Quartile: Detection of outliers using quartiles and by comparing with...

In statisticsnorway/Kostra: Functions for Kostra

Detection of outliers using quartiles and by comparing with other data in same or previous period.

Description

Detection of outliers using quartiles and by comparing with other data in same or previous period.

Usage

Quartile(
  data,
  id,
  x1,
  y1,
  x2 = NULL,
  y2 = NULL,
  strataName = NULL,
  pKL = 1.5,
  pKU = 1.5
)

Arguments

data	Input of Quartile is a data set of class data.frame.
id	Name of the identification variable.
x1	Name of x variable in period t.
y1	Name of y variable in period t.
x2	Name of x variable in period t-1. Optional
y2	Name of y variable in period t-1. Optional
strataName	Name of the stratification variable. Optional
pKL	Parameter for lower limit.
pKU	Parameter for upper limit.

Value

Output of Quartile is a data set of class data.frame. Only units with both x1 and y1 not missing and greater than zero are included. The variables are:

id	The input identification variable
x1	The input x1 variable
y1	The input y1 variable
x2	The input x2 variable
y2	The input y2 variable
ratio	The ratio between x1 and y1
ratio2	The ratio between x2 and y2
ratioAll	The ratio between the sum of x1 and the sum of y1 aggregated over the whole data set
ratioAll2	The ratio between the sum of x2 and the sum of y2 aggregated over the whole data set
ratioStr	The ratio between the sum of x1 and the sum of y1 aggregated over the stratum
ratioStr2	The ratio between the sum of x2 and the sum of y2 aggregated over the stratum
lowerLimit	The lower limit of the ratio
upperLimit	The upper limit of the ratio
outlier	A binary variable indicating whether the observation is outside the limits [q1 - pKL*(M - q1), q3 + pKU*(q3 - M)]

, where M is the median and q1 and q3 the 1st an 3rd quartile respectively.

strata	Strata name or number
ranking	The rank of ratio. For plotting purposes

Author(s)

Magnar Lillegård

References

Datarevisjon: Kontroll, granskning og retting av data. Anbefalt praksis, Statistisk sentralbyrås håndbøker, 2005/84.

Examples

 minedata <- KostraData("testdata")
 minedata$strata <- as.character(c(rep(1, 61), rep(2, 91), rep(3, 98), rep(4, 81), rep(5, 85)))
 Quartile(data = minedata, id = "Region", x1 = "areal_130_eier_2015", y1 = "areal_130_leier_2015", pKL = 2, pKU = 2)
 Quartile(data = minedata, id = "Region", x1 = "areal_130_eier_2015", y1 = "areal_130_leier_2015", strataName = "strata")
 Quartile(data = minedata, id = "Region", x1 = "areal_130_eier_2015", y1 = "areal_130_leier_2015",
          x2 = "areal_130_eier_2014", y2 = "areal_130_leier_2014", strataName = "strata")

statisticsnorway/Kostra documentation built on Sept. 25, 2024, 10:37 a.m.