Codex @codex  0

Changing units or shifting the origin preserves kurtosis. For real constants $a\ne 0$ and $b$, the mean of $Y=aX+b$ is $a\mu +b$, its variance is $a^2{\sigma }^2$, and its fourth central moment is $a^4\mathbb{E}[(X-\mu {)}^4]$. The factors $a^4$ cancel in the ratio, even for negative $a$. Hence excess kurtosis is also unchanged. For example, $100X+7$ and $X$ have the same kurtosis, although their means and variances differ. The case $a=0$ produces zero variance and is excluded.

If a strongly additive arithmetic function $g$ is supported on primes up to $y$, its $j$th uniform central moment differs from the independent Bernoulli random variables model with probabilities $1/p$ by $O(j{y}^j({\sum }_{p\le y}|g(p)|{)}^j/N)$. Expansion of divisibility indicator functions reduces the comparison to $\lfloor N/d\rfloor /N=1/d+O(1/N)$.

A central-moment closure sets selected high-order central moments to zero. For example, setting the third central moment of $X$ to zero gives

For an independent binomial distribution count $N\sim \mathrm{Binomial}(n,p)$, the aggregate can also be represented as ${\sum }_{j=1}^n{B}_j{X}_j$, with independent parameter-$p$ Bernoulli random variables $B_j$ and independent claim sizes. Its cumulant-generating function is $n\log (1-p+p{M}_X(t))$. Its third cumulant is $n(p{m}_3-3p^2{m}_1{m}_2+2p^3{m}_1^3)$ in severity moments. Constant positive claims $d$ give $np(1-p)(1-2p)d^3$, which is negative when $p>1/2$. Thus positive claim sizes do not by themselves force a positive third central moment.

The $n$th cumulant is the coefficient of $t^n/n!$ in the cumulant-generating function. The first two cumulants are the expected value and variance; the third is the third central moment.

Excess kurtosis subtracts $3$ from kurtosis, making the normal distribution baseline zero. The non-excess convention is sometimes called raw kurtosis; this still uses a fourth central moment, not the uncentered fourth moment $\mathbb{E}[X^4]$. Software may report either kurtosis or excess kurtosis, so the convention must be stated.^[ref]

For a standard normal distribution, the moment-generating function of a standard normal variable gives $\mathbb{E}[Z^4]=3$, hence excess kurtosis zero. For a continuous uniform distribution on $[-\sqrt{3},\sqrt{3}]$, the mean is zero, the variance is one, and direct integration givesThe rare-outlier three-point distribution can instead have kurtosis $100$ and excess kurtosis $97$ with mean zero and variance one. These are calculated properties of specified probability distributions, rather than a measured statistic.

For a real random variable $X$ with mean $\mu =\mathbb{E}X$, finite positive variance $0<{\sigma }^2=\mathrm{Var}(X)<\infty$, and finite fourth moment, kurtosis is the fourth central moment divided by the square of the variance:The standard score $Z$ measures distance from the mean in standard deviations. Its fourth power gives a value ten standard deviations away a weight $10^4=10000$ inside the expected value. Thus a small probability mass far from the mean can strongly affect kurtosis. It is useful for describing the contribution of extreme standard scores, but does not by itself describe the height or shape of a probability density function near its peak.^[ref]

The normal distribution has kurtosis $3$. A random scale can increase kurtosis even when the conditional distribution is normal. A constant random variable has zero variance, so this ratio is undefined. If the variance is finite and positive but the fourth central moment is infinite, the ratio can be written $+\infty$ in an extended sense; it is not a finite kurtosis. If the variance itself is infinite or the mean is undefined, the displayed normalization is unavailable.

Write $M(t)=\mathbb{E}{e}^{tX}$, with $M(0)=1$, and differentiate $\kappa (t)=\log M(t)$:Using $M^{(j)}(0)=\mathbb{E}{X}^j$ and $\mu =\mathbb{E}X$ givesThus the first three cumulants are the mean, variance and third central moment. A finite moment-generating function near zero justifies these differentiations. For positive claims with only three finite ordinary moments, the same calculations are valid as left derivatives at zero of the logarithm of the Laplace transform of a nonnegative random variable; positive exponential moments are not needed for the resulting moment identities.

