R语言实现描述性统计

# 01分布
a<- runif(20)
a

  

 

  
1
  
2
  
3
 

1. 0.0534173720516264
2. 0.0381318787112832
3. 0.253885793266818
4. 0.851638266118243
5. 0.356620342005044
6. 0.175922254333273
7. 0.270358079113066
8. 0.421792675741017
9. 0.675487545551732
10. 0.139561568852514
11. 0.649348761420697
12. 0.0383495420683175
13. 0.673801982775331
14. 0.131142142694443
15. 0.241756724659353
16. 0.205821343231946
17. 0.826634412631392
18. 0.827650502324104
19. 0.48426380334422
20. 0.385196640854701

# 算术平均数
mean(a)

  

 

  
1
  
2
 

0.385039081587456

# 几何平均数
exp(mean(log(a)))

  

 

  
1
  
2
 

0.269715541826603

# 中位数
median(a)

  

 

  
1
  
2
 

0.313489210559055

b <- sort(a)
(b[10]+b[11])/2

  

 

  
1
  
2
 

0.313489210559055

# 产生0到10的20个数round取整
c <- round(runif(20,0,10))
c

  

 

  
1
  
2
  
3
 

1. 6
2. 1
3. 10
4. 9
5. 6
6. 9
7. 3
8. 10
9. 6
10. 3
11. 4
12. 4
13. 7
14. 2
15. 3
16. 3
17. 5
18. 9
19. 2
20. 0

# 众数 table 统计出现的次数
x <- table(c)
x

  

 

  
1
  
2
  
3
 

c
 0  1  2  3  4  5  6  7  9 10 
 1  1  2  4  2  1  3  1  3  2 

  

 

  
1
  
2
  
3
 

# 取出次数最多的
names(x)[x==max(x)]

  

 

  
1
  
2
 

‘3’

a <- round(runif(100,1,10))
table(a)

  

 

  
1
  
2
 

a
 1  2  3  4  5  6  7  8  9 10 
 4  8 11  7 16 10 11  8 14 11 

  

 

  
1
  
2
  
3
 

stem(a)

  

 

  
1
 

  The decimal point is at the | 1 | 0000 2 | 00000000 3 | 00000000000 4 | 0000000 5 | 0000000000000000 6 | 0000000000 7 | 00000000000 8 | 00000000 9 | 00000000000000
  10 | 00000000000

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
 

hist(a)

  

 

  
1
 

hist(a,breaks=50)

  

 

  
1
 

a<- rnorm(100,0,1)

  

 

  
1
 

hist(a)

  

 

  
1
 

# 协方差与相关系数
x<-runif(20)
y<-runif(20)
cov(x,y)

  

 

  
1
  
2
  
3
  
4
 

0.00322176575114672

e<- runif(20,0,0.1)
z<- x*3+e
cov(x,z)

  

 

  
1
  
2
  
3
 

0.191163714793349

#与相关系数
cor(x,z)

  

 

  
1
  
2
 

0.999193595914862

# 一元线性回归|
x<- runif(10)
y<- 3*x +5+ runif(10,0,0.5)
plot(x,y)

  

 

  
1
  
2
  
3
  
4
 

# 线性模型
lm(y~x)

  

 

  
1
  
2
 

Call:
lm(formula = y ~ x)

Coefficients:
(Intercept) x 5.349 2.780  

  

 

  
1
  
2
  
3
  
4
  
5
  
6
 

plot(x,y)
abline(lm(y~x),col="red")

  

 

  
1
  
2
 

# 多元回归
x1<- runif(10)
x2 <- runif(10)
y <- 3*x1+5*x2+2+runif(10,0,0.1) 
lc<- lm(y~x1+x2)

  

 

  
1
  
2
  
3
  
4
  
5
 

summary(lc)

  

 

  
1
 

Call:
lm(formula = y ~ x1 + x2)

Residuals: Min 1Q   Median 3Q Max 
-0.04436 -0.02495  0.00357  0.02298  0.04432 

Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept)  2.08064 0.03958   52.56 2.36e-10 ***
x1 2.97190 0.03884   76.51 1.71e-11 ***
x2 4.97719 0.04625  107.61 1.58e-12 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 0.03303 on 7 degrees of freedom
Multiple R-squared:  0.9995,	Adjusted R-squared:  0.9993 
F-statistic:  6916 on 2 and 7 DF,  p-value: 2.91e-12

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
  
13
  
14
  
15
  
16
  
17
  
18
 

文章来源: maoli.blog.csdn.net，作者：刘润森！，版权归原作者所有，如需转载，请联系作者。

原文链接：maoli.blog.csdn.net/article/details/97902429