News
ChainLadder Contributors
2021-01-05
Version 0.2.12 [2021-01-05]
- Moved continuous integration testing from TravisCI to GitHub Actions
- Changed vignette format from Sweave to RMarkdown to facilitate easier testing using GitHub Actions
Version 0.2.11 [2020-02-10]
- Fixed as.triangle for a ‘long’ data set, when input data had missing values. Thanks to Dimitri Minassian for reporting this issue.
- Fixed standard error estimation in MackChainLadder when tail factor > 1 and alpha = 2. Thanks to Valentin Cornaciu for reporting this issue.
Version 0.2.10 [2019-05-27]
- Added Berquist-Sherman Paid Claim Development Adjustment methods to adjust paid claims based on the underlying relation between paid and closed claims.
- Added tests to check calendar year effect, correlation between development factors and inflation.
Thanks to Marco De Virgilis.
Version 0.2.9 [2018-12-06]
- Fix to as.triangle.data.frame. The labels of origin and development period were mixed up with the move away from reshape2 to aggregate in version 0.2.8. Thanks to Edward Tasker for reporting this issue.
Version 0.2.8 [2018-11-10]
- Fix to print statements to align them with the generic print methods. Thanks to Markus Senn
- Clarified how the ‘weights’ argument in chainladder and MackChainLadder can be used
- Removed dependency on reshape2 as it has been deprecated
Version 0.2.7 [2018-10-16]
- New quantile method for ‘MackChainLadder’ andv function QuantileIFRS17 to estimate the IFRS 17 Risk Adjustment. Thanks to Eric Dal Moro and Yuriy Krvavych
Version 0.2.6 [2018-05-29]
- New function ‘triangle’ to create a triangle from the given set of vectors of observed data. Thanks to Vincent Goulet
Version 0.2.5 [2017-10-19]
- Fixed bug in Mack.S.E function when “sigma[i - 2]^2” is zero. Thanks to Patrick Green for reporting and fixing the issue.
Version 0.2.4 [2017-01-01]
- Fixed meta information of NEWS vignette, so it will be shown as NEWS on CRAN
Version 0.2.3 [2016-10-20]
Changes
NEWS file
Moved NEWS file into RMarkdown package vignette format.
Triangles may now have non-numeric rownames
Previously it was required that the row and column names of a triangle be convertible to numeric, although that “requirement” did not always cause a problem. For example, the following sets the rownames of GenIns to the beginning Date of the accident year.
## dev
## origin 1 2 3 4 5 6 7 8 9 10
## 2001-01-01 357.8 1125 1735 2218 2746 3320 3466 3606 3834 3901
## 2002-01-01 352.1 1236 2170 3353 3799 4120 4648 4914 5339 NA
## 2003-01-01 290.5 1292 2219 3235 3986 4133 4629 4909 NA NA
## 2004-01-01 310.6 1419 2195 3757 4030 4382 4588 NA NA NA
## 2005-01-01 443.2 1136 2128 2898 3403 3873 NA NA NA NA
## 2006-01-01 396.1 1333 2181 2986 3692 NA NA NA NA NA
## 2007-01-01 440.8 1288 2420 3483 NA NA NA NA NA NA
## 2008-01-01 359.5 1421 2864 NA NA NA NA NA NA NA
## 2009-01-01 376.7 1363 NA NA NA NA NA NA NA NA
## 2010-01-01 344.0 NA NA NA NA NA NA NA NA NAA plot with the lattice=TRUE option, which previously would blow up, now displays with nice headings.
It can often be useful to have “origin” values that are not necessarily convertible to numeric. For example, suppose you have a table of claim detail at various evaluation dates. Invariably, such a table will have a Date field holding the date of loss. It would be nice to be able to summarize that data by accident year “cuts”. It turns out there’s a builtin function in R that will get you most of the way there. It’s called ‘cut’.
