Forecasting practices of Canadian "rms: Survey results and comparisons Robert D. Klassen , Benito E. Flores *
Richard Ivey School of Business, University of Western Ontario, London, Ont., Canada N6A 3K7 Lowry Mays School of Business, Texas A&M University, College Station, TX 77843-4217, USA Received 20 March 2000; accepted 4 May 2000
Abstract A survey of forecasting practices was carried out to provide a better understanding of Canadian business practices, and when possible, compare them with US practices. Companies in the US and Canada have the same use for forecasting information. Forecasts are generated and used mostly by marketing/sales. Judgmental procedures are used more frequently than any other method. Quantitative, causal and newer methods are not used as much. In line with this, "rms do not keep as much data per product/service forecasted. Senior management revises the forecast frequently and believes that on average, accuracy is improved by the revision. Calculation of improvement metrics shows that the variation in the improvement may negate the advantage gained. 2001 Elsevier Science B.V. All rights reserved. Keywords: Forecasting; Survey; Canada
1. Introduction The objective of this paper is to report the results of a survey designed to evaluate forecasting practices in businesses. Forecasting practices vary in the countries with which the United States (US) trades. The two largest trading partners of the US are Canada and Mexico. The three of them are the NAFTA partners. It behooves us to learn more about the practices of "rms in the North American Region. For this reason Canadian "rms were surveyed.
* Corresponding author. Tel.: #1-979-845-4248; fax: #1979-845-5653. E-mail address: firstname.lastname@example.org (B.E. Flores).
From a business standpoint, forecasting is very important. The decisions that "rms make using forecasts go from the elaboration of budgets, market planning, to capital budgeting. All companies need, as a vital input, the forecast estimate of demand or sales. Academics tend to look at the world through the eye of the elegant, but not necessarily as practical, statistical viewpoint. This permeates in the classes that are taught at universities. The university teaching should be in tune with what companies do, or need, and if possible be technologically ahead. Comparative studies, like this one, bring together the practices. The results of surveys done in the US have been reported by, among others, Dalrymple [1,2], Cerullo and Avila , Mentzer and Cox , Mentzer and Kahn , Sanders and Mandrot , Sanders . It is clear from these reports that
0925-5273/01/$ - see front matter 2001 Elsevier Science B.V. All rights reserved. PII: S 0 9 2 5 - 5 2 7 3 ( 0 0 ) 0 0 0 6 3 - 3
R.D. Klassen, B.E. Flores / Int. J. Production Economics 70 (2001) 163}174
forecasting is a common business practice and a key component of the planning and operating functions of most companies in the US. The forecasting practices of US "rms have been documented as described above. The practices of Mexican companies have been documented recently by Duran and Flores . Information about forecasting practices of Canadian "rms has been reported in the past by Davidson , Drury [10,11], Hurwood et al. , Small , and West . A recent new survey was made of the forecasting practices of Canadian "rms in 1997. The results of the survey are presented here and are contrasted, when possible, with US practices. This study follows, as much as possible, a framework that was suggested in a paper by Winklhofer et al. . They proposed a framework to organize survey data. The results reveal that practices in Canada are quite similar to the US but have some characteristics of their own. The paper unfolds as follows. First the research method of the survey is described in detail. Then, general information is presented. Afterwards, design issues are...