Return to 2016-05-29-a-in.txt CVS log

Up to [local] / OpenXM / src / hgm / mh / src / Testdata

Added a test data to study numerical instatiblity.

%!version2.0
%Mg=
2
%Beta=
20
0.03
%X0g=
0.3
%Hg=
0.001
%Dp=
1
%Xng=
200.0
## (m+1)/2=1.5, (n1+n2)/2=(5+10)/2=7.5
## (n1+m+1)/2=(5+2+1)/2=4
%p_pFq=2, 1.5, 7.5
%q_pFq=1, 4.0
%ef_type=2

## a<-hgm.p2wishart(m=2,beta=c(20,0.03),q=0.3,q0=0.1,err=c(1e-15,1e-10))
## [1] 0.3007164510 0.0004639517 0.0011994333 0.0244888143 0.0631431534
##
## ../hgm_jack-n --idata 2016-05-29-a-in.txt 
##  Output of this input: Iv[0] = 16577.4
##  Ef= 2.58651e-08,  Iv[0]*Ef = 0.0004287658  with approxdeg=88
## Error rate:  only one digit is valid.
## 16577*2.58651e-8-a[2]
## [1] -3.518591e-05
## 16577*2.58651e-8/a[2]
## [1] 0.9241604
## degree 130 does not improve the Iv[0] value.
## Iv[0] herpaps should be 17937.36
##
## plot(hgm.p2wishart(m=1,beta=c(0.03),q=20,q0=0.3,err=c(1e-15,1e-10),autoplot=1))
## already gives a wrong answer.