Time-series data that reflect a periodic pattern are often used in psychology. In personality psychology, Brown and Moskowitz (1998) used spectral analysis to study whether fluctuations in the expression of four interpersonal behaviors show a cyclical pattern. Spline smoothing had also been used in the past to track the non-periodic trend, but no research has yet been done that combines spectral analysis and spline smoothing. The present thesis describes a new model which combines these two techniques to capture both periodic and non-periodic trends in the data. / The new model is then applied to Brown and Moskowitz's time-series data to investigate the long-term evolution to the four interpersonal behaviors, and to the GDP data to examine the periodic and non-periodic pattern for the GDP values of the 16 countries. Finally, the extent to which the model is accurate is tested using simulated data.
| Identifer | oai:union.ndltd.org:LACETR/oai:collectionscanada.gc.ca:QMM.79765 |
| Date | January 2002 |
| Creators | Fok, Carlotta Ching Ting, 1973- |
| Contributors | Ramsay, James O. (advisor) |
| Publisher | McGill University |
| Source Sets | Library and Archives Canada ETDs Repository / Centre d'archives des thèses électroniques de Bibliothèque et Archives Canada |
| Language | English |
| Detected Language | English |
| Type | Electronic Thesis or Dissertation |
| Format | application/pdf |
| Coverage | Master of Arts (Department of Psychology.) |
| Rights | All items in eScholarship@McGill are protected by copyright with all rights reserved unless otherwise indicated. |
| Relation | alephsysno: 001984203, proquestno: AAIMQ88639, Theses scanned by UMI/ProQuest. |
Page generated in 0.0017 seconds