Add single row to definitions table for missing data
defMiss(
dtDefs = NULL,
varname,
formula,
logit.link = FALSE,
baseline = FALSE,
monotonic = FALSE
)Definition data.table to be modified
Name of variable with missingness
Formula to describe pattern of missingness
Indicator set to TRUE when the probability of missingness is based on a logit model.
Indicator is set to TRUE if the variable is a baseline measure and should be missing throughout an entire observation period. This is applicable to repeated measures/longitudinal data.
Indicator set to TRUE if missingness at time t is followed by missingness at all follow-up times > t.
A data.table named dtName that is an updated data definitions table
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(dtName = dtAct, missDefs = defM, idvars = "id")
missMat
#> Key: <id>
#> id x1 x2 x3 u m
#> <int> <int> <int> <int> <int> <num>
#> 1: 1 0 0 1 1 0
#> 2: 2 1 0 0 1 0
#> 3: 3 0 0 0 1 0
#> 4: 4 0 0 0 1 0
#> 5: 5 0 0 1 1 0
#> ---
#> 996: 996 0 0 0 1 0
#> 997: 997 1 1 0 1 0
#> 998: 998 0 1 0 1 0
#> 999: 999 1 0 0 1 0
#> 1000: 1000 1 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 0 NA 21.820790 20.43769558 NA
#> 2: 2 1 NA NA 41.30834431 41.063218
#> 3: 3 1 NA 19.800832 21.14481614 17.695432
#> 4: 4 0 NA 2.048093 0.03823499 -2.655493
#> 5: 5 0 NA 18.781027 19.19143369 NA
#> ---
#> 996: 996 0 NA 20.459640 18.98130419 19.944863
#> 997: 997 1 NA NA NA 40.116043
#> 998: 998 1 NA 40.320403 NA 40.856016
#> 999: 999 0 NA NA 20.27016776 19.921736
#> 1000: 1000 0 NA NA 18.40629184 21.432758