ERRORS IN ERRORS IN EPIDEMIOLOGICAL EPIDEMIOLOGICAL STUDIES STUDIES Pratap Singhasivanon Singhasivanon Pratap Department of Tropical Hygiene Department of Tropical Hygiene
An important goal of epidemiological studies is to measure accurately the occurrence of exposure/risk factors and disease outcome
Page 3 = + = + SYSTEMATIC ERROR RANDOM ERROR SYSTEMATIC ERROR RANDOM ERROR ERROR ERROR ERROR Fluctuation of and A false or mistaken BIAS estimate around the BIAS result obtained in BIAS population value a study or (RANDOM VARIABILITY) experiment Error due to factorsthat inherent in the Result obtained in sample design, conduct differs from result that would and analysis be obtained if the entire population were studies
Page 4 ERROR ERROR Is defined as a false or mistaken result obtained in a study or experiment Consists of 2 components Systematic error Random error Random error
Page 5 RANDOM ERROR RANDOM ERROR Is the divergence, due to chance alone, of Is an observation on an sample from the true population value
Page 6 RANDOM ERROR RANDOM ERROR Refers to fluctuations around a true value because of Sampling variability SYSTEMATIC ERROR SYSTEMATIC ERROR Any difference between the true value and that actually obtained that is the result of all causes other than Sampling variability.
Errors in epidemiological studies E r r o r Random error (chance) Systematic error (bias) S t u d y s i z e Source: Rothman, 2002
Bias � Bias occurs when an estimated association (RR, OR, difference in means etc.) deviates from the true measure of association � Consequence of bias � systematic error in RR, OR etc. � Bias may be introduced at design, implementation or analysis phase of a study
SYSTEMATIC ERROR : : SYSTEMATIC ERROR INFORMATION BIAS SELECTION BIAS CONFOUNDING Page 9
Should I believe my measurement? Smoking Lung cancer OR = 9.1 Random Error? True association Bias? causal non-causal Confounding?
Page 11 VALIDITY VALIDITY Is the expression of the degree to which a Is test is capable of measuring what it is intended to measure A study is valid if its results corresponds to A the truth, no systematic error and random error should be as small as possible
Page 12 A high reliability A high reliability means that in repeated measurements the results fall very close to each other; conversely, A low reliability A low reliability means that they are scattered.
Page 13 Different combinations of high and low Different combinations of high and low reliability and validity reliability and validity High Low Low High VALIDITY VALIDITY High High High High RELIABILITY RELIABILITY Low Low Low Low
Page 14 Internal and E External Validity xternal Validity Internal and External External Population Population Target Population INT. . INT EXT. EXT . Study Sample VALIDITY VALIDITY VALIDITY
Page 15 SELECTION BIAS SELECTION BIAS is a distorsion in the estimate of effect resulting from the manner in which subject are selected for the study population MAJOR SOUREC OF SELECTION BIAS SELECTION BIAS MAJOR SOUREC OF 1) flaws in the choice of groups to be compared 2) choice of sampling frame 3) loss to follow up or nonresponse during data collection 4) selective survival
Selection Bias � Systematic error resulting from manner in which subjects are selected or retained in the study � Can occur when: • Characteristics of subjects selected for study differ systematically from those in the target population • Study and comparison groups are selected from different populations
Selection Bias � Distortions that arise from – Procedures used to select subjects – Factors that influence study participation – Factors that influence participant attrition � Systematic error in identifying or selecting subjects – Examples are…
Selection Bias Example: � If cases & controls or exposed & non- exposed individuals were selected in such a way that an association is observed even though exposure & disease are not associated � May result from withdrawal or losses to follow-up of study subjects
Selection Bias � Problematic – Can result in over- or under- estimation of the true magnitude of the relationship between an exposure and an outcome – May produce an apparent association when none exists • OR/RR may be incorrect estimates ⇒ Invalid inferences about association of exposure & disease – May conceal a real association
Selection Bias � To avoid it, ensure that: – Subjects are representative of target population – Study and comparison groups are similar except for variables being investigated – Subject losses are kept to a minimum
Page 21 INFORMATION BIAS is a distortion in the INFORMATION BIAS measurement error or misclassification of subject on one or more variables MAJOR SOURCES OF INFORMATION BIAS MAJOR SOURCES OF INFORMATION BIAS 1) invalid measurement 2) incorrect diagnostic criteria 3) omissions imprecisions 4) other inadequacies in previously recorded data
Information Bias Information Bias � Definition Definition: : � � A distortion in the measure of association A distortion in the measure of association � caused by a lack of accurate caused by a lack of accurate measurements of the exposure (risk measurements of the exposure (risk factor) or disease state factor) or disease state � Also known as Also known as Measurement bias Measurement bias �
Information bias Information bias � Systematic error in the measurements of Systematic error in the measurements of � information on exposure or outcome information on exposure or outcome � Result in: Result in: � � Differences in accuracy Differences in accuracy of: of: � - exposure data between cases and controls exposure data between cases and controls - - outcome data between different exposure outcome data between different exposure - groups groups
Information bias Information bias � Sources of information bias include: Sources of information bias include: � � - - Defects in the measurement instruments Defects in the measurement instruments � � - - Deficiencies in the questionnaires Deficiencies in the questionnaires � � - - Inaccurate diagnostic procedures Inaccurate diagnostic procedures � � - - Ambigious Ambigious definition of exposure definition of exposure � � - - Poorly defined diagnostic criteria of Poorly defined diagnostic criteria of � disease disease � - - Incomplete or unreliable data sources Incomplete or unreliable data sources �
Information Bias Information Bias � Cause Cause: : � � Information bias arises when Information bias arises when � study variables (exposure, disease, or study variables (exposure, disease, or confounders) are inaccurately measured confounders) are inaccurately measured or classified resulting in Misclassification Misclassification or classified resulting in
MISCLASSIFICATION BIAS MISCLASSIFICATION BIAS Definition: Definition: the erroneous classification of an individual, a the erroneous classification of an individual, a value, or an attribute into a category other value, or an attribute into a category other than that to which it should be assigned than that to which it should be assigned � often results from an improper often results from an improper “ “cutoff point cutoff point” ” in in � disease diagnosis or exposure classification disease diagnosis or exposure classification � Hence errors are made in classifying to Hence errors are made in classifying to � either disease or exposure status either disease or exposure status
MISCLASSIFICATION BIAS MISCLASSIFICATION BIAS � Types of misclassification bias Types of misclassification bias � � Non differential (random) Non differential (random) � � Differential (systematic) Differential (systematic) �
Nondifferential Misclassification Misclassification Nondifferential Bias Bias � Occurs when there is equal misclassification of Occurs when there is equal misclassification of � exposure between diseased and non- -diseased diseased exposure between diseased and non study subjects study subjects � OR OR � � When there is equal misclassification of When there is equal misclassification of � disease between exposed and non- -exposed exposed disease between exposed and non study subjects study subjects
Non- -differential Misclassification differential Misclassification Non Bias Bias � If exposure or disease is dichotomous, If exposure or disease is dichotomous, � then, then, Non- -differential misclassification differential misclassification Non causes a bias of the RR or OR causes a bias of the RR or OR towards the null towards the null
Recommend
More recommend
