Let and . The stochastic exponential solution gives
Boundedness of the predictable process implies the Novikov condition on every finite horizon, so this exponential has conditional expectation . The pathwise bounds and positivity of give
This proves the required bound in the independent-volatility case, and the exponential argument in fact does not need independence. In the usual filtration generated by Brownian motion and an independent volatility history, one can alternatively condition on the whole volatility path: the Brownian integral is then conditionally Gaussian with variance . The result is
the conditional square-root price under independent volatility. The outer conditional expectation cannot in general be removed.
On , these positive price bounds justify the unique square-root stock implied volatility
There is a genuine zero-price qualification: if , the nonnegative stock is absorbed at zero and both claim prices are zero for every volatility parameter. The price equation then does not determine a unique . One may set on that event to retain the bounds; identification by inversion requires .
Solving the geometric Brownian motion equation over gives
The Brownian increment is independent of and has a normal distribution with variance . Its exponential moment-generating function therefore gives
The required deterministic price function is
This includes , and . For and , it is continuous and strictly decreasing in , with range .
The square root is concave on , and is integrable since . For , the conditional Jensen inequality and the martingale property give
Taking conditional expectations with respect to and using the tower property of conditional expectation yields
Thus the maturity curve for a square-root stock claim is nonincreasing; it need not be strictly decreasing, as a constant stock gives equality. The inequality holds for every ordered pair of maturities. Under the usual right-continuous versions of the market processes, it gives the corresponding nonincreasing version of the maturity curve.
Let denote the original zero-coupon bond price computed above. A deterministic shift of the short rate, with , gives . Subtracting the two recursions shows that the required added drift is
Since the shift is nonrandom, the new discount factor differs by , and hence .
For deterministic calibration of an autoregressive short rate, define
All these quantities are finite. The telescoping sum gives . Explicitly,
These constants fit every maturity simultaneously. Each successive maturity fixes uniquely, so the deterministic calibration is also unique with the prescribed .
Put and define the finite geometric series
Starting the autoregressive process of order one at time gives . Consequently
The future innovations are independent and identically distributed random variables, independent of . Factorizing their exponential conditional expectation and using the cumulant-generating function yields
Thus the exponential-affine bond pricing coefficients are
They vanish at maturity, giving . Everywhere finiteness of ensures that each zero-coupon bond price is positive and finite, including when is zero, negative, or one.
For the autoregressive process of order one, the formula at reads , with an empty sum. If it holds at time , substitution into the recursion gives
Thus mathematical induction proves
No restriction such as is needed for this finite-time identity.
The ratio of expected process variance to variance of hypothetical means is , and the credibility factor is . Holding fixed, an increase in decreases . Hence the credibility factor increases, approaching one as tends to infinity. Extending the formula to real makes the sign explicit:
For the integer values in the model this establishes the same strict monotonicity. The collective claim expected value also changes, but the conclusion concerns the relative weight of experience: conditional noise declines faster than the variation of the risk means.
The severity is an equal-weight mixture distribution of rate- and rate- exponential distributions. Its expected value is
The moment-generating function, finite exactly for , is
Canceling the nonzero in the adjustment coefficient equation and multiplying by the positive denominator on gives
Thus the required polynomial is
Since , , and the leading coefficient is positive, one root lies in and the other exceeds . Only the smaller root is in the moment-generating function domain. Consequently
The rationalized expression avoids subtraction of nearly equal numbers when is small.
The erroneously chosen same-mean exponential distribution gives . Direct substitution shows , so lies strictly between the two polynomial roots, and in particular . Therefore
while both bounds equal one at . The exponential misspecification produces a smaller claimed upper bound. The Lundberg inequality certifies for the actual mixture; it does not certify the smaller expression computed from the wrong severity law.
For a unit-rate exponential distribution, and for . The adjustment coefficient equation is
Its nonzero root is
It lies in for , so the moment-generating function is finite there and the Lundberg inequality applies.
The original PDF specifies a geometric distribution on , with probabilities . Its probability generating function is . By independence, the total original claim count has
The coefficient follows from the negative binomial series. Thus one representation uses independent unit-rate exponential distribution steps and a negative binomial distribution count .
There is a second useful random sum of independent claims representation. For one policy, the random-sum transform identity gives
This is the mixture distribution of zero with probability and a rate- exponential distribution with probability . Consequently
with the binomial distribution count independent of the independent steps. Equality follows by multiplying the moment-generating functions. This is a negative-binomial sum of exponential claims.
When , the three values of give
Thus the zero mass is , and the conditional positive probability density function is
Its integral is . Equivalently the positive-component cumulative distribution function is
so . For , .
Write , and suppose first that . Let be policy 's aggregate, and the moment-generating function of its claim sizes. The Poisson distribution count has probability generating function , so the random-sum transform identity and independence of the policies give
The expression in the weighted sum is the moment-generating function of a mixture distribution with claim cumulative distribution function
Thus the aggregate has a compound Poisson distribution with intensity and severity law . This identification remains valid without positive exponential moments, using the same calculation for Laplace transforms of nonnegative random variables and their uniqueness. It is the Poisson superposition of insurance portfolios.
For common unit-rate exponential distribution severities, the merged count is Poisson distributed with mean . Because each severity is strictly positive, exactly when , giving
For , the sum of unit-rate exponential distribution claims has Erlang distribution density . This density follows by induction: convolving the -claim density with gives . Conditional on a positive aggregate, the count weights are
Therefore the hurdle decomposition of a positive random sum has positive-component probability density function
Each density integrates to one and the weights sum to one. Hence for , where is the conditional cumulative distribution function given . If , the aggregate is identically zero, and the positive component is undefined; the requested presupposes a positive total intensity.
