Skip to content

IAI Actuarial Core Principles · Actuarial Statistics · Purpose and function of data analysis

A Bengaluru insurer runs a regression on 5 years of policy data and finds that policyholders who buy an add-on cover have lower claim costs. A manager concludes that selling the add-on will reduce claim costs for any customer. What is the most appropriate actuarial response?

The data is observational, so the negative association may be due to confounding, such as cautious customers choosing the add-on. It does not prove that selling the add-on lowers claim costs for any customer. A negative coefficient or a large sample cannot establish causation.

  1. AThe data is observational, so the association may reflect confounding and does not prove a causal effectCorrect
  2. BThe conclusion is valid because the regression coefficient is negative
  3. CThe conclusion is valid if the sample size exceeds 1,000 policies
  4. DThe conclusion is valid because regression always estimates causal effects
  5. The conclusion is invalid because regression cannot show any association

Explanation

Observational data show association only. Customers who choose the add-on may differ, for example being more cautious, which confounds the relationship. A negative coefficient or a large sample does not establish causation, but regression does show association.

Did you get it right without looking?

One question tells you little. A timed set on Purpose and function of data analysis shows your real accuracy, how long you take and where you lose marks.

Practise Purpose and function of data analysisFree diagnostic mock

More Purpose and function of data analysis questions