README.md
In m-montero/LDTr: Loss Development Triangle Data
LDTr
Introduction
A loss development triangle (LDT) is a table that shows changes in the values of a set of claims over time.
As an Actuary, utilizing loss development triangles is one of the first steps for an actuarial analysis. However, for efficiency reasons, the structure of the data is not stored in a triangular format which adds an additional layer of complexity.
The LDTr package is designed to simplify the use of this data structure by providing the following features:
- work alongside the tidy data framework without any additional constraints
- provide a way to view the triangle data in an easier format
- provide a way to transform from/to: incremental, cumulative, and/or development triangles
- provide a way to work with triangle data which contains multiple triangles
Installation
The development version can be installed using:
# install.packages("devtools")
devtools::install_github("m-montero/LDTr")
Warning: This package is not at a stable state and is subject to major updates. Please use with caution.
Getting Started
After installing the package, load "LDTr".
The "LDTr" package depends on both the "dplyr" and "tidyr" packages.
library(LDTr)
Sample Dataset
Run off triangle of incremental claims data in the traditional data format.
data(RAA,package="LDTr")
head(RAA, n = 20)
## origin dev value
## 1 1981 1 5012
## 2 1982 1 106
## 3 1983 1 3410
## 4 1984 1 5655
## 5 1985 1 1092
## 6 1986 1 1513
## 7 1987 1 557
## 8 1988 1 1351
## 9 1989 1 3133
## 10 1990 1 2063
## 11 1981 2 3257
## 12 1982 2 4179
## 13 1983 2 5582
## 14 1984 2 5900
## 15 1985 2 8473
## 16 1986 2 4932
## 17 1987 2 3463
## 18 1988 2 5596
## 19 1989 2 2262
## 20 1990 2 NA
tbl_tri()
Transform the dataset to a triangle while maintaining the current structure of the data.
RAA %>% tbl_tri(type = "Incremental")
## # A triangle: 10 x 11
## origin 1 2 3 4 5 6 7 8 9 10
## 1981 5012 3257 2638 898 1734 2642 1828 599 54 172
## 1982 106 4179 1111 5270 3116 1817 -103 673 535 *
## 1983 3410 5582 4881 2268 2594 3479 649 603 * *
## 1984 5655 5900 4211 5500 2159 2658 984 * * *
## 1985 1092 8473 6271 6333 3786 225 * * * *
## 1986 1513 4932 5257 1233 2917 * * * * *
## 1987 557 3463 6926 1368 * * * * * *
## 1988 1351 5596 6165 * * * * * * *
## 1989 3133 2262 * * * * * * * *
## 1990 2063 * * * * * * * * *
## #
##
## # A tibble: 100 x 3
## origin dev TRI_INC
## <int> <int> <int>
## 1 1981 1 5012
## 2 1982 1 106
## 3 1983 1 3410
## 4 1984 1 5655
## 5 1985 1 1092
## 6 1986 1 1513
## 7 1987 1 557
## 8 1988 1 1351
## 9 1989 1 3133
## 10 1990 1 2063
## # ... with 90 more rows
transform()
Transform the dataset from an "Incremental" triangle to a "Cumulative" triangle.
RAA %>% tbl_tri(type = "Incremental") %>% transform(type = "Cumulative")
## # A triangle: 10 x 11
## origin 1 2 3 4 5 6 7 8 9 10
## 1981 5012 8269 10907 11805 13539 16181 18009 18608 18662 18834
## 1982 106 4285 5396 10666 13782 15599 15496 16169 16704 *
## 1983 3410 8992 13873 16141 18735 22214 22863 23466 * *
## 1984 5655 11555 15766 21266 23425 26083 27067 * * *
## 1985 1092 9565 15836 22169 25955 26180 * * * *
## 1986 1513 6445 11702 12935 15852 * * * * *
## 1987 557 4020 10946 12314 * * * * * *
## 1988 1351 6947 13112 * * * * * * *
## 1989 3133 5395 * * * * * * * *
## 1990 2063 * * * * * * * * *
## #
##
## # A tibble: 100 x 4
## origin dev TRI_CUM TRI_INC
## <int> <int> <int> <int>
## 1 1981 1 5012 5012
## 2 1982 1 106 106
## 3 1983 1 3410 3410
## 4 1984 1 5655 5655
## 5 1985 1 1092 1092
## 6 1986 1 1513 1513
## 7 1987 1 557 557
## 8 1988 1 1351 1351
## 9 1989 1 3133 3133
## 10 1990 1 2063 2063
## # ... with 90 more rows
Transform the dataset from an "Incremental" triangle to a "Development" triangle.
