Hypothesis testing is a method for using sample data to decide between two competing
claims (hypotheses) about a population characteristic.
A hypothesis is a statement about the value of a population parameter developed for the
purpose of testing.
e.g. The mean salary for ALL graduates of four-year business schools is $2,200
The mean monthly income for ALL systems analysts is at least $3,625.
Less than twenty percent of ALL juvenile offenders are caught and sentence to
Types of hypotheses
Null hypothesis – A claim about a population characteristic that is initially assumed to be
true. Denoted H .
Alternative hypothesis – The competing claim. Denoted H or H . A 1
In carrying out a test of H 0ersus H , tAe hypothesis H will 0e rejected in favor of H only ifA
sample evidence strongly suggests that H is fal0e.
Two possible conclusions
Reject H a0d claim H is tAue
Fail to reject H 0
Note: Failing to reject H 0s not the same as saying H is tr0e. We just do not have enough
evidence to claim that it is false.
Hypothesis for tests comparing a parameter to a value
The alternative hypothesis has the following forms
HA: population characteristic < hypothesized value
HA: “ > “ H A “ ≠ “
The null corresponding to above is
H 0 population characteristic ≥ hypothesized value
H 0 “ ≤ “
H : “ = “