Exam P · exam technique
Exam P: Common Traps Flashcards
A rapid-review cram deck of the classic mistakes candidates make on SOA/CAS Exam P — each card sets up the tempting trap, then states the correct rule and formula plainly.
35 cards10 topicsFree · fact-checked · LaTeX math
Tap card or press Space to flip
Answer
Every deck is built into the Willys app
All of these decks, including the full practice problem banks, come built into Willys AI Flashcards & Quizzes for iPhone, iPad & Mac, with FSRS + SM-2 spaced repetition, streaks, and exam-date cram mode. 14-day free trial, then $14.99. To load a deck in the app: Settings → Library → Browse, then pick your exam and deck.
More Exam P decks:
Conditional Probability & Bayes Conditional Probability & Bayes Practice Continuous Distributions Continuous Distributions Practice Covariance, Sums & CLT Covariance, Sums & CLT Practice Discrete Distributions Discrete Distributions Practice
Browse all 35 cards as a list
- distributionsA problem says 'a die is rolled until the first six.' You're handed $E[X]=q/p$. Trap?**Trap:** two geometric conventions. 'Number of *trials* until the first success' has support $\{1,2,\dots\}$ and mean $E[X]=\dfrac{1}{p}$. 'Number of *failures* before the first success' has support $\{0,1,\dots\}$ and mean $\dfrac{q}{p}$. Number-of-rolls means $E[X]=\dfrac{1}{p}=6$, not $\dfrac{5/6}{1/6}=5$. Read which one is counted.
- distributionsBoth geometric forms have the *same* variance — so does the convention even matter for $\mathrm{Var}$?**Trap:** since $Y=X-1$ is just a shift, $\mathrm{Var}(Y)=\mathrm{Var}(X)=\dfrac{q}{p^{2}}$ — identical for both conventions. The convention only changes the *mean* (by exactly $1$) and the *pmf support*. So don't second-guess the variance, but always re-check the mean and which $\Pr(X=k)$ the problem wants.
- independenceYou compute $\mathrm{Cov}(X,Y)=0$. Can you now treat $X$ and $Y$ as independent?**Trap:** No. Independence $\Rightarrow$ uncorrelated, but **not** the converse. Zero covariance only rules out a *linear* relationship; $X$ and $Y$ can be strongly dependent nonlinearly (e.g. $Y=X^{2}$ with $X$ symmetric about $0$ gives $\mathrm{Cov}=0$). The lone exception: for a **bivariate normal**, $\rho=0$ *does* imply independence.
- variance-rulesAn exam answer for $\mathrm{Var}(X+Y)$ reads $\mathrm{Var}(X)+\mathrm{Var}(Y)$. When is that wrong?**Trap:** dropping the covariance term. In general $\mathrm{Var}(X+Y)=\mathrm{Var}(X)+\mathrm{Var}(Y)+2\,\mathrm{Cov}(X,Y)$. The cross term vanishes **only** if $X$ and $Y$ are uncorrelated (e.g. independent). If the problem gives a covariance or correlation, it almost certainly wants the $2\,\mathrm{Cov}(X,Y)$ term.
- variance-rules$X-Y$: do you subtract the variances?**Trap:** variances **add**, the covariance sign flips: $\mathrm{Var}(X-Y)=\mathrm{Var}(X)+\mathrm{Var}(Y)-2\,\mathrm{Cov}(X,Y)$. For *independent* $X,Y$ this is $\mathrm{Var}(X)+\mathrm{Var}(Y)$ — never $\mathrm{Var}(X)-\mathrm{Var}(Y)$. The diff of two independent normals $N(\mu_1,\sigma_1^{2})-N(\mu_2,\sigma_2^{2})$ is $N(\mu_1-\mu_2,\ \sigma_1^{2}+\sigma_2^{2})$.
- variance-rulesYou scale a loss by $3$: is $\mathrm{Var}(3X)=3\,\mathrm{Var}(X)$?**Trap:** No — the constant comes out **squared**: $\mathrm{Var}(aX)=a^{2}\,\mathrm{Var}(X)$, so $\mathrm{Var}(3X)=9\,\mathrm{Var}(X)$. Additive shifts drop out entirely: $\mathrm{Var}(aX+b)=a^{2}\,\mathrm{Var}(X)$. For standard deviation, $\mathrm{SD}(aX+b)=|a|\,\sigma$.
