作者gintin1003 (俊廷)
看板Statistics
标题[程式] 无母 SAS Wilcoxon & t-test 有何不同?
时间Wed Oct 5 22:05:26 2011
[软体程式类别]:SAS
[程式问题]:用一样的DATA跑Wilcoxon & t-test，两者有何异同? (SAS要看单尾双尾?)
[软体熟悉度]:(1~3个月)
[问题叙述]:
students in an introductory statistics class were asked how many brothers and sisters they have and whether their hometown is urban or rural.
number of siblings rural versus urban areas
rural 3 2 1 1 2 1 3 2 2 2 2 5 1 4 1 1 1 1 6 2 2 2 1 1
urban 1 0 1 1 0 0 1 1 1 8 1 1 1 0 1 1 2
a.
test for a significant difference between rural and urban areas using the
wilcoxon rank-sum test.
b.
test for a significant difference using the two-sample t-test,
and compare the results with those obtained in part a. w
hy are the results different?
[程式范例]:
data wh7;
INPUT Areas $ number @@;
CARDS;
Rural 3 Rural 2 Rural 1 Rural 1 Rural 2 Rural 1 Rural 3 Rural 2 Rural
2 Rural 2 Rural 2 Rural 5
Rural 1 Rural 4 Rural 1 Rural 1 Rural 1 Rural 1 Rural 6 Rural 2 Rural
2 Rural 2 Rural 1 Rural 1
Urban 1 Urban 0 Urban 1 Urban 1 Urban 0 Urban 0 Urban 1 Urban 1
Urban 1 Urban 8 Urban 1
Urban 1 Urban 1 Urban 0 Urban 1 Urban 1 Urban 2
;
PROC NPAR1WAY WILCOXON;
CLASS Areas;
EXACT WILCOXON;
VAR number;
RUN;
PROC TTEST;
CLASS Areas;
VAR number;
RUN;
PROC NPAR1WAY;
CLASS Areas;
EXACT SCORE=DATA/N=1000;
VAR number;
RUN;
--
※ 发信站: 批踢踢实业坊(ptt.cc)
◆ From: 220.132.181.187
1F：→ Chsieh:假设检定不同阿 一个是曲线下面积 一个是平均数 10/05 22:39
2F：→ gintin1003:那想问这两个检定用SAS跑出来後 有雷同之处? 与差异吗? 10/05 23:20
3F：→ gintin1003:wilcoxon & t-test 分别是 是要看单尾还是双尾? 10/05 23:21
4F：→ Chsieh:单尾还是双尾应该是看你的H0吧 跟用什麽方法没差 10/06 02:17
5F：→ yhliu:Wilcoxon 的方法是非参数化方法(所谓 "无母数方法"), 是比较 10/06 13:17
6F：→ yhliu:中位数; t test 是基於常态性条件的方法, 是比较平均数. 10/06 13:17