Nonparametric Regression Estimation of Growth Rate of India’s Fish Production and Export

Abstract

Mechanistic growth models, parametric and nonparametric
regression models were used to estimate
the trend and growth rate of fish production in India
during the period 1980 to 2014 and fish export
during the period 1960 to 2014. It was found that
parametric and mechanistic growth models produced
high R2 values and low RMSE, but error
terms of fitted models were not independent. The
local polynomial regression of order one was fitted
to the data and found to be the best model to
estimate the trend of fish production and export
over the decades. Nonparametric regression approach
used to estimate the compound growth rate
of fish production and export efficiently compared
to parametric and mechanistic growth models.