Composite Index for Quantative Assessment of Forestry Companies Competitiveness

Abstract

The goal of present study is to propose reliable composite index for quantitative assessment of competitiveness of forestry companies on the basis of data from Training and Experimental Forest Range �G. Avramov�, Yundola. Concerning this some multidimensional statistical methods that permit quantification of complex indicator as competitiveness are studied. On this grounds for obtaining composite index (quantitative assessment) of the level of competitiveness of forestry companies the implementation of factor analysis and linear ordering in multidimensional space are justified. Through these methods and on the basis of system of indicators and subindicators developed within the framework of scientific project NIS-B-1140 financed by University of Forestry-Sofia [1, 2] the competitiveness of Training and Experimental Forest Range �G. Avramov�, Yundola during the period 2010 � 2021 is assessed through composite indices construction. Their comparative analysis gives grounds to be concluded that in the ordering of Training and Experimental Forest Range �G. Avramov�, Yundola by level of competitiveness during the years no significant differences are observed, i.e. both methods permit objective quantitative assessment of the level of competitiveness during the different years (in concrete case they are the units in the studied multitude). The disadvantages of factor analysis in forestry companies competitiveness assessment are mainly associated with some basic requirements for its implementation and namely: the number of observations should be at least 50; variables have to be correlated. The application of the method of linear ordering in multidimensional space is not associated with such limitations, which makes it universal in assessing the competitiveness of forestry companies through composite index construction especially when the number of observations is limited. At the same time the factor analysis is more sensitive to changes in the values of the studied subindicators than the method of linear ordering in multidimensional space. It also defines the variable that contributes mostly for determining the number of factors.