The Paired Availability Design and Related Instrumental Variable Meta-analyses

By Stuart G. Baker, 2017


This software computes meta-analysis and extrapolation estimates for an instrumental variable meta-analysis of randomized trial or before-and-after studies (the latter also known as the paired availability design). The software also checks on the assumptions if sufficient data are available.


Baker SG and Lindeman KL Revisiting a discrepant result: a propensity score analysis, the paired availability design for historical controls, and a meta-analysis of randomized trials, Journal of Causal Inference 2013; 1:51–82; correction 2014:113.

Requirement:  Mathematica Version 11 or later

To run the program

copy all files into some folder called "FOLDER"
start a new Mathematica session
type   SetDirectory["FOLDER"]
type <<pfit.m
type initially to generate symbolic results PFit[dataset, options]

Key Function: PFit[dataset] where
dataset={data, names of studies, name of data set, label for x-axis, label for y-axis}
with -1 denoting a missing value for c00, c01,c10,c11

n0 Number in group 0 (control or before group)
e0 Number receiving treatment in group 0
c00 Number in group 0 receiving no treatment with outcome 1
c01 Number in group 0 receiving treatment with outcome 1
c0 Number in group 0 with outcome 0
n1 Number in group 1 (experimental or after group)
e1 Number receiving treatment in group 1
c10 Number in group 1 receiving no treatment with outcome 1
c11 Number in group 1 receiving treatment with outcome 1
c1 Number in group 1 with outcome 1
Option Default Explanation
ShowTables False Prints table of data and table of basic estimates
ShowExtrapolation False Plots extrapolation estimates using regression models

File Contents

Download All (ZIP, 10 KB)

pfit.m main package
pfitmeta meta-analysis
pfitreg regression extrapolation
pfitplot plotting function
pfitdata data for epidural analgesia example


This code is provided "as is", without warranty of any kind, express or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose and non-infringement. In no event shall the NCI or the individual developers be liable for any claim, damages or other liability of any kind. Use of this code by recipient is at recipient's own risk. NCI makes no representations that the use of the code will not infringe any patent or proprietary rights of third parties.

Last updated: April 30, 2018