Business Context
An actuary needs to project future liabilities where the claim amounts are expected to grow due to economic inflation. Instead of changing the base model parameters, they want to apply a dynamic 5% inflation factor to the simulated severity values during the generation process.
Data Preparation
Creation of a basic Gamma distribution severity definition.
Copied!
| 1 | |
| 2 | DATA mycas.sev_def_inf; |
| 3 | LENGTH model $8; |
| 4 | model='Gamma'; |
| 5 | alpha=3; |
| 6 | theta=1200; |
| 7 | dist='GAMMA'; |
| 8 | OUTPUT; |
| 9 | |
| 10 | RUN; |
| 11 |
Étapes de réalisation
1
Execution using the 'adjustedSeverity' parameter to apply a SAS formula (multiplying by 1.05) to the drawn values.
Copied!
| 1 | PROC CAS; |
| 2 | cdm.cdm / |
| 3 | nReplicates=5000, |
| 4 | countDistributions={{name='POISSON', parmValues={{value=10}}}}, |
| 5 | severityDefinitions={name='mycas.sev_def_inf'}, |
| 6 | adjustedSeverity={symbols={'InflatedLoss'}, sasCode='InflatedLoss = Gamma * 1.05;'}, |
| 7 | OUTPUT={outSample={name='inflation_sim', replace=true}}; |
| 8 | RUN; QUIT; |
Expected Result
The action executes the embedded SAS code for every severity draw. The resulting 'inflation_sim' table should contain the 'InflatedLoss' variable, where values are consistently 5% higher than what would be expected from the raw Gamma distribution, validating the custom adjustment logic.