精益六西格玛统计工具介绍假设检验.ppt

* * * * Need a TR example inserted here!!! * * * Rev C Deleted reference to underlying statistical model * Rev C – Changed title; Added three bullets to this slide for logical flow. * Note: Can use Cochran’s suggestion that states: “none of the expected frequencies should be less than one and no more than 20% of the expected frequencies shoild be less than 5”. See: Cochran, W.G. (1952) The Chi Square Goodnes-of-fit test. Annals of Mathematical Statistics, 23, 315-345. * The computed P-Value of 0.028 indicates that there IS a relationship between day of the week and rejection rate. What we do not know from this analysis, however, is which days are different. To learn this, we must dig deeper into the data and run additional analyses on subsets of the full data. We will do this on the following slides. StatTablesChi-Square Test * The computed P-Value of 0.028 indicates that there IS a relationship between day of the week and rejection rate. What we do not know from this analysis, however, is which days are different. To learn this, we must dig deeper into the data and run additional analyses on subsets of the full data. We will do this on the following slides. StatTablesChi-Square Test * The computed P-Value of 0.001 again indicates that there is a lack of independence between Friday and all of the others. We may interpret this as meaning that Friday is different from the others. We still do not know, however, whether there are any differences between the other days. To determine this, we need to do further analysis. StatTablesChi-Square Test * The computed P-Value of 0.001 again indicates that there is a lack of independence between Friday and all of the others. We may interpret this as meaning that Friday is different from the others. We still do not know, however, whether there are any differences between the other days. To determine this, we need to do further analysis. StatTablesChi-Square Test * In our final analysis, we compute a P-Value of 0.895, which