Biostatistics Flashcards
Sample
A small part of the population to show what it is like
Population
What we are investigating
Why don’t we test the population?
Costly and difficult
Percent equation
100 x number with characteristic / total number
Continuous variables
Can take on any value
Mean, standard deviation
Standard deviation
Tells us how far away each observation is from the mean on average
Two types of errors
- Sampling variability
2. Bias
Population mean symbol
μ
Population standard deviation symbol
σ
Sample mean symbol
x̄
Sample size symbol
n
Sample standard deviation symbol
s
Sampling distribution
Variability of sampling distribution is called standard error (SE)
Standard error
Standard deviation of the sampling distribution
SE = s/√n
Binary variables
Proportion
Normal distribution
Symmetrical bell curve
95% confidence interval equation for samples
± 1.96 x SE
95% confidence interval equation for means
x̄ ± 1.96 x s√n
Box plots
The median 50% of the sample is above this point and 50% is below this point
‘25th percentile’ - 25% of sample is below this point and 75% is above
‘75th percentile’ - 75% of sample is below this point and 25% is below
What do we need to consider?
- The wording of the question
- Assume there is no difference because we are looking for evidence against
- What results do we expect
- Bias and sampling errors