Observational studies

Question 1

what is a case and what is a control

Answer 1

case- have disease of interest

controls- dont have the disease (usually age and sex matched to cases)

Question 2

what is a randomised control trial

Answer 2

a number of similar people are randomly assigned to 2 (or more) groups to test a specific drug, treatment or other intervention. One group (the experimental group) has the intervention being tested, the other (the comparison or control group) has an alternative intervention, a dummy intervention (placebo) or no intervention at all. The groups are followed up to see how effective the experimental intervention was.

Question 3

how do you do a case control study

Answer 3

out cases and controls in different groups and split both into exposed and not exposed

calculate the odds of exposure in diseased and not diseased

calculate odds ratio, association present id disease odds more than not diseased

shows you probability of getting disease after exposure

Question 4

what are the bias’ in case control studies

Answer 4

selection, observer, recall, survivor

Question 5

what is selection bias

Answer 5

cases may not represent exposure distribution in all cases in the source population
controls may not represent exposure distribution in those without disease

Question 6

what is recall bias

Answer 6

cases and controls recall prior exposures differently

Question 7

what is survivor bias

Answer 7

if exposure is fatal will obscure data

Question 8

what is a confounder

Answer 8

a variable that is independently associated with exposure and disease

Question 9

what do corhort studies show

Answer 9

the risk of developing a disease after exposure (exposure after trail started)
incidence risk

Question 10

how do you calculate incidence risk

Answer 10

= risk present in diseased / (risk present in disease + undiseased)

or

= risk absent in diseased / (risk absent in disease and undiseased)

Question 11

what is the relative risk ratio

Answer 11

Compares the risk across exposure groups

= risk of disease in exposed / risk of disease in unexposed

Question 12

how do you interpret relative risk

Answer 12

RR>1 : exposure is harmful
RR<1 : exposure is protective
RR=1 : exposure does nothing

RR=3.0 : 3 fold increase in risk of outcome in exposed compared to unexposed
RR=1.7 : 70% increase
RR=0.8 : 20% decrease

Question 13

what are the two types of cohort study

Answer 13

determined by the type of follow up

prospective and retrospective

Question 14

is there recall bias in a cohort study

Answer 14

no

Question 15

what bias in cohort studies

Answer 15

Selection bias
Initial cohort is not representative of underlying population (poor sampling frame, low response rate)
Loss to follow-up (esp if different between exposed and un-exposed)
Information bias
Misclassification of exposure or outcome
Confounding
Unmeasured day-to-day exposures

Question 16

describe case control vs cohort

Answer 16

cohort 
1. Select population 
without disease 
and classify into 
exposed/unexposed
2. Measure disease 
incidence in exposed 
vs unexposed

case control 
1. Select (diseased) cases and (undiseased)
controls
2. Measure exposure
 in cases vs controls

Question 17

what is a p value

Answer 17

probability of an observed result assuming the null hypothesis is true

Question 18

what is the null hypothesis

Answer 18

the hypothesis that there is no significant difference between specified populations/samples