Statistics is a powerful tool for data measurement. Statistical techniques properly planned and executed give meaning to meaningless data. The difficulty some practitioners encounter hinges on the fact that though the...Statistics is a powerful tool for data measurement. Statistical techniques properly planned and executed give meaning to meaningless data. The difficulty some practitioners encounter hinges on the fact that though there are numerous statistical methods available for use in analysis, the extent of their understanding and ease of using these tools for analysis is limited. This study has twofold purpose: firstly, literature on categorical data commonly used in research w</span><span style="font-family:Verdana;">as</span><span style="font-family:Verdana;"> reviewed</span><span style="font-family:Verdana;">;</span><span style="font-family:""><span style="font-family:Verdana;"> next, we reported the results of a survey we designed and executed. Categorical data was collected via questionnaire and analyzed to serve as a backbone of the robustness of categorical data. Several conjec</span><span style="font-family:Verdana;">tures about the independence of the socio-economic variables and e-commence</span><span style="font-family:Verdana;"> were tested. Some of the factors influencing patronage of e-commerce were </span><span style="font-family:Verdana;">identified. It is clear from the literature that as one’s academic qualification</span><span style="font-family:Verdana;"> improves</span></span><span style="font-family:Verdana;">, </span><span style="font-family:""><span style="font-family:Verdana;">there is an associated improvement in their preference for e-commerce, but the results revealed otherwise. Size of family was found to influence e-commerce. Both income and social status positively affected pa</span><span style="font-family:Verdana;">tronage in e-commerce. Gender also appeared to affect patronage in e-commerce</span><span style="font-family:Verdana;">. 62.3% of staff had patronized e-commerce</span></span><span style="font-family:Verdana;">.</span><span style="font-family:Verdana;"> This shows that e-commerce patronage was gradually increasing. It is therefore our considered view that policy documents regulating and monitoring the use of e-commerce be developed to increase e-commerce participation across the globe</span><span style="font-family:Verdana;">. </span><span style="font-family:Verdana;">It is also recommended that the bottlenecks which obstruct patronage in e-commence be addressed so that a lot more staff will develop a positive attitude towards e-commerce.展开更多
密度峰值聚类算法在处理分类型数据时难以产生较好的聚类效果。针对该现象,详细分析了其产生的原因:距离计算的重叠问题和密度计算的聚集问题。同时为了解决上述问题,提出了一种面向分类型数据的密度峰值聚类算法(Cauchy kernel-based d...密度峰值聚类算法在处理分类型数据时难以产生较好的聚类效果。针对该现象,详细分析了其产生的原因:距离计算的重叠问题和密度计算的聚集问题。同时为了解决上述问题,提出了一种面向分类型数据的密度峰值聚类算法(Cauchy kernel-based density peaks clustering for categorical data,CDPCD)。算法首先指出分类型数据距离度量过程中有序特性(分类型数据属性值之间的顺序关系)鲜有考虑的现状,进而提出一种基于概率分布的加权有序距离度量来缓解重叠问题。通过结合柯西核函数,在共享最近邻密度峰值聚类算法基础上重新评估数据密度值,改进了密度计算和二次分配方式,增强了密度多样性,降低了聚集问题带来的影响。多个真实数据集上的实验结果表明,相较于传统的基于划分和密度的聚类算法,CDPCD都取得了更好的聚类结果。展开更多
文摘Statistics is a powerful tool for data measurement. Statistical techniques properly planned and executed give meaning to meaningless data. The difficulty some practitioners encounter hinges on the fact that though there are numerous statistical methods available for use in analysis, the extent of their understanding and ease of using these tools for analysis is limited. This study has twofold purpose: firstly, literature on categorical data commonly used in research w</span><span style="font-family:Verdana;">as</span><span style="font-family:Verdana;"> reviewed</span><span style="font-family:Verdana;">;</span><span style="font-family:""><span style="font-family:Verdana;"> next, we reported the results of a survey we designed and executed. Categorical data was collected via questionnaire and analyzed to serve as a backbone of the robustness of categorical data. Several conjec</span><span style="font-family:Verdana;">tures about the independence of the socio-economic variables and e-commence</span><span style="font-family:Verdana;"> were tested. Some of the factors influencing patronage of e-commerce were </span><span style="font-family:Verdana;">identified. It is clear from the literature that as one’s academic qualification</span><span style="font-family:Verdana;"> improves</span></span><span style="font-family:Verdana;">, </span><span style="font-family:""><span style="font-family:Verdana;">there is an associated improvement in their preference for e-commerce, but the results revealed otherwise. Size of family was found to influence e-commerce. Both income and social status positively affected pa</span><span style="font-family:Verdana;">tronage in e-commerce. Gender also appeared to affect patronage in e-commerce</span><span style="font-family:Verdana;">. 62.3% of staff had patronized e-commerce</span></span><span style="font-family:Verdana;">.</span><span style="font-family:Verdana;"> This shows that e-commerce patronage was gradually increasing. It is therefore our considered view that policy documents regulating and monitoring the use of e-commerce be developed to increase e-commerce participation across the globe</span><span style="font-family:Verdana;">. </span><span style="font-family:Verdana;">It is also recommended that the bottlenecks which obstruct patronage in e-commence be addressed so that a lot more staff will develop a positive attitude towards e-commerce.
文摘密度峰值聚类算法在处理分类型数据时难以产生较好的聚类效果。针对该现象,详细分析了其产生的原因:距离计算的重叠问题和密度计算的聚集问题。同时为了解决上述问题,提出了一种面向分类型数据的密度峰值聚类算法(Cauchy kernel-based density peaks clustering for categorical data,CDPCD)。算法首先指出分类型数据距离度量过程中有序特性(分类型数据属性值之间的顺序关系)鲜有考虑的现状,进而提出一种基于概率分布的加权有序距离度量来缓解重叠问题。通过结合柯西核函数,在共享最近邻密度峰值聚类算法基础上重新评估数据密度值,改进了密度计算和二次分配方式,增强了密度多样性,降低了聚集问题带来的影响。多个真实数据集上的实验结果表明,相较于传统的基于划分和密度的聚类算法,CDPCD都取得了更好的聚类结果。
