Activity Number:
|
408
- SPAAC Poster Competition
|
Type:
|
Topic Contributed
|
Date/Time:
|
Tuesday, July 31, 2018 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Scientific and Public Affairs Advisory Committee
|
Abstract #329558
|
|
Title:
|
Measuring the Percentage of Smoothness in the Trend of a Univariate Time Series: An Application to a Time Series of Mexico's GDP
|
Author(s):
|
Daniela Cortés Toto* and Víctor M. Guerrero and Hortensia J. Reyes Cervantes
|
Companies:
|
Universidad De Las Américas Puebla (UDLAP) and Instituto Tecnológico Autónomo de México (ITAM) and Benemérita Universidad Autónoma de Puebla (BUAP)
|
Keywords:
|
Index of smoothness;
Penalized least squares;
Smoothing parameter;
Trend estimation;
Mexico's GDP;
Hodrick and Prescott filter
|
Abstract:
|
A smoothness index is presented to measure the amount of smoothness achieved when estimating trends of univariate time series where the noise follows an autoregressive process of order one. To achieve this, we fix a priori the percentage of smoothness that one wishes to reach in the estimation of the trend (through the smoothness index). Then, the trend is estimated using Penalized Least Squares in such a way that the index of smoothness previously fixed is satisfied. The application of the smoothness index is presented through an example of a time series of Mexico's GDP, where the trend is estimated with different percentages of smoothness, including the classic case in which the estimation of the trend is made by means of the Hodrick and Prescott filter.
|
Authors who are presenting talks have a * after their name.