《高级心理统十六讲》R示例及R-project介绍(ppt 51).ppt

授课计划 参加上机工作坊同学的预先准备 访问 /bin/windows/base/ 下载最新版R-(版本号)-win32.exe文件安装 安装后点图标运行。在联网条件下，点 Packages ? Install Package(s) … 如果弹出CRAN Mirror选择框，可单选 Austria 然后在弹出的Packages选择框里多选自己所需要安装的附加包，比如多层分析的nlme或lme4；缺失数据norm；结构方程的sem；可模拟多元正态分布数据的MASS；仿SPSS界面的Rcmdr。 访问 /R/R-doc/ 下载参考书 提取本页嵌入的PPT R代码 可以浏览http://R-/ 看看有哪些文档资源 五分钟的R-入门介绍 所有R代码、大部分R文献都属于公共版权，其中若干著名的入门教材有华人学者贡献的中译本 R的Windows界面 ctrl-r ctrl-l up-arrow/down-arrow tab esc help.search(“要查找的词语”) ?要查找的关键词 demo(lm.glm); example(anscombe); Google xxx site:R- R文档中的例示 R对大小写敏感 R(S)的语言风格 函数调用(试试如果不输入括弧) 函数包的调用 install.packages(); library(Rcmdr); data.frame df-data.frame(x,y,…) write.csv(df,choose.files());read.csv(choose.files()); 面向对象编程风格 Lm1-lm(y1~x1,data=anscombe);methods(plot); plot(Lm1) 就是plot.lm(Lm1) plot(anscombe)就是plot(anscombe,method=class(anscombe)) 向量和矩阵 %*% “p=.01” of Haller Krauss (2002). Try it on-line /go.php?url=lixiaoxu/zsu03DEC …You compare the means of your control and experimental groups (say, 20 subjects in each sample). Furthermore, suppose you use a simple independent means t-test and your result is significant (t=2.7, df=18, p=.01). … You have absolutely disproved the null hypothesis. Y/N You have found the probability of the null hypothesis being true. Y/N You have absolutely proved your experimental hypothesis. Y/N You can deduce the probability of the experimental hypothesis being true. Y/N You know, if you decide to reject the null hypothesis, the probability that you are making the wrong decision. Y/N You have a reliable experimental finding in the sense that if, hypothetically, the experiment were repeated a great number of times, you would obtain a significant result on 99% of occasions. Y/N 02/16 假设检验、区间估计之R示例 经典N-P方案：实验前决定拒绝域和二择对立分布，推算并报告α和Power；实验后报告“显著与否” 而非准确p值。 不同效应量的对立假设Power不同； 不同Power、不同主观概率，被说服程度不同。 α=.05, Power=.8, H1主观概率为.22的例示 Prosecutor’s Fallacy Defendant’s Fallacy (Thompson Schumann, 1987) 10e7人口的城市中有唯一罪犯 DNA比对巧合配对的概率是10e-4 罪犯比对DNA一定配对 某嫌疑犯DNA能够配对