hse_finite | R Documentation |
Herd Sensitivity calculated with the assumption of a finite population
hse_finite( id, n_tested, N, test_Se, dp, rounding = c("none", "ceiling", "round", "floor") )
id |
The herdid. |
n_tested |
The number tested in each URG |
N |
The number of units in each of the URG |
test_Se |
The sensitivity of the test. This may have length == 1 if all URG and all herds have the same test_Se. It may also have length(test_Se) == length(n_tested). |
dp |
The design prevalence (dp) could be length(dp) == 1 if all URG and herds have the same dp. It could alternatively be length(dp) == length(n_tested) if different design prevalences are to be applied to each URG. |
rounding |
How should the proportion of animals be rounded? Default value is 'none' which does no rounding. Other options are 'round', 'ceiling', and 'floor'. 'round' rounds the dp * N to the nearest integer and then selects 1 if the value is 0. 'ceiling' takes the ceiling of dp * N, this is consistent with the method in the Rsurveillance package. 'floor' takes the floor of dp * N and makes it 1 if the result is 0. |
Calculate the Herd sensitivity when multiple samples from individual units within the herd. The function uses the total population size to adjust the estimates consistent with a finite population. This method for calculation of HSe is typically used when greater than 10
A data.frame. A dataframe is returned with 2 columns: "id" and HSe
df <- data.frame(id = seq(1:20), n_tested = rpois(20, 5), N = 100, test_Se = 0.3, dp = 0.05) ## Calculate the herd level sensitivity for each of these herds hse_finite(df$id, df$n_tested, df$N, df$test_Se, df$dp)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.