Exam 2: lecture 1 BIAS

Question 1

Bias

Answer 1

Systematic (non random) error in study design or conduct leading to erroneous results

Question 2

What does bias distort?

Answer 2

Relationship between exposure and outcome

Question 3

Can a bias be fixed?

Answer 3

No; once it has already occurred (after study ends)

Question 4

What can be done to lower bias?

Answer 4

Prospective consideration

-still must assess for it to confirm internal validity

Question 5

That are the elements of bias impact that investigator look at?

Answer 5

Source/type
Magnitude/strength
Direction

Question 6

Magnitude/ strength in bias

Answer 6

One of the elements investigated

• Can account ENTIRELY for a weak association (small RR/OR)
• Not likely to account entirely for a VERY STRONG association (large RR/OR)

Question 7

Direction in bias

Answer 7

Can OVER or UNDER estimate the true measure of association

-can have an ENHANCING or MINIMIZING effect on the true measure of association (toward or away from a ration of 1.0)

Question 8

Selection- related bias

Answer 8

Any aspect in the way the researcher selects or acquires study subjects which creates systematic difference between groups

DONT DO ANYTHING THAT IS DIFFERENT, OR CREATES A DIFFERENCE, BETWEEN GROUPS

!!!!SAME-SAME-SAME!!!!

Question 9

Measurement-related (info/observed) BIAS

Answer 9

Any aspect in the way the researcher collects info, or measures/observes subjects which creates a systematic difference between groups
-errors in measurement can also cause a resultant error in patient classification

Question 10

Types of selection Bias

Answer 10

Healthy-worker bias

Self-selection/ participant (responder) bias

Question 11

Healthy worker bias

Answer 11

Can easily be seen in prospective cohort studies

Question 12

Self-selection bias

Answer 12

Those that wish to participate may be different in some way to those that don’t volunteer or self-select

Question 13

Types of measurement Bias “subject related”

Answer 13

Recall bias
Contamination bias
Compliance/ adherence bias
Lost to follow up bias

Question 14

Recall bias

Answer 14

Reporting bias

• differential level of accuracy/detail provided info between study group
• exposed or diseased subjects may have greater sensitivity for recalling their history or amplify their responses
• individuals can report their “effects” of exposure, disease symptoms or treatment differently bc they are part of a study

Question 15

Hawthorne effect

Answer 15

People know they are being watch, they do what their suppose to

Question 16

Contamination bias

Answer 16

Controlled group accidentally, or outside of study protocol, receive the treatment

Question 17

Compliance/adherence bias

Answer 17

Groups being interventionally studied have different compliance (people follow rules differently)

Question 18

Lost to follow up bias

Answer 18

Groups being studied have different withdrawal or lost to follow-up RATES or there are OTHER DIFFERENCES between those that stay in the study and those that withdraw or are lost to follow up
-differential vs non differential
(Lose more people in one group than other)

Question 19

Types of measurement Bias “observer-related”

Answer 19

Interview Bias

Diagnosis/surveillance bias

Question 20

Interviewer bias (proficiency)

Answer 20

-Difference in soliciting, recording, or interpreting on the part of the researcher
-interviewers knowledge may influence the structure, or tone, of questions or follow-up questions which may influence response form the study subject OR
-interventions/treatments are not applied equally between groups due to skill or training differences of study personnel or differences n stud procedure compliance by Staff at different sites
(Conscious or unconscious)

Question 21

Diagnosis/ surveillance bias

Answer 21

Expectation bias

• different evaluation, classification, diagnosis, or observation between study groups
• observers may have preconceived expectations of what they shout find in examination, evaluation, or follow up

Question 22

Interviewer’s Hawthorne

Answer 22

Interviewer has preconceived notions
Smoker could get more questions geared to heart disease
Non smoker could get more questions geared to no heart disease

Question 23

Measurement bias “screening related”

Answer 23

Lead-time bias

Question 24

Lead time bias

Answer 24

Benefit from a healthcare screening due to the early detection fo disease despite an unchanged clinical outcome
-extra time afforded by early detection

Question 25

Misclassification bias

Answer 25

Error in classifying either disease or exposure status, or both
(Measurement bias)

Question 26

Non differential Misclassification bias

Answer 26

Error in both groups
-attenuate the effect estimates
(Moves closer to 1/ example: 1.3—>1.1 or 0.3–>0.7)
UNRELATED

Question 27

Differential Misclassification bias

Answer 27

Error in one group
-can inflate or attenuate the effect estimates
Inflation moves away from 1

Question 28

Controlling for bias using three things

Answer 28

Precise
Accurate
Medically appropriate

Question 29

Types of controls for biases

Answer 29

Blinding/masking
Use multiple sources to gather information
Randomly allocate observers/interviewers for data collection (AND TRAIN THEM)
Build in as many methods to minimize loss to follow up