Classification Algorithm for Skin Color (CASCo): A new tool to measure skin color in social science research

Objective

A growing body of literature reveals that skin color has significant effects on people's income, health, education, and employment. However, the ways in which skin color has been measured in empirical research have been criticized for being inaccurate, if not subjective and biased.

Objective

Introduce an objective, automatic, accessible and customizable Classification Algorithm for Skin Color (CASCo).

Methods

We review the methods traditionally used to measure skin color (verbal scales, visual aids or color palettes, photo elicitation, spectrometers and image-based algorithms), noting their shortcomings. We highlight the need for a different tool to measure skin color

Results

We present CASCo, a (social researcher-friendly) Python library that uses face detection, skin segmentation and k-means clustering algorithms to determine the skin tone category of portraits.

Conclusion

After assessing the merits and shortcomings of all the methods available, we argue CASCo is well equipped to overcome most challenges and objections posed against its alternatives. While acknowledging its limitations, we contend that CASCo should complement researchers. toolkit in this area.     

DO PRICES TRANSMIT RATIONALLY EXPECTED INFORMATION?

A simple model with asymmetric information, in which inventory holders or traders submit demand curves to an auctioneer, has a unique partially revealing equilibrium. We wonder whether the agents can plausibly coordinate on this equilibrium through “eductive” reasoning relying on common knowledge. The analysis stresses the role of two effects, sensitivity and amplification, whose product should be small enough. The property is obtained whenever the equilibrium excess demand is steep enough, i.e., when the search for information does not distort demand too much. Neither the influence of the number of informed agents nor that of noise trading are monotonic. Real‐time learning has strikingly different features. (JEL: D82, D84)