Time Series Analysis and Indicators of Economic Activity (Forecasting)

Some of the problems involved in identification of time series models and forecasting variables of interest are considered. A theoretical/empirical comparison of various information criteria of interest is provided and it is concluded that Hannan and Kavalieris criterion is the most appropriate criterion to be used for model selection. Appropriate time series models for forecasting state income tax receipts are identified by employing information criteria and Box-Cox transformation. Furthermore, bivariate time series models with the index of leading indicators as the input variable are used to forecast a coincident indicator of interest. The weights assigned to the elements of the index of leading indicators are found by constructing and minimizing the variance of forecast error function for several steps ahead forecasting.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Economics

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2014

Author dc:creator

• Nazmi, Nader

• Economics, General

Identifier

(UMI)AAI8600275

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/70767