When exactly am I supposed to reject the null hypothesis on CFA Level I?

Question

AcadiFi · Accepted Answer

The cleanest way to think about rejection is that you are testing whether the sample evidence looks too extreme to be consistent with the null hypothesis.

Use one of these equivalent rules:

- Critical-value method: reject the null if the test statistic falls in the rejection region.
- P-value method: reject the null if the p-value is less than the significance level.

Suppose fictional firm **Elm Ridge Advisors** tests whether average monthly excess return differs from `0`. If the test statistic is `2.18` in a two-tailed test at the `5%` level, and the critical cutoff is about `1.96`, the result is extreme enough, so you reject the null.

The key is not to memorize random phrases. It is to compare evidence against a threshold. If the evidence clears the threshold, reject. If it does not, fail to reject.

```mermaid
flowchart LR
    A["Compute test statistic"] --> B{"More extreme than cutoff?"}
    B -->|Yes| C["Reject H0"]
    B -->|No| D["Fail to reject H0"]
    A --> E{"p-value < alpha?"}
    E -->|Yes| C
    E -->|No| D
```

On exam day, write the conclusion in evidence language: "There is sufficient evidence to reject the null hypothesis." That keeps you away from the common wording trap of saying the null is "proven false."

When exactly am I supposed to reject the null hypothesis on CFA Level I?

Master Level I with our CFA Course

Related Questions

Related Articles

Practice Questions