Standardized earnings exceeded expectations
factor.formula
Standardized Earning Surprise:
Median Absolute Deviation (MAD):
Robust Standard Deviation Estimation (Robust Standard Deviation Estimation, $\bar{\sigma}$):
in:
- :
The actual announced earnings per share (EPS). Using EPS instead of earnings allows for better comparison of companies of different sizes and reduces the impact of company size on the factor.
- :
Analyst consensus EPS Estimate. Consensus EPS Estimate represents the market's average view of a company's earnings, usually using the average of multiple analysts' forecasts.
- :
Robust standard deviation estimate of the company's net profit per share over the past five years. Calculated using the median absolute deviation (MAD) to reduce the impact of extreme values (such as one-time gains and losses) on the standard deviation estimate and improve factor robustness.
- :
A sample of historical data on the company's net profit per share over the past five years.
- :
The median of the company's historical data sample of net profit per share over the past five years is used to calculate the central value of MAD.
- :
The scaling factor constant used to convert the MAD to an estimate of the standard deviation. For data that is approximately normally distributed, k is usually taken to be approximately 1.4826, which is derived from the relationship between the MAD and the standard deviation of the normal distribution, and can make the MAD better approximate the standard deviation.
factor.explanation
The standardized earnings surprise factor reflects the market's reaction to a company's earnings information by measuring the deviation between actual earnings and expected earnings and standardizing it using a robust standard deviation estimate. A positive factor value indicates that a company's earnings exceed market expectations, which may lead to an increase in stock prices, while a negative value may lead to a decrease in stock prices. This factor can be used in quantitative investment to screen stocks with the potential to exceed earnings expectations, build multi-factor models, and conduct event-driven trading. This factor takes into account the unexpectedness of earnings information and has more predictive power than a single earnings indicator.