When carrying out a
hypothesis test, the result will depend on whether or not the test
statistic falls into the critical region or regions. The critical regions
are determined by critical values, which are themselves determined by
the level of test or significance level.
A two-tailed test
Suppose you are to do a
two-tailed, 10% level of test. This means that the blue area should be 10% of
the total area under the normal curve, and therefore that the probability of a
random variable from the distribution being between -z and z will be 0.90. The
value of z can be found. This value is called a critical value. Use the
display below to find z. Find z for a 5% level of test, 2.5% level of test and
1% level of test. |
 |
A one-tailed test
Suppose you are to do a
one-tailed, 10% level of test. This means that the blue area should be 90% of
the total area under the normal curve, and therefore that the Probability of a
random variable from the distribution being less than z will be 0.90. The value
of z can be found. This value is called a critical value. Use the
display below to find z. Find z for a 5% level of test, 2.5% level of test and
1% level of test. |
 |
|
© MathsNet 2001