Forecasting Tax Revenues, Frequency of Observation Matter.
Loading...
Date
2022-10-26
Authors
Masoud, Mohammed Albimana
Issa, Moh’d Hemedb
Journal Title
Journal ISSN
Volume Title
Publisher
Kenya School of Revenue Administration
Abstract
This paper intends to examine whether using higher frequency data has more power in forecasting than low frequency data. The sample size ranges from 1996 to 2016 and 2000 to 2015. Ordinary Least Square (OLS) method was used to forecast three components of tax revenues including total revenue (TR), Pay As You Earn (PAYE) and Value-added Tax (VAT). The results show that, both TR and PAYE forecasts are slightly better when using low frequency data. However, for VAT, forecasting power is slightly better when using higher frequency data. Also, the nature of the tax can have different implications in selection of data frequency.
Description
Keywords
Forecasting, Tax Revenue