Systematic sampling for milk yield data
Loading...
Date
2013-07
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand)
Abstract
The present study uses systematic sampling procedures for milk yield data exhibiting some non-linear trends. The data relate to milk yields of four breeds of cows (two brands S16 and S19 of Sahiwal cows and two brands X124 and X205 of crossbred cows) and one breed (Murrah brand no. M125) of buffaloes over one lactation period during 2011-2013. The best fitted mathematical forms of non-linear trend present in the milk yield data are obtained and the expressions of average variances of the estimators of population mean under simple random, usual systematic and modified systematic sampling procedures by taking into account the trend present in the data have been derived from the formulae already derived by Ashutosh (1995) for populations showing general trend. A comparative study is made among these three sampling procedures for five data sets by calculating average variances using best fitted trend equations. Usual systematic sampling is found more precise than simple random and modified systematic sampling procedures for four data sets whereas modified systematic sampling is found better than the other two procedures for one data set. Stratification of milk yield data has resulted in the significant reduction of average variances under all the three sampling schemes. The distribution of milk yield is found to vary from one data set to another. Dagum (4P) distribution is found the best fitted distribution for milk yield of Sahiwal cows, whereas for crossbred cows with brand numbers X124 and X205, it is Gumble Min. and Lognormal respectively. Moreover, the distribution of milk yield of Murrah buffaloes brand number M125 is general extreme values.
Description
Keywords
null