Analysts' perceptions of 'earnings quality'

This paper examines sell-side analysts' perceptions of 'earnings quality'. Prior research suggests that analysts' stock recommendations, price targets, earnings forecasts and written reports are relevant to share price formation. One of the main inputs in analysts' forecasting and valuation models is earnings, and analysts' perceptions of earnings quality are therefore important. There is, however, little direct evidence in the literature on what these perceptions are and on what role they have in decision-making. This paper seeks first to understand earnings quality as interpreted by analysts, and it then tests this interpretation against its actual usage in analysts' research reports. An inductive approach is used that combines interview data with content analysis, and the findings are interpreted in the light of findings from market-based and other research. We find that the concept of earnings quality is both accounting-based (relating to notions of core or sustainable earnings, cash and accrual components of earnings, and accounting policies) and non-accounting-based (relating to information drawn from outside the financial statements). We find more non-accounting than accounting references to earnings quality, and that (relatively subjective) non-accounting references are especially widely used where analysts express positive or negative opinions about earnings quality. It is relatively unusual for an analyst's opinion to be both negative and accounting-based. If, however, an analyst does express negative, accounting-based views on earnings quality, then he or she is highly unlikely to be positive in other respects. We interpret this evidence to be consistent with analysts' economic incentives to generate trading volume yet to be favourably biased towards companies, while seeking to use value-relevant information relating to earnings. We also conclude that the importance of accounting-based information relating to earnings quality is more important than it might seem, and that it exerts a significant influence on the analysis and recommendations in analysts' reports.