If we take k samples
from a normal distribution with fixed unknown mean and variance, and if we
compute the sample mean and sample variance for these k samples,
then the t-distribution (for k) can be defined as the distribution of the location of the
true mean. In this way the t-distribution can be used to estimate how likely
it is that the true mean lies in any given range.
If the data are normally distributed, the one-sided (1 − a)-upper
confidence limit (UCL) of the mean, can be calculated using the following
equation:
In the given problem, we have the following values:
·
Number of samples taken=20.
·
Sampling mean=375
·
Sample variance =130
We have been asked to test the following hypothesis: “the
mean distance is a least 425 meters”. We are to use the hypothesis procedure to
determine if there is sufficient evidence at a level of significance of 0.025
to refute the given hypothesis.
First let’s calculate the standard deviation of the sampling
mean, which equals the following: s/(square root of n) = 130/(4.47) = 29.07
Since the sample size is small, we will use a t-distribution
table instead of a standard normal distribution table. The value of t is equal
to (value – sampling mean)/(standard deviation of the sampling mean).
Now we can go back to our UCL formula and solve the problem:
UCL1-a = 375 + 2.093*29.07 (Note: you can find t0.025, 19 = 2.093 in a t-distribution table for “one tail”).
UCL1-a = 435.84
The upper confidence limit of the mean distance is 435.86, which means there is only a 2.5% chance that the mean distance is above 435.86. That means that there is a slightly greater than 2.5% chance that the mean distance is above 425. Therefore, we do not have sufficient evidence at level of significance of 0.025 that the mean distance is above 425.