With regards to t-test, the function t.test()
in R may be used. This is a rather simple function which performs both one- and two-sample t-tests (it is thus likely that we will meet that function elsewhere in this website).
Assuming that you have stored your sample data in the variable called scores
, the command to use is t.test(scores, alternative="ALT", mu = Y)
where:
ALT
shall be replaced by either greater
or less
or two.sided
depending of your alternative hypothesis Ha
. The null hypothesis H0
states that the sample mean is NOT different from the population mean. Your alternative hypothesis Ha
is one of the following:
greater
),less
),two.sided
).Y
shall be replaced by the value of the population mean.Using our previous example, this looks like:
t.test(scores, alternative="greater", mu=120)
##
## One Sample t-test
##
## data: scores
## t = 3.9591, df = 39, p-value = 0.0001547
## alternative hypothesis: true mean is greater than 120
## 95 percent confidence interval:
## 123.6476 Inf
## sample estimates:
## mean of x
## 126.35
R returns several lines of text. One of them provides a p-value while the next line states the alternative hypothesis which depends on the parameter alternative
that you have entered in the t.test()
. This alternative hypothesis Ha
is considered valid when the p-value is less than 0.05.
Read more about t.test()
and find more options by clicking here or there or by simply typing ?t.test
in the R console.