RAA %>% tbl_tri(type = "Incremental") %>% transform(type = "Development")
## # A triangle: 10 x 10
## origin 1-to-2 2-to-3 3-to-4 4-to-5 5-to-6 6-to-7 7-to-8 8-to-9 9-to-10
## 1981 1.65 1.319 1.082 1.147 1.195 1.113 1.033 1.003 1.009
## 1982 40.425 1.259 1.977 1.292 1.132 0.993 1.043 1.033 *
## 1983 2.637 1.543 1.163 1.161 1.186 1.029 1.026 * *
## 1984 2.043 1.364 1.349 1.102 1.113 1.038 * * *
## 1985 8.759 1.656 1.4 1.171 1.009 * * * *
## 1986 4.26 1.816 1.105 1.226 * * * * *
## 1987 7.217 2.723 1.125 * * * * * *
## 1988 5.142 1.887 * * * * * * *
## 1989 1.722 * * * * * * * *
## 1990 * * * * * * * * *
## #
##
## # A tibble: 90 x 3
## origin TRI_LINK TRI_DEV_FCT
## <int> <chr> <dbl>
## 1 1981 1-to-2 1.649840
## 2 1981 2-to-3 1.319023
## 3 1981 3-to-4 1.082332
## 4 1981 4-to-5 1.146887
## 5 1981 5-to-6 1.195140
## 6 1981 6-to-7 1.112972
## 7 1981 7-to-8 1.033261
## 8 1981 8-to-9 1.002902
## 9 1981 9-to-10 1.009217
## 10 1982 1-to-2 40.424528
## # ... with 80 more rows
Transform the dataset from an "Incremental" triangle, to a "Cumulative" triangle, to finally a "Development" triangle.
RAA %>% tbl_tri(type = "Incremental") %>% transform(type = "Cumulative") %>% transform(type = "Development")
## # A triangle: 10 x 10
## origin 1-to-2 2-to-3 3-to-4 4-to-5 5-to-6 6-to-7 7-to-8 8-to-9 9-to-10
## 1981 1.65 1.319 1.082 1.147 1.195 1.113 1.033 1.003 1.009
## 1982 40.425 1.259 1.977 1.292 1.132 0.993 1.043 1.033 *
## 1983 2.637 1.543 1.163 1.161 1.186 1.029 1.026 * *
## 1984 2.043 1.364 1.349 1.102 1.113 1.038 * * *
## 1985 8.759 1.656 1.4 1.171 1.009 * * * *
## 1986 4.26 1.816 1.105 1.226 * * * * *
## 1987 7.217 2.723 1.125 * * * * * *
## 1988 5.142 1.887 * * * * * * *
## 1989 1.722 * * * * * * * *
## 1990 * * * * * * * * *
## #
##
## # A tibble: 90 x 3
## origin TRI_LINK TRI_DEV_FCT
## <int> <chr> <dbl>
## 1 1981 1-to-2 1.649840
## 2 1981 2-to-3 1.319023
## 3 1981 3-to-4 1.082332
## 4 1981 4-to-5 1.146887
## 5 1981 5-to-6 1.195140
## 6 1981 6-to-7 1.112972
## 7 1981 7-to-8 1.033261
## 8 1981 8-to-9 1.002902
## 9 1981 9-to-10 1.009217
## 10 1982 1-to-2 40.424528
## # ... with 80 more rows
m-montero/LDTr documentation built on May 21, 2019, 9:17 a.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
LDTr
Introduction
A loss development triangle (LDT) is a table that shows changes in the values of a set of claims over time.
