We provide an applied introduction to Bayesian estimation methods for empirical accounting research. To showcase the methods, we compare and contrast the estimation of accruals models via a Bayesian approach with the literature’s standard approach. The standard approach takes a given model of normal accruals for granted and neglects any uncertainty about the model and its parameters. By contrast, our Bayesian approach allows incorporating parameter and model uncertainty into the estimation of normal accruals. This approach can increase power and reduce false positives in tests for opportunistic earnings management as a result of better estimates of normal accruals and more robust inferences. We advocate the greater use of Bayesian methods in accounting research, especially since they can now be easily implemented in popular statistical software packages.

We use a simple k-nearest neighbors algorithm (hereafter, k-NN*) to forecast earnings. k-NN* forecasts of one-, two-, and three-year-ahead earnings are more accurate than those generated by popular extant forecasting approaches. k-NN* forecasts of two- and three-year (one-year)-ahead EPS and aggregate three-year EPS are more (less) accurate than those generated by analysts. The association between the unexpected earnings implied by k-NN* and the contemporaneous market-adjusted return (i.e., the earnings association coefficient (EAC)) is positive and exceeds the EAC on unexpected earnings implied by alternate approaches. A trading strategy that is long (short) firms for which k-NN* predicts positive (negative) earnings growth earns positive risk-adjusted returns that exceed those earned by similar trading strategies that are based on alternate forecasts. The k-NN* algorithm generates an empirically reliable ex ante indicator of forecast accuracy that identifies situations when the k-NN* EAC is larger and the k-NN* trading strategy is more profitable. Data Availability: Data are available from the public sources described in the text.