EFFICIENT ESTIMATION OF FACTOR MODELS
This paper considers the factor model <italic>X</italic> = Λ<italic>F</italic> + <italic>e</italic>. Assuming a normal distribution for the idiosyncratic error <italic>e</italic> conditional on the factors {<italic>F</italic>}, conditional maximum likelihood estimators of the factor and factor-loading spaces are derived. These estimators are called generalized principal component estimators (GPCEs) without the normality assumption. This paper derives asymptotic distributions of the GPCEs of the factor and factor-loading spaces. It is shown that variance of the GPCE of the common component is smaller than that of the principal component estimator studied in Bai (2003, <italic>Econometrica</italic> 71, 135–172). The approximate variance of the forecasting error using the GPCE-based factor estimates is derived and shown to be smaller than that based on the principal component estimator. The feasible GPCE (FGPCE) of the factor space is shown to be asymptotically equivalent to the GPCE. The GPCE and FGPCE are shown to be more efficient than the principal component estimator in finite samples.
Year of publication: |
2012
|
---|---|
Authors: | Choi, In |
Published in: |
Econometric Theory. - Cambridge University Press. - Vol. 28.2012, 02, p. 274-308
|
Publisher: |
Cambridge University Press |
Description of contents: | Abstract [journals.cambridge.org] |
Saved in:
Saved in favorites
Similar items by person
-
Choosing the Level of Significance : A Decision‐theoretic Approach
Kim, Jae H., (2019)
-
Differencing versus nondifferencing in factor‐based forecasting
Choi, In, (2020)
-
A multilevel factor model : Identification, asymptotic theory and applications
Choi, In, (2018)
- More ...