Binomial Distribution Sample Confidence Intervals Estimation 3. Post and Pre Test Odds
|
 |
|
Post a Comment
|
|
|
|
|
|
ABSTRACT:
When a diagnostic test results are dichotomous a 2L2 contingency table can be create, and some indices can be compute according to the method in which the data were collected. The posttest odds is define as the odds that the patient has the target disorder, after the test is carry out. Posttest odd is a point estimator of a diagnostic test and must be accompanying by a confidence intervals in order to be correctly interpret. The paper introduces some new methods of computing confidence intervals for post and pre test odds and presents theirs performances.
In order of assessing the methods, a PHP program was creates. A set of criterions was uses in order to assess implemented methods: the average of the experimental errors, the standard deviations, and the deviation relative to the imposed significance level ( = 5%). The methods were also assessed using random values from 4 to 1000.
The experimental results shows that the Logit and Binomial methods obtained the lowest standard deviation while the Clopper-Pearson method obtained the closed average of the experimental error to the imposed significance level ( = 5%).
|
|
|
|
STATISTICS
|
|
Click on # to view
|
|
Citations
|
|
3
|
|
References
|
|
2
|
|
Comments
|
|
0
|
|
Quality
|
|
0/0.00
|
|
Interest
|
|
0/0.00
|
|
View(er)s
|
|
1/492
|
|
|
|
|
|
|
| Prev |
Next |
|