adjlg {spaMM}

Simulated data set for testing sparse-precision code

Description

This is used in tests/test-adjacency-long.R

Usage

data("adjlg")

Format

Includes an adjacency matrix adjlgMat. and a data frame adjlg with 5474 observations on the following 8 variables.

ID

a factor with levels 1 to 1000

months

a numeric vector

GENDER

a character vector

AGE

a numeric vector

X1

a numeric vector

X2

a numeric vector

month

a numeric vector

BUY

a numeric vector

Source

The simulation code shown below is derived from an example produced by Jeroen van den Ochtend. Following a change incorporated in spaMM version 3.8.0, that implied stricter checks of the input matrix, it appeared that the precision matrix generated by this example had inappropriate (repeated) dimnames. This example was then updated to reproduce past fitting results with a correctly formatted matrix. Note that changing the names of an adjacency matrix (as below) is generally unwise as it generally changes the statistical model because these names are matched whenever possible to levels of the grouping factor in the data.

The code was also modified to compensate for changes in R's default random number generator.

Examples

data(adjlg)
## See further usage in tests/test-adjacency-long.R
## Not run: 
# as produced by:
  library(data.table) ## Included data produced using version 1.10.4.3
  library(igraph) ## Included data produced using version 1.2.1
  
  rsample <- function(N=100, ## size of implied adjacency matrix
                      month_max=10,seed) {
    if (is.integer(seed)) set.seed(seed)
    dt <- data.table(ID=factor(1:N))
    dt$months <- sample(1:month_max,N,replace=T) ## # of liens for each level of ID
    dt$GENDER <- sample(c("MALE","FEMALE"),N,replace=TRUE)
    dt$AGE <- sample(18:99,N,replace=T)
    dt$X1 <- sample(1000:9900,N,replace=T)
    dt$X2 <-  runif(N)
    
    dt <- dt[, c(.SD, month=data.table(seq(from=1, to=months, by = 1))), by = ID] 
    dt[,BUY := 0]
    dt[month.V1==months,BUY := sample(c(0,1),1),by=ID]
    setnames(dt,"month.V1","month")
    
    #### create adjacency matrix
    Network <- data.table(OUT=sample(dt$ID,N*month_max*4/10))
    Network$IN <- sample(dt$ID,N*month_max*4/10)
    Network <- Network[IN != OUT]
    Network <- unique(Network)
    g <- graph.data.frame(Network,directed=F)
    g <- add_vertices(g,sum(!unique(dt$ID) %in% V(g)),
             name=unique(dt[!dt$ID %in% V(g),list(ID)])) # => improper names
    Network <- as_adjacency_matrix(g,sparse = TRUE,type="both")
    colnames(Network) <- rownames(Network) <- seq(nrow(Network)) # post-v3.8.0 names 
    return(list(data=dt,adjMatrix=Network))
  }

  RNGkind("Mersenne-Twister", "Inversion", "Rounding"  )
  set.seed(123)
  adjlg_sam <- rsample(N=1000,seed=NULL) 
  RNGkind("Mersenne-Twister", "Inversion", "Rejection"  )
  #
  adjlg <- as.data.frame(adjlg_sam$data)
  adjlgMat <- adjlg_sam$adjMatrix

## End(Not run)