Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: Midas
From
Roger Harbord <[email protected]>
To
[email protected], [email protected]
Subject
Re: st: Midas
Date
Thu, 5 May 2011 21:24:39 +0100
- metandi tp fn fn tn- gives the same error message (Stata 11.2;
-metandi- user-written command from SJ-9-2 st0163).
- metandi tp fn fn tn, gllamm- runs without error, however. In my
experience, -gllamm- is somewhat more reliable (if slower) than
-xtmelogit-, which is used by -midas- and -metandi- by default when
available (i.e. in Stata 10 and above).
In this case, some of the standard errors and confidence intervals are
missing, and the correlation between the logit-transformed sensitivity
and specificity is estimated as -1, on the boundary of the parameter
space. This may be related to the convergence issues; see Riley et al
2007 <http://dx.doi.org/10.1186/1471-2288-7-3>
. metandi tp fp fn tn, gllamm plot
True positives: tp False positives: fp
False negatives: fn True negatives: tn
Fitting univariate model for Sensitivity, Se = tp / (tp + fn)
Fitting univariate model for Specificity, Sp = tn / (tn + fp)
Fitting bivariate model:
Running adaptive quadrature
Iteration 0: log likelihood = -57.666576
Iteration 1: log likelihood = -56.600815
Iteration 2: log likelihood = -56.386241
Iteration 3: log likelihood = -56.38023
Iteration 4: log likelihood = -56.380145
Iteration 5: log likelihood = -56.380145
Adaptive quadrature has converged, running Newton-Raphson
Iteration 0: log likelihood = -56.380145
Iteration 1: log likelihood = -56.380145 (backed up)
Iteration 2: log likelihood = -56.380129
Iteration 3: log likelihood = -56.380129
Meta-analysis of diagnostic accuracy
Log likelihood = -56.380129 Number of studies = 11
------------------------------------------------------------------------------
| Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
Bivariate |
E(logitSe) | 2.219334 .362558 1.508733 2.929934
E(logitSp) | .5358204 .214943 .1145398 .957101
Var(logitSe) | .8619995 .5538091 .2447008 3.036538
Var(logitSp) | .3491799 .224272 .0991603 1.229591
Corr(logits) | -1 . . .
-------------+----------------------------------------------------------------
HSROC |
Lambda | 2.442185 .2538694 1.94461 2.93976
Theta | .5494571 .2833487 -.005896 1.10481
beta | -.4518337 .3683124 -1.23 0.220 -1.173713 .2700453
s2alpha | 0 . . .
s2theta | .5486282 . . .
-------------+----------------------------------------------------------------
Summary pt. |
Se | .9019723 .0320568 .8188733 .9493065
Sp | .6308396 .0500561 .5286037 .722541
DOR | 15.72346 4.089394 9.44421 26.17765
LR+ | 2.443307 .276928 1.956598 3.051086
LR- | .1553925 .0430096 .0903304 .2673167
1/LR- | 6.435319 1.781172 3.740882 11.07047
------------------------------------------------------------------------------
Covariance between estimates of E(logitSe) & E(logitSp) -.055003
Roger.
--
Roger Harbord
http://www.epi.bris.ac.uk/staff/rharbord.htm
On 5 May 2011 13:07, Ronan Conroy <[email protected]> wrote:
> On 2011 Beal 5, at 09:17, <[email protected]> <[email protected]> wrote:
>
>> When I run the midas command
>>
>> midas tp fp fn tn
>>
>> with this data:
>>
>> tp fp fn tn
>> 17 27 1 47
>> 18 3 2 11
>> 21 5 1 13
>> 44 3 22 15
>> 17 13 0 12
>> 56 28 1 16
>> 23 16 0 14
>> 79 9 23 26
>> 24 1 6 17
>> 28 21 3 24
>> 66 38 12 63
>
>
> The problem is reproducible on StataSE 11.2 on OS X.
>
> The sting is in the line
>
> 23 16 0 14
>
> If you omit this, midas runs.
>
> And that's all the help I can give, I'm afraid.
>
*
* 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/