Sampling from a normal distribution

From observing real-world data, we may determine that most data follows a normal distribution. That is to say, when we use a density curve (or histogram) to plot the data, we should see it as bell-shaped. As this kind of distribution is so commonly seen in nature or social science, scientists often use a normal distribution to represent real-value random variables from an unknown distribution. In this recipe, we will demonstrate how R generates samples from a normal distribution.

Getting ready

In this recipe, you need to prepare your environment with R installed.

How to do it…

Please perform the following steps to generate samples from a normal distribution:

1. First, you can use the rnorm function to generate 30 and 1000 samples from a normal distribution:

   > set.seed(123)
   > data1 <- rnorm(30)
   > data2 <- rnorm(1000)
   

2. We can then use the hist function to plot the histogram of data1 and data2:

   > par(mfrow = c(1,2))
   > hist(data1, main="30 samples...