Module 2: Biostatistics Flashcards
What is the overlying reason we need statistics in health sciences?
To understand the health of a population
What is the percentage of 6/10, and what is the proportion?
60%
0.6
What is the maximum possible proportion?
1
Population
The group we’re interested in
Sample
Small group from population
What can we do with a sample?
Investigate it and use it to make an inference about the population
Standard deviation
A measure of the spread of data points in a sample
How far away, on average, the data is from the mean
A larger sample size will cause a ____ deviation?
What does this mean for our investigation?
Narrower
We have more certainty in our answers
Categorical variable
A variable which has a set number of possibilities
Continuous variable
A variable that can take on any value
Estimate + or - 1.96 x SE
Is the equation for what?
95% confidence interval
What does 1.96SE from the true population mean include?
95% of all sample means
Is it correct to say the 95% confidence interval gives a 95% chance of the answer lying within the interval?
No, we are 95% confident it does
What are the two parameters of the confidence interval called?
Lower confidence limit
Upper confidence limit
Will the sample’s 95% confidence interval include the true population mean?
Most of the time (95% of samples)
Median
Line where 50% of sample lies below, and 50% above
25th percentile
Line where 25% of sample lies below
75th percentile
Line where 25% of sample lies above
Bias
Error which moves us away from the truth
Two types of error
Errors that make our answers more uncertain
Errors that move us away from the truth
How do we minimise errors that add variability? (2)
Use same measuring system
Make other variables constant
How do we best avoid bias?
Take a random sample from the population
Convenience sample- what’s wrong with it?
Sample isn’t truly random. It misses reaching everyone who isn’t convenient to contact
Standard error
Variability of sampling distribution
Measures how far away the sample means are from the population mean
μ
Population mean
σ
Population standard deviation
x̄
Sample mean
n
Sample size
s
Sample standard deviation
What shape does the sampling distribution follow with a large sample size?
Bell shaped curve
y = a + bx
Formula for regression line