Abstract: The present paper deals with some modifications on the computational aspects of MIVQUE of variance components in mixed linear models. As a result two modified MIVQU estimators namely (MIVQUE I and MIVQUE II) are introduced. Further the relative performances of Modified MIVQU estimators are assessed with that of Mitra Type Estimators (MTE) and MIVQU estimators for unbalanced one way random model based on different optimality criteria with various n-patterns.
Abstract: The present paper deals with the introduction of new experimental designs namely “Orthogonal Sudoku Square Designs”. A simple “sequential method” of constructing orthogonal Sudoku square designs (OSSD) of odd order is presented. The analysis of orthogonal Sudoku square designs is also discussed. The entire above is explained with the help of numerical examples.
Keywords: Latin squares, Graeco Latin squares, sequential method
Abstract: The present paper deals with a modification on the selection of linear systematic sample, consequently the proposed method is called modified linear systematic sampling. The performances of the modified linear systematic sampling are assessed with that of simple random sampling and the linear systematic sampling for certain hypothetical populations as well as for certain natural populations. As a result, it is observed that the modified linear systematic sample mean performs better than the simple random sample mean and the usual systematic sample mean for estimating the population mean in the presence of linear trend among the population values. Further improvements…are achieved by introducing Yates type end corrections. The applications of the proposed sampling scheme in constructing mating designs are also discussed with an example.
Show more
Keywords: Linear trend, mating designs, partial diallel crosses, modified systematic sampling, natural population, simple random sampling, trend free sampling, Yates end corrections, Yates type end corrections
Abstract: The modern manufacturing technology requires the effective use of statistical tools for analyzing quality problems and controlling, monitoring, maintaining and improving the performance of manufacturing process. When dealing with measurable quality characteristics, it is necessary to monitor the behaviour of the process average of the quality characteristics and its variability. Control charts are widely used to take a proper and a meaningful decision such as: How long the present process can be allowed for production? When do we interfere into the process for correction / modification / rectification? It is important to take a proper decision so as to improve…the quality and its productivity. The present paper deals with the use of diagonal systematic sampling in industrial applications for on line process control. The relative performance of diagonal systematic sampling with that of systematic sampling and the simple random sampling is assessed for a certain natural population obtained from an automobile ancillary industry with the presence of linear trend among the observed values due to the tool wear. The efficiency of the different sampling schemes is measured for estimating the mean of quality characteristics; for controlling and monitoring the manufacturing process and also for the effective computation of process capability indices. Consequently it has been recommended to use the diagonal systematic sampling for the selection of random samples to assess the quality characteristics of the components produced; to take a proper and meaningful decision whether the present manufacturing process can be allowed further or not in a short production run of engineering industries in the presence of systematic assignable causes.
Show more
Keywords: Diagonal systematic sampling, systematic sampling, simple random sampling, linear trend, industrial applications, control charts, process capability analysis and quality characteristics
Abstract: Diagonal systematic sampling scheme is introduced by Subramani (2000, Jour. Ind. Soc. Ag. Statist.) as an alternative to linear systematic sampling, provided the population size N = n k and the sample size n ⩽ k , where k is the number of samples. In this paper an attempt has been made to relax the condition of n ⩽ k . Further the efficiency of the generalized diagonal systematic sampling with the simple random sampling and the systematic sampling is assessed for certain labelled and natural populations. Yates type end corrections are also suggested for further improvements.
Abstract: The present paper deals with the introduction of new experimental designs namely “Sudoku Designs”. The construction, analysis and application of sudoku designs are also discussed. The entire above is explained with the help of numerical examples.
Keywords: Latin squares, sequential method, sudoku designs