Application of Time-Varying Coefficient Regression Model for Forecasting Financial Data

Authors

  • Jyothi Manoj Department of Statistics, Kristu Jayanti College, Bangalore, Karnataka, India
  • Suresh K K Department of Statistics, Bharathiar University, Coimbatore, Tamil Nadu, India

Keywords:

Time-varying coefficient models, kernel smoothing, multiple linear regression, RMSE, Akaike information criteria

Abstract

Regression analysis using ordinary least squares method is a very powerful statistical technique widely used. Though this method is widely accepted, its ability to model accurately when the predictors are dynamic in time is suspected. In scenarios where we use panel data with endogenous variables possessing serial correlation, the role of time-varying coefficient regression is worth analyzing. The present study probes this aspect with price of gold in India as the dependent variable. The predictors considered are US dollar exchange rate, oil price, demand of gold and NIFTY. A comparative analysis of multiple linear regression modeling and time-varying coefficient linear regression modeling is carried out in the present study using a 7-year panel data set ranging from 2012 to 2019.

Downloads

Download data is not yet available.

Downloads

Published

2022-12-29

How to Cite

Manoj, J. ., & K K, S. . (2022). Application of Time-Varying Coefficient Regression Model for Forecasting Financial Data. Thailand Statistician, 21(1), 180–195. Retrieved from https://ph02.tci-thaijo.org/index.php/thaistat/article/view/248032

Issue

Section

Articles