One data function under two parameter laws

Goal and scope

Validate a total estimator and its parameterwise expectations.

Expectations here do not automatically establish estimator quality.

Givens and symbols

• work

• G1 — Theta={1/4,3/4}, Omega={00,01,10,11}; P_(1/4)=(9,3,3,1)/16 and P_(3/4)=(1,3,3,9)/16.
• G2 — U(x)=(x1+x2)/4 has total table(0,1/4,1/4,1/2) in Omega order, with target g(theta)=theta.

• θ — fixed unknown parameter
• U — one total statistic

Rules and sources

• mko_definition · cited — On a finite parameter model with one common sample space, the statistic table depends only on the observation. Expectations can be computed under each parameter law, but no unbiasedness, consistency, sufficiency, identifiability or posterior claim follows here. Full sampling distributions are a later object. · mko-statistical-estimator
• work · prerequisite — Finite laws have nonnegative probabilities summing to one; a statistic depends only on data, and expectation sums all weighted outcomes.

Main derivation

\Omega=\{00,01,10,11\}

U=(0,1/4,1/4,1/2)

U(x)=(x_1+x_2)/4

U\text{ does not depend on }\theta

x=01

u_{\rm obs}=U(01)=1/4

E_{1/4}[U]=0(9/16)+(1/4)(3/16)+(1/4)(3/16)+(1/2)(1/16)

E_{1/4}[U]=1/8

E_{3/4}[U]=0(1/16)+(1/4)(3/16)+(1/4)(3/16)+(1/2)(9/16)

E_{3/4}[U]=3/8

E_{1/4}[U]=1/8,\quad E_{3/4}[U]=3/8

\theta\mapsto E_\theta[U]\text{ is a parameterwise table}

V_\theta(x)=\theta

V_\theta\text{ is not a usable unknown-parameter estimator rule}

U:\Omega\to\mathbb Q\text{ total and parameter-independent}

U\text{ qualifies as an estimator for this model}

Substeps and lemmas

No substeps in this guide.

Reverse audits

• S08 · premise_audit · G1, G2, S07, work — The two expectation values are not inflated into consistency or posterior claims.
• S07 · premise_audit · G1, G2, S06, work — Each fixed Vtheta is a function, but not the one common data function required here.
• S06 · premise_audit · G1, G2, S05, work — The law changes, not the estimator definition.
• S05 · premise_audit · G1, G2, S04, work — Do not mix weights from different theta laws.
• S04 · premise_audit · G1, G2, S03, work — 01 and 10 share a value but each contributes mass.
• S03 · premise_audit · G1, G2, S02, work — The value 1/4 is not the entire four-entry function U.
• S02 · premise_audit · G1, G2, S01, work — Both theta values use the same U table.
• S01 · premise_audit · G1, G2, work — Neither11 nor any single-valuedness check is omitted.

Error controls and negative controls

Total table

Assign every outcome even when values coincide.

Parameter and data

Keep one U and two Ptheta laws; do not silently change U.

• U may be total without a value at 11. → reject — Totality requires a value for every carrier outcome.
• Set U(x)=theta to estimate unknown theta from data. → reject — The unknown parameter cannot be an input to the data rule.
• The observed 1/4 equals E_(1/4)U. → reject — The complete expectation is 1/8.

Result and limitations

U is one total estimator; at 01 the estimate is 1/4, while its two law expectations are 1/8 and 3/8.

Verification and source binding

2 declared checks for this guide; only the listed expressions are covered.

• source commit: b1b2f1dcf8c50d67a93fe52d95f8eef7b3abba9f
• adopted source SHA-256: 7d2a71efe1386b0a4e2ae04a859c98e82bdbfb5e2aa1303f1a80575333c06239
• original source SHA-256: 17561f6cd64c683c14d172706c4eb1d4846352d8213e1cf1b580c63cbb581dce
• Lean: NOT_RUN · independent AI: SCOPED_LEAD_AND_BILINGUAL_CONTEXT_REVIEW

Same-source full JSON (formulas, ASTs, controls and revision log)