Skip to main content
Professor Saeed Heravi

Professor Saeed Heravi

Professor in Quantitative Methods

Cardiff Business School

Email
heravis@cardiff.ac.uk
Telephone
+44 (0)29 2087 5787
Campuses
E24, Aberconway Building, Colum Road, Cathays, Cardiff, CF10 3EU

Overview

Saeed Heravi is professor of quantitative analysis at Cardiff Business School. He obtained his PhD in Statistics from University of Manchester Institute of Science and Technology (UMIST) in 1986.  Since then he has held full-time posts in different universities as Researcher \ Lecturer \ Senior Lecturer and Reader. During this time, he has taught various quantitative courses and his research activities includes applied statistics, time series analysis, forecasting and computing. He has a broad knowledge of statistical modelling techniques, particularly non-linear and non-stationary time series. Prior to joining the Cardiff Business School, he was actively involved in a number of research projects with the University of Manchester and Reading University. These projects include research on the theory and applications of non-linear time series models, data revisions, modelling European industrial production and a series of articles analysing the accuracy of OECD forecasts. In addition, he has worked on a number of new areas, particularly on measuring consumer price index using scanner data. His current research includes forecasting with Singular Spectrum Analysis (SSA), Comparison of performance of various sampling schemes on price index estimation using the TNS dataset, Relation between violence on alcohol prices and Tourism forecasting.

Biography

Publications

2021

2020

2019

2018

2017

2016

2015

2014

2013

2011

2009

2008

2007

2006

2005

2004

2003

2002

2001

Teaching

Teaching commitments

  • Applied Statistics and Mathematics in Economics and Business (undergraduate, year 1);
  • Inferential Statistics, Statistical Modelling & Survey Methods (undergraduate, year 2)

PhD supervision research interests

  • Hedonic regression
  • Time series forecasting