Generate missing data

Generate missing data

genMiss(
  dtName,
  missDefs,
  idvars,
  repeated = FALSE,
  periodvar = "period",
  envir = parent.frame()
)

Arguments

dtName

Name of complete data set

missDefs

Definitions of missingness

idvars

Index variables

repeated

Indicator for longitudinal data

periodvar

Name of variable that contains period

envir

parent.frame() by default, allows functionality with double-dot notation

Value

Missing data matrix indexed by idvars (and period if relevant)

See also

defMiss, genObs

Examples

def1 <- defData(varname = "m", dist = "binary", formula = .5)
def1 <- defData(def1, "u", dist = "binary", formula = .5)
def1 <- defData(def1, "x1", dist = "normal", formula = "20*m + 20*u", variance = 2)
def1 <- defData(def1, "x2", dist = "normal", formula = "20*m + 20*u", variance = 2)
def1 <- defData(def1, "x3", dist = "normal", formula = "20*m + 20*u", variance = 2)

dtAct <- genData(1000, def1)

defM <- defMiss(varname = "x1", formula = .15, logit.link = FALSE)
defM <- defMiss(defM, varname = "x2", formula = ".05 + m * 0.25", logit.link = FALSE)
defM <- defMiss(defM, varname = "x3", formula = ".05 + u * 0.25", logit.link = FALSE)
defM <- defMiss(defM, varname = "u", formula = 1, logit.link = FALSE) # not observed
defM
#>    varname        formula logit.link baseline monotonic
#>     <char>         <char>     <lgcl>   <lgcl>    <lgcl>
#> 1:      x1           0.15      FALSE    FALSE     FALSE
#> 2:      x2 .05 + m * 0.25      FALSE    FALSE     FALSE
#> 3:      x3 .05 + u * 0.25      FALSE    FALSE     FALSE
#> 4:       u              1      FALSE    FALSE     FALSE

# Generate missing data matrix

missMat <- genMiss(dtAct, defM, idvars = "id")
missMat
#> Key: <id>
#>          id    x1    x2    x3     u     m
#>       <int> <int> <int> <int> <int> <num>
#>    1:     1     1     0     0     1     0
#>    2:     2     0     0     0     1     0
#>    3:     3     0     0     0     1     0
#>    4:     4     0     0     0     1     0
#>    5:     5     1     1     1     1     0
#>   ---                                    
#>  996:   996     0     0     0     1     0
#>  997:   997     0     0     0     1     0
#>  998:   998     0     0     1     1     0
#>  999:   999     0     0     0     1     0
#> 1000:  1000     0     0     0     1     0

# Generate observed data from actual data and missing data matrix

dtObs <- genObs(dtAct, missMat, idvars = "id")
dtObs
#> Key: <id>
#>          id     m     u        x1         x2         x3
#>       <int> <int> <int>     <num>      <num>      <num>
#>    1:     1     1    NA        NA 21.1885831 20.8909210
#>    2:     2     0    NA -1.969552 -0.2170204  0.1291439
#>    3:     3     0    NA -1.678498 -1.2700800 -1.0723500
#>    4:     4     1    NA 38.018644 41.1946704 41.1647107
#>    5:     5     1    NA        NA         NA         NA
#>   ---                                                  
#>  996:   996     0    NA 18.649865 21.1546430 19.7298909
#>  997:   997     1    NA 17.800273 21.5847249 18.0452866
#>  998:   998     1    NA 39.993959 39.7405706         NA
#>  999:   999     0    NA  1.717430 -2.4099942 -1.6156891
#> 1000:  1000     0    NA 20.935144 20.4240502 21.1476167