The International Journal of Accounting

I provide a framework that will help evaluate the value of for replication studies. I then provide a discussion of the fourm papers.

Most quasi-experimental empirical analyses in accounting involve determining a set of sample selection criteria and then applying these criteria to obtain an exhaustive sample for analysis. By including all available observations, one might reasonably view such analyses as population studies. In this paper, I propose a structure and provide related interpretive guidance for conducting intentional, focused replications of population analyses defined by such sample selection criteria.

Stock returns are decomposed into their regular and outlier components using a maximum likelihood outlier-resistant estimation method. Analytical results depicting the impact of outliers on the ordinary least square (OLS) estimated models and cumulative abnormal return (CAR) statistics are derived and validated using Monte Carlo simulations. The implications of outliers for past event studies are investigated using samples drawn randomly from the universe of stocks in the CRSP database. The OLS-CAR statistics fail to forecast about 37% of the negative-impact and 43% of the positive-impact events. These results raise serious concerns about the validity of conclusions of past event studies, especially those that rejected the hypothesis of significant-impact events.

Empirical research analyzes real-life data that often do not conform to a normal distribution with statistical tools such as linear regressions that require the assumption of normality. The lack of conformity to a known statistical distribution requires researchers to handle outliers properly. Accounting studies typically treat outliers with a “delete-and-forget” approach, which assumes that extreme values are erroneous and results remain insensitive to the deletion of a small number of observations. Results in this study refute these assumptions by showing that the ambiguity in handling outliers and variable selection motivates researchers to explore various analytic alternatives, which in turn produce unstable regression coefficients and heightened false-positive rates.

This paper investigates whether a consideration of linguistic history is important when studying the relationship between economic and linguistic behaviors. Several recent economic studies have suggested that differences between languages can affect the way people think and behave (linguistic relativity or Sapir–Whorf hypothesis). For example, the way a language obliges one to talk about the future might influence intertemporal decisions, such as a company’s earnings management. However, languages have historical relations that lead to shared features—they do not constitute independent observations. This can inflate correlations between variables if not dealt with appropriately (Galton’s problem). We discuss this problem and provide an overview of the latest methods to control linguistic history. We then provide an empirical demonstration of how Galton’s problem can bias results in an investigation of whether a company’s earnings management behavior is predicted by structural features of its employees’ language. We find a strong relationship when not controlling linguistic history, but the relationship disappears when controls are applied. In contrast, economic predictors of earnings management remain robust. Overall, our results suggest that careful consideration of linguistic history is important for distinguishing true causes from spurious correlations in economic behaviors.

This study aims to replicate the analysis of the relationship between earnings quality and cost of equity in the Italian context, a context characterized by high ownership concentration and weak investor protection dominated by the type II agency problem. We hypothesize a different intensity of the earnings quality–cost of equity relation between concentrated-held firms and dispersed-held ones. The analysis is based on a sample of 774 firm-year observations from 128 Italian nonfinancial listed firms, from 2011 to 2017. Empirical results confirm the existence of a negative relationship between earnings quality and cost of equity. Moreover, findings show that in Italy, this relation is stronger for firms with concentrated ownership and weaker for firms with more dispersed ownership. Consistent with our hypothesis, this finding suggests that ownership structure affects the sensitivity of the earnings quality–cost of equity relationship.