Earnings Surprises and Signal Analysis matt mcConnell David Nabwangu Eskil Sylwan Johnson Yeh
Agenda Background Hypothesis Methodology Data Fitting Explanatory Variables Regression Results Conclusion
Market Reaction to News We expect stock price to react to news like this: In a More Realistic World In an Ideal World Reality Delay Overshoot Settling Time Announcement Date
Step Response of a Second-Order System Parameter Effect Initial Level Level before reaction begins Offset Beginning of reaction Magnitude Size of reaction ωn Shape of curve ωd ζ + -
Hypothesis Abnormal returns after earnings surprises follow a curved pattern which can be modeled using the step response of a second-order system 6 Curve parameters are predictable using information about the company * Results could be applicable to any news item – earnings are measurable
Methodology Identify earnings surprises (Factset) 600 events, 100 companies Retrieve price and other data series (Datastream) Calculate abnormal returns in ±30 day window Fit a curve to each event Least squares method with solver 6 parameters for each event Regress 6 parameters on several explanatory variables
Fitting the Data Average Correlation = 80% In some instances the data fit very well In some instances fit not good Correlation = 91.6% Average Correlation = 80% Correlation = 70%
Explanatory Variables 6 explanatory variables for curve parameters Quarterly Earnings Surprise % Positive influence on magnitude, Zeta 1-Year Price Growth Negative Impact on Offset, Positive Impact on Magnitude, and Zeta Quarterly Earnings Surprise $ Positive Impact on Magnitude, Zeta Price to Earnings Ratio Positive Impact on Offset, Negative Impact on Zeta Beta Positive Impact on wm, wd, & Magnitude 10-Day Abnormal Return Negative Impact on Magnitude
Regression Results
Conclusion Holds promise: Some predictive power Paths forward: Better fitting method Least squares method more applicable to linear Improve predictive regressions More predictor variables Non-linear predictor variables Test predictability over time Larger data set Create and test trading strategies