As an Actuary, utilizing loss development triangles is one of the first steps for an actuarial analysis. However, for efficiency reasons, the structure of the data is not stored in a triangular format which adds an additional layer of complexity.
The LDTr package is designed to simplify the use of this data structure by providing the following features:
- work alongside the tidy data framework without any additional constraints
- provide a way to view the triangle data in an easier format
- provide a way to transform from/to: incremental, cumulative, and/or development triangles
- provide a way to work with triangle data which contains multiple triangles
Installation
The development version can be installed using:
# install.packages("devtools")
devtools::install_github("m-montero/LDTr")
Warning: This package is not at a stable state and is subject to major updates. Please use with caution.
Getting Started
After installing the package, load "LDTr". The "LDTr" package depends on both the "dplyr" and "tidyr" packages.
library(LDTr)
Sample Dataset
Run off triangle of incremental claims data in the traditional data format.
data(RAA,package="LDTr")
head(RAA, n = 20)
## origin dev value
## 1 1981 1 5012
## 2 1982 1 106
## 3 1983 1 3410
## 4 1984 1 5655
## 5 1985 1 1092
## 6 1986 1 1513
## 7 1987 1 557
## 8 1988 1 1351
## 9 1989 1 3133
## 10 1990 1 2063
## 11 1981 2 3257
## 12 1982 2 4179
## 13 1983 2 5582
## 14 1984 2 5900
## 15 1985 2 8473
## 16 1986 2 4932
## 17 1987 2 3463
## 18 1988 2 5596
## 19 1989 2 2262
## 20 1990 2 NA
tbl_tri()
Transform the dataset to a triangle while maintaining the current structure of the data.
RAA %>% tbl_tri(type = "Incremental")
## # A triangle: 10 x 11
## origin 1 2 3 4 5 6 7 8 9 10
## 1981 5012 3257 2638 898 1734 2642 1828 599 54 172
## 1982 106 4179 1111 5270 3116 1817 -103 673 535 *
## 1983 3410 5582 4881 2268 2594 3479 649 603 * *
## 1984 5655 5900 4211 5500 2159 2658 984 * * *
## 1985 1092 8473 6271 6333 3786 225 * * * *
## 1986 1513 4932 5257 1233 2917 * * * * *
## 1987 557 3463 6926 1368 * * * * * *
## 1988 1351 5596 6165 * * * * * * *
## 1989 3133 2262 * * * * * * * *
## 1990 2063 * * * * * * * * *
## #
##
## # A tibble: 100 x 3
## origin dev TRI_INC
## <int> <int> <int>
## 1 1981 1 5012
## 2 1982 1 106
## 3 1983 1 3410
## 4 1984 1 5655
## 5 1985 1 1092
## 6 1986 1 1513
## 7 1987 1 557
## 8 1988 1 1351
## 9 1989 1 3133
## 10 1990 1 2063
## # ... with 90 more rows
transform()
Transform the dataset from an "Incremental" triangle to a "Cumulative" triangle.
RAA %>% tbl_tri(type = "Incremental") %>% transform(type = "Cumulative")
## # A triangle: 10 x 11
## origin 1 2 3 4 5 6 7 8 9 10
## 1981 5012 8269 10907 11805 13539 16181 18009 18608 18662 18834
## 1982 106 4285 5396 10666 13782 15599 15496 16169 16704 *
## 1983 3410 8992 13873 16141 18735 22214 22863 23466 * *
## 1984 5655 11555 15766 21266 23425 26083 27067 * * *
## 1985 1092 9565 15836 22169 25955 26180 * * * *
## 1986 1513 6445 11702 12935 15852 * * * * *
## 1987 557 4020 10946 12314 * * * * * *
## 1988 1351 6947 13112 * * * * * * *
## 1989 3133 5395 * * * * * * * *
## 1990 2063 * * * * * * * * *
## #
##
## # A tibble: 100 x 4
## origin dev TRI_CUM TRI_INC
## <int> <int> <int> <int>
## 1 1981 1 5012 5012
## 2 1982 1 106 106
## 3 1983 1 3410 3410
## 4 1984 1 5655 5655
## 5 1985 1 1092 1092
## 6 1986 1 1513 1513
## 7 1987 1 557 557
## 8 1988 1 1351 1351
## 9 1989 1 3133 3133
## 10 1990 1 2063 2063
## # ... with 90 more rows
Transform the dataset from an "Incremental" triangle to a "Development" triangle.