This is an EM algorithm for a censored lognormal competing-risks mixture. Write and suppose , with mixing weights , . The missing data are and for censored patients; neither is missing for recorded deaths or recoveries. The complete-data log-likelihood, apart from terms independent of the parameters, is
The lognormal Jacobian is also parameter-independent and therefore does not affect the maximization.
At iteration , set for each censored patient and let . Bayes' rule gives the E-step class weights
Given that class, has a truncated normal distribution above . With the inverse Mills ratio , compute both moments needed for the E-step:
Thus , , and the corresponding second moment is . For an observed outcome at time , use , , and . These specify the full conditional expectation of .
Put and let be the total number of patients. Maximizing that expected complete-data log-likelihood gives the M-step
All moments on the right are evaluated at the old parameters. Repeat the E-step and M-step until the observed log-likelihood stabilizes, using positive initial variances and mixing weights. The expectation-maximization algorithm increases that likelihood at each exact iteration, but need not find its global maximum; multiple starts help distinguish local optima. The resulting estimates give the case fatality probability and
These are conditional event-time distributions, distinct from the cumulative incidence functions and .
Let denote eventual death or recovery, respectively; is the time from admission to that terminal event, and . A patient still hospitalized at collection has right censoring: only is known, where is the elapsed time since admission. Both eventual outcomes are then unobserved. A recorded death or discharge is an observed terminal event in this competing risks model; discharge is not censoring of an otherwise observable later in-hospital death. Assume the observation deadline, conditional on relevant admission information, is noninformative for .
After adjusting for location, adding the period effect reduces deviance by on one degree of freedom, giving the supplied likelihood-ratio test . The adjusted incidence rate ratio is
Under this Poisson exposure model, the accident rate after installation is estimated to be about lower, with a statistically significant reduction. The remaining lack of fit merits residual checks and possibly a Quasi-Poisson model or a model allowing location-specific changes. This before-and-after observational study establishes an association under the fitted model; changes in traffic volume, broader trends, or regression to the mean at sites chosen for high prior counts could also contribute, so the estimated reduction is not by itself a causal treatment effect.
The second Poisson exposure model allows each location its own baseline accident rate:
The last equality is the corner-point constraint. The common after-to-before incidence rate ratio remains . This model is appropriate because the sites can have different background risks; treating those differences as unexplained Poisson variation made the first model fit poorly, with deviance on 14 residual degrees of freedom.
Adding seven location effects to the first fitted model reduces the deviance by , which is large relative to . The supplied sequential analysis of deviance reports a slightly different location contribution because it enters locations before the period indicator. The full model is much better but its deviance on 7 degrees of freedom still gives an approximate goodness-of-fit -value . That suggests residual lack of fit or overdispersion, although sparse accident counts make the asymptotic deviance goodness-of-fit test approximate.
Let be the accident count at location in period , and its exposure in years, where denotes after installation. The Poisson exposure model is
The offset has its coefficient fixed at one. The model assumes constant rates within each period, a common before rate across locations, a common treatment rate ratio, independent counts, and Poisson variance equal to the mean. The incidence rate ratio is , so
An approximate 95% Wald confidence interval transforms the interval for :
The line compares the two pooled accident rates, dividing the total number of accidents by total observation years in each period. It gives the unadjusted incidence rate ratio
corresponding to an estimated reduction of about . Pooling does not adjust for differences between locations or for the unequal location composition of observation time before and after installation.

Pinned article: Introduction to the OurBigBook Project

Welcome to the OurBigBook Project! Our goal is to create the perfect publishing platform for STEM subjects, and get university-level students to write the best free STEM tutorials ever.
Everyone is welcome to create an account and play with the site: ourbigbook.com/go/register. We belive that students themselves can write amazing tutorials, but teachers are welcome too. You can write about anything you want, it doesn't have to be STEM or even educational. Silly test content is very welcome and you won't be penalized in any way. Just keep it legal!
We have two killer features:
  1. topics: topics group articles by different users with the same title, e.g. here is the topic for the "Fundamental Theorem of Calculus" ourbigbook.com/go/topic/fundamental-theorem-of-calculus
    Articles of different users are sorted by upvote within each article page. This feature is a bit like:
    • a Wikipedia where each user can have their own version of each article
    • a Q&A website like Stack Overflow, where multiple people can give their views on a given topic, and the best ones are sorted by upvote. Except you don't need to wait for someone to ask first, and any topic goes, no matter how narrow or broad
    This feature makes it possible for readers to find better explanations of any topic created by other writers. And it allows writers to create an explanation in a place that readers might actually find it.
    Figure 1.
    Screenshot of the "Derivative" topic page
    . View it live at: ourbigbook.com/go/topic/derivative
  2. local editing: you can store all your personal knowledge base content locally in a plaintext markup format that can be edited locally and published either:
    This way you can be sure that even if OurBigBook.com were to go down one day (which we have no plans to do as it is quite cheap to host!), your content will still be perfectly readable as a static site.
    Figure 5. . You can also edit articles on the Web editor without installing anything locally.
    Video 3.
    Edit locally and publish demo
    . Source. This shows editing OurBigBook Markup and publishing it using the Visual Studio Code extension.
  3. https://raw.githubusercontent.com/ourbigbook/ourbigbook-media/master/feature/x/hilbert-space-arrow.png
  4. Infinitely deep tables of contents:
    Figure 6.
    Dynamic article tree with infinitely deep table of contents
    .
    Descendant pages can also show up as toplevel e.g.: ourbigbook.com/cirosantilli/chordate-subclade
All our software is open source and hosted at: github.com/ourbigbook/ourbigbook
Further documentation can be found at: docs.ourbigbook.com
Feel free to reach our to us for any help or suggestions: docs.ourbigbook.com/#contact