This Exam P sample reference tests Continuous Distributions. The unknown normalizing constant does not affect the maximizer. Differentiating the density kernel gives a sign change at x=cube root of 2, or 1.25992, which is choice C.
These notes identify the calculation error associated with each wrong letter when that error is reproducible.
AAt the lower endpoint the density kernel tends to zero, so 0.00 cannot maximize it.
BThe value 0.79 is approximately the cube root of 1/2. It comes from inverting the stationary equation x³=2.
DAt 4.42 the derivative is negative and the kernel is about 0.22365, far below its value 0.52913 at the critical point.
EChoosing the upper endpoint amounts to maximizing the numerator alone. The denominator grows cubically, and the kernel at 5 is only 25/126.
Original practice · fully worked
Original variant: calibrate a density exponent from its mode
For x>0, a workload index has density c xᵃ exp(-x/2), where c is a normalizing constant and a is positive. Calibration records show that the density has its unique mode at x=6. Determine the exponent a.
A 1
B 2
C 3
D 4
E 6
Variant answer in brief
The log-density derivative is a/x-1/2, so the mode is located at x=2a. Requiring that location to be 6 gives a=3, choice C.
Setup
Setup
Work with the logarithm of the density kernel; the normalizing constant does not depend on x.
ℓ(x)=alnx−2x+constant
Model
Model
Differentiate and locate the stationary point in terms of the unknown exponent.
ℓ′(x)=xa−21
ℓ′(x)=0⟺x=2a
Compute
Compute
Match the modeled stationary point to the observed modal location.
The 3108-page Probability Proof Manual reorganizes 718 verified Exam P solutions by syllabus skill and adds formula proofs, error patterns, and original worked practice.