Imagine that, in hypothetical study shown in table below, cases underestimated their exposure and, as a result, 20% of exposed cases were falsely categorized as unexposed, however that the classification of controls was not affected.
True results of the hypothetical case-control study with no measurement Error.
|
|
Cases
|
Controls
|
Total
|
|
Exposed
|
300
|
250
|
550
|
|
Unexposed
|
100
|
150
|
250
|
|
Total
|
400
|
400
|
800
|
Explain whether this type of misclassification random or systematic? Is it differential or nondifferential?
b) What effect would it have over the results of study? Draw up a two-by-two table displaying the misclassification, then determines estimates of the risk ratio for both true and the misclassified results and make comment on their difference to illustrate the effect.