TY - JOUR
TI - EXPERIMENTAL QUANTILES OF EPIDEMIOLOGIC INDEXES IN CASE-CONTROL STUDIES
WITH NONDIFFERENTIAL MISCLASSIFICATION
AU - MARINOS, AT
AU - TZONOU, AJ
AU - KARANTZAS, ME
JO - Statistics in Medicine
PY - 1995
VL - 14
TODO - 12
SP - 1291-1306
PB - John Wiley & Sons, Ltd
SN - 0277-6715, 1097-0258
TODO - 10.1002/sim.4780141203
TODO - null
TODO - The formulae for some typical epidemiological indices in case-control
studies with non-differential misclassification are expressed in terms
of two groups (alpha, beta) and (gamma, delta) of misclassification
probabilities of exposure E and confounder C, respectively, and the
initially estimated frequencies. The parameters alpha and beta denote
the probability that subjects exposed to E are classified as non-exposed
and the probability that non-exposed ones will be classified as exposed,
respectively. Similarly, delta and gamma stand for the probability that
those who have been exposed to C will be classified as non-exposed and
the probability that non-exposed subjects are classified as exposed,
respectively. The non-negativeness of the expressions for the ‘true’
frequencies in terms of the measured ones and the misclassification
probabilities leads to the construction of feasibility regions for
alpha, beta, gamma and delta. For a number of ‘acceptable’ 4-tuples
(alpha, beta, gamma, delta), all of which lie inside these feasibility
regions, a sequence of feasible values for an epidemiological index is
determined, after employing a systematic procedure by means of a
‘searching net’ with increments Delta alpha, Delta beta, Delta gamma,
Delta delta. The procedure serves to determine the characteristics of
the (experimental) cumulative distribution function for any selected
epidemiological index. The final stage in exploiting the structure of
feasibility regions for alpha, beta, gamma and delta is to use the
cumulative distribution function to calculate quantiles for the index
associated with prescribed probabilities.
ER -