Difference between two numerical variables
Diff2NumVar.RdCalculating the difference between two numerical variables Listing units with big difference, either the k units with the biggest absolute difference, or units with a absolute difference greater than a threshold Only units with value on both variables are used in the calculations
Usage
Diff2NumVar(
data,
idVar,
xVar,
yVar,
strataVar = NULL,
antall = 5,
grense = NULL,
zVar = NULL,
kommentarVar = NULL
)Arguments
- data
Input data set of class data.frame.
- idVar
Name of an identification variable.
- xVar
Name of the x variable to be compared.
- yVar
Name of the y variable to be compared.
- strataVar
Name of stratification variable. Optional. If strataVar is given, the calculation and listing is performed within each stratum.
- antall
Parameter specifying how many units with the biggest difference to be listed. Default 5.
- grense
Parameter specifying a threshold for the units to be listed. This parameter overrules antall. Optional.
- zVar
Name of the original y variable, before editing. Optional.
- kommentarVar
Name of a variable giving information about the editing. Optional.
Value
Output of Diff2NumVar is a data set of class data.frame. The variables in the data frame are:
- strata
The stratum (if strataVar is given, "1" otherwise)
- id
The input identification variable
- x
The input x variable
- y
The input y variable
- Forh
The ratio between x and y: y / x
- Diff
The difference between x and y: y - x
- AbsDiff
The absolute difference: |Diff|
- DiffProsAvx
The difference in percent of x: (Diff / x) * 100
- DiffProsAvSumx
The difference in percent of the stratum total for x: (Diff / stratum x) * 100
- DiffProsAvTotx
The difference in percent of the total for x: (Diff / total x) * 100
- SumDiffProsAvSumx
The stratum difference in percent of the stratum total for x: ((stratum y - stratum x) / stratum x) * 100
- SumDiffProsAvTotx
The stratum difference in percent of the total for x: ((stratum y - stratum x) / total x) * 100
- z
The input z variable
- EdEndring
The difference between z and y: y - z
- Kommentar
The input kommentar variable
Examples
testdata <- KostraData("testdata")
# lager en grupperingsvariabel
testdata$gr <- c(rep(3, 30), rep(5, 40), rep(1, 61), rep(2, 91), rep(3, 68), rep(4, 61),
rep(5, 45), rep(4, 20))
# lager en z-variabel
testdata$z <- testdata$areal_130_eier_2015
testdata$z[4*(1:104)] <- testdata$areal_130_eier_2014[2*(1:104)]
testdata$z[10*(1:40)] <- 1.2 * testdata$areal_130_eier_2015[10*(1:40)]
testdata$z[10*(1:40) - 5] <- 0.7 * testdata$areal_130_eier_2015[10*(1:40) - 5]
# lager en kommentarvariabel
testdata$kommentar <- ifelse(testdata$areal_130_eier_2015 == testdata$z, "ikke kontrollert",
"godkjent")
testdata$kommentar[c(88)] <- "oppgavegiver kontaktet"
# uten strata
Diff2NumVar(data = testdata, idVar = "Region", xVar = "areal_130_eier_2014", yVar = "areal_130_eier_2015",
