Re: st: metandi error: matrix has missing values

["Ben Dwamena" <bdwamena@med.umich.edu>]

I used midas for your data without difficulty....ssc install midas

 midas tp fp fn tn, res(all)



META-ANALYTIC INTEGRATION OF DIAGNOSTIC TEST ACCURACY STUDIES



SUMMARY DATA AND PERFORMANCE ESTIMATES
Bivariate Binomial Mixed Model
 
Number of studies =  4
 
Reference-positive Subjects =  189
 
Reference-negative Subjects =   27
 
Pretest Prob of Disease =0.875
 
 
ROC Area, AUROC = 0.87 [0.84 - 0.90]


Heterogeneity (Chi-square): LRT_Q = -0.000, df =3.00, LRT_p =0.500

Inconsistency (I-square): LRT_I2 = 100.00, 95% CI = [0.00-100.00]



Parameter                   Estimate          95% CI

Sensitivity                    0.852 [   0.794,   0.896]

Specificity                    0.741 [   0.547,   0.871]

Positive Likelihood Ratio      3.286 [   1.732,   6.233]

Negative Likelihood Ratio      0.200 [   0.133,   0.301]

Diagnostic Score               2.799 [   1.849,   3.749]

Diagnostic Odds Ratio         16.428 [   6.356,  42.466]

Ben Adarkwa Dwamena, MD

Assistant Professor of  Radiology
Division of Nuclear Medicine
Department of Radiology
University of Michigan Medical School
1500 E. Medical Center Drive
B1  G505   University  Hospital
Ann Arbor, MI 48109-0028

bdwamena@umich.edu

http://sitemaker.umich.edu/metadiagnosis



Staff Physician
D748 Nuclear Medicine Service (115), 
VA Ann Arbor Health Care System
2215 Fuller Road
Ann Arbor, MI 48105
734-761-7886 Phone
734-761-5229 Fax


>>> john metcalfe  04/12/10 6:06 PM >>>
Dear Statalist,
I am using -metandi- with Stata 11. With one of my subsets of data
(the smallest, below), I get the error ‘Maximum number of iterations
exceeded’ when I specify the *gllamm- option, and ‘invsym(): matrix
has missing values’ when I do not.

Is there a workaround for this, or am I trying to summarize too little
data?
Thank you,
John


      | id        tp        fp         fn       tn |
     |--------------------------------------------|
   2. |  2        28         0         5         6 |
   4. |  4        35         3         4         5 |
   5. |  5        18         3         4         7 |
  14. | 14        80         1        15       2 |

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

**********************************************************
Electronic Mail is not secure, may not be read every day, and should not
be used for urgent or sensitive issues
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/