simstudy (version 0.2.0)

addCorGen: Create multivariate (correlated) data - for general distributions

Description

Create multivariate (correlated) data - for general distributions

Usage

addCorGen(
  dtOld,
  nvars,
  idvar = "id",
  rho,
  corstr,
  corMatrix = NULL,
  dist,
  param1,
  param2 = NULL,
  cnames = NULL,
  method = "copula",
  formSpec = NULL,
  periodvar = "period"
)

Arguments

dtOld

If an existing data.table is specified, then wide will be set to TRUE and n will be set to the nrow(dt) without any warning or error.

nvars

Number of new variables to create for each id.

idvar

String variable name of column represents individual level id for correlated data.

rho

Correlation coefficient, -1 <= rho <= 1. Use if corMatrix is not provided.

corstr

Correlation structure of the variance-covariance matrix defined by sigma and rho. Options include "cs" for a compound symmetry structure and "ar1" for an autoregressive structure.

corMatrix

Correlation matrix can be entered directly. It must be symmetrical and positive semi-definite. It is not a required field; if a matrix is not provided, then a structure and correlation coefficient rho must be specified.

dist

A string indicating "normal", "binary", "poisson" or "gamma".

param1

A string that represents the column in dtOld that contains the parameter for the mean of the distribution. In the case of the uniform distribution the column specifies the minimum.

param2

A string that represents the column in dtOld that contains a possible second parameter for the distribution. For the normal distribution, this will be the variance; for the gamma distribution, this will be the dispersion; and for the uniform distribution, this will be the maximum.

cnames

Explicit column names. A single string with names separated by commas. If no string is provided, the default names will be V#, where # represents the column.

method

Two methods are available to generate correlated data. (1) "copula" uses the multivariate Gaussian copula method that is applied to all other distributions; this applies to all available distributions. (2) "ep" uses an algorithm developed by Emrich and Piedmonte.

formSpec

The formula (as a string) that was used to generate the binary outcome in the `defDataAdd` statement. This is only necessary when method "ep" is requested.

periodvar

A string value that indicates the name of the field that indexes the repeated measurement for an individual unit. The value defaults to "period".

Value

Original data.table with added column(s) of correlated data

Examples

# NOT RUN {
# Wide example

def <- defData(varname = "xbase", formula = 5, variance = .4, dist = "gamma", id = "cid")
def <- defData(def, varname = "lambda", formula = ".5 + .1*xbase", dist = "nonrandom", link = "log")
def <- defData(def, varname = "p", formula = "-2 + .3*xbase", dist = "nonrandom", link = "logit")

dt <- genData(500, def)

dtX1 <- addCorGen(
  dtOld = dt, idvar = "cid", nvars = 3, rho = .7, corstr = "cs",
  dist = "poisson", param1 = "lambda"
)

dtX2 <- addCorGen(
  dtOld = dt, idvar = "cid", nvars = 4, rho = .4, corstr = "ar1",
  dist = "binary", param1 = "p"
)

# Long example

def <- defData(varname = "xbase", formula = 5, variance = .4, dist = "gamma", id = "cid")
def <- defData(def, "nperiods", formula = 3, dist = "noZeroPoisson")

def2 <- defDataAdd(
  varname = "lambda", formula = ".5+.5*period + .1*xbase",
  dist = "nonrandom", link = "log"
)
def2 <- defDataAdd(def2,
  varname = "p", formula = "-3+.2*period + .3*xbase",
  dist = "nonrandom", link = "logit"
)
def2 <- defDataAdd(def2,
  varname = "gammaMu", formula = ".2*period + .3*xbase",
  dist = "nonrandom", link = "log"
)
def2 <- defDataAdd(def2,
  varname = "gammaDis",
  formula = 1, dist = "nonrandom"
)
def2 <- defDataAdd(def2,
  varname = "normMu",
  formula = "5+period + .5*xbase", dist = "nonrandom"
)
def2 <- defDataAdd(def2,
  varname = "normVar", formula = 4,
  dist = "nonrandom"
)
def2 <- defDataAdd(def2,
  varname = "unifMin",
  formula = "5 + 2*period + .2*xbase", dist = "nonrandom"
)
def2 <- defDataAdd(def2,
  varname = "unifMax",
  formula = "unifMin + 20", dist = "nonrandom"
)

dt <- genData(1000, def)

dtLong <- addPeriods(dt, idvars = "cid", nPeriods = 3)
dtLong <- addColumns(def2, dtLong)

# Poisson distribution

dtX3 <- addCorGen(
  dtOld = dtLong, idvar = "cid", nvars = 3, rho = .6, corstr = "cs",
  dist = "poisson", param1 = "lambda", cnames = "NewPois"
)
dtX3

# Binomial distribution - copula method

dtX4 <- addCorGen(
  dtOld = dtLong, idvar = "cid", nvars = 3, rho = .6, corstr = "cs",
  dist = "binary", param1 = "p", cnames = "NewBin"
)

dtX4

# Gamma distribution

dtX6 <- addCorGen(
  dtOld = dtLong, idvar = "cid", nvars = 3, rho = .6, corstr = "ar1",
  dist = "gamma", param1 = "gammaMu", param2 = "gammaDis",
  cnames = "NewGamma"
)

dtX6

# Normal distribution

dtX7 <- addCorGen(
  dtOld = dtLong, idvar = "cid", nvars = 3, rho = .6, corstr = "ar1",
  dist = "normal", param1 = "normMu", param2 = "normVar",
  cnames = "NewNorm"
)

# Binary outcome - ep method

probform <- "-2 + .3*period"

def1 <- defDataAdd(
  varname = "p", formula = probform,
  dist = "nonrandom", link = "logit"
)

dx <- genData(100)
dx <- addPeriods(dx, nPeriods = 4)
dx <- addColumns(def1, dx)

dg <- addCorGen(dx,
  nvars = 4,
  corMatrix = NULL, rho = .3, corstr = "cs",
  dist = "binary", param1 = "p",
  method = "ep", formSpec = probform,
  periodvar = "period"
)
# }