StatCrunch Computing Confidence Intervals for a Mean with Raw Data Video

In this video you will learn to compute
one sample t
confidence intervals with raw data using
StatCrunch. The dataset I'm using
is called
"apple juice bottles". This dataset comes
from Statistics:
Informed Decisions Using Data by Michael
Sullivan. The "apple juice" column contains the
amount in ounces it each
22 bottles taken as a random sample
manufacturer's assembly-line.
The filling machine is not precise which
makes the amount or juice vary from bottle
to bottle.
Each bottle's label states it contains
64 ounces of apple juice.
The manufacturer requires that the mean
amount of juice in a bottle be 64.05 ounces.
To decrease the chance to a bottle being
under the 64-ounce threshold by random chance.
Given the manufacturer's concern about
filling bottles,
we're going to compute a confidence interval to determine
if the mean amount per bottle may be less than the target
64.05 ounces. To do so,
under the "Stat" menu, you will choose "T Stats",
"one sample", "with data".
We'll choose the "apple juice" column,
and then under "perform"
we'll choose "confidence interval". By
default StatCrunch uses the value 0.95,
which will produce a 95 percent
confidence interval so the population
mean mu.
For this example I'll leave it at 0.95
and click compute. The results show a 95
percent confidence interval and the
percent confidence interval and the mean amount
in one in the manufacturer's bottles with
"L. Limit" representing the lower limit
"U. Limit" representing the upper limit
of the confidence interval.
StatCrunch can also store these results
in the data table.
To do so under "options"
choose "edit". This takes us back to the
original window we set up our confidence
interval.
Under "output"
I'll choose "store in data table". I'll click
compute.
And now
the results are stored in new data
columns that can be used for future
calculations.