第 3 章 函数

介绍R中的函数编写知识。

library(ggplot2)
library(dplyr)

## 
## 载入程辑包：'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(tidyr)
library(modelr)
library(lubridate)

## 
## 载入程辑包：'lubridate'

## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

library(pastecs)

## 
## 载入程辑包：'pastecs'

## The following object is masked from 'package:tidyr':
## 
##     extract

## The following objects are masked from 'package:dplyr':
## 
##     first, last

3.1 概述

当需要对同一代码复制超过3次时，最好的办法就是写成函数

3.2 将下公式写为函数

\[Var(x)=\frac{1}{n-1}\sum_{i=1}^n(x_i-\bar{x})^2\] 偏度分布公式:

\[Skew(x)=\frac{\frac{1}{n-2}(\sum_{i=1}^n(x_i-\bar{x})^3)}{Var(x)^{3/2}}\]

练习题解答

#方差
x = rnorm(100,10,2)

Var <- function(x){
  n = length(!is.na(x))
  sum = sum((x - mean(x, na.rm = T))^2)
  sum/(n-1)
}

Skew <- function(x){
  n = length(!is.na(x))
  sum = sum((x - mean(x, na.rm = T))^3)
  sum/(Var(x)^(3/2)*(n-2))
}

Skew(x)

## [1] 0.2423189

hist(x)

stat.desc(x, norm = T)

##      nbr.val     nbr.null       nbr.na          min          max        range 
##  100.0000000    0.0000000    0.0000000    5.2317462   16.2631395   11.0313933 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
## 1011.4877182   10.1067112   10.1148772    0.1987801    0.3944227    3.9513509 
##      std.dev     coef.var     skewness     skew.2SE     kurtosis     kurt.2SE 
##    1.9878005    0.1965225    0.2374725    0.4919064    0.8388284    0.8768281 
##   normtest.W   normtest.p 
##    0.9789541    0.1101551