strataVar = NULL, antall = 5, grense = NULL, zVar = NULL, kommentarVar = NULL)
#> strata id x y Forh Diff AbsDiff DiffProsAvx DiffProsAvSumx
#> 1 1 60400 0 14677 Inf 14677 14677 Inf 0.8904250
#> 2 1 112000 12141 22815 1.8791698 10674 10674 87.91698 0.6475708
#> 3 1 110200 24000 33029 1.3762083 9029 9029 37.62083 0.5477718
#> 4 1 190200 10765 19292 1.7921040 8527 8527 79.21040 0.5173165
#> 5 1 40300 11234 3739 0.3328289 -7495 7495 -66.71711 -0.4547071
#> DiffProsAvTotx SumDiffProsAvSumx SumDiffProsAvTotx z EdEndring Kommentar
#> 1 0.8904250 1.363757 1.363757 NA NA NA
#> 2 0.6475708 1.363757 1.363757 NA NA NA
#> 3 0.5477718 1.363757 1.363757 NA NA NA
#> 4 0.5173165 1.363757 1.363757 NA NA NA
#> 5 -0.4547071 1.363757 1.363757 NA NA NA
# med strata
Diff2NumVar(data = testdata, idVar = "Region", xVar = "areal_130_eier_2014", yVar = "areal_130_eier_2015",
strataVar = "gr", antall = 5, grense = NULL, zVar = NULL, kommentarVar = NULL)
#> strata id x y Forh Diff AbsDiff DiffProsAvx DiffProsAvSumx
#> 1 1 60400 0 14677 Inf 14677 14677 Inf 5.5973152
#> 2 1 70100 6969 13646 1.9581002 6677 6677 95.81002 2.5463837
#> 3 1 61500 2100 0 0.0000000 -2100 2100 -100.00000 -0.8008695
#> 4 1 62500 7128 5066 0.7107183 -2062 2062 -28.92817 -0.7863776
#> 5 1 54000 4263 2501 0.5866760 -1762 1762 -41.33240 -0.6719677
#> 6 2 112000 12141 22815 1.8791698 10674 10674 87.91698 2.7081954
#> 7 2 110200 24000 33029 1.3762083 9029 9029 37.62083 2.2908278
#> 8 2 112100 11195 5510 0.4921840 -5685 5685 -50.78160 -1.4423919
#> 9 2 113000 1116 5947 5.3288530 4831 4831 432.88530 1.2257159
#> 10 2 111900 5727 9645 1.6841278 3918 3918 68.41278 0.9940706
#> 11 3 13600 10562 5648 0.5347472 -4914 4914 -46.52528 -1.3165615
#> 12 3 10100 0 3956 Inf 3956 3956 Inf 1.0598936
#> 13 3 150500 7660 5040 0.6579634 -2620 2620 -34.20366 -0.7019518
#> 14 3 144300 4000 2080 0.5200000 -1920 1920 -48.00000 -0.5144074
#> 15 3 142100 5540 3940 0.7111913 -1600 1600 -28.88087 -0.4286729
#> 16 4 200400 10568 13690 1.2954201 3122 3122 29.54201 1.1427066
#> 17 4 164800 5696 4008 0.7036517 -1688 1688 -29.63483 -0.6178375
#> 18 4 200200 675 1428 2.1155556 753 753 111.55556 0.2756112
#> 19 4 174000 1026 1734 1.6900585 708 708 69.00585 0.2591404
#> 20 4 201800 1014 1498 1.4773176 484 484 47.73176 0.1771525
#> 21 5 190200 10765 19292 1.7921040 8527 8527 79.21040 2.4679745
#> 22 5 40300 11234 3739 0.3328289 -7495 7495 -66.71711 -2.1692822
#> 23 5 23500 11878 16748 1.4100017 4870 4870 41.00017 1.4095269
#> 24 5 23000 15531 13287 0.8555148 -2244 2244 -14.44852 -0.6494822
#> 25 5 193800 0 1935 Inf 1935 1935 Inf 0.5600482
#> DiffProsAvTotx SumDiffProsAvSumx SumDiffProsAvTotx z EdEndring Kommentar
#> 1 0.89042500 5.803634 0.9232464 NA NA NA
#> 2 0.40508059 5.803634 0.9232464 NA NA NA
#> 3 -0.12740291 5.803634 0.9232464 NA NA NA
#> 4 -0.12509752 5.803634 0.9232464 NA NA NA
#> 5 -0.10689711 5.803634 0.9232464 NA NA NA
