WEEK 4: RANDOM SAMPLING ERROR, BIAS

Question 1

What is the goal of epidemiology and health research

Answer 1

Identification of causes and preventions for disease

Question 2

Strong evidence is:

Answer 2

1) Of the lowest possible random sampling error (a
statistically significant exposure/outcome association)
2) Based on a good design
➢ Free of selection and information biases
➢ Under minimal influence of confounding (next
session)

Question 3

Sources of Error

Answer 3

• chance
• bias
  - systematic error in selection of partipants and or measurement
• cofounding

Question 4

Bias

Answer 4

• refers to a systematic error in the design or conduct of a study
• When bias occurs in a study the observed association between the exposure
  and outcome will be different from the true association

Question 5

two types of biases

Answer 5

selection bias, information bias

Question 6

consequence of information bias

Answer 6

people will be classified into a wrong
cell (recall the 2X2 table): misclassification

Question 7

Selection Bias

Answer 7

refers to a systematic error in the way participants are
selected or retained in a study
- when individuals have different probabilities of being included or retained in the study according to the exposure and/or
outcome.

Question 8

Why does selection bias happen

Answer 8

➢How we approach people, how we invite them, whether
they decide to be part of (or remain in) the study….
➢Not issues related to sampling (random sampling error,
generalizability)

Question 9

Types of Selection bias

Answer 9

1. Inappropriate control selection (case control)
2. Differential Participation ( case control, cohort)
3. Diffrential loss to follow up (cohort, expiremental)

Question 10

Examples of selection bias

Answer 10

volunteer bias, non response bias, membership bias, loss to follow up bias

Question 11

reducing selection bias

Answer 11

➢Little (or nothing) can be done to fix selection bias once it has occurred
- must be avoided in design and conduct

Question 12

Information bias

Answer 12

Can occur when the means for obtaining info about the subjects in the study arte flawed so that some of the info gathered regarding exposures and diseases outcomes is incorre

Question 13

Recall Bias

Answer 13

operates to enhance recall in cases compared with controls
- Certain pierce of info (potentially relevant exposure) may be recalled by case but forgotten bya control

Question 14

Reporting Bias

Answer 14

a subject may be reluctant to report an exposure he is aware of bc of attitudes, beliefs, and perceptions

Question 15

Wish Bias

Answer 15

introduced by subjects who have developed a diseases and who, in attempt to answer the question” “Why me”, seek to show that the disease is not their fault

Question 16

Internal Validity

Answer 16

inner workings of a study
- can not be measured or quantified

Question 17

external validity

Answer 17

refers to how well the results of this particular study could be applied to the larger population

Question 18

Healthy Worker Bias

Answer 18

type of selection bias referring to the fact that people who can work are generally healthier than the overall population bc the overall population includes people who are too sick to work

Question 19

sensitivity analysis

Answer 19

set of extra analyses conducted after the main results of a study are known with the goal of quantifying how much bias there might have been and in which direction it shifted the results

Question 20

confidence interval

Answer 20

explicit admission that the result of a study (the point or effect estimate) is not exactly right, but the real answer is somewhere within a given range - the confidence interval
- if we repeat the study many times with different people, 95% of the 95% CI would include the true value

Question 21

statistical vs clinical significance

Answer 21

the clinical significance observes dissimilarity between the two groups or the two treatment modalities, while statistical significance implies whether there is any mathematical significance to the carried analysis of the results or not