Impute the mean value into a vector with missing values

This can be useful if you are imputing specific values, however we would generally recommend to impute using other model based approaches. See the simputation package, for example simputation::impute_lm().

impute_mean(x)

# Default S3 method
impute_mean(x)

# S3 method for class 'factor'
impute_mean(x)

Arguments

x

vector

Value

vector with mean values replaced

Examples

library(dplyr)
vec <- rnorm(10)

vec[sample(1:10, 3)] <- NA

impute_mean(vec)
#>  [1]  0.12779601  1.34467162 -2.51183820  0.12779601  0.80880184  0.32186331
#>  [7]  0.05810520 -0.04448689  0.91745520  0.12779601

dat <- tibble(
  num = rnorm(10),
  int = as.integer(rpois(10, 5)),
  fct = factor(LETTERS[1:10])
) %>%
  mutate(
    across(
      everything(),
      \(x) set_prop_miss(x, prop = 0.25)
    )
  )

dat
#> # A tibble: 10 × 3
#>       num   int fct  
#>     <dbl> <int> <fct>
#>  1 -0.532     5 NA   
#>  2 NA         4 B    
#>  3  1.04      4 C    
#>  4  0.202     5 D    
#>  5 NA        11 E    
#>  6 -0.283     9 NA   
#>  7 -0.201    NA G    
#>  8  1.33      7 H    
#>  9  1.03      6 I    
#> 10  1.17     NA J    

dat %>%
  nabular() %>%
  mutate(
    num = impute_mean(num),
    int = impute_mean(int),
    fct = impute_mean(fct),
  )
#> # A tibble: 10 × 6
#>       num   int fct   num_NA int_NA fct_NA
#>     <dbl> <dbl> <fct> <fct>  <fct>  <fct> 
#>  1 -0.532  5    E     !NA    !NA    NA    
#>  2  0.470  4    B     NA     !NA    !NA   
#>  3  1.04   4    C     !NA    !NA    !NA   
#>  4  0.202  5    D     !NA    !NA    !NA   
#>  5  0.470 11    E     NA     !NA    !NA   
#>  6 -0.283  9    E     !NA    !NA    NA    
#>  7 -0.201  6.38 G     !NA    NA     !NA   
#>  8  1.33   7    H     !NA    !NA    !NA   
#>  9  1.03   6    I     !NA    !NA    !NA   
#> 10  1.17   6.38 J     !NA    NA     !NA   

dat %>%
  nabular() %>%
  mutate(
    across(
      where(is.numeric),
      impute_mean
    )
  )
#> # A tibble: 10 × 6
#>       num   int fct   num_NA int_NA fct_NA
#>     <dbl> <dbl> <fct> <fct>  <fct>  <fct> 
#>  1 -0.532  5    NA    !NA    !NA    NA    
#>  2  0.470  4    B     NA     !NA    !NA   
#>  3  1.04   4    C     !NA    !NA    !NA   
#>  4  0.202  5    D     !NA    !NA    !NA   
#>  5  0.470 11    E     NA     !NA    !NA   
#>  6 -0.283  9    NA    !NA    !NA    NA    
#>  7 -0.201  6.38 G     !NA    NA     !NA   
#>  8  1.33   7    H     !NA    !NA    !NA   
#>  9  1.03   6    I     !NA    !NA    !NA   
#> 10  1.17   6.38 J     !NA    NA     !NA   

dat %>%
  nabular() %>%
  mutate(
    across(
      c("num", "int"),
      impute_mean
    )
  )
#> # A tibble: 10 × 6
#>       num   int fct   num_NA int_NA fct_NA
#>     <dbl> <dbl> <fct> <fct>  <fct>  <fct> 
#>  1 -0.532  5    NA    !NA    !NA    NA    
#>  2  0.470  4    B     NA     !NA    !NA   
#>  3  1.04   4    C     !NA    !NA    !NA   
#>  4  0.202  5    D     !NA    !NA    !NA   
#>  5  0.470 11    E     NA     !NA    !NA   
#>  6 -0.283  9    NA    !NA    !NA    NA    
#>  7 -0.201  6.38 G     !NA    NA     !NA   
#>  8  1.33   7    H     !NA    !NA    !NA   
#>  9  1.03   6    I     !NA    !NA    !NA   
#> 10  1.17   6.38 J     !NA    NA     !NA