Statistics > Confidence Intervals > 1-Population Proportion
This utility computes the confidence intervals for a population proportion
in one population using normal approximation. The confidnece
intervals are calculated using the following formula:
where 
n = sample size
= sample proportion
= inverse cumulative
probability of the z distribution at
1 - α/2.
If the conditions for normal approximation (
,
) are not met, a warning
will be shown along with the results of the computation.
To use the utility, select Statistics > Confidence Intervals >
1-Population Variance.
- You can provide sample data in a column of the Datasheet or provide
summary data. If you provide sample data, put sample values of at most two categories in
a column in the Datasheet. Select
the Samples in column: radio button, and select the column
name in the given drop-down menu.
- If individual sample data is not available, you can provide summary
information of the sample data. In this case, select the Summarized
sample data radio button. Enter the number of trials and
the number of events in the provided text boxes.
- Enter the confidence level (between 0 and 1) in the
Confidence level: text box.
- Click OK to compute the confidence interval. The results
will be shown in the log window.
The number of trials, number of events, and proportion in the sample
are displayed,
along with the resulting the margin of error and the confidence interval
for the population proportion.
Here is an example:
Confidence Interval - One population proportion: confidence level = 0.95
Input: Summary data
Number of trials |
Number of Events |
Sample proportion |
Margin of Error |
95.00%CI |
100 |
10 |
0.100 |
0.059 |
(0.0412, 0.1588) |