FRM Part I · FRM Exam Part I · Hypothesis Testing
A normally distributed return series has 31 observations and a sample variance of 0.0050. Which expression gives the 95% confidence interval for the population variance, where chi-square values have 30 degrees of freedom?
The confidence interval for variance runs from (n-1)s^2 divided by the upper 2.5% chi-square point to (n-1)s^2 divided by the lower 2.5% point, using 30 degrees of freedom. The larger critical value gives the lower bound.
- A[30 x 0.0050 / chi2 upper 2.5% point, 30 x 0.0050 / chi2 lower 2.5% point]Correct
- B[30 x 0.0050 / chi2 lower 2.5% point, 30 x 0.0050 / chi2 upper 2.5% point]
- C[31 x 0.0050 / chi2 upper 2.5% point, 31 x 0.0050 / chi2 lower 2.5% point]
- D[0.0050 +/- 1.96 x 0.0050 / sqrt(31)]
Explanation
The interval is (n-1)s^2 divided by the upper critical value for the lower bound, and by the lower critical value for the upper bound. Swapping them inverts the interval, using n is wrong, and the normal-based form is for a mean.
Did you get it right without looking?
One question tells you little. A timed set on Hypothesis Testing shows your real accuracy, how long you take and where you lose marks.
More Hypothesis Testing questions
- A researcher tests 20 independent, uncorrelated trading strategies, each at a 5% significance level, and every null hypothesis (no excess re…
- A risk manager tests whether the mean daily P&L of a desk differs from zero using 400 observations. The sample mean is 0.08 (in $ thousand) …
- A sample of 100 daily P&L observations has a mean of 1.50 (in USD thousands) and a sample standard deviation of 10.0. Using a large-sample n…
- A 95% confidence interval for a portfolio's mean annual excess return is computed as 2.0% to 8.0% from a large sample. A risk manager uses t…
- A multiple regression with 3 explanatory variables and 44 observations gives a coefficient estimate of 1.20 with standard error 0.50. Test H…
- A risk analyst tests whether the mean daily P&L of a trading desk differs from zero. She sets H0: mu = 0 against H1: mu ≠ 0 at a 5% signific…