Information Technology Reference
In-Depth Information
The solutions just described are similar to those for
Recipe 1.10
, where we selected
columns by position. The only difference is that here we use column names instead of
column numbers. All the observations made in
Recipe 1.10
apply here:
•
dfrm[["name"]]
returns one column, not a data frame.
•
dfrm[c("
name
1
", "
name
2
", ..., "
name
k
")]
returns a data frame, not a column.
•
dfrm["name"]
is a special case of the previous expression and so returns a data frame,
not a column.
• The matrix-style subscripting can return either a column or a data frame, so be
careful how many names you supply. See
Recipe 1.10
for a discussion of this
“gotcha” and using
drop=FALSE
.
There is one new addition:
dfrm$name
This is identical in effect to
dfrm[["name"]]
, but it's easier to type and to read.
See Also
See
Recipe 1.10
to understand more about selecting columns.
1.12 Forming a Confidence Interval for a Mean
Problem
You have a sample from a population. Given that sample, you want to determine a
confidence interval for the population's mean.
Solution
Apply the
t.test
function to your sample
x
:
>
t.test(x)
The output includes a confidence interval at the 95% confidence level. To see intervals
at other levels, use the
conf.level
argument.
If your sample size
n
is small, the underlying population must be normally distributed
for there to be a meaningful confidence interval. A good rule of thumb is that “small”
means
n
< 30.
Discussion
Applying the
t.test
function to a vector yields a lot of output. Buried in the output is
a confidence interval: