Multidimensional Skills on LinkedIn Profiles: Measuring Human Capital and the Gender Skill Gap

TL;DR

This study analyzes nearly 9 million LinkedIn profiles to measure human capital through multidimensional skills, revealing how skills relate to experience, earnings, and gender gaps in the labor market.

Contribution

It introduces a large-scale, skill-based measure of human capital and demonstrates its relation to earnings and gender disparities using LinkedIn data.

Findings

Skills increase with experience and relate to age-earnings profiles.

More skills, especially managerial, correlate with higher pay.

Women’s slower skill accumulation explains part of the gender earnings gap.

Abstract

We measure human capital using the self-reported skill sets of nearly 9 million U.S. college graduates from professional profiles on LinkedIn. We aggregate skill strings into 48 clusters of general, occupation-specific, and managerial skills. Multidimensional skills can account for several important labor-market patterns. First, the number and composition of skills are systematically related to measures of human-capital investment such as education and work experience. The number of skills increases with experience, and the average age-skill profile closely resembles the well-established concave age-earnings profile. Second, workers who report more skills, especially specific and managerial ones, hold higher-paid jobs. Skill differences account for more earnings variation than detailed measures of education and experience. Third, we document a sizable gender gap in skills. While women and men report nearly equal numbers of skills shortly after college graduation, women's skill count increases more slowly with age subsequently. A simple quantitative exercise shows that women's slower skill accumulation can be fully accounted for by reduced work hours associated with motherhood. The resulting gender differences in skills rationalize a substantial proportion of the gender gap in job-based earnings.