Three essays on analysis of economic time series : with focus on cointegration /
| Main Author: | |
|---|---|
| Other Authors: | , |
| Format: | Thesis Book |
| Language: | English |
| Published: |
1994.
|
| Subjects: | |
| Online Access: | Link to OAKTrust copy http://proxy.library.tamu.edu/login?url=http://proquest.umi.com/pqdweb?did=740812551&sid=1&Fmt=2&clientId=2945&RQT=309&VName=PQD |
| Abstract: | The topic of cointegration has become one of the most frequently applied methods to analyze long run relationships between (among) time series data. Cointegrated series will move together in the long run, even though they may be individually nonstationary. The Granger Representation Theorem (1987) indicates that cointegrated series can be represented by an error correction model. Chapter II considers a special case of the Granger Representation Theorem. This case provides insight into the relationship between cointegration and error correction. Chapter III uses an iterated logarithmic transformation in modeling cointegration between official and black market exchange rates from Brazil. It applies a testing procedure of Johansen (1992) to determine the cointegration rank in the presence of a linear trend. Chapter IV considers a test of structure change on the cointegration relationship in U.S. sweetner data. Quintos' (1993) method is applied to test the stability of rank in the error correction framework. There exisits a structure break in the cointegration relationship between refined sugar (RS) and high fructose corn syrup (HFCS). The empirical results are discussed relative to the U.S. sweetener market. |
|---|---|
| Item Description: | Vita. "Major subject: Economics." |
| Physical Description: | ix, 105 leaves : illustrations ; 28 cm |
| Bibliography: | Includes bibliographical references. |