Conditional on , the future Bernoulli random variable is independent of the observed statistical sample and has success probability . Its posterior predictive probability is therefore the posterior mean of . Put and . Thenusing the beta-gamma identity and the Gamma function recurrence. HenceThe whole posterior predictive distribution of is the Bernoulli distribution with this success probability.
Let . The Bernoulli distribution likelihood function is . Multiplication by the beta distribution prior density and Bayes' theorem giveRecognizing the normalized beta distribution,This is Beta-binomial conjugacy; the same update applies whether the data are recorded as the individual Bernoulli trials or their success count.
Under the null hypothesis, the full model has two free positive statistical parameters and the constrained model has one. The Wilks theorem therefore givesas both sample sizes tend to infinity, with tending to a number strictly between zero and one. For the observed , calculateThe large-sample p-value is the upper-tail probabilitywhere is the cumulative distribution function of the standard normal distribution. The last equality uses the fact that the square of a standard normal random variable has a chi-squared distribution with one statistical degree of freedom. Values of on either side of are already included by the transformation to .
Put , and . Independence gives the likelihood functionThe unrestricted maximum-likelihood estimators are and . Under the null hypothesis, the common mean maximizes at . These are maxima because each one-parameter score function has the sign of its observed sum minus its sample size times its proposed mean.
Define the generalized likelihood ratio to be the constrained maximum divided by the unrestricted maximum. The exponential factors cancel, givingSince and ,It has maximum one at , when the two fitted means agree, and is small toward either endpoint. A likelihood-ratio test rejects for small , or equivalently large . This is the likelihood-ratio test for equality of exponential means.
Write and , with . Two exact facts about a normal sample areand independence of the normal sample mean and sample variance holds. A chi-squared distribution with statistical degrees of freedom is a sum of independent variables, each with mean one and variance two. The central limit theorem therefore givesFor , the derivative at is because . The delta method gives the asymptotic normality of a normal sample standard deviation:The exact independence of and makes their limiting normal distributions independent. Consequently,ThusThis has the same leading asymptotic variance as . The weights and are those in the optimal asymptotic combination of a normal sample mean and standard deviation. This does not require to be an exactly unbiased estimator of .
Let be the standard normal quantile. Since is a consistent estimator, Slutsky's theorem givesIts estimated standard error is , giving the approximate Wald confidence intervalFor each fixed , this procedure's coverage probability tends to . Intersecting with the positive parameter space preserves coverage of the true positive value.
Put , and . The normal distribution model givesand, up to a constant independent of , its log-likelihood function isThe score function and its zero equation areFor , this quadratic equation has exactly one positive root, giving the maximum-likelihood estimatorThe numerator of the score function is positive between its negative and positive roots and negative above its positive root. Thus the likelihood function increases up to and decreases afterwards: this is its unique global maximum on . Also, at both ends. The all-zero observation vector has probability zero; on that exceptional vector and there is no attained maximum.
The second derivative and the relevant moments areTherefore the expected Fisher information isThe support of a probability distribution is the whole real line, independent of the positive statistical parameter. The law of large numbers gives and in probability, so the displayed maximum-likelihood estimator is a consistent estimator. The regular asymptotic normality of a maximum likelihood estimator now yieldsThus the requested leading asymptotic variance on the unscaled estimator's scale is . The normal mean proportional to standard deviation model provides a reusable version of this calculation.
For a Bernoulli distribution with fixed , the mean and variance are and . The odds transformation has derivative . Applying the delta method from part (ii),More precisely, converges to a normal distribution of mean zero and variance , after defining the statistic arbitrarily on . That exceptional event has probability , so this extension does not change the limit. The unextended ratio is undefined there and has no finite exact variance if interpreted as infinite. At it is zero almost surely; at the denominator is always zero. This is the delta method for Bernoulli odds.
For , the central limit theorem givesIf is differentiable at , the delta method applies to the first-order expansionwhere the remainder notation means that its product with tends to zero in probability. HenceThe useful nondegenerate normal approximation requires . When , the first-order limit is zero and a higher-order expansion may be needed.
For the independent statistical sample, write the likelihood function and log-likelihood function asThe expected Fisher information in the whole statistical sample isUnder the regularity conditions that permit differentiation under the integral sign, the score function has expected value zero andFor an interior statistical parameter, assuming identifiability and , the regular asymptotic normality of a maximum likelihood estimator statesThus the large-sample normal approximation is . The inverse information is the leading sampling variance approximation; the displayed convergence specifies its precise asymptotic meaning.
For this homogeneous motion, suppose the matrix is symmetric. Put . The acceleration potential of a homogeneous motion iswhere is arbitrary. When taking the spatial gradient, , , , and are fixed. Symmetry givesThis verifies the potential directly and also proves sufficiency of the symmetric matrix condition within the static-family setting. Its dimension is , so the pressure correction has the dimension of stress. Combining with part (b)(ii), the corresponding dynamic Cauchy stress tensor iswhere . Substituting its divergence into the Cauchy momentum equation reproduces , as required.
