|
Activity Number:
|
382
- Novel Statistical Methodology for Insurance and Risk Management
|
|
Type:
|
Invited
|
|
Date/Time:
|
Tuesday, July 31, 2018 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Risk Analysis
|
|
Abstract #326493
|
Presentation
|
|
Title:
|
Maximum Likelihood Estimation of First-Passage Structural Credit Risk Models Correcting for the Survivorship Bias
|
|
Author(s):
|
Mathieu Boudreault* and Diego Amaya and Don L. McLeish
|
|
Companies:
|
Université du Québec à Montréal and Wilfrid Laurier University and University of Waterloo
|
|
Keywords:
|
survival bias;
geometric Brownian motion;
conditional estimation;
default probability;
inference;
diffusion processes
|
|
Abstract:
|
The survivorship bias in credit risk modeling is the bias that results in parameter estimates when the survival of a company is ignored. We study the statistical properties of the maximum likelihood estimator (MLE) accounting for survivorship bias for models based on the first-passage of the geometric Brownian motion. We find that if neglected, this bias always overestimates the drift and that it may not disappear asymptotically. We show that attempting to correct the bias by conditioning on survival in the likelihood function always underestimates the drift. Therefore, we propose a bias correction method for non-iid samples that is first-order unbiased and second-order efficient that we apply in this context. The economic impact of neglecting or miscorrecting for the survivorship bias is studied empirically based on a sample of more than 13,000 companies over the period 1980 through 2016 inclusive. Our results point to the important risk of misclassifying a company as solvent or insolvent due to biases in the estimates.
|
Authors who are presenting talks have a * after their name.
