.png){kind=icon}
.png){kind=icon}
Return
The robust beauty of small recent samples
.png){kind=icon}
PRE
AI
J
T
P
DOI：10.1016/j.ejor.2026.01.024.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Organizational theory typically advises managers to anticipate future conditions by gathering as much information as possible before making decisions. In practice, however, people often rely on small samples of recent experience. What should managers do? We argue that the answer depends on the environment's structure-particularly its temporal dependence. Our study examines the robustness of relying on small, recent samples as a function of the temporal patterns in the environment. Drawing on simulations, time-series analysis of managerial information environments, and an experiment, we show that reliance on recent samples improves predictive accuracy in temporally dependent environments, that managerial environments are strongly temporally dependent, and, finally, that individuals adapt sample size to match environmental structure. It is therefore good practice for managers to rely on small recent samples in prediction. Together, our findings contribute to behavioral operational research by showing that intuitive reliance on recent experience is not a flaw but an adaptive response to real-world temporal dynamics.
Keywords:
Decision analysis
Small samples of experience
Temporal autocorrelation
Predictions
Heuristics
Journal
IF:
6
Papers:
2.2W
Citations:
6.4W
Organization
Cited Papers