What question did this study set out to answer?

Evaluate statistical methods and threshold-based rules used to classify star entrepreneurs and introduce a precision-recall framework to clarify classification trade-offs.

August 19, 2026Entrepreneurship Theory and Practice

Stars Are Where You Draw the Line: Reassessing Methods for Identifying Star Entrepreneurs

View Full Paper

Ask AI

Bookmark

Authors

BNBoris Nikolaev

Discussion

Member takes

Overview

Empirical analysis reveals precision-recall trade-offs across threshold methods for identifying star entrepreneurs in high-growth firm data, indicating thresholds are subjective modeling choices.

Key Points

Evaluate statistical methods and threshold-based rules used to classify star entrepreneurs and introduce a precision-recall framework to clarify classification trade-offs.
Conducted simulation experiments to assess cutoff behavior and sample-size sensitivity in the bootstrap-based quantile absolute deviation (GS-QAD) method.
Benchmarked nine threshold-based star classification methods using 13 years of Inc. 5000 firm data linked to subsequent public listings.
Simulations demonstrated that the GS-QAD bootstrap method introduces systematic sample-size bias across comparisons and converges to a 17% to 20% rule as sample size increases.
Identified star firms were 10 to 20 times more likely to become publicly traded and accounted for most market capitalization, though no threshold method dominated across all precision-recall trade-offs.
Public listing probability increased smoothly with firm revenue without displaying a discrete cutoff discontinuity at any threshold.

Cite This Study

Boris Nikolaev (2026) studied this question.

synapsesocial.com/papers/6a85640f03308d306e2d7922 https://doi.org/10.1177/10422587261470833

View Full Paper

Ask AI

Bookmark

August 19, 2026Entrepreneurship Theory and Practice

Stars Are Where You Draw the Line: Reassessing Methods for Identifying Star Entrepreneurs

View Full Paper

Ask AI

Bookmark

Authors

BNBoris Nikolaev

Discussion

Member takes

Overview

Empirical analysis reveals precision-recall trade-offs across threshold methods for identifying star entrepreneurs in high-growth firm data, indicating thresholds are subjective modeling choices.

Key Points

Evaluate statistical methods and threshold-based rules used to classify star entrepreneurs and introduce a precision-recall framework to clarify classification trade-offs.
Conducted simulation experiments to assess cutoff behavior and sample-size sensitivity in the bootstrap-based quantile absolute deviation (GS-QAD) method.
Benchmarked nine threshold-based star classification methods using 13 years of Inc. 5000 firm data linked to subsequent public listings.
Simulations demonstrated that the GS-QAD bootstrap method introduces systematic sample-size bias across comparisons and converges to a 17% to 20% rule as sample size increases.
Identified star firms were 10 to 20 times more likely to become publicly traded and accounted for most market capitalization, though no threshold method dominated across all precision-recall trade-offs.
Public listing probability increased smoothly with firm revenue without displaying a discrete cutoff discontinuity at any threshold.

Cite This Study

Boris Nikolaev (2026) studied this question.

synapsesocial.com/papers/6a85640f03308d306e2d7922 https://doi.org/10.1177/10422587261470833

View Full Paper

Ask AI

Bookmark