Skip to content

Robust probabilistic inference via a constrained transport metric

Notifications You must be signed in to change notification settings

zovialpapai/D-BETEL

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

33 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Computer code to reproduce the numerical results presented in "Robust probabilistic inference via a constrained transport metric" (Chakraborty A., Bhattacharya A., Pati D., 2023+). Please reach out in abhisek_chakraborty@tamu.edu for any queries. Here, we present a short decription about the scripts in the repository.

(1) Clustering: Find the R scripts to carry out model based clustering in presence of small perturbation of the data genration mechanism (a) based on Standard/Fractional Bayesian proccedure (FractionalPost_Clustering.R) and D-BETEL based methodology (DBETEL_Clustering.R). This can be utilised to re-produce the results presented in Section 3.1 of the paper.

(2) Generalised linear regression: Find the R scripts to carry out robust Poisson regression in presence of small perturbation of the data genration mechanism (a) based on Standard Bayesian proccedure, (b) D-BETEL based methodology (DBETEL_PoissonRegression.R), and (c) Bayesian exponentially tilted empirical likelihood based on moment conditional models (MCM_PoissonRegression.R). This can be utilised to re-produce the results presented in Section 3.2 of the paper.

(3) Demographic Parity: Find the R scripts to carry out D-BETEL based analysis of COMPAS data (DBETEL_DP_COMPAS.R), and DAIC (DBETEL_DP_DAIC.R) data that ensure statistical/demographic parity. This can be utilised to re-produce the results presented in Section 4 of the paper.

DATA AVAILABILITY: The popular COMPAS dataset includes detailed information on criminal history for the defendants in Broward County, Florida, freely available from https://www.propublica.org/datastore/dataset/compas-recidivism-risk-score-data-and-analysis.

The Distress Analysis Interview Corpus (DAIC) is a multi-modal collection of semi-structured clinical interviews, available upon request from https://dcapswoz.ict.usc.edu/.

About

Robust probabilistic inference via a constrained transport metric

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages