Fast generation of synthetic data

Fast generation of (primitive) synthetic multivariate normal data.

dataGen(obj, ...)

Arguments

obj

an sdcMicroObj-class-object or a data.frame

...

see possible arguments below

n:

amount of observations for the generated data, defaults to 200

use:

howto compute covariances in case of missing values, see also argument use in cov. The default choice is 'everything', other possible choices are 'all.obs', 'complete.obs', 'na.or.complete' or 'pairwise.complete.obs'.

Value

the generated synthetic data.

Details

Uses the cholesky decomposition to generate synthetic data with approx. the same means and covariances. For details see at the reference.

Note

With this method only multivariate normal distributed data with approxiomately the same covariance as the original data can be generated without reflecting the distribution of real complex data, which are, in general, not follows a multivariate normal distribution.

References

Mateo-Sanz, Martinez-Balleste, Domingo-Ferrer. Fast Generation of Accurate Synthetic Microdata. International Workshop on Privacy in Statistical Databases PSD 2004: Privacy in Statistical Databases, pp 298-306.

See also

sdcMicroObj-class, shuffle

Author

Matthias Templ

Examples

data(mtcars)
# \donttest{
cov(mtcars[,4:6])
#>              hp        drat         wt
#> hp   4700.86694 -16.4511089 44.1926613
#> drat  -16.45111   0.2858814 -0.3727207
#> wt     44.19266  -0.3727207  0.9573790
cov(dataGen(mtcars[,4:6]))
#>              hp        drat        wt
#> hp   4475.61588 -20.0971161 49.432733
#> drat  -20.09712   0.3015923 -0.413207
#> wt     49.43273  -0.4132070  1.089170
pairs(mtcars[,4:6])

pairs(dataGen(mtcars[,4:6]))


## for objects of class sdcMicro:
data(testdata2)
sdc <- createSdcObj(testdata2,
  keyVars=c('urbrur','roof','walls','water','electcon','relat','sex'),
  numVars=c('expend','income','savings'), w='sampling_weight')
sdc <- dataGen(sdc)
# }