Big Data

Maximum Likelihood Estimation Of Factor Models On Data Sets With Arbitrary Pattern Of Missing Data

Download Now Date Added: May 2010
Format: PDF

In this paper the authors propose a methodology to estimate a dynamic factor model on data sets with an arbitrary pattern of missing data. They modify the Expectation Maximisation (EM) algorithm as proposed for a dynamic factor model by Watson and Engle (1983) to the case with general pattern of missing data. They also extend the model to the case with serially correlated idiosyncratic component. The framework allows handling efficiently and in automatic manner sets of indicators characterized by different publication delays, frequencies and sample lengths. This can be relevant e.g. for young economies for which many indicators are compiled only since recently.