Chapter Nine Evaluating Results from Samples：九章从样本的评价结果.pptVIP

下载本文档

2
0
约6.16千字
约 22页
2018-06-24 发布于四川
举报
版权申诉

Chapter Nine Evaluating Results from Samples：九章从样本的评价结果.ppt

1、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
7、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

Chapter Nine Evaluating Results from Samples：九章从样本的评价结果

Chapter Nine: Evaluating Results from Samples Review of concepts of testing a null hypothesis. Test statistic and its null distribution Type I and Type II errors Level of significance, probability of a Type II error, and power. Objective is to develop concepts that are useful for planning studies. Choose test statistic (usually this is a sample mean) Balance two types of errors by choice of α (probability of a Type I error) and β (probability of a Type II error) Determine sample size so that α and β specifications are met. Even arbitrary rules have defined α and β. Statistical Sampling of Populations ASSUME there is a defined population and that we want to estimate such parameters as the mean of the population. Observe a small number of randomly selected members from the larger population. Apply appropriate statistics to the sample to generate correct conclusions. Why random samples? Other sampling procedures have failed consistently. 1932 Literary Digest Poll. 1948 Opinion Polls of Outcome of Presidential race. Random samples, correctly drawn, have known properties. Value of theorems and mathematical argument. Procedure of Examining a Test of a Hypothesis Start with question. Is a student a random guesser or knowledgeable about statistics? Specify a null hypothesis H0: Student is a random guesser. Null hypothesis should be plausible. Probability measures generated by null hypothesis should be easy to compute with. Procedure of Examining a Test of a Hypothesis Specify a statistic, a sample size, and a rule. Statistic=S4, number of correct answers in a four question true-false test, with questions of equal difficulty in random order. Sample size is the length of the test, 4 questions (an unreasonably short examination). Rule is to reject H0 when S4≥4. The value 4 is the “critical value”. This is an example of a “binomial test.” Procedure of Examining a Test of a Hypothesis Determine the properties of the procedure. Specify the null distribution of your test s