#> 6 0.64757079 2.845965 0.6805135 NA NA NA
#> 7 0.54777184 2.845965 0.6805135 NA NA NA
#> 8 -0.34489788 2.845965 0.6805135 NA NA NA
#> 9 0.29308736 2.845965 0.6805135 NA NA NA
#> 10 0.23769743 2.845965 0.6805135 NA NA NA
#> 11 -0.29812281 -3.578347 -0.8102825 NA NA NA
#> 12 0.24000281 -3.578347 -0.8102825 NA NA NA
#> 13 -0.15895030 -3.578347 -0.8102825 NA NA NA
#> 14 -0.11648266 -3.578347 -0.8102825 NA NA NA
#> 15 -0.09706888 -3.578347 -0.8102825 NA NA NA
#> 16 0.18940566 1.040954 0.1725399 NA NA NA
#> 17 -0.10240767 1.040954 0.1725399 NA NA NA
#> 18 0.04568304 1.040954 0.1725399 NA NA NA
#> 19 0.04295298 1.040954 0.1725399 NA NA NA
#> 20 0.02936334 1.040954 0.1725399 NA NA NA
#> 21 0.51731648 1.897507 0.3977398 NA NA NA
#> 22 -0.45470705 1.897507 0.3977398 NA NA NA
#> 23 0.29545341 1.897507 0.3977398 NA NA NA
#> 24 -0.13613911 1.897507 0.3977398 NA NA NA
#> 25 0.11739268 1.897507 0.3977398 NA NA NA
# med z og kommentar
Diff2NumVar(data = testdata, idVar = "Region", xVar = "areal_130_eier_2014", yVar = "areal_130_eier_2015",
strataVar = "gr", antall = 5, grense = NULL, zVar = "z", kommentarVar = "kommentar")
#> strata id x y Forh Diff AbsDiff DiffProsAvx DiffProsAvSumx
#> 1 1 60400 0 14677 Inf 14677 14677 Inf 5.5973152
#> 2 1 70100 6969 13646 1.9581002 6677 6677 95.81002 2.5463837
#> 3 1 61500 2100 0 0.0000000 -2100 2100 -100.00000 -0.8008695
#> 4 1 62500 7128 5066 0.7107183 -2062 2062 -28.92817 -0.7863776
#> 5 1 54000 4263 2501 0.5866760 -1762 1762 -41.33240 -0.6719677
#> 6 2 112000 12141 22815 1.8791698 10674 10674 87.91698 2.7081954
#> 7 2 110200 24000 33029 1.3762083 9029 9029 37.62083 2.2908278
#> 8 2 112100 11195 5510 0.4921840 -5685 5685 -50.78160 -1.4423919
#> 9 2 113000 1116 5947 5.3288530 4831 4831 432.88530 1.2257159
#> 10 2 111900 5727 9645 1.6841278 3918 3918 68.41278 0.9940706
#> 11 3 13600 10562 5648 0.5347472 -4914 4914 -46.52528 -1.3165615
#> 12 3 10100 0 3956 Inf 3956 3956 Inf 1.0598936
#> 13 3 150500 7660 5040 0.6579634 -2620 2620 -34.20366 -0.7019518
#> 14 3 144300 4000 2080 0.5200000 -1920 1920 -48.00000 -0.5144074
#> 15 3 142100 5540 3940 0.7111913 -1600 1600 -28.88087 -0.4286729
#> 16 4 200400 10568 13690 1.2954201 3122 3122 29.54201 1.1427066
#> 17 4 164800 5696 4008 0.7036517 -1688 1688 -29.63483 -0.6178375
#> 18 4 200200 675 1428 2.1155556 753 753 111.55556 0.2756112
#> 19 4 174000 1026 1734 1.6900585 708 708 69.00585 0.2591404
#> 20 4 201800 1014 1498 1.4773176 484 484 47.73176 0.1771525
#> 21 5 190200 10765 19292 1.7921040 8527 8527 79.21040 2.4679745
#> 22 5 40300 11234 3739 0.3328289 -7495 7495 -66.71711 -2.1692822
#> 23 5 23500 11878 16748 1.4100017 4870 4870 41.00017 1.4095269
#> 24 5 23000 15531 13287 0.8555148 -2244 2244 -14.44852 -0.6494822
#> 25 5 193800 0 1935 Inf 1935 1935 Inf 0.5600482
#> DiffProsAvTotx SumDiffProsAvSumx SumDiffProsAvTotx z EdEndring
#> 1 0.89042500 5.803634 0.9232464 9089.0 5588.0
#> 2 0.40508059 5.803634 0.9232464 3330.0 10316.0
