Estimating prevalence
# Estimated true prevalence and predictive values from survey testing

Sample size
Number positive
Test sensitivity
Test specificity
Confidence level
0.9
0.95
0.98
0.99
Confidence interval for apparent prevalence
Normal approximation
Clopper-Pearson exact
Wilson
Jeffreys
Agresti-Coull
Confidence interval for true prevalence
Normal approximation
Clopper-Pearson exact
Sterne
Blaker
Wilson
All
Submit

Estimate the true prevalence, as well as positive and negative predictive values and likelihood ratios from survey testing results using a test of known sensitivity and specificity.

Confidence limits for both apparent and true prevalence estimates are calculated. Values are also plotted for a range of possible survey results.

Confidence limits for apparent prevalence use methods from:

Brown, LD, Cat, TT and DasGupta, A (2001). Interval Estimation for a proportion.*Statistical Science* **16**:101-133.

True prevalence estimates are calculated as described by:

Rogan and Gladen (1978). Estimating prevalence from the results of a screening test.*American Journal of Epidemiology* **107**:71-76.

True prevalence estimates that are less than zero or greater than one are not consistent with assumed sensitivity and specificity values, and are indicated by "<0" and ">1", respectively Confidence limit calculations assume sensitivity and specificity are known exactly. The normal approximation method uses the formula described by Greiner, M and Gardner, IA (2000). Application of diagnostic tests in epidemiologic studies.*Preventive Veterinary Medicine* **45**:43-59.

Blaker's, Sterne, Clopper-Pearson and Wilson confidence limits are calculated as described by Reiczigel, Földi, Ózsvári (2010). Exact confidence limits for prevalence of a disease with an imperfect diagnostic test,*Epidemiology and Infection* **138**:1674-1678. The authors recommend Blaker's interval for general use.

Estimate the true prevalence, as well as positive and negative predictive values and likelihood ratios from survey testing results using a test of known sensitivity and specificity.

Confidence limits for both apparent and true prevalence estimates are calculated. Values are also plotted for a range of possible survey results.

Confidence limits for apparent prevalence use methods from:

Brown, LD, Cat, TT and DasGupta, A (2001). Interval Estimation for a proportion.

True prevalence estimates are calculated as described by:

Rogan and Gladen (1978). Estimating prevalence from the results of a screening test.

True prevalence estimates that are less than zero or greater than one are not consistent with assumed sensitivity and specificity values, and are indicated by "<0" and ">1", respectively Confidence limit calculations assume sensitivity and specificity are known exactly. The normal approximation method uses the formula described by Greiner, M and Gardner, IA (2000). Application of diagnostic tests in epidemiologic studies.

Blaker's, Sterne, Clopper-Pearson and Wilson confidence limits are calculated as described by Reiczigel, Földi, Ózsvári (2010). Exact confidence limits for prevalence of a disease with an imperfect diagnostic test,

© Ausvet 2023