Jack-knifing in small samples of survival data: when bias meets variance to increase estimate precision

Estimates performed particularly using small samples are a priori inaccurate. Furthermore, estimations of m-year survival rates, especially for large m ≫ 0, are inevitable of low precision because they are calculated as fractions with both low numerators and denominators. In this study, we use different degrees of jack-knifing of the original dataset used for m-year survival rates estimations to optimize the trade-off between decreasing variance (and increasing accuracy) and increasing bias of the estimates. Assuming the jack-knife enriches the original data in an allowed way since it does not generate new, non-existing observations, the results could suggest overcoming the small sample issue.