HUBS Lecture 12-15 biostats Flashcards
what does a bigger sample mean
a more accurate representation of the population
are histograms better for looking at large or small amount of data
large
are dot plots better for looking at large or small numbers of data
small
what is standard deviation
the average distance of every observation away from the mean. a measurement of the spread or variability of the data.
what is the most common way we get bias in a sample
the people we choose to participate the study
does increasing the sample size help make a study more reliable if the study is bias
no
what are the two types of error
errors that make our data more uncertain - more variability - we can’t avoid this type of error
errors that move us away from from truth - we can avoid this type of error
for continuous variables how can we describe the population
the population mean and population standard deviation
for continuous variables how can we describe the sample
the sample mean and the sample standard deviation
for continuous variables how can we describe the sampling distribution
standard error = standard deviation of the sampling distribution
the sampling distribution is centred on the population mean (when there is no bias)
for binary variables how can we describe the population and sample
by population and sample proportions
for binary variables how can we describe the sampling distribution
the sampling distribution is centred on the population proportion (when there is no bias)
standard error = variability/standard deviation for the sampling distribution
what two things impact the width of the SD
sample size goes up and the distribution gets narrower
more variability means the sampling distribution gets wider
how many standard deviations do you have to go out from the mean to have 95% of the data between the upper and lower limit
1.96 standard deviations
what is a large sample
more than 30
if we only have one sample is out standard deviation the population standard deviation
it is our best guess of the population SD
if our sample is large what do we know about our sampling distribution
our sampling distribution will be normal and the standard error can be estimated using the formula SE=s/sqaure root of n
if we have the 95% confidence interval can we say that the mean is between the upper and lower limits
we can say that we are 95% confident that the true mean in the population is between the upper ad lower limits of the 95% confidence interval
