<p><strong><font size="4">线性回归的最经典入门教材，不多介绍了</font></strong></p><p><strong><font size="4">作者信息：</font></strong></p><p><font size="3"><strong>SANFORD WEISBERG<br/>University of Minnesota<br/>School of Statistics<br/>Minneapolis, Minnesota</strong></font></p><p><font size="4"><strong>A JOHN WILEY & SONS, INC., PUBLICATION</strong></font></p><p><strong><font size="5"></font></strong></p><p><font size="5"><strong>What’s New in this Edition</strong></font><br/>Many of the examples and homework data sets from the second edition have been<br/>kept, although some have been updated. The fuel consumption data, for example,<br/>now uses 2001 values rather than 1974 values. Most of the derivations are the<br/>same as in the second edition, although the order of presentation is somewhat<br/>different. To keep the length of the book nearly unchanged, methods that failed to<br/>gain general usage have been deleted, as have the separate chapters on prediction<br/>and missing data. These latter two topics have been integrated into the remaining<br/>text.</p><p>The continuing theme of the second edition was the need for diagnostic methods,<br/>in which fitted models are analyzed for deficiencies, through analysis of residuals<br/>and influence. This emphasis was unusual when the second edition was published<br/>and important quantities like Studentized residuals and Cook’s distance were not<br/>readily available in the commercial software of the time.</p><p>Times have changed, and so has the emphasis of this book. This edition stresses<br/>graphical methods including looking at data both before and after fitting models.<br/>This is reflected immediately in the new Chapter 1, which introduces the key idea of<br/>looking at data with scatterplots and the somewhat less universal tool of scatterplot<br/>matrices. Most analyses and homework problems start with drawing graphs. We<br/>tailor analyses to correspond to what we see in the graphs, and this additional<br/>step can make modeling easier and fitted models reflect the data more closely.<br/>Remarkably, this also lessens the need for diagnostic methods.</p><p>The emphasis on graphs leads to several additional methods and procedures that<br/>were not included in the second edition. The use of smoothers to help summarize<br/>a scatterplot is introduced early, although only a little of the theory of smoothing<br/>is presented (in Appendix A.5). Transformations of predictors and the response<br/>are stressed, and relatively unfamiliar methods based both on smoothing and on<br/>generalization of the Box–Cox method are presented in Chapter 7.</p><p>Another new topic included in the book is computationally intensive methods<br/>and simulation. The key example of this is the bootstrap, in Section 4.6, which<br/>can be used to make inferences about fitted models in small samples. A somewhat<br/>different computationally intensive method is used in an example in Chapter 10,<br/>which is a completely rewritten chapter on variable selection.</p><p>The book concludes with two expanded chapters on nonlinear and logistic regression,<br/>both of which are generalizations of the linear regression model. I have<br/>included these chapters to provide instructors and students with enough information<br/>for basic usage of these models and to take advantage of the intuition gained<br/>about them from an in-depth study of the linear regression model. Each of these<br/>can be treated at book-length, and appropriate references are given.</p><p></p><p>
276707.rar
(3.68 MB, 需要: 5 个论坛币)
本附件包括：- Applied Linear Regression.pdf
</p><p></p><br/>
[此贴子已经被作者于2008-12-15 11:41:03编辑过]
发帖
雷达卡
加好友,备注cda
京公网安备 11010802022788号
论坛法律顾问：王进律师
知识产权保护声明
免责及隐私声明