Here we take the GenIns data in long format and generate 50 claims per accident period. We assign each claim a random date within the year. The incurred (or paid) “value” given is a random perturbation of one-fiftieth of GenInsLong$value.
We accumulate the detail into an accident year triangle using ChainLadder’s as.triangle method. The summarized triangle displayed at the end is very similar to GenIns, and has informative row labels.
x <- GenInsLong
# start off y with x's headings
y <- x[0,]
names(y)[1] <- "lossdate"
set.seed(1234)
n = 50 # number of simulated claims per accident perior
for (i in 1:nrow(x)) {
y <- rbind(y,
data.frame(
lossdate = as.Date(
as.numeric(as.Date(paste0(x[i, "accyear"]+2000, "-01-01"))) +
round(runif(n, 0, 364),0), origin = "1970-01-01"),
devyear = x[i, "devyear"],
incurred.claims = rnorm(n, mean = x[i, "incurred claims"] / n,
sd = x[i, "incurred claims"]/(10*n))
))
}
# here's the magic cut
y$ay <- cut(y$lossdate, breaks = "years")
# this summarized triangle is very similar to GenIns
as.triangle(y, origin = "ay", dev = "devyear", value = "incurred.claims")## devyear
## ay 1 2 3 4 5 6 7 8
## 2001-01-01 349741 1109368 1737850 2265706 2749056 3318464 3469142 3549578
## 2002-01-01 352821 1245621 2132200 3377061 3820987 4148933 4610189 4891852
## 2003-01-01 296548 1275881 2198221 3235844 3944931 4113276 4623159 4900318
## 2004-01-01 313669 1392038 2171462 3774168 4035879 4461897 4661352 NA
## 2005-01-01 443941 1138787 2190873 2905444 3371444 3849587 NA NA
## 2006-01-01 391527 1324732 2230006 3000719 3742811 NA NA NA
## 2007-01-01 446942 1292116 2416001 3404734 NA NA NA NA
## 2008-01-01 349330 1425022 2844242 NA NA NA NA NA
## 2009-01-01 369893 1368242 NA NA NA NA NA NA
## 2010-01-01 346493 NA NA NA NA NA NA NA
## devyear
## ay 9 10
## 2001-01-01 3769684 3980606
## 2002-01-01 5311927 NA
## 2003-01-01 NA NA
## 2004-01-01 NA NA
## 2005-01-01 NA NA
## 2006-01-01 NA NA
## 2007-01-01 NA NA
## 2008-01-01 NA NA
## 2009-01-01 NA NA
## 2010-01-01 NA NAThe user is encouraged to experiment with other cut’s – e.g., breaks = "quarters" will generate accident quarter triangles.
New as.LongTriangle function
A new function, as.LongTriangle, will convert a triangle from “wide” (matrix) format to “long” (data.frame) format. This differs from ChainLadder’s as.data.frame.triangle method in that the rownames and colnames of Triangle are stored as factors. This feature can be particularly important when plotting a triangle because the order of the “origin” and “dev” values is important.
Additionally, the columns of the resulting data frame may be renamed from the default values (“origin”, “dev”, and “value”) using the “varnames” argument for “origin”/“dev” and the “value.name” argument for “value”.
In the following example, the GenIns triangle in ChainLadder is converted to a data.frame with non-default names:
GenLong <- as.LongTriangle(GenIns, varnames = c("accident year", "development age"),
value.name = "Incurred Loss")
head(GenLong)## accident year development age Incurred Loss
## 1 1 1 357.8
## 2 2 1 352.1
## 3 3 1 290.5
## 4 4 1 310.6
## 5 5 1 443.2
## 6 6 1 396.1In the following plot, the last accident year and the last development age are shown last, rather than second as they would have been if displayed alphabetically (ggplot’s default for character data):
library(ggplot2)
ggplot(GenLong, aes(x=`development age`, y = `Incurred Loss`,
group = `accident year`, color = `accident year`)) +
geom_line()
glmReserve “exposure” attribute may now have names
Previously, when an “exposure” attribute was assigned to a triangle for use with glmReserve, it was assumed/expected that the user would supply the values in the same order as the accident years. Then, behind the scenes, glmReserve would use an arithmetic formula to match the exposure with the appropriate accident year using the numeric “origin” values after the triangle had been converted to long format.
glmReserve now allows for “exposure” to have “names” that coincide with the rownames of the triangle, which are used to match to origin in long format. Here is an example, newly found in ?glmReserve.
