Bias and Confounding Tutorial Dr Rufaidah Dabbagh MBBS
Bias and Confounding Tutorial Dr. Rufaidah Dabbagh MBBS, MPH Dr. Armen Torchyan MD, MPH CMED 304 Family and Community Medicine Department
Objectives To understand bias and how it can be minimized Recognize different types of bias Understand concept of confounding Learn how to think of possible confounding factors for associations between exposures and outcomes
Bias Types of Bias: ◦ Selection bias ◦ Information bias can lead to “misclassification” of your study participants. What could cause misclassification?
Misclassification of diagnosis Why misclassification of disease status? • Incorrect Diagnosis • Limited knowledge • Diagnostic process complex • Inadequate access to technology • Laboratory error • Disease subclinical • Detection bias (e. g. more thorough exam in exposed) • Subject Self report • Incorrect recall • Reluctant to be truthful • Records incorrectly coded in data-base Available at: http: //www. sph. emory. edu/activepi/Instructors/Kevin_MSword/Lesson_9 boh. htm. Accessed on Oct 18, 2011.
Misclassification of exposure Why misclassification of exposure status? • Imprecise measurement • Subject Self report • Interviewer bias • Incorrect coding of exposure data Available at: http: //www. sph. emory. edu/activepi/Instructors/Kevin_MSword/Lesson_9 boh. htm. Accessed on Oct 18, 2011.
So how can we minimize selection bias? Two general surgeons wanted to measure the association between eating healthy vegetables and having gall stones. They recruited patients in their hospital and formed two groups of participants: gall stone group, non-gall stone group. They interviewed individuals from each group to inquire about the previous intake of fruits and vegetables over the past 5 years.
How can we minimize selection bias? Reducing non-response Reducing loss to follow up Increasing sample size
What type of bias is this? You and your colleagues would like to conduct a study to see the prevalence of substance abuse among high school students living in Riyadh. You randomly chose your sample from a number of schools in Riyadh and distributed your questionnaires. What type of bias is this study be subject to? as i b n o i t a m r o Inf rting bias) o )/(rep s a i B e s n o p s (non-re
What type of bias is this? You were conducting a study on the association between duration of breastfeeding and malnutrition. You randomly select a group of mothers attending the MMR immunization clinic and ask them about the pattern and duration of breastfeeding they had for their children. What type of bias might this study be subject s a to? i b n o i t a m r ) o s f a i In b l l a (rec
Types of misclassification (differential and non-differential) Differential misclassification: ◦ When the misclassification results in exposure is incorrectly more in cases than in controls. Or vice versa; like one group has a lot more incorrect information than the other group Non-differential misclassification: ◦ When the misclassification is not related to exposure status or disease status. And is occurring at the same proportion in both groups; e. g. if 20% of cases are classified incorrectly on exposure in cases and about 20% in controls too
1. What type of misclassification is this? An obstetrician wanted to study the association between congenital malformations and history of infections during pregnancy. He interviewed women (a group who delivered children with malformations, and a group of women with normal children). He asked about history of all types of infections during pregnancy.
1. What type of misclassification can occur in this type of study? After finishing the interviews, he also wanted to go through the women's’ medical records, in order to minimize recall bias. He discovered that women who had a baby with malformation tended to remember all infections during pregnancy more than the mothers with normal babies. What kind of misclassification is this? Differential misclassification. (differential recall of exposure)
Differential misclassification
� CAN YOU THINK OF ANOTHER EXAMPLE ON DIFFERENTIAL MISCLASSIFICATION?
Available at: http: //ebp. lib. uic. edu/applied_health/files/images/random_cry. gif. Accessed on Oct 18, 2011.
Artificial Sweetener and Bladder Cancer A case-control study was conducted to investigate the association between artificial sweetener and bladder cancer. Controls were selected from a group of people diagnosed with obesity related conditions. It is well known that obesity related conditions are associated with an increased likelihood of using artificial sweetener. Could the association between artificial sweetener and bladder cancer be confounded by any external factors?
Confounding Obesity related conditions Artificial sweetener --- Bladder Cancer Unhealthy lifestyle (consumption of other artificial preservatives & carcinogens) Can you think of any other factors?
Birth Order and Down Syndrome A study was done to explore the association between birth order and Down syndrome. It was found with increasing birth order, there was also an increase in the occurrence of Down syndrome. The prevalence of Down syndrome was 6/1000 live births at the first birth and 16/1000 live births, for birth of 5 or greater.
Affected babies per 1000 live births Birth Order and Down syndrome Kennith J. Rothman, Epidemiology and introduction, p 102
What do you think could affect this trend? Mother’s age Birth order ------ Down syndrome Because mother age and birth order are highly correlated, we expect that mothers who give birth to their fifth baby might be considerably older than mothers giving birth to first baby. We also know that the risk of Down syndrome increases with maternal age.
Exercise on Confounding A study was done to examine the association between Caffeine and Breast cancer. The following data was obtained: Caffeine Breast Cancer No breast cancer Yes 30 18 No 70 82 Total 100 What are the odds of caffiene intake in cases compared to controls? OR= 30 x 82 = 1. 95 70 x 18
Is age a confounder? The investigators thought that the calculated OR was confounded by the effect of age. They stratified participants according to age: Age <40 Age ≥ 40 Caffeine Ca No Ca Yes 5 8 Yes 25 10 No 45 72 No 25 10 Total 50 80 Total 50 20 OR=? OR= 5 x 72 = 1 OR=? What do you conclude? Age confounds the association between caffeine intake and breast cancer 45 x 8 OR= 25 x 10 = 1 25 x 10
Exercise 2 Nurse’s Health study; a cohort study was done to determine the association between oral contraceptive use and ovarian cancer. The following data were obtained: Oral contraceptive Ovarian Ca No ovarian Ca Total Yes 350 200 550 No 125 200 325 Total 475 400 875 What is the crude RR? RR= 350÷ 550 = 1. 65 125÷ 325
Is smoking a confounder? The investigators thought that the calculated Risk ratio might be confounded by the effect of smoking. Data were stratified according to smoking status and relationship was studied : Smokers Non-smokers OCP Ovarian Ca No ovarian Ca Total Yes 95 5 100 Yes 298 152 450 No 150 25 175 No 100 50 150 RR=? RR= 95÷ 100 = 1. 1 150÷ 175 RR=? RR= 298÷ 450 = 0. 99 100÷ 150
Useful link http: //stattrek. com/ap-statistics-2/surveysampling-bias. aspx
Thank you
- Slides: 26