How to find a Trimmed Mean in R

Trimmed Mean in R, A trimmed mean is a dataset’s mean that has been determined after deleting a certain percentage of the dataset’s smallest and greatest values.

In other words, before determining the mean, a tiny percentage of the biggest and smallest values are removed using the Trimmed Mean method of averaging.

A ten percent trimmed mean, for example, represents the mean of a dataset after the ten percent smallest and greatest values have been eliminated.

The following basic syntax is the simplest approach to calculate a trimmed mean in R:

The basis syntax for the calculated 10% trimmed mean

mean(x, trim=0.1)

In reality, the following examples demonstrate how to utilize this function to calculate a trimmed mean.

Calculate the Vector’s Trimmed Mean

The code below demonstrates how to compute a 10% trimmed mean for a vector of data.

Let’s create a data set

data1<-c(10, 8, 12, 10, 9, 7, 25, 23, 11, 9, 18, 19, 15, 11, 12, 14, 23, 19)

Now we can calculate the 10% trimmed mean

mean(data1, trim=0.1)
[1] 13.9375

The 10% trimmed mean is 13.93.

After the last 10% and greatest 10% of values have been eliminated from the dataset, this is the mean of the dataset.

In a data frame, calculate the trimmed mean of each column.

The following code demonstrates how to calculate a 5% trimmed mean in a data frame for a specified column.

data<- data.frame(A=c(10, 8, 12, 10, 9, 7, 25, 23, 11, 9),
                B=c(8, 8, 10, 8, 9, 17, 20, 21, 10, 19),
                C=c(10, 18, 11, 12, 17, 18, 20, 21, 17, 12))
data

       A        B       C
1      10       8       10
2       8       8       18
3      12      10       11
4      10       8       12
5       9       9       17
6       7      17       18
7      25      20       20
8      23      21       21
9      11      10       17
10      9      19       12

Now we can calculate a 7% trimmed mean of points

mean(data$A, trim=0.07)
[1] 12.4

The 7% trimmed mean of the values in the ‘points’ column is 12.4.

After the least and biggest 7% of values have been deleted, this is the mean of the ‘A’ column.

Calculate the Trimmed Mean of a Large Number of Columns

The code below demonstrates how to compute a 5% trimmed mean for numerous columns in a data frame:

data<- data.frame(A=c(10, 8, 12, 10, 9, 7, 25, 23, 11, 9),
                B=c(8, 8, 10, 8, 9, 17, 20, 21, 10, 19),
                C=c(10, 18, 11, 12, 17, 18, 20, 21, 17, 12))

Let’s calculate the 5% trimmed mean of A and B.

sapply(data[c('A', 'B')], function(x) mean(x, trim=0.05))
   A    B
 12.4 13.0

We can observe the following from the output:

The ‘A’ column’s 5 percent trimmed mean is 12.4.

The ‘B’ column has a 5 percent trimmed mean of 13.0.

Intraclass Correlation Coefficient in R-Quick Guide » finnstats