RAA %>% tbl_tri(type = "Incremental") %>% transform(type = "Development")
## # A triangle: 10 x 10
## origin 1-to-2 2-to-3 3-to-4 4-to-5 5-to-6 6-to-7 7-to-8 8-to-9 9-to-10
## 1981 1.65 1.319 1.082 1.147 1.195 1.113 1.033 1.003 1.009
## 1982 40.425 1.259 1.977 1.292 1.132 0.993 1.043 1.033 *
## 1983 2.637 1.543 1.163 1.161 1.186 1.029 1.026 * *
## 1984 2.043 1.364 1.349 1.102 1.113 1.038 * * *
## 1985 8.759 1.656 1.4 1.171 1.009 * * * *
## 1986 4.26 1.816 1.105 1.226 * * * * *
## 1987 7.217 2.723 1.125 * * * * * *
## 1988 5.142 1.887 * * * * * * *
## 1989 1.722 * * * * * * * *
## 1990 * * * * * * * * *
## #
##
## # A tibble: 90 x 3
## origin TRI_LINK TRI_DEV_FCT
## <int> <chr> <dbl>
## 1 1981 1-to-2 1.649840
## 2 1981 2-to-3 1.319023
## 3 1981 3-to-4 1.082332
## 4 1981 4-to-5 1.146887
## 5 1981 5-to-6 1.195140
## 6 1981 6-to-7 1.112972
## 7 1981 7-to-8 1.033261
## 8 1981 8-to-9 1.002902
## 9 1981 9-to-10 1.009217
## 10 1982 1-to-2 40.424528
## # ... with 80 more rows
Transform the dataset from an "Incremental" triangle, to a "Cumulative" triangle, to finally a "Development" triangle.
RAA %>% tbl_tri(type = "Incremental") %>% transform(type = "Cumulative") %>% transform(type = "Development")
## # A triangle: 10 x 10
## origin 1-to-2 2-to-3 3-to-4 4-to-5 5-to-6 6-to-7 7-to-8 8-to-9 9-to-10
## 1981 1.65 1.319 1.082 1.147 1.195 1.113 1.033 1.003 1.009
## 1982 40.425 1.259 1.977 1.292 1.132 0.993 1.043 1.033 *
## 1983 2.637 1.543 1.163 1.161 1.186 1.029 1.026 * *
## 1984 2.043 1.364 1.349 1.102 1.113 1.038 * * *
## 1985 8.759 1.656 1.4 1.171 1.009 * * * *
## 1986 4.26 1.816 1.105 1.226 * * * * *
## 1987 7.217 2.723 1.125 * * * * * *
## 1988 5.142 1.887 * * * * * * *
## 1989 1.722 * * * * * * * *
## 1990 * * * * * * * * *
## #
##
## # A tibble: 90 x 3
## origin TRI_LINK TRI_DEV_FCT
## <int> <chr> <dbl>
## 1 1981 1-to-2 1.649840
## 2 1981 2-to-3 1.319023
## 3 1981 3-to-4 1.082332
## 4 1981 4-to-5 1.146887
## 5 1981 5-to-6 1.195140
## 6 1981 6-to-7 1.112972
## 7 1981 7-to-8 1.033261
## 8 1981 8-to-9 1.002902
## 9 1981 9-to-10 1.009217
## 10 1982 1-to-2 40.424528
## # ... with 80 more rows
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.