On the Predictability of Future Impact in Science

TL;DR

This paper critically evaluates models predicting scientists' future impact, revealing significant flaws in current approaches like the h-index, especially for early-career researchers, and questions their reliability for recruitment decisions.

Contribution

The study identifies intrinsic autocorrelation in impact measures and demonstrates the limited predictive accuracy of existing models across career stages.

Findings

Cumulative impact measures like h-index have intrinsic autocorrelation.

Predictive models overestimate future impact due to autocorrelation.

Model accuracy varies significantly with scientists' career age.

Abstract

Correctly assessing a scientist's past research impact and potential for future impact is key in recruitment decisions and other evaluation processes. While a candidate's future impact is the main concern for these decisions, most measures only quantify the impact of previous work. Recently, it has been argued that linear regression models are capable of predicting a scientist's future impact. By applying that future impact model to 762 careers drawn from three disciplines: physics, biology, and mathematics, we identify a number of subtle, but critical, flaws in current models. Specifically, cumulative non-decreasing measures like the h-index contain intrinsic autocorrelation, resulting in significant overestimation of their "predictive power". Moreover, the predictive power of these models depend heavily upon scientists' career age, producing least accurate estimates for young researchers. Our results place in doubt the suitability of such models, and indicate further investigation is required before they can be used in recruiting decisions.