- variance-rulesFor the sample mean $\bar X$ of $n$ iid draws, you write $\mathrm{Var}(\bar X)=\sigma^{2}$. Spot the error.**Trap:** forgetting the $1/n$. With $\bar X=\dfrac{1}{n}\sum_{i=1}^{n}X_i$, the $1/n$ comes out squared: $\mathrm{Var}(\bar X)=\dfrac{1}{n^{2}}\cdot n\sigma^{2}=\dfrac{\sigma^{2}}{n}$. The standard error is $\dfrac{\sigma}{\sqrt{n}}$, not $\sigma$. (The *sum* has variance $n\sigma^{2}$; don't confuse sum with mean.)
- clt-normalApproximating a discrete count with the normal: which way does the $\pm 0.5$ go for $\Pr(X\leq k)$ vs $\Pr(X\geq k)$?**Trap:** wrong continuity-correction direction. To *include* the integer $k$, widen the interval toward it: $\Pr(X\leq k)\approx\Pr(Z\leq\frac{k+0.5-\mu}{\sigma})$ and $\Pr(X\geq k)\approx\Pr(Z\geq\frac{k-0.5-\mu}{\sigma})$. For a strict $\Pr(X<k)$ use $k-0.5$; for $\Pr(X>k)$ use $k+0.5$. Only apply this for **integer-valued** variables.
- distributionsA 'given it has already lasted $s$' lifetime problem tempts you to use memorylessness. Always valid?**Trap:** memorylessness holds **only** for the exponential (continuous) and the geometric (discrete). For those, $\Pr(X>s+t\mid X>s)=\Pr(X>t)$. For a Weibull, gamma, Pareto, uniform, etc., you must compute the conditional honestly: $\Pr(X>s+t\mid X>s)=\dfrac{S(s+t)}{S(s)}$.
- loss-modelsUnder deductible $d$, a problem asks for the average payment 'on claims that are paid.' Is that $E[(X-d)_{+}]$?**Trap:** confusing per-loss with per-payment. **Per loss** averages over *all* losses (including the $0$ payments below $d$): $E[(X-d)_{+}]$. **Per payment** conditions on $X>d$: $E[X-d\mid X>d]=\dfrac{E[(X-d)_{+}]}{S(d)}$. 'Paid claims' / 'per payment' is the *larger* conditional figure — divide by $S(d)$.
- expectationGiven $E[X]$, is $E[g(X)]=g(E[X])$ a safe shortcut (e.g. $E[X^{2}]=(E[X])^{2}$)?**Trap:** Jensen's inequality. In general $E[g(X)]\neq g(E[X])$. For a *convex* $g$, $E[g(X)]\geq g(E[X])$ (e.g. $E[X^{2}]\geq(E[X])^{2}$, the gap being $\mathrm{Var}(X)\geq 0$); for *concave* $g$, the inequality reverses. Equality holds only if $g$ is linear or $X$ is degenerate.
- probability-rulesA test has $99\%$ sensitivity and the disease prevalence is $0.1\%$. A positive test — is the patient probably sick?**Trap:** base-rate neglect. A high true-positive rate does **not** mean a high $\Pr(\text{disease}\mid +)$ when the prior is tiny. Use Bayes: $\Pr(D\mid +)=\dfrac{\Pr(+\mid D)\,\Pr(D)}{\Pr(+\mid D)\Pr(D)+\Pr(+\mid D^{c})\Pr(D^{c})}$. With a rare disease the false positives swamp the true ones, so $\Pr(D\mid +)$ can stay small.
- probability-rules$\Pr(A\cup B\cup C)$ — you add the three single probabilities and the three pairwise ones. Done?**Trap:** double-counting in inclusion–exclusion. You must *subtract* the pairwise overlaps and *add back* the triple: $\Pr(A\cup B\cup C)=\sum\Pr(A)-\sum\Pr(A\cap B)+\Pr(A\cap B\cap C)$. Forgetting to subtract overlaps (or omitting the $+\Pr(A\cap B\cap C)$) is the classic Venn-diagram error.
