Abstract
This article describes the use of flexible Bayesian regression models for estimating a partially identified probability function. Our approach permits efficient sensitivity analysis concerning the posterior impact of priors on the partially identified component of the regression model. The new methodology is illustrated on an important problem where only partially observed data are available—inferring the prevalence of accounting misconduct among publicly traded U.S. businesses. Supplementary materials for this article are available online.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 14-26 |
| Number of pages | 13 |
| Journal | Journal of the American Statistical Association |
| Volume | 111 |
| Issue number | 513 |
| DOIs | |
| State | Published - Jan 2 2016 |
| Externally published | Yes |
Fingerprint
Keywords
- Bayesian inference
- Nonlinear regression
- Partial identification
- Sampling bias
- Sensitivity analysis
- Set identification
ASJC Scopus subject areas
- Statistics and Probability
- Statistics, Probability and Uncertainty
Cite this
A Bayesian Partial Identification Approach to Inferring the Prevalence of Accounting Misconduct. / Hahn, Paul; Murray, Jared S.; Manolopoulou, Ioanna.
In: Journal of the American Statistical Association, Vol. 111, No. 513, 02.01.2016, p. 14-26.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - A Bayesian Partial Identification Approach to Inferring the Prevalence of Accounting Misconduct
AU - Hahn, Paul
AU - Murray, Jared S.
AU - Manolopoulou, Ioanna
PY - 2016/1/2
Y1 - 2016/1/2
N2 - This article describes the use of flexible Bayesian regression models for estimating a partially identified probability function. Our approach permits efficient sensitivity analysis concerning the posterior impact of priors on the partially identified component of the regression model. The new methodology is illustrated on an important problem where only partially observed data are available—inferring the prevalence of accounting misconduct among publicly traded U.S. businesses. Supplementary materials for this article are available online.
AB - This article describes the use of flexible Bayesian regression models for estimating a partially identified probability function. Our approach permits efficient sensitivity analysis concerning the posterior impact of priors on the partially identified component of the regression model. The new methodology is illustrated on an important problem where only partially observed data are available—inferring the prevalence of accounting misconduct among publicly traded U.S. businesses. Supplementary materials for this article are available online.
KW - Bayesian inference
KW - Nonlinear regression
KW - Partial identification
KW - Sampling bias
KW - Sensitivity analysis
KW - Set identification
UR - http://www.scopus.com/inward/record.url?scp=84969822622&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84969822622&partnerID=8YFLogxK
U2 - 10.1080/01621459.2015.1084307
DO - 10.1080/01621459.2015.1084307
M3 - Article
AN - SCOPUS:84969822622
VL - 111
SP - 14
EP - 26
JO - Journal of the American Statistical Association
JF - Journal of the American Statistical Association
SN - 0162-1459
IS - 513
ER -