The fillmissing() function replaces missing measurements in single-case
data.
Arguments
- data
A single-case data frame. See
scdf()to learn about this format.- dvar
Character string with the name of the dependent variable. Defaults to the attributes in the scdf file.
- mvar
Character string with the name of the measurement time variable. Defaults to the attributes in the scdf file.
- na.rm
If set
TRUE,NAvalues are also interpolated. Default isna.rm = TRUE.
Value
A single-case data frame with interpolated missing data points. See
scdf() to learn about the SCDF Format.
Details
This procedure is recommended if there are gaps between measurement times
(e.g. MT: 1, 2, 3, 4, 5, ... 8, 9) or explicitly missing values in your
single-case data and you want to calculate overlap indices (overlap()) or a
randomization test (rand_test()).
See also
Other data manipulation functions:
add_l2(),
as.data.frame.scdf(),
as_scdf(),
moving_median(),
outlier(),
ranks(),
rescale(),
scdf(),
select_cases(),
set_vars(),
shift(),
smooth_cases(),
standardize(),
truncate_phase()
Examples
## In his study, Grosche (2011) could not realize measurements each
## single week for all participants. During the course of 100 weeks,
## about 20 measurements per person at different times were administered.
## Fill missing values in a single-case dataset with discontinuous
## measurement times
Grosche2011filled <- fill_missing(Grosche2011)
study <- c(Grosche2011[2], Grosche2011filled[2])
names(study) <- c("Original", "Filled")
study
#> #A single-case data frame with two cases
#>
#> Original: values mt phase │ Filled: values mt phase │
#> 13 0 A │ 13 0 A │
#> 17.4 1 A │ 17.4 1 A │
#> 13 6 A │ 16.52 2 A │
#> 7.74 10 A │ 15.64 3 A │
#> 8.82 13 A │ 14.76 4 A │
#> 7.5 15 A │ 13.88 5 A │
#> 5.82 36 A │ 13 6 A │
#> 6.26 38 B │ 11.69 7 A │
#> 5.6 41 B │ 10.37 8 A │
#> 12.79 43 B │ 9.05 9 A │
#> 9.17 48 B │ 7.74 10 A │
#> 10.59 50 B │ 8.1 11 A │
#> 9.23 55 B │ 8.46 12 A │
#> 10.71 59 B │ 8.82 13 A │
#> 7.61 62 B │ 8.16 14 A │
#> # ... up to 87 more rows
## Fill missing values in a single-case dataset that are NA
Maggie <- random_scdf(design(level = list(0,1)), seed = 123)
Maggie_n <- Maggie
replace.positions <- c(10,16,18)
Maggie_n[[1]][replace.positions,"values"] <- NA
Maggie_f <- fill_missing(Maggie_n)
study <- c(Maggie, Maggie_n, Maggie_f)
names(study) <- c("original", "missing", "interpolated")
study
#> #A single-case data frame with three cases
#>
#> original: phase values mt │ missing: phase values mt │
#> A 47.2 1 │ A 47.2 1 │
#> A 48.85 2 │ A 48.85 2 │
#> A 57.79 3 │ A 57.79 3 │
#> A 50.35 4 │ A 50.35 4 │
#> A 50.65 5 │ A 50.65 5 │
#> B 68.58 6 │ B 68.58 6 │
#> B 62.3 7 │ B 62.3 7 │
#> B 53.67 8 │ B 53.67 8 │
#> B 56.57 9 │ B 56.57 9 │
#> B 57.77 10 │ B <NA> 10 │
#> B 66.12 11 │ B 66.12 11 │
#> B 61.8 12 │ B 61.8 12 │
#> B 62 13 │ B 62 13 │
#> B 60.55 14 │ B 60.55 14 │
#> B 57.22 15 │ B 57.22 15 │
#> # ... up to five more rows
#> # One more case