# sample size to get 99.6% confidence on a one-tailed test

If I have a normally distributed population of 3.5 million elements, and I want to sample enough of them to make a statement with 99.6% confidence on a 1-tailed test, what should my sample size be? Is 100 enough, or would it need to be significantly larger?

• Do you have an achieved amount of power that you want?
– user25658
Sep 12, 2013 at 17:04
• (1) One-tailed test of what parameter? The mean? Standard deviation? Variance? etc. (2) The answer for the mean is a sample size of one. With this you can construct a 99.6% confidence interval. It will be very wide, though :-).
– whuber
Sep 12, 2013 at 17:18

You can use the following R script to generate your required sample:

library(pwr)

pwr.t.test(n = SAMPLE_SIZE , d = EXPECTED_EFFECT_SIZE, sig.level = 0.004 , power = DESIRED_POWER, type = c("one.sample"), alternative = "greater"/"less")

You need to provide 3 of the 4 values (n,*d*,sig.level, and power), while making the 4th value = NULL. For example, if you wanted to see if 100 subjects is enough, you could fill in information for n, d (if you have an expected effect size, for this example d will be equal to 0.4), your significance level of 0.004 (or 99.6% CI), while leaving power as Null. Lastly, you will need to choose the direction for the one-tailed test by choosing "greater" or "less", which for this example, I chose to use "greater". The below R script will perform this calculation:

library(pwr)

pwr.t.test(n = 100 , d = 0.4, sig.level = 0.004 , power = NULL, type = c("one.sample"), alternative = greater)

Below is the generated output:

 One-sample t test power calculation

n = 100
d = 0.4
sig.level = 0.004
power = 0.8991141
alternative = greater


As you can see in the above output, we have 89.9% power to test our null hypothesis with an expected difference in effect size of 0.4 with 99.6% confidence ($a$ = 0.004).

• Thanks -- really like this one because you're "teaching a man to fish", while at the same time not being a jerk because he doesn't know how! Very cool. Sep 12, 2013 at 18:02
• No problem! I try to keep things as simple as possible because everything involving stats can be overwhelming (to say the least!). Let me know if there is anything else that I can help you with in regards to this calculation! Best of luck! Sep 12, 2013 at 19:42
• @MattR - The word greater requires quotes in pwr.t.test(). Sep 12, 2013 at 21:23