Sunil Kumar G
Optimum stratification for yield estimation in cocoa (Theobroma Cacao L.) - Vellanikkara Department of Agricultural Statistics, College of Horticulture 2000
Investigation on "Optimum stratification for yield estimation In cocoa
(Theobroma cacao. L)" was carried out in the department of Agricultural Statistics,
College of Horticulture, V ellanikkara during 1997-99 using data on 1025 'F orestro'
variety cocoa trees from the Cadbury-KAU Co-operative Cocoa Research Project
(CCRP), College of Horticulture, Kerala Agricultural University.
Four different stratification rules, viz, cumulative root 'f rule, cumulative
cube root 'f rule, Ekman's rule and an iterative procedure for function minimisation,
were used to arrive at boundary points of strata. For each of these rules stratification
was carried out on average yield of yester years, canopy spread, value of HxG2
where 'H' is height and 'G' is the girth of the trees, the first principal component
derived from these variates and height and girth of the trees and regression estimate
of the study character with the predictor variables mentioned above. Sampling
variance of the estimator of the population mean under Neyman allocation for two to
five strata situations was estimated in each case, assuming a uniform sample size of
200. Different stratification rules and stratification variables were compared using
these estimates.
No single rule was found to be appropriate for all the stratification variables
and for different number of strata. But in most of the cases the cumulative root 'f
rule was found to be good for smaller number of strata followed by the cumulative
cube root 'f rule. For large number of strata, the iterative procedure performed
consistently well compared to all the other methods. In the case of stratification
based on the canopy spread, the Ekman' s method was found to be good for different
numbers of strata.
Regarding the stratification variables, the average yield of yester years was
found to be best followed by the regression estimate in the sense of resulting in
smaller sampling variance of the estimator of the population mean. Stratification
based on value of HxG2 and the first principal component were found to be inferior.
Average yield of yester years or regression estimate of yield could be used as
covariate to perform the analysis of covariance for experiments in cocoa and also
blocking of trees could be done based on these for the conduct of planned
experiments on cocoa.
630.31 / SUN/OP
Optimum stratification for yield estimation in cocoa (Theobroma Cacao L.) - Vellanikkara Department of Agricultural Statistics, College of Horticulture 2000
Investigation on "Optimum stratification for yield estimation In cocoa
(Theobroma cacao. L)" was carried out in the department of Agricultural Statistics,
College of Horticulture, V ellanikkara during 1997-99 using data on 1025 'F orestro'
variety cocoa trees from the Cadbury-KAU Co-operative Cocoa Research Project
(CCRP), College of Horticulture, Kerala Agricultural University.
Four different stratification rules, viz, cumulative root 'f rule, cumulative
cube root 'f rule, Ekman's rule and an iterative procedure for function minimisation,
were used to arrive at boundary points of strata. For each of these rules stratification
was carried out on average yield of yester years, canopy spread, value of HxG2
where 'H' is height and 'G' is the girth of the trees, the first principal component
derived from these variates and height and girth of the trees and regression estimate
of the study character with the predictor variables mentioned above. Sampling
variance of the estimator of the population mean under Neyman allocation for two to
five strata situations was estimated in each case, assuming a uniform sample size of
200. Different stratification rules and stratification variables were compared using
these estimates.
No single rule was found to be appropriate for all the stratification variables
and for different number of strata. But in most of the cases the cumulative root 'f
rule was found to be good for smaller number of strata followed by the cumulative
cube root 'f rule. For large number of strata, the iterative procedure performed
consistently well compared to all the other methods. In the case of stratification
based on the canopy spread, the Ekman' s method was found to be good for different
numbers of strata.
Regarding the stratification variables, the average yield of yester years was
found to be best followed by the regression estimate in the sense of resulting in
smaller sampling variance of the estimator of the population mean. Stratification
based on value of HxG2 and the first principal component were found to be inferior.
Average yield of yester years or regression estimate of yield could be used as
covariate to perform the analysis of covariance for experiments in cocoa and also
blocking of trees could be done based on these for the conduct of planned
experiments on cocoa.
630.31 / SUN/OP