求编程算出下列数据的SA与SE

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

data machine;
input x1 x2 x3 @@;
cards;
0.236 0.257 0.258
0.238 0.253 0.264
0.248 0.255 0.259
0.245 0.254 0.267
0.243 0.261 0.262
;
SA即组间偏差平方和。SE即组内偏差平方和。
我的目的是希望能不用PROC ANOVA的情况下求出来
请教各位大虾啦

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：machine ANOVA Input cards Data machine

1# 6203479170

I assume you are thinking of this ANOVA:

1. 
   
2. data machine1;
   
3. keep y c;
   
4. set machine;
   
5. array x(3);
   
6. do c = 1 to 3;
   
7.   y = x(c); output;
   
8. end;
   
9. run;
   
10. proc anova;
    
11. class c;
    
12. model y = c;
    
13. run; quit;

复制代码

So, the SSA/QA and SSE/QE may calculate like that:

1. 
   
2. data have;
   
3. keep QE QA;
   
4. do until(Eof);
   
5.   set machine end = Eof;
   
6.   array x(3); array SumX(3); array nX(3); array MeanX(3);
   
7.   do i = 1 to 3;
   
8.    SumX(i) = sum(SumX(i), X(i)); nX(i) = sum(nX(i), (not missing(x(i))));
   
9.   end;
   
10. end;
    
11. do i = 1 to 3;
    
12.   MeanX(i) = SumX(i)/nX(i);
    
13. end;
    
14. GmeanX = sum(of SumX(*))/sum(of nX(*));
    
15. do i = 1 to nobs;
    
16.   set machine nobs = nobs  point = i;
    
17.   array ss(3); array sss(3);
    
18.   do k = 1 to 3;
    
19.    ss(k) = (x(k)-MeanX(k))**2;  sss(k) = (MeanX(k)-GmeanX)**2;
    
20.   end;
    
21.   QE = sum(QE, sum(of ss(*))); QA = sum(QA, sum(of sss(*)));
    
22. end;
    
23. run;

复制代码