John S Bogaardt
John S Bogaardt
I get a different answer depending on whether I fit just the work comp LOB vs all LOBs and then slice work comp. These approaches should yield the same answer,...
offending code: ```python import chainladder as cl import pandas as pd data = [['2010-01-01', '2011-06-30', 'premium', 100.0], ['2010-01-01', '2011-12-31', 'incurred', 100.0], ['2010-01-01', '2012-06-30', 'premium', 200.0], ['2010-01-01', '2012-12-31', 'incurred', 100.0], ['2010-01-01',...
Needs additional hyperparameters to provision for future calendar period inflation
Barnett and Zehnwirth refer to the `Development` estimator setup as the Extended Link Ratio Family (ELRF). There are parts of the framework that are missing from chainladder. Specifically, the ability...
The `BootstrapODPSample` is limited to sampling residuals from the overdispersed poisson GLM and should be generalized to any GLM form as in [Shapland (3.4)](https://www.casact.org/pubs/monographs/papers/04-shapland.pdf). As the name `BootstrapODPSample` is inappropriate...
Many assumptions/hypterparameters of Estimators take on a vector-like feel along an axis of a Triangle. However, there is a great deal of inconsistency in implementation across estimators with at least...
Need to create cross-validation functionality that holds out valuation dates similar to `sklearn.model_selection.TimeSeriesSplit`.
Prototype implementation of [Clark LDF Loglogistic curve fit](https://www.casact.org/pubs/forum/03fforum/03ff041.pdf): ```python import chainladder as cl import numpy as np from scipy.optimize import minimize self = cl.load_sample('genins') # Put data in tablular form...
Add method to do Baesian MCMC. See: [CAS Monograph #1](https://www.casact.org/pubs/monographs/index.cfm?fa=meyers-monograph01)
Need to include Shapland's hetero grouping option in ODP Bootstrap simulation.