#> 3 -0.12740291 5.803634 0.9232464 0.0 0.0
#> 4 -0.12509752 5.803634 0.9232464 5066.0 0.0
#> 5 -0.10689711 5.803634 0.9232464 2501.0 0.0
#> 6 0.64757079 2.845965 0.6805135 15970.5 6844.5
#> 7 0.54777184 2.845965 0.6805135 33029.0 0.0
#> 8 -0.34489788 2.845965 0.6805135 0.0 5510.0
#> 9 0.29308736 2.845965 0.6805135 5947.0 0.0
#> 10 0.23769743 2.845965 0.6805135 9645.0 0.0
#> 11 -0.29812281 -3.578347 -0.8102825 970.0 4678.0
#> 12 0.24000281 -3.578347 -0.8102825 3956.0 0.0
#> 13 -0.15895030 -3.578347 -0.8102825 8126.0 -3086.0
#> 14 -0.11648266 -3.578347 -0.8102825 2080.0 0.0
#> 15 -0.09706888 -3.578347 -0.8102825 2758.0 1182.0
#> 16 0.18940566 1.040954 0.1725399 13690.0 0.0
#> 17 -0.10240767 1.040954 0.1725399 4008.0 0.0
#> 18 0.04568304 1.040954 0.1725399 1428.0 0.0
#> 19 0.04295298 1.040954 0.1725399 1734.0 0.0
#> 20 0.02936334 1.040954 0.1725399 1498.0 0.0
#> 21 0.51731648 1.897507 0.3977398 19292.0 0.0
#> 22 -0.45470705 1.897507 0.3977398 3739.0 0.0
#> 23 0.29545341 1.897507 0.3977398 16748.0 0.0
#> 24 -0.13613911 1.897507 0.3977398 13287.0 0.0
#> 25 0.11739268 1.897507 0.3977398 3498.0 -1563.0
#> Kommentar
#> 1 oppgavegiver kontaktet
#> 2 godkjent
#> 3 ikke kontrollert
#> 4 ikke kontrollert
#> 5 ikke kontrollert
#> 6 godkjent
#> 7 ikke kontrollert
#> 8 godkjent
#> 9 ikke kontrollert
#> 10 ikke kontrollert
#> 11 godkjent
#> 12 ikke kontrollert
#> 13 godkjent
#> 14 ikke kontrollert
#> 15 godkjent
#> 16 ikke kontrollert
#> 17 ikke kontrollert
#> 18 ikke kontrollert
#> 19 ikke kontrollert
#> 20 ikke kontrollert
#> 21 ikke kontrollert
#> 22 ikke kontrollert
#> 23 ikke kontrollert
#> 24 ikke kontrollert
#> 25 godkjent
# med grense
Diff2NumVar(data = testdata, idVar = "Region", xVar = "areal_130_eier_2014", yVar = "areal_130_eier_2015",
strataVar = "gr", antall = 5, grense = 5000, zVar = "z", kommentarVar = "kommentar")
#> strata id x y Forh Diff AbsDiff DiffProsAvx DiffProsAvSumx
#> 1 1 60400 0 14677 Inf 14677 14677 Inf 5.597315
#> 2 1 70100 6969 13646 1.9581002 6677 6677 95.81002 2.546384
#> 3 2 112000 12141 22815 1.8791698 10674 10674 87.91698 2.708195
#> 4 2 110200 24000 33029 1.3762083 9029 9029 37.62083 2.290828
#> 5 2 112100 11195 5510 0.4921840 -5685 5685 -50.78160 -1.442392
#> 6 5 190200 10765 19292 1.7921040 8527 8527 79.21040 2.467975
#> 7 5 40300 11234 3739 0.3328289 -7495 7495 -66.71711 -2.169282
#> DiffProsAvTotx SumDiffProsAvSumx SumDiffProsAvTotx z EdEndring
#> 1 0.8904250 5.803634 0.9232464 9089.0 5588.0
#> 2 0.4050806 5.803634 0.9232464 3330.0 10316.0
#> 3 0.6475708 2.845965 0.6805135 15970.5 6844.5
#> 4 0.5477718 2.845965 0.6805135 33029.0 0.0
#> 5 -0.3448979 2.845965 0.6805135 0.0 5510.0
#> 6 0.5173165 1.897507 0.3977398 19292.0 0.0
#> 7 -0.4547071 1.897507 0.3977398 3739.0 0.0
#> Kommentar
#> 1 oppgavegiver kontaktet
#> 2 godkjent
#> 3 godkjent
#> 4 ikke kontrollert
#> 5 godkjent
#> 6 ikke kontrollert
#> 7 ikke kontrollert