Robustness check for survivorship bias (Heckman two-step procedure)
| Original gi (mean) | Heckman adjusted gi | λ (IMR) Coeff. | p-value | |
|---|---|---|---|---|
| All funds | −0.182 | −0.179 | 0.034 | 0.442 |
| UK | −0.165 | −0.163 | 0.028 | 0.512 |
| France | −0.210 | −0.207 | 0.041 | 0.356 |
| Germany | −0.194 | −0.191 | 0.031 | 0.588 |
| Original | Heckman adjusted | λ (IMR) Coeff. | ||
|---|---|---|---|---|
| All funds | −0.182 | −0.179 | 0.034 | 0.442 |
| UK | −0.165 | −0.163 | 0.028 | 0.512 |
| France | −0.210 | −0.207 | 0.041 | 0.356 |
| Germany | −0.194 | −0.191 | 0.031 | 0.588 |
Note(s): The results of a two-step selection model developed by Heckman (1979) to evaluate potential survivorship bias over the 2020–2024 period are presented in the table above. The likelihood of a fund surviving the 2020–2024 era is estimated in the first stage using a probit model (not displayed) based on fund size, age, and investment focus. In the second stage, the performance equation incorporates the Inverse Mills Ratio (λ) as a regressor. The original gi represents the unadjusted mean performance, while the Heckman adjusted gi accounts for selection bias
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.