Bias and Confounding Reading

Question 1

define bias

Answer 1

lack of internal validity or incorrect assessment of association between exposure and effect

Question 2

how did Sackett and Choi classify biases

Answer 2

according to the stages of research
specification and selection of sample
execution of experiment
measurement of exposure
data analysis

Question 3

what did Kleinbaum et al find

Answer 3

3 groups of biases
confounding
selection bias
information bias

Question 4

explain competing risks

Answer 4

when 2 or more outputs are mutually exclusive and compete for same subject
e.g death only happens once and the risk factor for death can be affected by an earlier risk

Question 5

what is healthcare access bias

Answer 5

patients admitted to institution do not represent cases originated in the community
either because admissions are determined by interest of health personnel (popularity bias)
or if patients are attracted to the prestige of a hospital (centripetal bias)

Question 6

what is Neyman bias

Answer 6

e.g smoking and myocardial infarction
if smokers/non-smokers are interviewed after heart attack and smokers die more frequently then the sample left will show lower frequency of smoking
undervalues the association

Question 6

what is spectrum bias

Answer 6

validity when researcher only included clear or definitive cases - dont represent conditions of normal diagnosis
specificity and sensitvity of a diagnostic test are wrongly increased

Question 7

what is survivor treatment selection bias

Answer 7

those who live longer and more likely to receieve certain treatment
so retrospective analysis can yield positive association between treatment and survival

Question 8

what is the healthy worker effect

Answer 8

lower mortality observed in employed population, tend to be healthier

Question 9

what is Berkson’s bias

Answer 9

when probability of hospitalisation and cases and controls differs
influenced by exposure

Question 10

why can matching sometimes cause selection bias

Answer 10

overmatching - when researchers match by non-confounding variables (associated with the exposure but not disease)
which underestimates the association

Question 11

what is relative control bias

Answer 11

correlation in exposure status between cases and relative controls yields biased estimated of association between exposure and outcome

Question 12

what does a non-random sampling bias yield

Answer 12

a non representative sample

Question 13

what does loss to follow up affect

Answer 13

validity of statistical results

Question 14

what are the 3 main types of information bias

Answer 14

misclassification bias
ecological fallacy
regression to the mean

Question 15

what is misclassification bias

Answer 15

when sensitivity or specificity of procedure to detect exposure is not perfect so diseases subjects mistakenly classified as non diseased and vice versa

Question 16

what is differential misclassification bias

Answer 16

when misclassification is different in the groups to be compared

Question 17

what is non-differential misclassification bias

Answer 17

misclassification is the same across groups to be compared

Question 18

in what studies does detection bias typically occur

Answer 18

its an information bias typically occurring in cohort/clinical trials

Question 19

what is rumination bias

Answer 19

happens within recall bias when the presence of disease influences the perception of its causes

Question 20

outline reporting bias

Answer 20

participants collaborating with researchers to give answers they believe are of interest
or underreporting bias is common with socially undesirable behaviours like alcohol consumption

Question 21

what is ecological fallacy

Answer 21

bias when analyses realised in ecological (group) level are used to make inferences at individual level

Question 22

what is the regression to the mean phenomenon

Answer 22

variable that shows an extreme value on first assessment will tend to be closer to centre of its distribution on later measurement

Question 23

how can we neutralise regression to the mean phenomenon

Answer 23

use appropriate reference group

Question 24

what is sick quitter bias

Answer 24

related to protopathic bias
people with risky behaviours quitting their habits as a consequence of disease - so studies label them as non-exposed and underestimate the true association

Question 25

what is temporal ambiguity

Answer 25

when it cannot be established that the exposure precedes effect
common in cross sectional and ecological studies

Question 26

outline confounding

Answer 26

when a variable is a risk factor for effect among non-exposed people and is associated with exposure of interest in pop from which the effect derives, without being affected by exposure or disease

Question 27

at what stages can confounding be neutralised

Answer 27

at design stage - by matching or randomisation
analysis - if confounders have been measured properly

Question 28

outline confounding by group

Answer 28

in ecological study when exposure prevalence of each community is correlated with disease risk in non-exposed of same community
can produce ecological fallacy

Question 29

outline confounding by indication

Answer 29

when treatment is indicated by perceived high risk, poor prognosis or some symptoms
the confounder is the indication
mainly in retrospective observational studies analysing interventions

Question 30

what is allocation of intervention bias

Answer 30

when intervention is differentially assigned to population
common in non-randomised trial
if sequence is known in advance may produce selection bias

Question 31

what is compliance bias

Answer 31

degree of compliance influences efficacy assessment of the intervention.

Question 32

what is contamination bias

Answer 32

when intervention-like activities find their way into control group
biases the estimate of intervention effect toward null hypothesis