StatCrunch: Confidence Intervals for the Difference between Two Proportions with Summary Data Video Lecture | Statcrunch Tutorials for Beginners - Data & Analytics

In this video you will learn to compute
confidence intervals for the difference
between two proportions
with summary data using StatCrunch. This
example comes from a Gallup survey taken
in July and August 2014,
which asked 945 republicans 854
democrats
to name the biggest problem for the
United States. The number of republicans
classifying
each item as a top problem is as
follows: immigration: 208,
dysfunctional government:189, economy: 161,
unemployment: 113, and other:
274. The number democrats classify each
item as a top problem is as follows:
immigration: 94, dysfunctional government: 137,
economy: 111, unemployment: 111,
and other: 401. So for this video the
statistical question I'm going to
investigate
is: "Is there significant difference
between the proportion of republicans
and the portion democrats that
identified immigration
as the top problem?" To compute the
appropriate confidence interval,
under the "Stat" menu I'll choose
"proportion stats",
"2 Sample", "sample with summary",
since I don't actually have the data in
the StatCrunch data table.
In StatCrunch
a success is used to define the outcome
interest, so in this case we'll consider
"immigration" response to be a success.
Sample 1 will represent republican
and sample 2, democrats. So under sample 1 we'll enter 208
for the number of successes and 945 for
the number of observations.
For sample 2
We'll enter 94 for the number of successes
854
for the number observations.
Under "perform",
I'll choose "confidence interval"
by default StatCrunch has a value of 0.95 for the Level
which will produce a 95 percent
confidence interval for the population
proportion.
For this example I will enter 0.99 for
the input
to produce a 99 percent confidence
interval. I'll click compute.
The results show a 99 percent confidence
interval for the difference between the
two population proportions
with 'L. Limit" representing a lower
limit and "U. Limit" representing the
upper limit
of this confidence interval.