Robust and consistent estimation of generators in credit risk
From MaRDI portal
Publication:4554476
Abstract: Bond rating Transition Probability Matrices (TPMs) are built over a one-year time-frame and for many practical purposes, like the assessment of risk in portfolios or the computation of banking Capital Requirements (e.g. the new IFRS 9 regulation), one needs to compute the TPM and probabilities of default over a smaller time interval. In the context of continuous time Markov chains (CTMC) several deterministic and statistical algorithms have been proposed to estimate the generator matrix. We focus on the Expectation-Maximization (EM) algorithm by Bladt and Sorensen (2005) for a CTMC with an absorbing state for such estimation. This work's contribution is threefold. Firstly, we provide directly computable closed-form expressions for quantities appearing in the EM algorithm and associated information matrix, allowing to easily approximate confidence intervals. Previously, these quantities had to be estimated numerically and considerable computational speedups have been gained. Secondly, we prove convergence to a single set of parameters under very weak conditions (for the TPM problem). Finally, we provide a numerical benchmark of our results against other known algorithms, in particular, on several problems related to credit risk. The EM algorithm we propose, padded with the new formulas (and error criteria), outperforms other known algorithms in several metrics, in particular, with much less overestimation of probabilities of default in higher ratings than other statistical algorithms.
Recommendations
- An extended likelihood framework for modelling discretely observed credit rating transitions
- scientific article; zbMATH DE number 5010403
- Estimating rating transition probabilities with missing data
- Capturing model risk and rating momentum in the estimation of probabilities of default and credit rating migrations
- A simple Markov chain structure for the evolution of credit ratings
Cites work
- scientific article; zbMATH DE number 5010403 (Why is no real title available?)
- scientific article; zbMATH DE number 472922 (Why is no real title available?)
- scientific article; zbMATH DE number 1834445 (Why is no real title available?)
- scientific article; zbMATH DE number 1867247 (Why is no real title available?)
- scientific article; zbMATH DE number 849920 (Why is no real title available?)
- A dependent hidden Markov model of credit quality
- A note on parameter differentiation of matrix exponentials, with applications to continuous-time modelling
- Asymptotic normality for discretely observed Markov jump processes with an absorbing state
- Computing integrals involving the matrix exponential
- Consistent estimation for discretely observed Markov jump processes with an absorbing state
- Direct Calculation of the Information Matrix via the EM Algorithm
- Exponential Operators and Parameter Differentiation in Quantum Physics
- Exponential families of stochastic processes
- Finding generators for Markov chains via empirical transition matrices, with applications to credit ratings
- Markov Chains
- Maximum‐likelihood estimation for constrained‐ or missing‐data models
- ON LIKELIHOOD ESTIMATION FOR DISCRETELY OBSERVED MARKOV JUMP PROCESSES
- On the Existence and Uniqueness of the Real Logarithm of a Matrix
- On the convergence properties of the EM algorithm
- Regulatory capital modeling for credit risk
- Robustness and sensitivity analysis of risk measurement procedures
- Statistical Inference for Discretely Observed Markov Jump Processes
- Summary Statistics for Endpoint-Conditioned Continuous-Time Markov Chains
- The Calculation of Posterior Distributions by Data Augmentation
- The EM Algorithm and Extensions, 2E
- The Logarithm Function for Finite-State Markov Semi-Groups
Cited in
(12)- Predicting forward default probabilities of firms: a discrete-time forward hazard model with firm-specific frailty
- Predicting credit ratings and transition probabilities: a simple cumulative link model with firm-specific frailty
- The robustness of simulation-based Markovian transition probabilities for ultra-small samples of non-performing credit
- The new robust conic GPLM method with an application to finance: prediction of credit default
- Bank-sourced credit transition matrices: estimation and characteristics
- Estimating rating transition probabilities with missing data
- Statistical inference for Markov chains with applications to credit risk
- Evolutionary optimization of transition probability matrices for credit decision-making
- An extended likelihood framework for modelling discretely observed credit rating transitions
- Capturing model risk and rating momentum in the estimation of probabilities of default and credit rating migrations
- scientific article; zbMATH DE number 5723918 (Why is no real title available?)
- On the estimation of partially observed continuous-time Markov chains
This page was built for publication: Robust and consistent estimation of generators in credit risk
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4554476)
