# 🎓 CS1 Style Guide: University Stats $\rightarrow$ IFoA Actuarial
**Target:** Transitioning from theoretical statistics to actuarial application.

## 🔍 The Fundamental Shift
| Feature | University Statistics | IFoA CS1 (Actuarial) |
| :--- | :--- | :--- |
| **Goal** | Prove the theorem / Find the value | Apply the tool / Interpret the impact |
| **Focus** | Mathematical elegance & rigor | Practical utility & business meaning |
| **Question** | "Prove that the MLE of $\theta$ is..." | "Calculate the MLE and explain what it means for the premium..." |
| **R-Role** | Tool for calculation/plotting | Tool for evidence $\rightarrow$ Interpretation of output |
| **Context** | Generic datasets (Iris, Mtcars) | Insurance data (Claims, Exposure, Policyholders) |

## ⚠️ Common Pitfalls for "Strong Stats" Students
1. **Over-proving:** Spending too much time on a derivation that is "assumed" in the exam. In CS1, if the formula is in the formula sheet, **use it and move on**.
2. **The "Number-Only" Trap:** Providing a correct numerical answer but failing to provide the **interpretation**. 
   - *Wrong:* "The p-value is 0.03."
   - *Right:* "The p-value is 0.03, which is below the 5% significance level; therefore, we reject the null hypothesis and conclude that the new pricing model significantly reduces claim variance."
3. **Ignoring the "Actuarial" Context:** Treating a GLM as just a math problem instead of a tool for "Insurance Pricing" or "Reserving".

## 🛠️ Practical Tips for Study
- **Read the Marking Scheme:** IFoA marks are often split: 1 mark for the formula, 1 mark for the calculation, 1 mark for the **conclusion**.
- **Think "Underwriter":** Whenever you get a result, ask: *"If I were the person signing the check, why would I care about this number?"*
- **R-Output Fluency:** Practice reading `summary(glm(...))` outputs. Don't just look at the coefficients; look at the **Deviance** and **AIC** to justify model choice.