Take two time derivatives at fixed reference position :The constraint ensures that the deformation gradient is invertible, so . Thus the spatial material acceleration is the affine vector fieldIts spatial gradient is , and its curl isPart (b)(iii) therefore requiresEquivalently, multiplying on the left by and on the right by givesThe translation contributes no spatial curl and is unrestricted by this condition. A useful equivalent first integral isthe antisymmetric matrix in parentheses must be constant, and need not vanish. The separate constraint is still required; differentiating it also gives .
The condition is understood in the setting of part (b), where a static family already exists under the prescribed body force. For a homogeneous elastic deformation gradient, the elastic stress is spatially constant. Static balance of linear momentum consequently gives , ensuring that has a scalar potential. If the static-family assumption were dropped and an arbitrary time-independent body force allowed, the general necessary condition would instead be .
Past exam of the solid mechanics course of the University of Oxford 2023 3 b iii Solution 2026-10-25
For a twice continuously differentiable scalar potential, mixed second partial derivatives commute. Taking the spatial curl of the equation from part (i) givesFor example, its first component is . The curl acts on the spatial representation of the material acceleration, not directly on its expression in reference coordinates.
This is a necessary local condition. It is sufficient locally, and sufficient globally on a simply connected domain under the usual smoothness assumptions. On a domain with holes, a global scalar potential additionally requires every closed-loop line integral of the material acceleration to vanish. The homogeneous motion in part (c) admits an explicit global scalar potential, so this topological qualification causes no obstruction there.
The pressure adjustment from part (i) can be writtenIndeed, since , the difference of the two Cauchy momentum equations isThus is constant in space on each connected component. The function is fixed by any prescribed pressure or surface traction datum. In terms of the usual compressive pressure multiplier, . The plus sign in therefore does not identify with the compressive multiplier itself.
Restore the particle label suppressed in the question, writing the static family as . At each fixed , its Cauchy stress tensor satisfiesThis dynamic continuation of a static incompressible elastic deformation sets to form a motion. At every time its deformation gradient is the same as that of the corresponding static member. For an elastic material the elastic part of the Cauchy stress tensor depends on that deformation gradient, while incompressibility leaves an arbitrary scalar constraint reaction in hyperelastic stress. Therefore writeHere is the identity matrix. Subtracting static balance of linear momentum from dynamic balance of linear momentum givesSince the homogeneous incompressible material has constant mass density, define . NecessarilyConversely, suppose this acceleration potential exists. Choose . ThenThe added isotropic stress is symmetric, so angular momentum conservation remains satisfied. This proves both directions for the field equations and the elastic constitutive equation. The surface tractions for the motion are those of the adjusted stress; identical prescribed static tractions would impose an additional boundary restriction on .
For general , put . The reduced strain energy density and its derivative areThe same factorization as in part (i) yieldsThis form removes the apparent singularity at : its limit is , finite for every fixed . Thus only the upper endpoint can obstruct convergence of the improper integral.
As , , givingFor , the comparison test with a power integral implies convergence exactly when . Thereforeis precisely the range with finite critical pressure, the cavitation criterion for power-law strain energy. At the divergence is logarithmic; for larger it is a power divergence. These materials require an unbounded tensile loading magnitude in this ideal model. The qualification excludes the degenerate zero-energy material.
The neo-Hookean solid corresponds to , with positive shear modulus . Substitution of the principal stretches givesThe identity simplifies the integrand:The two improper integrals are elementary:Thus the critical tensile stress magnitude is . As a check on the finite-sphere limit, part (c) giveswhich tends to as the cavity radius tends to zero.
Past exam of the solid mechanics course of the University of Oxford 2023 2 b iii Solution 2026-10-25
Take the inner surface to be free of traction, as appropriate to an empty cavity with no surface tension. At the outer surface the imposed pressure is compressive when positive. The outward normal vectors are at and at , givingIntegrating the ordinary differential equation from part (ii) between the two surfaces givesThe outer stretch follows from incompressibility:Hence an expression entirely in terms of the inner stretch and the reference radii isEquivalently . For an expanding shell, ; when on this range, , correctly describing an outward tensile loading. If an inner pressure were present, the same derivation would give on the left. Thus the empty-cavity condition specifies the pressure reference needed for the requested answer.
Let denote derivatives of the strain energy density with respect to its three principal stretches. The principal stress formula for incompressible hyperelasticity isIt follows by applying in principal axes. Equal tangential principal stretches and material isotropy give at . Differentiating the reduced strain energy density by the chain rule givesThe unknown pressure cancels in this difference. Substituting in part (i), and then using the supplied derivative of , givesConsequently the desired ordinary differential equation isFor completeness, the supplied derivative follows from : , and differentiating gives . At the undeformed value the division must be interpreted by a limit; the spherically symmetric deformation with has and should be handled directly by the radial equilibrium equation.
The Cauchy momentum equation in static elastic equilibrium, with zero body force, is . The Cauchy stress tensor is symmetric. Material isotropy and the equal tangential principal stretches imply , so its radial equation isAll stresses and spatial derivatives in this equation are measured in the current configuration.
There are unlisted articles, also show them or only show them.