crazy p-value

#1
I am taking data analysis, and am having a bit of trouble. It has been a couple years since i took intro to stats, so i am very rusty. I performed a t-test (two sided, and both alternates) on Sleuth 2 ex0222, and I get a p value with an negative exponent. this seems ridiculous to me, and I have no idea if I did something wrong, or if I should run with it. the tests I ran were:
t.test(ex0222$Cholesterol ~ ex0222$Group, var.equal = TRUE)
t.test(ex0222$Cholesterol ~ ex0222$Group,alternative = "less", var.equal=TRUE)
t.test(ex0222$Cholesterol ~ ex0222$Group,alternative = "greater",var.equal=TRUE
I just want guidance, because I want to learn this stuff..
any help is greatly appreciated!
 

Dason

Ambassador to the humans
#2
I assume by 'negative exponent' you mean something like 2.6E-10? In which case that's just scientific notation for 2.6 * 10^(-10) = .00000000026 which is a perfectly fine p-value.
 
#4
thanks guys.
I get what it means, that it is a significant outlier, but for the first week of a data analysis class, to get 1.23^-12 for one 2.47^-12 for two sided doesnt seem right to me. i was hoping for a straight forward .02 or something so I could make a clean analysis instead of being shocked by such an extreme outlier.
 

Dason

Ambassador to the humans
#5
It's not an 'extreme outlier'. It just means that this result isn't very likely if the null hypothesis is true. Having an extremely significant result doesn't make your analysis dirty.