Stock-selection timing test – bootstrapping approach
| Bottom t-statistics of i | Top t-statistics of i | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| 1% | 5% | 10% | 25% | 75% | 90% | 95% | 99% | ||
| All funds | t | −4.79 | −3.63 | −2.04 | −1.09 | 1.59 | 3.04 | 4.59 | 6.08 |
| p | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | |
| UK | t | −4.53 | −3.15 | −1.73 | −0.89 | 1.73 | 3.37 | 4.80 | 6.32 |
| p | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | |
| France | t | −5.36 | −4.73 | −2.66 | −1.49 | 1.28 | 2.09 | 4.19 | 4.69 |
| p | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | |
| Germany | t | −5.28 | −4.46 | −2.81 | −1.52 | 1.31 | 2.12 | 4.03 | 4.77 |
| p | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | |
| Bottom | Top | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| 1% | 5% | 10% | 25% | 75% | 90% | 95% | 99% | ||
| All funds | −4.79 | −3.63 | −2.04 | −1.09 | 1.59 | 3.04 | 4.59 | 6.08 | |
| 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | ||
| UK | −4.53 | −3.15 | −1.73 | −0.89 | 1.73 | 3.37 | 4.80 | 6.32 | |
| 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | ||
| France | −5.36 | −4.73 | −2.66 | −1.49 | 1.28 | 2.09 | 4.19 | 4.69 | |
| 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | ||
| Germany | −5.28 | −4.46 | −2.81 | −1.52 | 1.31 | 2.12 | 4.03 | 4.77 | |
| 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | ||
Note(s): The table above presents the bootstrapped p-values associated with the Newey-West t-statistics of the stock-selection timing coefficients in the bottom, top, and extreme percentiles. The Newey-West t-statistics of the stock-selection timing coefficients gi are estimated using the following cross-sectional equation: ACTi,t = ci + giSSOt+1 + εi,t+1, where ACTi,t denotes the active share in monthly period t and SSOt+1 represents the stock-selection opportunity in period t+1. Active share is defined according to Cremers and Petajisto (2009) and stock-selection opportunity is the average positive FF6 alpha value estimated from daily returns during period t+1. The p-values represent the bootstrapped values of the cross-sectional t-statistics for the pseudo-funds from 10,000 simulations exceeding the actual estimated values of the cross-sectional statistics. The sample period spans from January 1, 2012, to December 31, 2024
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.