Scribd
Upload
56 views12 pages

Bias and Confounders

This document defines bias and confounders in epidemiological studies. It discusses two types of bias - information bias (which occurs during data collection) and selection bias (when study groups are not representative). It also defines confounders as variables that distort the observed association between exposure and outcome. The document recommends various methods to control for bias and confounders, including blinding subjects, using objective records, randomization, matching, restriction, and statistical modeling during analysis.

Uploaded by

Jake Miller
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
56 views12 pages

Bias and Confounders

This document defines bias and confounders in epidemiological studies. It discusses two types of bias - information bias (which occurs during data collection) and selection bias (when study groups are not representative). It also defines confounders as variables that distort the observed association between exposure and outcome. The document recommends various methods to control for bias and confounders, including blinding subjects, using objective records, randomization, matching, restriction, and statistical modeling during analysis.

Uploaded by

Jake Miller
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 12

BIAS AND CONFOUNDERS

DEFINITION
• BIAS- IS AN ERROR THAT RESULTS IN THE
SYSTEMATIC DEVIATION OF THE TRUE
ESTIMATION OF THE ASSOCIATION BETWEEN
THE EXPOSURE AND OUTCOME
• TYPES:
• INFORMATION (MEASUREMENT BIAS)
• SELECTION BIAS
INFORMATION (MEASUREMENT
BIAS)
• OCCURS AT DATA COLLECTION STAGE. THIS
TYPE OF BIAS IS COMMON IN A CASE-
CONTROL STUDY (RECALL BIAS). DURING AN
INTERVIEW, THIS TYPE OF BIAS IS MOST
LIKELY TO OCCUR DURING AN INTERVIEWER –
ADMINSTERED METHOD OF DATA
COLLECTION.
• FAULTY DATA COLLECTION TOOLS; SCALE, BP,
GLUCOMETERS ETC
SELECTION BIAS
• OCCURS WHEN THE STUDY PARTICIPANTS
SELECTED FOR A STUDY DO NOT REPRESENT
THE GENERAL POPULATION TO WHICH THE
STUDY WILL ULTIMATELY BE APPLIED TO. IT
CAN ALSO OCCUR IF STUDY GROUPS ARE NOT
COMPARABLE
• EXAMPLE A STUDY AMONG TERTIARY
FACILITY HEALTH WORKERS BUT DATA
COLLECTED FROM PHC FACILITIES
AVOIDING BIAS
• BLINDING (INFORMATION BIAS)
• USE OF OBJECTIVE RECORDS (INFORMATION
BIAS)
• USE OF WELL DESIGNED QUESTIONNAIRE
• USE QUALITY MEASUREMENT TOOLS; PRE-
TESTING IS IMPORTANT
CONFOUNDERS
• CONFOUNDERS ARE VARIABLES THAT
PROVIDE AN ALTERNATIVE ASSOCIATION
BETWEEN AN EXPOSURE AND AN OUTCOME

• OCCUPATION LUNG CANCER

• SMOKING
• CONFOUNDING OCCURS WHEN AN OBSERVED
ASSOCIATION BETWEEN AN EXPOSURE AND
AN OUTCOME IS DISTORTED BECAUSE THE
EXPOSURE OF INTEREST IS CORRELATED WITH
ANOTHER RISK FACTOR
CONTROL OF CONFOUNDERS
• DONE AT THE DESIGN STAGE AND/OR THE
ANALYSIS STAGE
DESIGN STAGE
• RESTRICTION: One way to control
confounding is to limit the study to people
who have particular characteristics.
• For example, in a study on the effects of
coffee on coronary heart disease,
participation in the study could be restricted
to nonsmokers, thus removing any potential
effect of confounding by cigarette smoking.
RANDOMISATION
• THIS IS THE BEST METHOD USED TO CONTROL
FOR CONFOUNDERS
• IT ENSURES THE CONFOUNDING VARIABLES
ARE EQUALLY DISTRIBUTED AMONG THE TWO
GROUPS BEING COMPARED. USED MORE IN
INTERVENTIONAL STUDIES
• A STUDY TO DETERMINE THE EFFECT ON A
SMOKING CESSATION INTERVENTION AMONG
YOUTHS
MATCHING
• COMMONLY USED IN CASE-CONTROL STUDIES
AND ENSURES THE CONTROLS SELECTED ARE
SIMILAR TO CASES IN TERMS OF POTENTIAL
CONFOUNDERS
ANALYSIS STAGE
• STRATIFICATION
• STATISTICAL MODELLING

You might also like