GenIns2 <- GenIns
rownames(GenIns2) <- paste0(2001:2010, "-01-01")
expos <- (7 + 1:10 * 0.4) * 10
names(expos) <- rownames(GenIns2)
attr(GenIns2, "exposure") <- expos
glmReserve(GenIns2)## Latest Dev.To.Date Ultimate IBNR S.E CV
## 2002-01-01 5339 0.98252 5434 95 110.1 1.1589
## 2003-01-01 4909 0.91263 5379 470 216.0 0.4597
## 2004-01-01 4588 0.86599 5298 710 260.9 0.3674
## 2005-01-01 3873 0.79725 4858 985 303.6 0.3082
## 2006-01-01 3692 0.72235 5111 1419 375.0 0.2643
## 2007-01-01 3483 0.61527 5661 2178 495.4 0.2274
## 2008-01-01 2864 0.42221 6784 3920 790.0 0.2015
## 2009-01-01 1363 0.24162 5642 4279 1046.5 0.2446
## 2010-01-01 344 0.06922 4970 4626 1980.1 0.4280
## total 30457 0.61982 49138 18681 2945.7 0.1577glmReserve adds support for negative binomial GLM
The glmReserve function now supports the negative binomial GLM, a more natural way to model over-dispersion in count data. The model is fitted through the glm.nb function from the MASS package.
To fit the negative binomial GLM to the loss triangle, simply set nb = TRUE in calling the glmReserve function:
## Latest Dev.To.Date Ultimate IBNR S.E CV
## 2 5339 0.98288 5432 93 39.61 0.4260
## 3 4909 0.91655 5356 447 133.66 0.2990
## 4 4588 0.88197 5202 614 148.48 0.2418
## 5 3873 0.79594 4866 993 211.05 0.2125
## 6 3692 0.71771 5144 1452 290.03 0.1997
## 7 3483 0.61440 5669 2186 433.05 0.1981
## 8 2864 0.43837 6534 3670 772.92 0.2106
## 9 1363 0.24826 5491 4128 967.76 0.2344
## 10 344 0.07076 4862 4518 1380.14 0.3055
## total 30457 0.62724 48557 18100 2232.92 0.1234New unit tests
New files in the /inst/unittests/ folder can be used for future enhancements
- runit.Triangles.R for Triangles.R
- runit.glmReserve.R for glmReserve.R
Contributors of new contributions to those R files are encouraged to utilize those runit scripts for testing, and, of course, add other runit scripts as warrantted.
Clarified warnings issued by MackChainLadder
By default, R’s lm method generates a warning when it detects an “essentially perfect fit”. This can happen when one column of a triangle is identical to the previous column; i.e., when all link ratios in a column are the same. In the example below, the second column is a fixed constant, 1.05, times the first column. ChainLadder previously issued the lm warning below.
x <- matrix(byrow = TRUE, nrow = 4, ncol = 4,
dimnames = list(origin = LETTERS[1:4], dev = 1:4),
data = c(
100, 105, 106, 106.5,
200, 210, 211, NA,
300, 315, NA, NA,
400, NA, NA, NA)
)
mcl <- MackChainLadder(x, est.sigma = "Mack")
Warning messages:
1: In summary.lm(x) : essentially perfect fit: summary may be unreliable
2: In summary.lm(x) : essentially perfect fit: summary may be unreliable
3: In summary.lm(x) : essentially perfect fit: summary may be unreliablewhich may have raised a concern with the user when none was warranted.
Now ChainLadder issues an “informational warning”: