Replication Data for: Using Supervised Learning to Select Audit Targets in Performance-Based Financing in Health: An Example from Zambia (doi:10.7910/DVN/LHUIBO)

View:

Part 1: Document Description
Part 2: Study Description
Part 5: Other Study-Related Materials
Entire Codebook

Replication Data for: Using Supervised Learning to Select Audit Targets in Performance-Based Financing in Health: An Example from Zambia

doi:10.7910/DVN/LHUIBO

Harvard Dataverse

2018-12-14

1

Grover, Dhruv; Bauhoff, Sebastian; Friedman, Jed, 2018, "Replication Data for: Using Supervised Learning to Select Audit Targets in Performance-Based Financing in Health: An Example from Zambia", https://doi.org/10.7910/DVN/LHUIBO, Harvard Dataverse, V1

Replication Data for: Using Supervised Learning to Select Audit Targets in Performance-Based Financing in Health: An Example from Zambia

doi:10.7910/DVN/LHUIBO

Grover, Dhruv (University of California, San Diego)

Bauhoff, Sebastian (Center for Global Development)

Friedman, Jed (World Bank)

Harvard Dataverse

Bauhoff, Sebastian

Bauhoff, Sebastian

2018-12-14

https://doi.org/10.7910/DVN/LHUIBO

Social Sciences, Health Policy, Pay for Performance, Audit

Independent verification is a critical component of performance-based financing (PBF) in health care, in which facilities are offered incentives to increase the volume of specific services but the same incentives may lead them to over-report. We examine alternative strategies for targeted sampling of health clinics for independent verification. Specifically, we empirically compare several methods of random sampling and predictive modeling on data from a Zambian PBF pilot that contains reported and verified performance for quantity indicators of 140 clinics. Our results indicate that machine learning methods, particularly Random Forest, outperform other approaches and can increase the cost-effectiveness of verification activities.

<a href="http://creativecommons.org/publicdomain/zero/1.0">CC0 1.0</a>

Grover, Dhruv; Bauhoff, Sebastian & Friedman, Jed "Using supervised learning to select audit targets in performance-based financing in health: An example from Zambia" CGD Working Paper 481

Grover, Dhruv; Bauhoff, Sebastian & Friedman, Jed "Using supervised learning to select audit targets in performance-based financing in health: An example from Zambia" CGD Working Paper 481

Label:

Zambia_data dictionary.docx

application/vnd.openxmlformats-officedocument.wordprocessingml.document

Label:

Zambia_data.xlsx

application/vnd.openxmlformats-officedocument.spreadsheetml.sheet

Label:

license.txt

text/plain

Label:

README.txt

text/plain

Label:

oneHotDecode.m

text/plain; charset=US-ASCII

Label:

oneHotEncode.m

text/plain; charset=US-ASCII

Label:

parseData.m

text/plain; charset=US-ASCII

Label:

readData.m

text/plain; charset=US-ASCII

Label:

computeFoldSizes.m

text/plain; charset=US-ASCII

Label:

getFoldVectors.m

text/x-matlab

Label:

getVecsPerCat.m

text/plain; charset=US-ASCII

Label:

mainCrossVal.m

text/plain; charset=US-ASCII

Label:

randSortAndGroup.m

text/plain; charset=US-ASCII

Label:

README.txt

text/plain

Label:

computeF1.m

text/plain; charset=US-ASCII

Label:

computePR.m

text/plain; charset=US-ASCII

Label:

computeROC.m

text/plain; charset=US-ASCII

Label:

plotPR.m

text/plain; charset=US-ASCII

Label:

plotROC.m

text/plain; charset=US-ASCII

Label:

computeRS.m

text/plain; charset=US-ASCII

Label:

computeSRSbyDistrict.m

text/plain; charset=US-ASCII

Label:

computeSRSbyRbf.m

text/plain; charset=US-ASCII

Label:

predictML.m

text/plain; charset=US-ASCII

Label:

trainLR.m

text/plain; charset=US-ASCII

Label:

trainNB.m

text/plain; charset=US-ASCII

Label:

trainRF.m

text/plain; charset=US-ASCII

Label:

trainSVM.m

text/plain; charset=US-ASCII

Label:

bayesOptRF.m

text/plain; charset=US-ASCII

Label:

oobErrRF.m

text/plain; charset=US-ASCII

Label:

plotParamsRF.m

text/plain; charset=US-ASCII