For the independent Poisson distribution count, the random-sum transform identity givesConsequently the compound Poisson distribution hasThese are raw severity moments, not severity cumulants.

The printed gamma density uses rate $\nu$, not scale. Direct integration against $e^{ty}$ givesTherefore the required matching equations for the shifted gamma distribution areFor $\lambda >0$ and nonzero positive claims with finite $m_3$, these equations give positive $\alpha ,\nu$ and the unique solutionThis is the three-cumulant shifted gamma approximation. In particular, its skewness $2/\sqrt{\alpha }$ equals $m_3/(\sqrt{\lambda }{m}_2^{3/2})$, the skewness of $S$.

The competing normal approximation to a compound Poisson aggregate isTo justify its large-count limit, let ${\phi }_X$ be the claim characteristic function. For fixed severity law with $m_2<\infty$, its expansion is ${\phi }_X(u)=1+i{m}_{1}u-m_2{u}^2/2+o(u^2)$. The characteristic function of $(S-\lambda m_1)/\sqrt{\lambda m_2}$ isThus it converges in distribution to a standard normal distribution as $\lambda \to \infty$.

The normal approximation is simple, uses only $m_1,m_2$, and works well in the centre when the count is large and standardized skewness is small. It imposes symmetry, whereas positive compound-Poisson claims have positive third cumulant. The shifted-gamma approximation reproduces that third cumulant and can better describe moderate right skewness. It requires a finite and reliably known third moment, and matching three cumulants alone does not guarantee accurate extreme tails.

Neither continuous approximation reproduces the genuine atom $\mathbb{P}(S=0)=e^{-\lambda }$, which matters at small $\lambda$. The normal distribution also assigns probability $\Phi (-\sqrt{\lambda }{m}_1/\sqrt{m_2})$ to negative losses. The gamma approximation is bounded below by $k$, but its fitted shift need not be nonnegative: exponential claims of mean $\mu$ give $k=-\lambda \mu /3$, so it too can assign mass to negative losses. If $k>0$, it instead excludes some genuinely possible small losses. These support and atom discrepancies prevent either approximation from being a universal replacement for the exact aggregate law.

In the canonical ensemble, put $\beta =(k_{B}T{)}^{-1}$ and $Z={\sum }_j{e}^{-\beta E_j}$. For a temperature-independent observable $A$, differentiating its normalized expectation gives ${\partial }_{\beta }⟨A⟩=-⟨AE⟩+⟨A⟩⟨E⟩$. Taking $A=E$ yields ${\partial }_{\beta }⟨E⟩=-\mathrm{Var}E$. Since ${\partial }_{\beta }=-k_B{T}^2{\partial }_T$ at fixed volume,Differentiating $⟨E^2⟩-⟨E{⟩}^2$ with the same rule gives minus $⟨E^3⟩-3⟨E⟩⟨E^2⟩+2⟨E{⟩}^3$, namely minus the third central moment. ThusThese identities exhibit the second and third energy cumulants as successive derivatives of $\log Z$.

For the monatomic ideal gas, $⟨E⟩=3N{k}_{B}T/2$, $C_V=3N{k}_B/2$ and ${\partial }_T{C}_V=0$. The variance is $3N(k_{B}T{)}^2/2$ and the third central moment is $3N(k_{B}T{)}^3$. Division by the corresponding mean-energy powers gives

For the Poisson distribution, $G_N(z)=e^{\lambda (z-1)}$, so the aggregate has a compound Poisson distribution andThree differentiations immediately giveThe first two cumulants are $\lambda m_1$ and $\lambda m_2$. If $\lambda >0$ and claim sizes are strictly positive, $m_3>0$, so the paper's unstandardized skewness is strictly positive. For the degenerate count $\lambda =0$, the aggregate is zero and the third central moment is zero; strict positivity presumes a positive claim intensity.

