laomm002 发表于 2010-10-25 19:24 
bobguy 发表于 2010-10-25 04:34 
laomm002 发表于 2010-10-24 20:54 
问题如下:
已知血型的比例结构为
O型:q^2
A型:p^2+2pq
B型:r^2+2qr
AB型:2pr
其中q+p+r=1,p>0,q>0,r>0
现在任意调查了1000人,发现其中O型374人,A型436人,B型132人,AB型58人
在显著水平为0.05条件下,调查数据与理论比例是否相符?
请各位高手帮忙看一下这道题目怎么做,谢谢
Po =: prob of O型
Pa =: prob of A型
Pb =: prob of B型
Pab =: prob of AB型
Since q+p+r=1,p>0,q>0,r>0, then (q+p+r) ** =1 => Po, Pa, Pb, Pab is a multinomial distribution.
The estimates,
P(i) = N(i)/N i= o, a, b, ab, N(.) is the number in each type, N is the total number
var (P(i) )= P(i) * (1-P(i)) /N
Use types of O型374人,A型436人,B型132人 to estimate Po, Pa, Pb and their variance
Use the last one AB型58人 to do the checking/testing.
十分感谢
不过我不太清楚如何构造检验用的统计量,以及该统计量的分布如何
如果能详细讲解一下最好
可以贴到http://www.pinggu.org/bbs/thread-943862-1-1.html
在那里我设置了奖励
Here is the solution in SAS based on likelihood estimation. You may refer to SAS/Stats/Proc nlmixed for further directions. From estimates you can solve for p q r if wanted.
data t1;
n1=374 ; n2=436; n3=132; n4=58;
Size=sum(n1,n2,n3,n4);
do n=1 to Size;
if n<=n1 then Type=1;
else if n<=n1+n2 then Type=2;
else if n<=n1+n2+n3 then Type=3;
else Type=4;
output;
end;
run;
proc nlmixed data=t1;
parms Po=0.3 Pa=0.4 Pb=0.1;* Pab=0.058;
bounds 0<Po Pa Pb < 1;
if type=1 then p=Po;
else if type=2 then p=Pa;
else if type=3 then p=Pb;
else p=1-po-pa-pb;
P=MAX(1E-12,MIN(P,0.99999999));
loglik=log(p);
estimate 'test' 1-(Po+Pa+Pb) df=3;
model size ~ general(loglik);
run;
*************************results*****************************;
The NLMIXED Procedure
Specifications
Data Set WORK.T1
Dependent Variable Size
Distribution for Dependent Variable General
Optimization Technique Dual Quasi-Newton
Integration Method None
Dimensions
Observations Used 1000
Observations Not Used 0
Total Observations 1000
Parameters 3
Parameters
Po Pa Pb NegLogLike
0.3 0.4 0.1 1247.07722
Iteration History
Iter Calls NegLogLike Diff MaxGrad Slope
1 8 1170.80887 76.26835 461.134 -26161.1
2 11 1167.34289 3.46598 418.437 -639.639
3 13 1165.42142 1.921472 289.1771 -25.3955
4 14 1163.08601 2.335409 149.2346 -44.5881
5 15 1162.39915 0.686859 81.52841 -2.60364
6 17 1162.19791 0.201246 8.970628 -0.3725
7 19 1162.19606 0.001848 0.284705 -0.00372
8 21 1162.19604 0.000015 0.013426 -0.00003
9 23 1162.19604 4.725E-9 0.000062 -9.47E-9
NOTE: GCONV convergence criterion satisfied.
Fit Statistics
-2 Log Likelihood 2324.4
AIC (smaller is better) 2330.4
AICC (smaller is better) 2330.4
BIC (smaller is better) 2345.1
The SAS System 10:10 Tuesday, October 26, 2010 292
The NLMIXED Procedure
Parameter Estimates
Standard
Parameter Estimate Error DF t Value Pr > |t| Alpha Lower Upper Gradient
Po 0.3740 0.01530 1000 24.44 <.0001 0.05 0.3440 0.4040 0.000024
Pa 0.4360 0.01568 1000 27.80 <.0001 0.05 0.4052 0.4668 0.000062
Pb 0.1320 0.01070 1000 12.33 <.0001 0.05 0.1110 0.1530 0.000055
Additional Estimates
Standard
Label Estimate Error DF t Value Pr > |t| Alpha Lower Upper
test 0.05800 0.007392 3 7.85 0.0043 0.05 0.03448 0.08152