Working Paper: NBER ID: w31605
Authors: Christopher Conlon; Jeff Gortmaker
Abstract: We provide a general framework for incorporating many types of micro data from summary statistics to full surveys of selected consumers into Berry, Levinsohn, and Pakes (1995)-style estimates of differentiated products demand systems. We extend best practices for BLP estimation in Conlon and Gortmaker (2020) to the case with micro data and implement them in our open-source package PyBLP. Monte Carlo experiments and empirical examples suggest that incorporating micro data can substantially improve the finite sample performance of the BLP estimator, particularly when using well-targeted summary statistics or "optimal micro moments" that we derive and show how to compute.
Keywords: micro data; differentiated products; demand estimation; BLP; pyblp
JEL Codes: C13; C18; C30; D12; L0; L66
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Standardized econometric framework (C51) | enhances robustness and replicability of results (C59) |
| Incorporating micro data (C81) | improves finite sample performance of BLP estimator (C51) |
| Choice of micro moments (D01) | influences parameter estimates (C51) |
| Different weighting of aggregate vs micro data (C43) | leads to different outcomes in GMM estimator (C30) |
| Using optimal micro moments (C61) | leads to statistically efficient estimators (C51) |