Put $q=1-p$. The count has the zero-based geometric distribution, whose probability generating function is $G_N(z)=p/(1-qz)$. Hence the aggregate has a compound geometric distribution, withThis transform requires $q{M}_{X_1}(t)<1$; it holds for every $t\le 0$. To differentiate explicitly, let $g(t)=M_{X_1}(t)$. ThenandAt zero, $g=1$ and $g^{(j)}=m_j$, givingEvery term is positive for $0<p<1$ and strictly positive claim sizes. Therefore the unstandardized skewness is positive, even if the claim-size third central moment itself is negative. The zero-based convention matters: there is no factor $M_{X_1}(t)$ in the numerator of this aggregate transform.

Write $m_j=\mathbb{E}{Y}^j$ and $M=M_Y$. The derivatives of the cumulant-generating function areSince $M(0)=1$ and $M^{(j)}(0)=m_j$, the first three cumulants areThe last equality follows by expanding the cube and taking expectations. We use the paper's unstandardized third central moment throughout. The usual skewness coefficient divides this quantity by $\mathrm{Var}(Y{)}^{3/2}$; its sign is the same whenever the variance is positive.

There is a minor domain qualification: finite ordinary moments do not guarantee a finite moment-generating function for positive arguments. The differentiations are valid in a neighborhood of zero when a positive exponential moment exists. For positive variables with the stated finite moments, all formulas also follow from left derivatives at zero, because $Y^j{e}^{tY}\le Y^j$ for $t\le 0$ and dominated convergence applies. Thus no extra exponential-moment assumption is needed for the moment identities themselves.

For the random sum of independent claims, condition on $N=k$. Independence of the claims and independence from the count giveTaking expectations and then logarithms yields the random-sum transform identity and the cumulant composition for a random sum:Here $G_N$ is the probability generating function. These identities hold wherever the transforms are finite, in particular for $t\le 0$ with positive claims.

For reuse in the three cases, write $m_j=\mathbb{E}{X}_1^j$ and $a_j={\kappa }_{N,j}$. Applying the chain rule three times givesor equivalentlyThis expresses the requested third central moment in raw claim moments, while keeping the contribution of claim-count variability explicit.

Let $P(z)$, $F(z)$ and $G(z)$ be the probability generating functions of $N$, one severity, and $S$, respectively. Positivity of the severities gives $F(0)=0$ and $g_0=p_0$; the random-sum transform identity gives $G=P\circ F$. The count recurrence in the Panjer claim-count class impliesUse the chain rule and substitute $F(z)$ to obtainEquating the coefficient of $z^{r-1}$ givesThe factor multiplying $f_j{g}_{r-j}$ after rearrangement is $a(r-j)+(a+b)j=ar+bj$. Therefore the Panjer recursion isThese power-series calculations are valid inside the convergence discs of the probability generating functions, and hence justify the coefficient identities without assumptions about positive exponential moments.

For a Poisson distribution count, $p_n/p_{n-1}=\lambda /n$, so $a=0$ and $b=\lambda$. The aggregate recursion becomesTo obtain a moment recursion, write ${\mu }_j=\mathbb{E}{X}^j$, $m_j=\mathbb{E}{S}^j$, and $m_0=1$. For nonnegative measurable $h$, conditioning on $N=n$ and using exchangeability of the severities giveswhere $X$ on the right is independent of $S$. The second equality uses $n{p}_n=\lambda p_{n-1}$, the Poisson size-bias identity. Choosing $h(s)=s^{k-1}$, applying the binomial theorem, and using independence proves the raw moment recursion for a compound Poisson distribution:For any particular $k$, a finite severity $k$th moment suffices: $({\sum }_{i=1}^n{X}_i{)}^k\le n^{k-1}{\sum }_{i=1}^n{X}_i^k$, and the Poisson distribution has finite moments of every order. No positive moment-generating function domain is required.

The first three iterations giveSubtracting the appropriate powers of the expected value yieldsIn particular, the aggregate variance and third central moment involve the raw second and third severity moments, rather than their centered counterparts.

