The Water Challenge in Tunisia: Crisis or Détente Application of NIPALS Algorithm and Box and Jenkins Methodology
Downloads
Two paradoxical analyses of the water sector in Tunisia can be advanced. According to the World Bank's report about the Tunisian water reserves published in 2009 "Tunisia is preparing to face, during the next decades, too many important water access problems, arising from growing demand and a decrease of supply. Institutions will also face more complex management problems" This orientation which highlights the scale of the water crisis in Tunisia is confronted with a totally contradictory statement of Abderrazek Souissi the General Director of the Office of Planning and the Hydraulic Equilibrium in the Agriculture Ministry, which proclaimed that "Water is scarce in Tunisia. But until now, we well managed our resources, so we cannot talk about water crisis. "
Thus, The main object of this paper is to analyze and dissect the evolution of the availability of water in Tunisia by forecasting it using the methodology of Box and Jenkins, thus, a manager can develop effective action plans to use these resources in a more efficient and optimal manner. Prior to the forecast step, we first apply the NIPALS algorithm to impute missing data in our series.
AL-DHOWALIA k.h.,(1996). Modeling Municipal Water Demand Using Box-Jenkins Technique. Jkau:eng. sct., VOLUME 8, 61-71
Preda C., Duhamel A., Picavet M., KechadiT., (2005). Gestion des données manquantes dans les grandes bases de données en Santé. Journées Francophones d’Informatique Médicale, Lille
Preda C., Saporta G., Hadj Mbarek M.,(2010). The NIPALS Algorithm for Missing Functional Data. Revue Roumaine de Mathématiques Pures et Appliquées, vol. 55(4), pp. 315-326
Josse J., Husson F., Pagés J., (2009). Gestion des données manquantes en Analyse en Composantes Principales. Journal de la Société Française de Statistique. Volume 150
Lawgali F.F., (2008). Forecasting water demand for agricultural, industrial and domestic use in Libya. International Review of Business Research Papers, VOLUME 4? 231-248
Little R.J.A., Rubin D.B. (1987). Statistical Analysis with Missing Data. New York: John Wiley.
Little RJA, Rubin DB. Statistical analysis with missing data. Wiley series in Probability and Statistics. 2nd ed. New York: Wiley, 2002.
Maidment d.r., et al (1985). Transfer Function Models of Daily Urban Water Use. Water Resources Research Volume 21, 425–432,
Schafer J.L., Imputation Procedures For Missing Data. USA Université de Pennsylvania 1999:
http://www.stat.psu.edu/~jls/session2.pdf
Tenenhaus M., La régression PLS Théorie et pratique. Editions Technip, 1998.
Wasito, I., Mirkin, B., (2006), Nearest neighbours in least-squares data imputation algorithms with different missing patterns, Computational Statistics and Data Analysis, 50, 926-949.
