vol. 106(1).
Version 1.0, March 2012 (publication version)
Victor Shih, Christopher Adolph*, and Mingxing Liu
Shih, Adolph, and Liu (2012; hereinafter sal) use original data from Shih, Shan, and Liu (2008; archived below) to examine the relationship between partially observed ranks in the Chinese Communist Party (ccp) and various individual-level covariates describing official’s demographics, education, past performance, and factional ties (see Shih, Adolph, and Liu 2012 for further details). This page archives replication data and R scripts for the baseline Bayesian partial rank models estimated in this article.
sal separately analyzed data from the 12th, 13th, 14th, 15th and 16th Party Congresses; these data are available in five comma-separated variable files. Details and replication scripts for the construction of these files from the underlying Shih, Shan, and Liu data are available on request.
Before you replicate the main results in sal, you will need the above data, an installation of R version 2.12.2 or higher, a number of packages available from cran (specifically, car, RColorBrewer, and WhatIf, as well as many dependencies), and the partialrank and tile packages (available from the Software page of this website).
To replicate the baseline analyses presented in Figures 1 through 3 of sal, you will first need to run these R scripts, which estimate the model and quantities of interest. I recommend creating a separate folder to contain the code, data, and output for each run; this folder must also contain the two helper scripts listed below. The analysis scripts will take some time to run even on a fast processor; half a day each would not be unusual.
After running the analysis scripts, you can recreate (approximations) of Figures 2 and 3 using the scripts below. Note that you will need to modify the graphing scripts to point to the correct folders containing your results from the analysis scripts.
To obtain replication materials for the robustness checks (including the multiple imputation, factor analyses, and time series models discussed in the Web Appendix to sal), or if you encounter any problems with these replication scripts, please contact the corresponding author.
Stand-alone Data *Corresponding author.
Biographical Data of Central Committee Members: First to Sixteenth Party Congress.
version 1.0, January 2008
Victor Shih*, Wei Shan, and Mingxing Liu
|Department of Political Science Center for Statistics and the Social Sciences||Copyright 2011–2014 Privacy · Terms|
Design: Chris Adolph and Erika Steiskal