Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
11 Cards in this Set
- Front
- Back
Common reasons why a surrogate endpoint may fail
|
1)D variable not relevant (whiteness of teeth and lung cancer).
2)D variable relevant but extreme value may confer poor health. 3)Procedures to change D have other adverse (worse) effects. |
|
Issues associated with measuring D
|
Correct measurement procedures.
How well executed. |
|
Diagnostic criteria
|
Involve expert.
Have definitive case definition |
|
Disease onset timeing
|
Index date: time of onset - should be explicitly outlined
|
|
Identifying Death
|
1)State vital records
2)National vital records 3)National death index 4)Medicare enrollment 5)Interview follow-up |
|
Issues for using death
|
1)Quality of code of death on death certificate.
2)Determine time of disease onset 3)Relevance to study question 4)Power |
|
Identify Diseases leading to medical care
|
1)Provider records
2)Registries 3)Insurance 4)Interview |
|
Key issues of medical care and disease
|
1)Access to records
2)Completeness 3)Exposure influece decision to diagnose/treat 4)Appropriate severity level |
|
Misclssification of D can
|
Incorrectly classify non-cases of D (False pos - Poor PPV or Specificity).
Fail to detect true D (Sensitivity). |
|
Nondifferential misclassification
|
false positive can bias towards null
|
|
Differential Misclassification
|
False negative: Bias AWAY from the null
|