Models Applied to Iran’s Cotton and Sugar Beet Production

Abstract

In this chapter all the parametric and non-parametric models are applied to two datasets from Iran’s cotton and sugar beet producing provinces. The data for cotton crop is a balanced panel of 13 provinces observed over 13 years from 2000 to 2012, with 169 observations. The dataset for sugar beet is also a balanced panel and includes 143 observations from 11 provinces over 13 years. The main variables used in the different models include output, labor, seeds, pesticides, chemical fertilizers and animal fertilizers. The variables which influence technical efficiency are share of chemical fertilizers in total fertilizers and the machinery utilization rate measured in percentage use. This chapter also sheds light on whether particular panel data stochastic frontier models are better suited to different datasets. It conducts tests of functional forms and nestedness and analyzes them. Based on these criteria and tests the best parametric model for each dataset is selected. The most efficient and inefficient provinces in cotton and sugar beet production are recognized based on the most suitable model and technical efficiency scores. Finally, the most efficient provinces in cotton and sugar beet production of Iran are recognized.

Some parametric models of this chapter are discussed in Rashidghalam et al. (2016).