Hypothesis Testing for Regression Coefficients
- LevelCFA Level ISee similar
- TopicQuantitative MethodsSee similar
- SubtopicREGRESSION
- DifficultyHardSeveral steps or a common exam trapSee similar
- Published
FIP-CFA-L1-QM-001
An analyst estimates a simple linear regression to test if a stock's beta is significantly different from 1.0. Based on 32 monthly observations, the estimated slope coefficient is 1.50 and the standard error of the slope is 0.25. At a 5% level of significance, which of the following is most likely correct? (Assume the critical t-value is 2.042).
Correct answer: B. The analyst should fail to reject the null hypothesis; the stock's beta is not significantly different from 1.0.
Formula
Why B is correct
Step 1: Identify the specific hypothesized value being tested ().
Step 2: Calculate the test statistic: t = (1.50−1.0)/0.25=2.0.
Step 3: Compare the calculated test statistic to the critical value: 2.0 < 2.042.
Step 4: Because the test statistic is less than the critical value, you fail to reject the null hypothesis.
Why A is incorrect
The calculated test statistic of 2.0 does not exceed the critical value of 2.042, so there is not enough evidence to reject the null hypothesis.
Common exam trap
Defaulting to testing if the slope equals zero (). Candidates often go on autopilot and divide the coefficient by the standard error without reading that the prompt asks to test against a specific value (1.0).
Covers: Introduction to Linear Regression reading
1-on-1 CFA® Level I coaching in Abu Dhabi or online across the UAE, AED 150 / hour
Challenge a friend
Get tomorrow’s question
MAWritten by Muhammad Ahmed RazaLead Instructor · CFA® & FRM®