- densitiesA pdf is given as $f(x)=c\,x^{2}$ on $[0,2]$. You start integrating with $c=1$. First step?**Trap:** assuming the density is already normalized. A pdf must integrate to $1$: solve $\int_{0}^{2}c\,x^{2}\,dx=1\Rightarrow c\cdot\frac{8}{3}=1\Rightarrow c=\frac{3}{8}$. **Always find the normalizing constant first** (and confirm $f\geq 0$ on the support) before computing any probability or moment.
- transformations$X\sim U(0,1)$, $Y=X^{2}$. You write $f_Y(y)=f_X(\sqrt{y})$. What's missing?**Trap:** forgetting the Jacobian. For a monotone $Y=g(X)$, $f_Y(y)=f_X\!\big(g^{-1}(y)\big)\left|\dfrac{dx}{dy}\right|$ — the **absolute value** of the derivative of the inverse. Here $x=\sqrt{y}$, $\frac{dx}{dy}=\frac{1}{2\sqrt{y}}$, so $f_Y(y)=1\cdot\frac{1}{2\sqrt{y}}$ on $(0,1)$. Omitting $\left|\frac{dx}{dy}\right|$ is the top transformation error.
- transformations$X_1,\dots,X_n$ are independent $\mathrm{Exp}(\lambda)$. The minimum — is its rate $\lambda/n$?**Trap:** the minimum has the **summed** rate, not the averaged one. $\Pr(\min>x)=\prod e^{-\lambda x}=e^{-n\lambda x}$, so $\min\sim\mathrm{Exp}(n\lambda)$ with mean $\dfrac{1}{n\lambda}$. The **maximum** is *not* exponential at all: its cdf is $F(x)^{n}=(1-e^{-\lambda x})^{n}$, and $E[\max]=\dfrac{1}{\lambda}\sum_{k=1}^{n}\dfrac{1}{k}$.
- estimationAn estimator question: is $\frac{1}{n}\sum (X_i-\bar X)^2$ an unbiased estimator of $\sigma^2$?**Trap:** dividing by $n$ gives the **biased** (MLE) variance estimator. The **unbiased** sample variance divides by $n-1$: $S^{2}=\dfrac{1}{n-1}\sum_{i=1}^{n}(X_i-\bar X)^{2}$, with $E[S^{2}]=\sigma^{2}$. Dividing by $n$ understates $\sigma^{2}$ because $\bar X$ is fitted from the same data (one lost degree of freedom).
- distributions$E[X]=\mu$ for the geometric — but which $\mu$? You see $E[X]=\frac{1-p}{p}$ in a table and $\frac{1}{p}$ in your notes.**Trap:** the same 'geometric' label hides two means. *Trials* form: $E[X]=\dfrac{1}{p}$, support $\{1,2,\dots\}$. *Failures* form: $E[X]=\dfrac{1-p}{p}=\dfrac{q}{p}$, support $\{0,1,\dots\}$. Tables and software differ — anchor to the *support* the problem describes, then pick the matching mean and pmf $q^{x-1}p$ vs $q^{x}p$.
- independence$\mathrm{Cov}(X,Y)=0$ for a bivariate normal pair — independent or not?**Trap (the exception to the exception):** for the **bivariate normal**, $\rho=0\Rightarrow$ independence — this is the one named family where uncorrelated *does* mean independent. But beware: two *marginally* normal variables that aren't *jointly* normal can be uncorrelated yet dependent. The implication needs the full joint normality, not just normal margins.
- variance-rulesLinear combination $aX+bY$ of dependent variables: is $\mathrm{Var}(aX+bY)=a^{2}\mathrm{Var}(X)+b^{2}\mathrm{Var}(Y)$?**Trap:** missing the cross term *and* its $ab$ factor. The full rule is $\mathrm{Var}(aX+bY)=a^{2}\mathrm{Var}(X)+b^{2}\mathrm{Var}(Y)+2ab\,\mathrm{Cov}(X,Y)$. Note the covariance term carries $2ab$ — and if $b$ is negative (a difference), that term is *subtracted*. Drop it only when $\mathrm{Cov}(X,Y)=0$ — independence is sufficient but not necessary, since uncorrelated dependent variables also have zero covariance.
