The formula for 95% confidence interval (CI) when the sample size is greater than 30 is
95% CI = mean ± z_score*standard deviation for the sample/square_root(sample size) ... (1)
z-score for 95% confidence interval is 1.96. It is recommended to use t-score instead of z-score if the sample size is less than 30.
95% CI = mean ± t_score*standard deviation for the sample/square_root(sample size) ... (2)
t-table is available on the internet. You need to use Degrees of freedom (df =sample size-1) to find the value of the t-score for the given sample size.
E.g., t-score for a 95% confidence interval if the sample size (n) is 20 = 2.093.
Let's say you have data in column A from A1:A20.
- You can compute the mean in LibreOffice Calc using the formula
=AVERAGE(A1:A20)
- Compute the ratio of standard deviation and the square root of the sample size using the following formula.
=STDEV(A1:A20)/SQRT(20)
Once you have the above two values, you can use them to find 95% confidence interval for the given sample using the formula 1 or 2, depending on the sample size.
