Stats/ critical numbers

Question 1

what is a case control study

Answer 1

Find people with disease and controls look back in time for exposure

Question 2

what are the pros of case control

Answer 2

• Good for rare outcomes
• Fast cheap
• Few ethical considerations

Question 3

cons of case control

Answer 3

• cannot prove causation/ eliminate confounding factors
• difficult to establish event order
• subject to recall bias
• only investigate single disease

Question 4

Describe cross sectional study

Answer 4

Sample a population and count number of affected and unaffected people

Question 5

pros of cross sectional

Answer 5

generates hypothesis
cheap fast
few ethical considerations

Question 6

cons of cross sectional

Answer 6

cannot prove causation/eliminate confounders
less suitable for rare disease
doesn’t establish event order
sample bias could occur

Question 7

what the cohort study do?

Answer 7

take a population monitor those with and without exposure for linked outcome
prospective

Question 8

pros of cohort study

Answer 8

event sequence clarity

few ethical considerations

Question 9

cons of a cohort study

Answer 9

Cannot rule out confounding factors
not suitable for rare disease 
time consuming and expensive 
requires follow up - could be difficult 
patients can change behaviors

Question 10

Wat do be a randomised controlled trial

Answer 10

multiple group organised into arms given different exposures/treatments and comparing outcomes.
Arms can be balanced by matching, randomising, cross-over, placebo, and blinding.

Question 11

pros of RCT

Answer 11

gold standard in proving causation and eliminating confounding factors and bias

Question 12

cons of RCT

Answer 12

expensive time consuming
not good for rare diseases
ethical approval trickier as gold standards are often unethical
requires compliance

Question 13

what is ecological study?

Answer 13

using massive samples to look at trends across populations not individuals.

Question 14

pros of ecological

Answer 14

fast cheap
large sample
easy
good first step for hypothesis generation

Question 15

cons of ecological

Answer 15

don’t know how data was collected
data may be missing
doesn’t prove causation
correlation not causation - ecology fallacy

Question 16

what are the types of sampling

Answer 16

random
systematic
convenience
cluster 
stratified

Question 17

lead time bias

Answer 17

illness detected sooner but no difference in treatment outcome

Question 18

length time bias

Answer 18

people who live with disease for longer more probable to be screened - false impression of screening improving survival

Question 19

what is risk

Answer 19

risk is probability

eg risk of rolling a 6 is 1/6

Question 20

how do you calculate number needed to treat/harm (NNT/H)

Answer 20

1/ absolute risk difference

must always be rounded up

Question 21

how to calculate odds

Answer 21

x/(n-x)
x=outcome
n=sample size
with/without

Question 22

how to calculate sensitivity

Answer 22

true positive/all population with disease

true pos/(true pos + false pos)

Question 23

how to calculate specificity

Answer 23

false positive/all healthy patients

think who is healthy but have been told they’re ill

Question 24

positive and negative predictive value

Answer 24

disease pos/all who’s results were pos

disease neg/ all who tested neg

Question 25

test accuracy how to calc

Answer 25

all correct results/ total tests performed | true positive + true negative ------------------------------------------ all results

Question 26

standard deviation equation

Answer 26

root of [sum of (each value-mean)^2 / n-1]

Question 27

standard error is?

Answer 27

standard deviation / n^(1/2) [which is square root n]

Question 28

when is interquartile range used and how is it calculated?

Answer 28

when data is skewed upper quartile - lower quartile Q3-Q1

Question 29

what is a 95% confidence interval

Answer 29

a range we are 95% sure the true population lies in

Question 30

how to calc 95% confidence interval?

Answer 30

mean +or- 1.96*SE

Question 31

what is correlation?

Answer 31

simple association - no causation

Question 32

when to use regression

Answer 32

when a change in one variable can predict another

Question 33

what is a test for correlation

Answer 33

pearson's correlation coefficient 1 pos -1 neg 0 nil

Question 34

when is a logistic regression best used

Answer 34

outcome is binary log(outcome)= a + bx a is where prob increases b is how fast it increases

Question 35

Carried out in a snap-shot of time without follow-up of subjects or looking back in time

Answer 35

Cross Sectional

Question 36

Collect information now and follow subjects up over time to explore outcomes

Answer 36

Cohort

Question 37

Collect information on an outcome now, and look back in time to see what exposures were experienced

Answer 37

Case-Control

Question 38

Information on groups of individuals (e.g. countries) rather than individual level data

Answer 38

Ecological