Working Paper: CEPR ID: DP7726
Authors: George Kapetanios; Massimiliano Marcellino
Abstract: This paper analyses the use of factor analysis for instrumental variable estimation when the number of instruments tends to infinity. In particular, we focus on situations where many weak instruments exist and/or the factor structure is weak. Theoretical results, simulation experiments and empirical applications highlight the relevance of Factor-GMM estimation, which is also easily implemented.
Keywords: factor models; GMM; instrumental variables; principal components; weak instruments; DSGE models
JEL Codes: C32; C51; E52
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Factors extracted from a large set of macroeconomic variables as instruments in GMM estimation (C51) | Improves the efficiency of parameter estimators (C51) |
| Many weak instruments (C36) | Factor model allows for a more effective summarization of information contained in these instruments (C58) |
| Weak factor structure (C38) | Consistent estimators for the parameters of interest can still be obtained (C51) |
| Factor-based approach (G41) | Alleviates issues associated with weak instruments (C26) |