estimation and confidence intervals 5/11 Flashcards
The spread of the sample mean can be obtained from…
… taking repeated samples (of the same size) from a population.
sample means can be plotted…
on …
dot plot
or
histogram.
In the distribution of sample means, the mean of all the sample means will be the same as…
the population mean
Define Standard error
a measure of the precision of a sample estimate
The standard deviation of the spread of mean SD of sample means (spread of means of repeated samples collected from the population) provides a measure of how far from the true value the sample estimate is likely to be.
Equation: SE of the mean
SD/√n
Equation: SE of a proportion
√(p(1−p)/n)
Equation: SE of the difference between sample means
SE(x ̅_1−x ̅_2 )=√((s_1^2)/n_1 +(s_2^2)/n_2 )
Equation: SE of the difference between sample proportions
SE(p ̅_1−p ̅_2 )=√(√(p(1−p)/n) +√(p2(1−p2)/n) )
3 Properties of Standard Errors
A large SE indicates that the estimate is imprecise.
A small SE indicates that the estimate is precise.
The SE is reduced (we obtain a more precise estimate) if the size of the sample is increased.
SE is used to construct CI
Equation: 95%CI (mean)
x ̅±[1.96× SE (of the mean)]
SE is used to construct CI
Equation:95% CI (proportion)
p±[1.96 x SE(proportion)]
Equation: 95% CI of the difference in two means
Difference in two means
(x ̅_1 − x ̅_2 ) ± [1.96 x SE(of the difference in the two means)]
Equation: 95% CI of the difference in two means (proportion)
Difference in two proportions
(p_1 − p_2 ) ± [1.96 x SE(of the difference in the two means)]
Define CI
A range of values that is likely to cover the true but unknown population mean value, μ.
define 95% CI
the range of values within which we are 95% confident that the true population mean lies (our best estimate is the mean
What does the width of the CI show?
The precision of the estimate. The width of the CI is determined by the size of the SE (depends on the sample size). When considering a numerical variable, the variability of the data. Therefore, small studies on variable data give wider CI than larger studies on less variable data.
What clinical implications can be drawn from a confidence interval?
The upper and lower limits of the interval provide a means of judging whether the results are clinically or practically important
Define: Random sample
All members of the population are equally likely to be picked, and each independently of each other.
this is done to pick a sample which is representative of the population
Define: Stratified random sample
Stratified random sample - Population divided into groups beforehand, e.g. males and females before random sampling conducted.
Define: Cluster sampling
Cluster sampling - e.g. GP practices randomised not individual GP’s.
Define: Quota sample
Quota sample - As used by opinion polls etc, supposedly more ‘representative’ of population.
Define: ‘Convenience’ sample
‘Convenience’ sample e.g. Those patients who turn up at an outpatient clinic. May nor be reflective of population