Alphabeta Math
TheoremStatement: Literature-sourcedProof: AI-adaptedPipeline-generatedprecheck passjudge pass (gpt-6-luna)
How statement and proof provenance work

The first chip identifies the source of the statement or construction; the second identifies the source of its local proof or verification.

  • Literature-sourced: the exact statement appears in a cited source; only wording and notation differ.
  • AI-adapted: a semantically identical restatement of literature-sourced material, modulo indexing, notation, and boundary cases adopted by the library.
  • AI-generated: a genuinely novel statement formulated by AI, with no source for the claim itself.

These labels describe origin, not correctness: citations and verification chips remain separate evidence.

Nonidentifiability precludes simultaneous consistency

Statement

Let P:Θ→P(X,A) be a parametric statistical model, let ψ:Θ→(T,d) be a metric-valued estimand, and let (Tn) be a nonrandomized estimator sequence for IID samples from this model. If ψ is not identifiable, then there is a pair of observationally equivalent parameters with distinct target values, and no estimator sequence is consistent in probability at both parameters.

Facts & Assumptions

Given: The model, estimand, estimator sequence, and hypotheses in the statement.

[F1]

Parametric statistical models: A parametric statistical model is the parameter map P:Θ→P(X,A) with P(θ)=Pθ.

[F2]

Observational equivalence: θ∼η exactly when Pθ=Pη as measures on the observation space.

[F3]

Estimands on a statistical model: An estimand is a specified function ψ:Θ→T.

[F4]

Identifiability of an estimand: An estimand is identifiable exactly when θ∼η implies ψ(θ)=ψ(η).

[F5]

Estimator sequences in IID experiments: The size-n experiment has law Pθ⊗n on (Xn,A⊗n), and an estimator is a measurable map Tn on that space.

[F6]

Pointwise consistency in probability: Consistency at θ means Pθ⊗n{d(Tn,ψ(θ))>ε}→0 for every ε>0.

[F7]

The product sigma-algebra and its finite iterates: The finite product sigma-algebra is generated recursively by measurable rectangles.

[F8]

For sigma-finite factors, the product measure exists, has the rectangle formula, is sigma-finite, and is unique: The product measure exists and gives each measurable rectangle the product of the factor measures.

[F9]

Measures agreeing on a generating pi-system are equal under an increasing finite-measure exhaustion from that pi-system: Measures agreeing on a generating π-system and on an increasing finite-measure exhaustion from it agree on the generated sigma-algebra.

[F10]

Metric space: d(x,y)=0 iff x=y, symmetry, and the triangle inequality; pseudometric and ultrametric: A metric is nonnegative, symmetric, separates distinct points, and satisfies the triangle inequality.

[F11]

A measurable function between measurable spaces: A map is measurable when the preimage of every target-measurable set is measurable.

[F12]

The Borel sigma-algebra of a topological space: The Borel sigma-algebra of a metric space contains every closed subset.

Proof

Given: The objects and hypotheses in the statement.

1.1F4givenchoose

By [F4], nonidentifiability supplies θ0,θ1∈Θ with θ0∼θ1 and ψ(θ0)≠ψ(θ1). Fix this pair.

2.1F1F2F7F8F9givenstep 1.1

Fix n≥1. By [F1], the observation laws in the model are Pθ. Measurable rectangles in Xn form a π-system generating A⊗n by [F7]. For every rectangle A1×⋯×An, [F8] and [F2] give Pθ0⊗n(A1×⋯×An)=∏j=1nPθ0(Aj)=∏j=1nPθ1(Aj)=Pθ1⊗n(A1×⋯×An). The full space is itself a rectangle and is an increasing exhaustion of finite mass one. Applying [F9] shows Pθ0⊗n=Pθ1⊗n on all of A⊗n.

2.2F3F10givenstep 1.1algebra

Put Δ=d(ψ(θ0),ψ(θ1))>0 and r=Δ/3. The two closed target balls Ci={t∈T:d(t,ψ(θi))≤r} are disjoint: a point in both would give Δ≤2r<Δ by [F10].

3.1F5F6F11F12F13givenstep 1.1step 2.2assume-contra

Suppose, for contradiction, that the estimator sequence is consistent at both parameters. For i∈{0,1} let Ei,n=Tn−1(Ci). These events are measurable because each Ci is closed by [F13] and Borel by [F12], while Tn is measurable by [F5] and preimages of Borel sets are measurable by [F11]. By [F6], Pθi⊗n(Ei,n)→1 for each i.

4.1step 2.1step 2.2step 3.1algebradischarge-contradiction: step 3.1∎

For each n, step 2.1 gives one common sample law for both probabilities, and step 2.2 gives disjoint events, so their probabilities sum to at most one. Step 3.1 says both probabilities tend to one, so their sum tends to two, a contradiction. Therefore the estimator sequence cannot be consistent at both parameters.

Depends on

Used by

Dependency tree · two levels

44 results within two dependency steps of this one, each drawn at its shortest distance from it. An arrow runs from a result to what uses it, so the chart reads left to right and ends at this result, which carries a heavier outline. Every node is a link to that result. Click elsewhere on the chart to enlarge it.

Sources