Earnings Volatility
factor.formula
First-order autoregressive model of annual returns:
Earnings volatility:
in:
- :
The annual earnings measure for company j in year t, usually earnings per share (EPS) or net profit, but other measures of profitability may also be used. The choice depends on the needs of the strategy and data availability.
- :
The constant term in the first-order autoregressive model of firm j represents the benchmark return level without the influence of previous period returns.
- :
The first-order autoregression coefficient of company j indicates the degree of influence of the previous year's earnings on the current year's earnings. This coefficient reflects the persistence of earnings. The higher the value, the stronger the autocorrelation of earnings.
- :
The residual (or error term) of the earnings model for firm j in year t represents the portion of earnings volatility that the model fails to explain, reflecting the randomness of earnings.
- :
The estimated value of the variance of the residual of the first-order autoregressive model of company j indicates the degree of volatility of the error term. It is a measure of the degree of dispersion of the error term.
- :
The estimate of the standard deviation of the residuals from the first-order autoregressive model for company j is the square root of the residual variance, which directly reflects the volatility not explained by the earnings forecasting model. It is the ultimate measure of earnings volatility.
factor.explanation
The lower the value of the Earnings Volatility Factor, the smaller the volatility of the company's historical earnings, the higher the predictability of earnings, and the more stable the operating performance. Conversely, the higher the value, the greater the volatility of the company's earnings, the lower the predictability of earnings, and the more unstable the operating performance. This factor can be used to screen companies with stable operating performance and high earnings quality. In quantitative investment strategies, you can build a long-short portfolio, go long on low-volatility companies and short on high-volatility companies. It should be noted that this factor is calculated based on historical data, and future earnings volatility may differ from historical situations. In addition, different earnings indicators (EPS, net profit, etc.) may result in slightly different factor values.