Binomial Distribution Sample Confidence Intervals Estimation 4. Post Test Probability
|
 |
|
Post a Comment
|
|
|
|
|
|
ABSTRACT:
Posttest probability is one of the key parameters which can be measured and interpret in dichotomous diagnostic tests. Defined as the proportion of patients, which present particular test result and the target disorder, the posttest probability is a parameter used in assessing the efficiency of the diagnostic. As a point estimated parameter, posttest probability needs a confidence interval in order to interpreting trustworthiness or robustness of the finding. Unfortunately, for post test probability there was no confidence intervals reported in literature. The aim of this paper is to introduce six methods named Wilson, Logit, LogitC, BayesF, Jeffreys, and Binomial as methods of computing confidence intervals for posttest probability and to present theirs performances.
Computer implementations of the methods use the PHP language. The performance of each method for different sample sizes and different values of binomial variable was asses using a set of criterions. One criterion was the average of experimental errors and standard deviations. Second, the deviation relative to imposed significance level (á = 5%). Third, the behavior of the methods when the sample size vary from 4 to 103 and on random sample and random binomial variable in 4..1000 domain.
The results of the experiments show us that the Binomial method obtain the best performances in computing the confidence intervals for posttest probability for sample size starting with 36.
|
|
|
|
STATISTICS
|
|
Click on # to view
|
|
Citations
|
|
2
|
|
References
|
|
2
|
|
Comments
|
|
0
|
|
Quality
|
|
0/0.00
|
|
Interest
|
|
0/0.00
|
|
View(er)s
|
|
1/443
|
|
|
|
|
|
|
| Prev |
Next |
|