Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
This paper presents a methodology for estimating time-homogeneous credit quality transition matrices. Using a unique data set on credit ratings of commercial loans in Colombia, we show that 70% of the time we cannot reject the null hypothesis of time homogeneity of transition matrices estimated this way. We also find that obtaining matrices for different subsamples is not necessary, given the similarities of the survival functions.