GaussSuppression (version 0.9.6)

IncrementalTimeSuppression: Incremental Time Suppression

Description

Suppression function useful for sequential calculations over successive time periods.

Usage

IncrementalTimeSuppression(
  data,
  fun,
  timeVar,
  formula,
  suppressedData = NULL,
  subTotals = FALSE,
  finalTotal = FALSE,
  totalPriority = !isFALSE(finalTotal),
  ...
)

Value

A data.frame

Arguments

data

Input data as a data frame

fun

A function: GaussSuppressionFromData or one of its wrappers such as SuppressSmallCounts and SuppressDominantCells.

timeVar

The time period variable

formula

formula A formula defining tables within the time periods. Therefore, the variable timeVar should not be included.

suppressedData

A data frame or a list of data frames as output from GaussSuppressionFromData.

subTotals

Whether all cumulative totals over time should be included.

finalTotal

When FALSE, the timeVar total is named according to time period categories.

totalPriority

When FALSE, the timeVar totals are not prioritized for publication. In other words, these totals are preferred for secondary suppression.

...

Further parameters to GaussSuppressionFromData

See Also

AdditionalSuppression

Examples

# Generating a dataset spanning four quarters 
d2s <- SSBtoolsData("d2s")
d <- rbind(d2s, d2s, d2s, d2s)
set.seed(10)
d$freq[25:96] <- round(d$freq[25:96] + 9 * rnorm(72))
d$freq[d$freq < 0] <- 0
d$quarter <- rep(c("Q1", "Q2", "Q3", "Q4"), each = 24)

# Redefine the function so that several parameters are preset. 
# Also, a simpler function name.   
STS <- function(data, ...) {
  IncrementalTimeSuppression(data, 
          fun = SuppressSmallCounts, 
          timeVar = "quarter", 
          formula = ~main_income * size, 
          maxN = 15, freqVar = "freq", ...)}
          
          
# Default settings without suppressedData as input
a1 <- STS(d[1:24, ])   
a2 <- STS(d[1:48, ])
a3 <- STS(d[1:72, ])
a4 <- STS(d, finalTotal = TRUE)

# The quarters and named totals
unique(a1$quarter)
unique(a2$quarter)
unique(a3$quarter)
unique(a4$quarter)

# Default settings with suppressedData as input
b2 <- STS(d[1:48, ], suppressedData = a1)
b3 <- STS(d[1:72, ], suppressedData = b2)
b4 <- STS(d, finalTotal = TRUE, suppressedData = b3)

# Without totalPriority, suppression will be the same as before. 
# suppressedData makes no difference.
# However, if, for example, there is a changed version of the suppression 
# algorithm, it may be important to use suppressedData 
identical(a2$suppressed, b2$suppressed)
identical(a3$suppressed, b3$suppressed)
identical(a4$suppressed, b4$suppressed) # totalPriority here, since finalTotal 

# With totalPriority and  all the subtotals 
# Note: subtotals are not prioritized
c2 <- STS(d[1:48, ], subTotals = TRUE, totalPriority = TRUE)
c3 <- STS(d[1:72, ], subTotals = TRUE, totalPriority = TRUE)
c4 <- STS(d, subTotals = TRUE, finalTotal = TRUE)
unique(c2$quarter)
unique(c3$quarter)
unique(c4$quarter)

# With such a method, we can see that is important to take into account 
# previously published results.
# Here this is not done and we see differences.
a2[a2$suppressed | c2$suppressed, ]
c2[a2$suppressed | c2$suppressed, ]
c3[SSBtools::Match( c2[a2$suppressed | c2$suppressed, 1:4], c3[1:4]), ]
c4[SSBtools::Match( c2[a2$suppressed | c2$suppressed, 1:4], c4[1:4]), ]


# Here we take into account previously published results.
d2 <- STS(d[1:48, ], subTotals = TRUE, totalPriority = TRUE, suppressedData = a1)
d3 <- STS(d[1:72, ], subTotals = TRUE, totalPriority = TRUE, suppressedData = d2)
d4 <- STS(d, subTotals = TRUE, finalTotal = TRUE, suppressedData = d3)

SSBtools::SortRows(d2[d2$suppressed, ])
SSBtools::SortRows(d3[d3$suppressed, ])

# With such a method, some annual totals must be suppressed
SSBtools::SortRows(d4[d4$suppressed, ]) 

# If necessary, several suppressed data sets can be taken into account
e4 <- STS(d, finalTotal = TRUE, suppressedData = list(a1, a2))