Use of REGWQ Multiple Comparisons of Qualitative Data

The REGWQ （Ryan-Einot-Gabriel-Welsch and Quiot） test produces allow us to compare a large numbers of data while controlling the probability of making at least one Type I error or Family wise error. The purpose of this study was to use the REGWQ multiple comparisons test of qualitative data. Okra characterization data was applied and submitted to ANOVA （P_0.05） with REGWQ for multiple comparisons of the means. The results of this study establish a summary strategy of following a significant ANOVA F with REGWQ test on multiple comparisons of means in summation a large entries/treatments to the small groups when variances are heterogeneous. Cluster analysis should be especially useful for grouping qualitative treatment and could also be used in conjunction of with REFWQ multiple produces. The development of study will be in REGWQ multiple producers in SAS option for distributed the large number of treatment to small group with summering the best choice of treatments.

A Topological Clustering of Variables

The clustering of objects(individuals or variables)is one of the most used approaches to exploring multivariate data.The two most common unsupervised clustering strategies are hierarchical ascending clustering(HAC)and k-means partitioning used to identify groups of similar objects in a dataset to divide it into homogeneous groups.The proposed topological clustering of variables,called TCV,studies an homogeneous set of variables defined on the same set of individuals,based on the notion of neighborhood graphs,some of these variables are more-or-less correlated or linked according to the type quantitative or qualitative of the variables.This topological data analysis approach can then be useful for dimension reduction and variable selection.It’s a topological hierarchical clustering analysis of a set of variables which can be quantitative,qualitative or a mixture of both.It arranges variables into homogeneous groups according to their correlations or associations studied in a topological context of principal component analysis(PCA)or multiple correspondence analysis(MCA).The proposed TCV is adapted to the type of data considered,its principle is presented and illustrated using simple real datasets with quantitative,qualitative and mixed variables.The results of these illustrative examples are compared to those of other variables clustering approaches.

Risk perception and safety analysis on petroleum production system of three gas fields in Bangladesh

Accidents are common in the petroleum industry.The risk of accidents can be easily minimized by understand-ing the harm early in the production system.This study presents a perception-based risk and safety analysis of petroleum production systems.Data were collected from three fields operated by Sylhet Gas Fields Limited in Bangladesh.The Statistical Package for the Social Sciences(SPSS)software was used to analyze the data.The results were then subjected to a frequency analysis,an analysis of variance(ANOVA),and a reliability analysis.The frequency analysis indicated the overall safety situation,and the ANOVA models and reliability analysis sub-stantiated the results.A chi-squared test indicated the association between the datasets.The outcomes of the risk matrix indicated various risk levels,such as low,moderate,and high.According to the implicit risks,necessary measures were recommended for the industry’s future.