[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

From |
Roger Harbord <roger.harbord@bristol.ac.uk> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: comparison of diagnostic procedures |

Date |
Mon, 12 Sep 2005 17:45:35 +0100 |

-serrbar- should plot point estimates as well as CIs automatically so i'm a bit confused. With -twoway rcap- you'd have to overlay a scatter of the point estimates e.g. something like

. twoway rcap sens_lci sens_uci test || scatter sens_pt test

By the way i just noticed this in current issue of Statistics in Medicine which may be of relevance (haven't read it yet) :

Andriy I. Bandos, Howard E. Rockette, David Gur. A permutation test sensitive to differences in areas for comparing ROC curves from a paired design. Statistics in Medicine Volume 24, Issue 18 , Pages 2873 - 2893

--On 11 September 2005 19:40 +0100 Roger Newson <roger.newson@kcl.ac.uk> wrote:

You might possibly want to use the -senspec- package (downloadable from SSC) to calculate sensitivities and specificities, and then calculate their standard errors using the standard formulas.. A good overall performance indicator for comparing two ROC curves is the ROC area, and the difference between ROC areas (with confidence limits) can be calculated using the -somersd- package (also downloadable from SSC) together with -lincom-. I hope this helps. Roger At 19:20 10/09/2005, you wrote:Αρχικό μήνυμα από Roger Harbord <roger.harbord@bristol.ac.uk>: i tried to save the estimates with "parmest" but it is not possible with "diagt". The graph options "serrbar" and "twoway rcap" can produce a graph with the confidence intervals of the estimates but it is not possible to include the values of sensitivity or specificity.Any advice will be very helpful. Thank you a lot! > Try -serrbar- or -twoway rcap-. However you'd need to first save the > estimates and CIs as variables. Roger Newson's -parmest- package could > be one way to do that, after which you could use his -eclplot- package > (both available on SSC) as an alternative to -serrbar- or -twoway > rcap-. > > Roger H. > > --On 08 September 2005 16:15 +0300 htzavara@med.uoa.gr wrote: > > > Αρχικό μήνυμα από Roger Harbord <roger.harbord@bristol.ac.uk>: > > > > thank you a lot for your help. This is the solution and i have > > already find it in a related article. I would like to ask you if > > you know how i will produce an error graph (graph of sensitivities > > and their confidence interval) for every diagnostic test? Does > > stata 8 support a graph like this? > > > > thank you a lot in advance!!!!!! > > > > > >> As Pepe mentions on p43, you can test the null hypothesis of equal > >> sensitivity or of equal specificity of two binary tests done on the > >> same people using McNemar's test (-symmetry- or -mcc- commands in > >> Stata). I think something like: > >> > >> . symmetry test1 test2 if disease==1 /* for sensitivity */ > >> . symmetry test1 test2 if disease==0 /* for specificity */ > >> > >> > >> However with 12 tests there are a lot of comparisons (66 for each of > >> sens & spec) so some allowance for multiple testing does seem a > >> good idea. > >> > >> A Bayesian approach seems quite attractive for this sort of problem > >> as you can then meaningfully ask "what is the probability that > >> test X has the highest sensitivity?", which you can't in a > >> frequentist framework. You'd need to switch to something like > >> WinBUGS to get an answer to that though. > >> > >> If one test has higher sensitivity than another but lower > >> specificity or vice-versa then which is better also depends on the > >> disbenefits of false positives compared to false negatives of > >> course. > >> > >> Roger. > >> > >> -- > >> Roger Harbord > >> roger.harbord@bristol.ac.uk MRC Health Services Research > >> Collaboration & Dept. of Social Medicine University of Bristol > >> http://www.epi.bris.ac.uk/staff/rharbord > >> > >> --On 07 September 2005 15:07 -0400 "Michael P. Mueller" > >> <michael.mueller@utoronto.ca> wrote: > >> > >> > You might want to take a look at this book: Pepe, M.S. (2003). > >> > Statistical Evaluation of Medical Tests for Classification and > >> > Prediction. Dr. Pepe has Stata programs on her webpage you can > >> > download. Hope this helps, > >> > Michael > >> > > >> > htzavara@med.uoa.gr wrote: > >> > > >> >> Αρχικό μήνυμα από Svend Juul <SJ@SOCI.AU.DK>: > >> >> > >> >> > >> >> > >> >>> htzvara (?) wrote: > >> >>> > >> >>> i have one variable which represents if the patient has the > >> >>> disease (coding: 0- > >> >>> 1)--and this is standard. > >> >>> Additionally i have 12 more variables which represents the > >> >>> outcome of 12 different diagnostic procedures (coding: 0-1 for > >> >>> all of them).I want to find which is the best diagnostic > >> >>> procedure. I calculate the sensitivity and specificity and > >> >>> their confidence intervals for each of them. If the confidence > >> >>> interval for the sensitivity of one diagnostic procedure do not > >> >>> overlap the confidence interval for the Se of another diagnostic > >> >>> procedure then the difference is significant. > >> >>> Is there any test to perform and give p_value? Is there a need > >> >>> to make a correction for multiple comparisons.? > >> >>> > >> >>> ---- > >> >>> > >> >>> It is not quite clear to me what you want. If it is to find the > >> >>> single test that has the "best" predictive value, try Paul > >> >>> Seed's -diagt- (findit diagt). However, you must look at both > >> >>> sensitivity and specificity to get a meaningful assessment. > >> >>> > >> >>> I am not sure why you want to test whether the sensitivity of > >> >>> two tests are significantly different. And the confidence > >> >>> interval comparison you describe is quite insensititive. > >> >>> > >> >>> Would this show what you need: > >> >>> Make a logistic regression followed by -lroc- (ROC analysis): > >> >>> . logistic disease test1-test12 > >> >>> . lroc > >> >>> > >> >>> You might then try to remove tests to see whether removal makes > >> >>> a difference to the AUC (area under curve). > >> >>> > >> >>> Hope this helps > >> >>> Svend > >> >>> > >> >>> > >> >>> Thank you very much for your help. > >> >>> > >> >>> > >> >> I know about diagt and i used it to obtain the sensitivity - > >> >> specificity. Roc analysis cannot help as the variables which > >> >> represents the diagnostic tests are not continuous but > >> >> dichotomous (0-1).Even if i can see, which test has the best > >> >> se-sp i want to perform a test to prove it. > >> >> > >> >> thank you again.

* * For searches and help try: * http://www.stata.com/support/faqs/res/findit.html * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

**References**:**Re: st: comparison of diagnostic procedures***From:*Roger Newson <roger.newson@kcl.ac.uk>

- Prev by Date:
**st: Hausman test and probit estimations** - Next by Date:
**st: Data types, collapse & egen** - Previous by thread:
**Re: st: comparison of diagnostic procedures** - Next by thread:
**Re: st: comparison of diagnostic procedures** - Index(es):

© Copyright 1996–2014 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |