Searching for and replacing missing values

Dealing With Missing Data in R

Nicholas Tierney

Statistician

What we are going to cover

How to look for hidden missing values
Replacing missing value labels with NA
Checking your assumptions on missingness

Searching for and replacing missing values

Ideal = NA
Missing values can be coded incorrectly: e.g., "missing", "Not Available", "N/A"
Assuming that missing values are coded as NA. This is a mistake.

Understanding Chaos

score	grade	place
3	N/A	-99
-99	E	97
4	missing	95
-99	na	92
7	n/a	-98
10		missing
12	.	88
16		.
9	N/a	86

Searching for missing values

miss_scan_count()

chaos %>%
  miss_scan_count(search = list("N/A"))

# A tibble: 3 x 2
  Variable     n
  <chr>    <int>
1 score        0
2 grade        1
3 place        0

Searching for missing values

chaos %>%
  miss_scan_count(search = list("N/A",
                                "N/a"))

# A tibble: 3 x 2
  Variable     n
  <chr>    <int>
1 score        0
2 grade        2
3 place        0

Replacing missing values

chaos %>%
  replace_with_na(replace = list(grade = c("N/A", "N/a")))

# A tibble: 9 x 3
  score grade   place  
  <dbl> <chr>   <chr>  
1     3 NA      -99    
2   -99 E       97     
3     4 missing 95     
4   -99 na      92     
5     7 n/a     -98    
6    10 " "     missing
7    12 .       88     
8    16 ""      .      
9     9 NA      86

"scoped variants" of replace_with_na

replace_with_na can be repetitive:
- Use it across many different variables and values
- Complex cases, replacing values less than -1, only affect character columns.
replace_with_na_all() All variables.
replace_with_na_at() A subset of selected variables.
replace_with_na_if() A subset of variables that fulfill some condition ( numeric, character).

Using scoped variants of replace_with_na

chaos %>%
  replace_with_na_all(condition = ~.x == -99)

# A tibble: 9 x 3
  score grade   place  
  <dbl> <chr>   <chr>  
1     3 N/A     NA     
2    NA E       97     
3     4 missing 95     
4    NA na      92     
5     7 n/a     -98    
6    10 " "     missing
7    12 .       88     
8    16 ""      .      
9     9 N/a     86

Using scoped variants of replace_with_na

chaos %>% 
  replace_with_na_all(condition = ~.x %in% c("N/A", "missing", "na"))

# A tibble: 9 x 3
  score grade place
  <dbl> <chr> <chr>
1     3 NA    -99  
2   -99 E     97   
3     4 NA    95   
4   -99 NA    92   
5     7 n/a   -98  
6    10 " "   NA   
7    12 .     88   
8    16 ""    .    
9     9 N/a   86

Let's practice!

Dealing With Missing Data in R