- clt-normalA binomial $\Pr(X\leq 45)$ with $n=100$, $p=0.5$ via the normal. You plug in $45$ directly. Fix it.**Trap:** no continuity correction on a discrete count. Here $\mu=50$, $\sigma=\sqrt{100(0.5)(0.5)}=5$. To include $45$, use $45+0.5$: $\Pr(X\leq 45)\approx\Pr\!\big(Z\leq\frac{45.5-50}{5}\big)=\Pr(Z\leq-0.9)\approx 0.1841$. Using $45$ gives the wrong tail.
- distributionsMemoryless 'expected additional wait': a bus is exponential with mean $10$, you've waited $7$. Expected remaining wait?**Trap:** subtracting elapsed time. For an **exponential**, by memorylessness the expected *remaining* wait is still the full mean $E[X-7\mid X>7]=10$, **not** $10-7=3$. Geometric behaves the same in discrete time. For any *non-memoryless* lifetime this shortcut is invalid.
- loss-modelsPer-payment expected cost: you compute $E[(X-d)_{+}]$ and report it as 'average payment per claim paid.' Right?**Trap:** you skipped dividing by $S(d)$. Per-loss $E[(X-d)_{+}]$ already averages in the zeros from losses below $d$. To get **per payment**, condition on a payment: $\dfrac{E[(X-d)_{+}]}{S(d)}$. For exponential losses this conditional mean is just $\theta$ (memorylessness), regardless of $d$ — a fast sanity check.
- expectationYou need $E[1/X]$ and reach for $1/E[X]$. Safe?**Trap:** Jensen again — $g(x)=1/x$ is convex on $(0,\infty)$, so $E\!\big[\tfrac{1}{X}\big]\geq\dfrac{1}{E[X]}$, with strict inequality unless $X$ is constant. You must integrate $\int \tfrac{1}{x}f(x)\,dx$. Same warning for $E[\sqrt{X}]\neq\sqrt{E[X]}$ (concave $\Rightarrow E[\sqrt X]\leq\sqrt{E[X]}$).
- probability-rulesBayes: $\Pr(B\mid A)$ — can you just reuse $\Pr(A\mid B)$ as if it were the same number?**Trap:** confusing the conditioning direction (the 'prosecutor's fallacy'). $\Pr(A\mid B)\neq\Pr(B\mid A)$ in general; they're linked by $\Pr(B\mid A)=\dfrac{\Pr(A\mid B)\,\Pr(B)}{\Pr(A)}$. You must weight by the prior $\Pr(B)$ and normalize by $\Pr(A)$ (often via total probability). Swapping them ignores the base rate.
- probability-rules$60\%$ speak French, $50\%$ Spanish. What's $\Pr(\text{at least one})$ — is it $0.6+0.5=1.1$?**Trap:** a probability above $1$ flags double counting. $\Pr(F\cup S)=\Pr(F)+\Pr(S)-\Pr(F\cap S)$ — you must subtract the bilingual overlap. The fact that $0.6+0.5>1$ *forces* $\Pr(F\cap S)\geq 0.1$. Use the Bonferroni-style sanity check: $\Pr(\text{union})\leq 1$ always.
- densitiesA density $f(x)=k(1-x)$ on $[0,1]$, and you're asked for $\Pr(X>0.5)$. You integrate with $k=1$. Problem?**Trap:** any probability you compute is wrong until $f$ is normalized. Solve $\int_{0}^{1}k(1-x)\,dx=k\cdot\tfrac{1}{2}=1\Rightarrow k=2$. Then $\Pr(X>0.5)=\int_{0.5}^{1}2(1-x)\,dx=0.25$. Skipping the constant scales every answer by the wrong factor (here, by $2$).
- transformationsBivariate transform $(U,V)=g(X,Y)$: you multiply by the Jacobian of $g$ itself. Correct factor?**Trap:** wrong Jacobian *and* sign. You need the absolute value of the determinant of the **inverse** map $(x,y)$ in terms of $(u,v)$: $f_{U,V}(u,v)=f_{X,Y}(x,y)\,|J|$, where $J=\dfrac{\partial x}{\partial u}\dfrac{\partial y}{\partial v}-\dfrac{\partial x}{\partial v}\dfrac{\partial y}{\partial u}$. Take $|J|$, and re-express the support in the new variables.
