Term
|
Definition
| systematic error that results in an incorrect estimate of measure of association |
|
|
Term
|
Definition
- create spurious association when there is none (bias away from the null hypothesis)
- mask association when there is one (bias toward null hypothesis)
|
|
|
Term
| sources and types main types of bias |
|
Definition
- source
- introduced by investigator or study participants
- in design and conduct of study (can be evaluated by not fixed in the analysis phase)
- main types
|
|
|
Term
| selection bias (most likely study to have it, cause) |
|
Definition
- cause
- procedures used to select subjects into study that lead to result different than what would have been obtained from entire population
- most likely to occur in case control and retrospective cohorts (exposure and outcome have already occurred at time of study)
|
|
|
Term
| result of selection bias in case control studies |
|
Definition
- occurs when controls and cases are more or less likely to be included in study if they have been exposed or unexposed (inclusion of study not independent of exposure)
- relationship between exposure and disease observed among study participants is different from relationship between exposure and disease in individuals who would have been eligible but were not included
- OR will incorrectly represent the true relationship between exposure and disease in overall study population
|
|
|
Term
| define self selection/participation bias |
|
Definition
| refusal/nonresponse or agreement to participate that is related to both exposure and disease |
|
|
Term
| selection bias in cohort study |
|
Definition
| occurs when selection of exposed and unexposed subjects is not independent of outcome (only in retrospective) |
|
|
Term
| How to avoid selection bias |
|
Definition
- via study design and conduction
- same criteria for selecting cases and controls
- obtain all relevant subject records
- obtaining high participation rates
- taking into account diagnostic and referral patterns of disease
|
|
|
Term
| definition and result of observation bias |
|
Definition
- definition- error that arises from systematic differences in the way info on exposure or disease is obtained from study groups
- results- participants who are incorrectly classified as either exposed or unexposed or as diseased or nondiseased
occurs after subjects enter study
|
|
|
Term
| different types of observation bias |
|
Definition
- recall
- interviewer
- loss to follow
- differential and non-differential misclassification
|
|
|
Term
| recall bias (definition and result) |
|
Definition
- people with disease remember or report exposures differently (more or less accurately) than those with disease
- can result in over or under estimation of measure of association
|
|
|
Term
| solutions for reducing observation bias |
|
Definition
- use controls who are themselves sick
- use standard questionnaires that obtain complete information
- blind subjects to study hypothesis
|
|
|
Term
| define interviewer bias and when it can occur |
|
Definition
- definition- systematic difference in soliciting, recording, interpreting information
- can occur whenever exposure information is sought when outcome is known (case control) or when outcome information is sought when exposure is known (cohort)
|
|
|
Term
| solutions to reduce interviewer bias |
|
Definition
- mask interviewer to study hypothesis and disease or exposure status of subjects
- use standardized questionnaires or standardized methods of outcome (or exposure) ascertainment
|
|
|
Term
| loss to follow up (definition, results) |
|
Definition
- definition- subjects can no longer be located or when they no longer want to participate
- can reduce power of study to detect association because of small sample size available at analysis
- mainly concern in cohort and experimental studies if people who are lost to follow up differ with respect to both the outcome and exposure from those that remain in study
|
|
|
Term
| solution to loss to follow up |
|
Definition
| must achieve high and equal rates of follow up for exposed and unexposed groups |
|
|
Term
| non-differential misclassification (definition and results) |
|
Definition
- inaccuracies with respect to disease classification are independent of exposure
- inaccuracies with respect to exposure are independent of disease
- results
- makes groups more similar
- bias toward null if exposure has two categories
|
|
|
Term
| differential misclassification (definition, when it occurs, effect) |
|
Definition
- definition- degree of misclassification differs between groups being compared
- effect for dichotomous exposure factors may bias the association either away from or toward the null hypothesis
- may occur when info is collected differently for each study group or is an example of response bias
|
|
|
