Detrend factor 5B adjusts for both pure premium trend and exposure trend. What is the difference between these trends?

Thank you!

Is there a historical problem where it shows how to apply rule 8?

Thank you!

If there is a deductible and no limit, then the excess trend will be greater or equal to ground up trend. However, if there is a limit, it is not certain. If tau_s = 8% and ground up inflation = 10%, and the exam asked why is tau_s lower than ground up inflation, how would I answer this?

Thank you!

If we were given the Partial Residual graph shown in the source paper, figure 8. And we were asked to select all that applies to make the partial residuals graph appropriate on the exam.

a. Add a polynomial second degree to AOI

b. Add a hinge function at age 15

c. Add a categorical variable at age 20, 30, 40, and 50

d. Add a natural cubic spline

I'm under the impression that all these answers would be correct, right? Does it matter how we bin the variable shown in c)?

Thanks!

Thanks!

Wouldn't the loss elimination ratio for retrospective premiums be the excess ratio? And LDD plans would have the LER shown in the solutions?

If we were asked to calculate the experience mod factor and the question had expected development, and say we were asked what would happen to the e-mod if the loss data was evaluated 3 months after the original date (e.g. Oct 1 instead of July 1).

The e-mod would decrease since the loss evaluation date would only affect expected development, and 3 months later would decrease AER, which would decrease the mod = Z*(AER-EER)/EER. Is this correct or am I missing something?

Thank you!

In your toolkit labeled Q1a_2018, you use ult claim count divided by EP to consider premium growth. Would it be incorrect to use ultimate losses instead of premium growth?

Thank you!

Does having a higher Gini Index mean the rating plan is able to differentiate the best and worst risks better than a rating plan that has a smaller Gini index?

Thanks in advance!

GLM Quantiles - I was surprised that each column here was normalized by the overall predicted premium. Thought practice was to create relativities for each column

on GLM_DLC - here we create relativities for each column. However, the % error calcs don't use them. These use the pure prediction - so the differences in the overall predictions by column become part of the differential.

Question is whether to implement. Read the examiners report and the 10 answers there - and here's what I don't get.

The "standard LR" includes the Xmod - correct (so sample 10 is wrong). Then if you think about the magnitude of the xmod that is baked into the standard LR - then you manual loss ratios taht are completely upside down, right. If it takes a .4 mod to get to a standard LR factor of .8, then then manual Loss ratio is a 2. So rather than saying that the plan "undercorrects" for risk differences - which would generally be true with upward sloping std loss ratio - you have to conclude that this plan just fails at identifying riks differences and gives giant credits to terrible performing risks. ...

In the standard approach and in the Present Average Company Rates method, we start with Basic Limits premium.

In the HEPCR method, we apply an ILF to the current rates * historic exposures * ELR to arrive at BLEL. This, to me, says that the provided current rates are not basic limits rates. If we are given current level premium, but could otherwise use the standard or PACR method, should we use ILFs as we do in the HEPCR method?

However, the ILFs vary with the aggregate limit of the *historic* period: 1) if we're adjusting current rates to basic limits, why would it depend on historic limits? 2) we use the basic limits per-occurrence & historic aggregate ILFs; doesn't basic limits denote a $200k aggregate? 3) The resulting CSLC will be compared to actual basic limits losses for the period - if those are adjusted to basic limits (including aggregate limits), why would expected losses be adjusted to a different aggregate limit?

Sorry for the long post, and thanks for your help.

part b) should the calculations in the solution stops at 9.1198 which I thought it's the "intercept term" asked in the question?

part c) will any credit be rewarded for stating "include the interaction term, and then assess p-value and std error ..."

part e) on 'full credibility of data,' would it be reasonable to argue in the direction of GLMM that there may be fewer electric vans, which could result in the predictor being not significant if there is a large number of cars or trucks?"

thank you in advance!

claim type: medical; loss of the claim:180,000

Sate per claim accident limit:175,000

split point for primary and excess loss:5000

I understand the primary loss is min(5000,180,000)*0.3=1500, but I am confused on excess loss calculation with the state per accident limit.

Thanks!

My first attempt at this alternate approach led me to trying to set the Max LR equal to L_G/SP, where L_G can be solved to equal (G/T -B)/c. Then 0.8 = (G/T - B)/c ---> G/T = 1.2304 and equivalently H/T = 0.5794. Both of these 2 numbers pop up in my algebra when solving the equations derived in the CAS solution.

Interestingly, the tax rate we solve for is exactly 1.25/1.2304 = 1.0159. So I feel like I'm on the right track, but I still don't quite see where the value of 1.25 comes from, and why if we can directly estimate G so easily, then why we don't also obtain H then solve for T using 0.651xT = G - H.

Thanks.

If I calculate the area of the triangle - i get 1/2bh = 1/2*(1-.625)^2 = .1406 /2 = .0703. Is this an error or what am i missing.

Should the denominator df here subtract 3 additional df in order to incorporate the new variable with 4 levels, since that will be in the "bigger" model?

Also, in the previous problem (GLM_ModelRefinement5), we said that a 2nd order polynomial added 2 parameters, but here we're saying that a 2nd order polynomial adds 3 degrees of freedom. Maybe this is a subtle distinction between parameters and degrees of freedom that I'm not picking up on. However, the wiki seems to make a direct connection between them.

Thanks in advance!

"Franchise deductible will eliminate more small values nuisance claims than the straight deductible"

can you please explain why this is true?

Am I right in assuming that these are being used interchangeably? Or is there a notable difference in the meaning of these terms.