Table 1.
Subsamples defined by the combination of age groups and fever status and observed frequencies of each pattern of test results.
Table 2.
Lower – – and upper –
– bounds of a
confidence level for a two-sided confidence interval –
– for a proportion
(
, where
is the number of successes) using different methods.
Table 3.
Some measures for the selected models (under HCI).
Table 4.
Bayesian estimates of prevalence, sensitivities, specificities and predictive values, given by posterior means and 95% credibility intervals – Mean [] – with non-informative priors, by age groups and fever status, using the models M3, M4 and M5.
Table 5.
Some information based on literature – RDT (ICT Diagnostics, Cape Town, South Africa).
Table 6.
Coefficients and theoretical quantiles (
) of Beta distributions for sensitivities (
) and specificities (
): a skeptical, a optimistic and our prior beliefs distribution.
Table 7.
Bayesian estimates of the malaria infection prevalence, sensitivities, specificities and predictive values, given by posterior means and 95% HPD intervals - Mean [95% HPD] - by age groups and fever status, using skeptical, optimistic and our prior distributions to M5.
Table 8.
Point estimates and 95% confidence intervals, though five different methods, for the sensitivity and the specificity of RDT in each subpopulation (
and
) and overall (
and
), using microscopy as a gold standard.