Statistical Terms
- Bayes'
theorem
- a mathematical formula for computing the
probability of event A (Pr(A)) given a prior estimate of Pr(A) and
some new information, B.
- confidence
interval
- an interval derived from a set of samples to
describe how accurately the mean can be estimated; see Prosecutor's Fallacy
- normal
- a
set of events that follow a bell curve defined by a mean and standard
deviation
- mean
- the
sum of a group of values divided by the number of values; often
represented by the Greek letter μ (mu).
- sample
mean
- the mean of a set of samples taken from a
distribution, represented by μ̂ (mu-hat) or x̄ (x-bar)
- sample
standard deviation
- a measure of the dispersion of values
around the mean, based on a series of samples; the square root of the
variance; often represented by the s or σ̂ (sigma-hat)
- standard
deviation
- a
measure of the dispersion of values around the mean; the square root
of the variance; often represented by the Greek letter σ (sigma)
- standard
error
- a measure of the amount of error in a sample mean;
often estimated as σ̂/√n, where σ̂ is the
sample standard deviation and n is the number of samples
- variance
- a
measure of the dispersion of values around the mean; the square of the
standard deviation; often represented by σ2 (sigma squared)
|
