Which of the following statements about skewness and kurtosis is least accurate? A) Positive values of kurtosis indicate a distribution that has fat tails. B) Kurtosis is measured using deviations raised to the fourth power. C) Values of relative skewness in excess of 0.5 in absolute value indicate large levels of skewness. D) Relative skewness is equal to the absolute skewness divided by the cubed standard deviation. Your answer: A was correct! Positive values of kurtosis do not indicate a distribution that has fat tails. Positive values of excess kurtosis (kurtosis > 3) indicate fat tails. Got this one right but I don’t remember anything about calculating skewness or kurtosis (answers b,c,d)
Positive Kurtosis will mean a more peaked distribution relative to a normal distribution. This will result in more observations appearing closer to the mean. With a more peaked distribution, the tails will be less fat compared to a normal distribution or a distribution with negative kurtosis. A normal distribution has a kurtosis of 3. Any excess Kurtosis of l1l is considered significant.
Greater than 3 results in excess; ie fat tails.
I hate this “least accurate” type of questions… And yes, I agree that the answer is A (mib20 explained why). Milos
That was a good level I question.
God - I always tend to miss these words… ‘excess’!
excess kurtosis = kurtosis - 3. for example if K = 4, excess kurtosis = 1 this is key since it is how buy side shops measure risk of investments. know that excess K = fat tails and fat tails = higher risk since room for extreme events is likelier. They could have used this sh## in the subprime blowup except most I bank models were off on default estimates. more defaults = lower value of MBS/CDO