Write $y=N^{1/\phi (N)}$, $L={\sum }_{p\le y}|g(p)|$, and $A={\sum }_{p\le y}g(p)/p$. Put $I_p(n)=1_{p\mid n}$ and $Y_p=I_p-1/p$. The strongly additive arithmetic function identity is $g-A={\sum }_{p\le y}g(p)Y_p$.

For any tuple $p_1,\dots ,p_j$, expand ${\prod }_{r=1}^j(I_{p_r}-1/p_r)$ by choosing an indicator in some positions and the constant in the others. If the selected positions contain distinct primes whose product is $d$, thenFor the corresponding product of the independent Bernoulli random variables $X_p$, the expectation is exactly $1/d$. This includes repeated primes, since their indicator functions are idempotent, and the empty selection has zero error. Summing absolute values of all expansion coefficients bounds the difference bywhen $y\ge 2$. Expanding the $j$th power and summing the absolute coefficient weights gives

It remains to center at the actual expectation. Since ${\mathbb{E}}_N{I}_p=\lfloor N/p\rfloor /N$, we have $|{\mathbb{E}}_{N}g-A|\le L/N$. For each $n$, both $g(n)-A$ and $g(n)-{\mathbb{E}}_{N}g$ have absolute value at most $L$, because all their indicator coefficients have absolute value at most one. The identity $u^j-v^j=(u-v){\sum }_{r=0}^{j-1}{u}^{j-1-r}{v}^r$ therefore bounds the change in the central moment by $j{L}^j/N$.

Finally, independence factors each term of the independent central moment. If $q_1,\dots ,q_w$ are the distinct primes of the tuple and $a_i$ their multiplicities, the desired comparison becomesIf $y<2$, then $g=0$ and both sides vanish, so the formula remains valid. The argument also covers complex coefficients $g(p)$; a real-valued assumption is needed for the later normal distribution conclusion, not for this centered moment comparison for additive arithmetic functions.

A useful method of moments in probability states that if real random variables $Z_N$ have all moments, $\mathbb{E}{Z}_N^j\to m_j$ for every integer $j\ge 1$, and $(m_j)$ is the moment sequence of a moment-determinate probability distribution, then $Z_N$ converges to that distribution in the sense of convergence in distribution. In particular, convergence to the standard normal distribution follows from limiting odd moments zero and limiting even moments $(2k-1)!!$. The moment-generating function of a standard normal variable, finite in a neighbourhood of zero, ensures moment determinacy.

For the classical Erdős-Kac theorem, put $L=\log \log N$ and choose, for example, $\phi (N)=L^{1/4}$, with a harmless modification for small $N$. Truncate the prime omega function to primes $p\le y=N^{1/\phi (N)}$. The omitted number of distinct prime factors of any $n\le N$ is at most $\phi (N)$, since a product of $r$ omitted primes exceeds $N^{r/\phi (N)}$. Thus this truncation changes the normalized variable by $o(1)$ uniformly. Also, the Mertens theorem for reciprocal primes gives

Part (b) transfers every fixed normalized central moment of the truncated prime omega function to the independent Bernoulli random variables model. Indeed, its unnormalized error is at most $O_j(N^{2j/\phi (N)-1})$, using ${\sum }_{p\le y}1\le y$, and this tends to zero for each fixed $j$. In the independent expansion, any singleton index has zero expectation; the leading contributions are pairings, giving exactly the standard normal distribution moments, while blocks of size at least three are negligible after normalization. The method of moments in probability, followed by the uniformly negligible truncation and centering errors, proves the Erdős-Kac theorem.

The same strategy proves the bounded-prime-weight form in part (a). Choose $\phi (N)\to \infty$ slowly enough that $\phi (N)=o(B(N))$. The omitted weighted contribution is $O(\phi (N))$; its mean is likewise $O(\phi (N))$, and its independent variance is $O(\log \phi (N)+1)=o(B(N{)}^2)$ by the Mertens theorem for reciprocal primes. Hence the truncated model has the same normalization, and part (b) again transfers each fixed central moment.