Using Machine Learning and Qualitative Interviews to Design a Five-Question Women's Agency Index (WP-21-23)
Seema Jayachandran, Monica Biradavolu, and Jan Cooper
The researchers propose a new method to design a short survey measure of a complex concept such as women's agency. The approach combines mixed-methods data collection and machine learning. They select the best survey questions based on how strongly correlated they are with a "gold standard'' measure of the concept derived from qualitative interviews. In their application, they measure agency for 209 women in Haryana, India, first, through a semi-structured interview and, second, through a large set of close-ended questions. The authors use qualitative coding methods to score each woman's agency based on the interview, which they treat as her true agency. To identify the close-ended questions most predictive of the "truth," they apply statistical algorithms that build on LASSO and random forest but constrain how many variables are selected for the model (five in their case). The resulting five-question index is as strongly correlated with the coded qualitative interview as is an index that uses all of the candidate questions. This approach of selecting survey questions based on their statistical correspondence to coded qualitative interviews could be used to design short survey modules for many other latent constructs.