- transformationsTwo independent $\mathrm{Exp}(\lambda)$ machines; the system fails when **both** fail. Is the time-to-fail exponential?**Trap:** 'both fail' is the **maximum**, which is *not* exponential and *not* memoryless. Its cdf is $(1-e^{-\lambda t})^{2}$ and $E[\max]=\dfrac{1}{\lambda}\big(1+\tfrac{1}{2}\big)=\dfrac{3}{2\lambda}$. Only 'system fails when the **first** fails' (a series / minimum) gives an exponential, $\mathrm{Exp}(2\lambda)$.
- estimationYou report the population variance formula $\frac{1}{n}\sum(X_i-\bar X)^2$ as the standard 'sample variance.' Bias?**Trap:** that divisor understates $\sigma^{2}$: $E\!\big[\tfrac{1}{n}\sum(X_i-\bar X)^{2}\big]=\dfrac{n-1}{n}\sigma^{2}<\sigma^{2}$. Multiply by $\dfrac{n}{n-1}$ (Bessel's correction) to debias, giving $S^{2}=\dfrac{1}{n-1}\sum(X_i-\bar X)^{2}$. Use $n$ only when the true mean $\mu$ is *known* (not estimated by $\bar X$).
- variance-rulesStandardizing a sum $S_n=\sum X_i$ for the CLT: do you divide by $\sigma$ or $\sigma\sqrt{n}$?**Trap:** using the wrong scale. The **sum** has SD $\sigma\sqrt{n}$, so $\dfrac{S_n-n\mu}{\sigma\sqrt{n}}\approx N(0,1)$. The **mean** has SD $\sigma/\sqrt{n}$, so $\dfrac{\bar X-\mu}{\sigma/\sqrt{n}}\approx N(0,1)$. Mixing up sum-scale and mean-scale (e.g. dividing the sum by $\sigma/\sqrt n$) is a frequent CLT slip.
- densities$\Pr(X=k)$ for a continuous random variable — you compute a positive number. Possible?**Trap:** for any *continuous* variable, $\Pr(X=k)=0$ — point masses contribute nothing. Hence $\Pr(X\leq k)=\Pr(X<k)$ and $\leq$ vs $<$ doesn't matter. This *fails* for **mixed** distributions (e.g. a censored loss $X\wedge u$ has an atom $\Pr(X\geq u)$ at $u$), where the boundary mass is real.
- variance-rules$\mathrm{Var}(X+Y+Z)$ for three *pairwise dependent* variables — just sum the three variances?**Trap:** you owe **three** covariance terms, one per pair: $\mathrm{Var}(X+Y+Z)=\mathrm{Var}(X)+\mathrm{Var}(Y)+\mathrm{Var}(Z)+2[\mathrm{Cov}(X,Y)+\mathrm{Cov}(X,Z)+\mathrm{Cov}(Y,Z)]$. In general $\mathrm{Var}\!\big(\sum_i X_i\big)=\sum_i\mathrm{Var}(X_i)+2\sum_{i<j}\mathrm{Cov}(X_i,X_j)$.
- distributionsA 'memoryless' wording trap: a *used* part's lifetime is uniform on $[0,10]$, $5$ years elapsed. Expected remaining life $=5$?**Trap:** the uniform is **not** memoryless. Given survival to $5$, the remaining life is uniform on $[0,5]$, so the expected residual is $\dfrac{5}{2}=2.5$, not $5$. Only exponential (and discrete geometric) lifetimes keep a constant expected residual; everything else needs $E[X-s\mid X>s]$ computed directly.
- transformationsOrder-statistic median of $n=4$ values — you reach for the average of the two middle order statistics' *expectations* as the median's distribution. Trap?**Trap:** the $k$-th order statistic has its **own** density, not a shortcut from the mean. For iid continuous $X_i$ with cdf $F$, pdf $f$: $f_{X_{(k)}}(x)=\dfrac{n!}{(k-1)!(n-k)!}F(x)^{k-1}[1-F(x)]^{n-k}f(x)$. The max is the $k=n$ case, the min the $k=1$ case — don't conflate $E[\text{stat}]$ with the stat itself.