TY - JOUR TI - Enhancing empirical accounting models with textual information DO - https://doi.org/doi:10.7282/T3DF6PG4 PY - 2014 AB - Rapid developments in information technologies and the increased availability of narrative disclosures in electronic form have provoked interest in textual analysis. In this dissertation, we survey research on textual analysis of mandatory and voluntary disclosures, describe methodologies for analyzing and incorporating text into quantitative models, and provide an analysis of MD&A text and earnings. Most empirical studies examine the association between text characteristics (e.g., tone and linguistic complexity) and future firm performance or market reactions. However, in-sample explanatory power is not equivalent to out-of-sample predictive power (Shmueli, 2010). We use regularized regression methods to examine whether textual disclosures in the Management Discussion and Analysis (MD&A) section of the 10-K report are helpful in predicting future earnings above and beyond traditional financial factors. We develop techniques to combine textual information from the MD&A section of the annual report with financial variables and generate explicit firm-level forecasts of future earnings. We employ the “bag-of-words” (BOW) approach to represent MD&A sections numerically and regularized regression methods to overcome problems of high-dimensionality and multicollinearity of data. We estimate and earnings forecasting models based solely on quantitative factors and compare them with models that include both quantitative information from financial statements and textual information from MD&A disclosures. We find that text-enhanced models are more accurate than models using quantitative financial variables alone. This supports the notion that the MD&A section has predictive value, one of the primary characteristics of relevance. Firms with larger changes in future performance, negative changes in future performance, higher accruals, greater market capitalization, and lower Z-scores have more informative MD&As, suggesting that MD&A content helps to reduce uncertainty. The MD&A is more informative in the period following recent regulatory reforms but less informative in the period covering the recent financial crisis, suggesting that managers may be unable to provide a reliable analysis of the business of the company in unstable economic periods. Finally, we show that financial analysts lose their forecasting superiority over text-enhanced statistical models for smaller firms and those with lower analyst following. KW - Management KW - Data transmission systems KW - Electronic data interchange LA - eng ER -