{
 "claims": [
  {
   "claim": "For the regression of the outcome on an intercept and a treatment indicator in a completely randomized experiment, the HC2 heteroskedasticity-robust variance estimate for the treatment coefficient is exactly equal to the conservative randomization-based Neyman variance estimator for the difference in means.",
   "claim_id": "P031-H1",
   "related_corrections": [],
   "tied_to": "Theorem 1; eq. (4)"
  },
  {
   "claim": "HC2 is conservative in expectation, $E[\\hat V_{HC2}(\\hat\\beta)]\\ge V(\\hat\\beta)$. Normal-approximation intervals based on Neyman/HC2 have approximately correct or conservative large-sample coverage, and the paper extends this conclusion to HR, HC1 and HC3 by asymptotic equivalence.",
   "claim_id": "P031-H2",
   "related_corrections": [
    "P031-E001"
   ],
   "tied_to": "Corollary 1; bias display on p. 367; coverage paragraph in Section 3; footnote 2"
  },
  {
   "claim": "The randomization variance of the difference in means under hypothesized constant additive effects equal to $\\hat\\beta$ is $(N-2)/(N-1)$ times the homoskedastic OLS variance estimate.",
   "claim_id": "P031-H3",
   "related_corrections": [
    "P031-E002",
    "P031-A001",
    "P031-N002"
   ],
   "tied_to": "Theorem 2; eq. (5)"
  },
  {
   "claim": "Under a balanced design, $N=2M$, the OLS, Neyman and HC2 variance estimates coincide, as does the constant-effects estimate after multiplication by $(N-1)/(N-2)$. The introduction describes all four estimators as equivalent and suggests that the choice of variance estimator is irrelevant in many cases.",
   "claim_id": "P031-H4",
   "related_corrections": [
    "P031-E002",
    "P031-A001"
   ],
   "tied_to": "Theorem 3"
  },
  {
   "claim": "For unbalanced designs the homoskedastic OLS variance estimator, and with it the constant-effects estimator, can be too large or too small relative to the true randomization variance, so intervals based on them are not assured to be correct or conservative, unlike Neyman/HC2, whose bias is nonnegative.",
   "claim_id": "P031-H5",
   "related_corrections": [
    "P031-E003",
    "P031-E002",
    "P031-E001"
   ],
   "tied_to": "Theorem 2 with Freedman (2008b, Theorem 5); Corollary 1; eq. (3); footnote 3; closing paragraph of Section 5"
  },
  {
   "claim": "Freedman's criticism that the usual homoskedastic variance estimate is inconsistent for the randomization variance has little practical force for current practice, because randomization justifies the heteroskedasticity-robust (HC2) variance estimator that practice uses, and the estimator Freedman criticises is the constant-effects randomization estimator up to a scaling factor.",
   "claim_id": "P031-H6",
   "related_corrections": [
    "P031-E001"
   ],
   "tied_to": "Theorems 1 and 2; Discussion, p. 370"
  }
 ],
 "date_published": "2026-10-25",
 "findings": [
  {
   "before_review": null,
   "class": "clarity_note",
   "date_modified": "2026-10-25",
   "date_published": "2026-10-25",
   "evidence_type": "exact_counterexample",
   "exhibits": [
    {
     "alt": "Crop of the paragraph that follows the displayed bias of the Neyman estimator. Red boxes mark the sentence beginning 'As demonstrated in Freedman (2008a, Theorem 1), asymptotic normality of beta-hat implies that large-sample confidence intervals' and ending 'approximately correct or conservative coverage'.",
     "caption": "Section 3, p. 367 (PDF p. 3), below the display of the bias of the Neyman estimator. The marked sentence infers coverage from asymptotic normality without stating further conditions.",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/exhibits/P031-E001.png"
    },
    {
     "alt": "Crop of the two lines after the proof of Corollary 1. Red boxes mark the sentences 'Above, we noted that large-sample confidence intervals based on V-hat-N had either approximately correct or conservative coverage. Clearly, this extends to V-hat-HC2', followed by the marker of footnote 2.",
     "caption": "Section 3, p. 368 (PDF p. 4), after the proof of Corollary 1. The marked sentences extend the coverage statement to the HC2 estimator.",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/exhibits/P031-E001-b.png"
    },
    {
     "alt": "Crop of footnote 2. Red boxes mark its second sentence, 'The other estimators are all asymptotically equivalent to HC2 and, thus, large-sample confidence intervals based on any of the heteroskedasticity-robust estimators have either approximately correct or conservative coverage'.",
     "caption": "Footnote 2, p. 368 (PDF p. 4). The marked sentence extends the statement to the other heteroskedasticity-robust estimators.",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/exhibits/P031-E001-c.png"
    }
   ],
   "formal_release": null,
   "formal_statements": [
    {
     "id": "P031-T5",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-T5"
    }
   ],
   "headline": "The statements about the large-sample coverage of the Neyman and HC2 intervals, and their extension to HR, HC1 and HC3 in footnote 2, hold in the asymptotic regime of the cited results, and the conditions of that regime should be stated.",
   "id": "P031-E001",
   "location": "Section 3, p. 367 (PDF p. 3), sentence after the bias display; p. 368 (PDF p. 4), sentence after Corollary 1 and footnote 2",
   "pdf_page": 3,
   "printed_page": "367",
   "reaches": [],
   "related_entries": [],
   "revisions": [],
   "same_defect_as": [],
   "severity": null,
   "subject": "paper",
   "target_ids": [
    "P031-T5"
   ],
   "text": {
    "as_printed": "p.~367: ``The Neyman estimator is therefore conservative: its bias is always nonnegative. As demonstrated in Freedman (2008a, Theorem 1), \\hl{asymptotic normality of} $\\hat\\beta$ \\hl{implies} that large-sample confidence intervals, using $\\hat V_N(\\hat\\beta)$ in a normal approximation will have either approximately correct or conservative coverage.''\n\np.~368: ``Above, we noted that large-sample confidence intervals based on $\\hat V_N(\\hat\\beta)$ had either approximately correct or conservative coverage. \\hl{Clearly, this extends} to $\\hat V_{HC2}(\\hat\\beta)$.''\n\np.~368, footnote 2: ``Implications for the other heteroskedasticity-robust estimators (HR, HC1, and HC3) studied in MacKinnon and White (1985) and Angrist and Pischke (2009, 299--308) are straightforward. The other estimators \\hl{are all asymptotically equivalent to HC2} and, thus, large-sample confidence intervals based on any of the heteroskedasticity-robust estimators have either approximately correct or conservative coverage.''",
    "corrected": "\\hl{Under conditions ensuring that} $(\\hat\\beta-\\beta)/\\sqrt{V(\\hat\\beta)}$ \\hl{converges in distribution to a standard normal variable and that} $\\hl{\\hat V_N(\\hat\\beta)/V(\\hat\\beta)\\to_p c\\in[1,\\infty)}$, normal confidence intervals based on the Neyman estimator or on HC2 have asymptotically correct or conservative coverage. \\hl{If both the treatment arm and the control arm grow}, HR, HC1 and HC3 are first-order equivalent to HC2 and inherit this conclusion under the same conditions. For the coverage result, it does not suffice that the variance estimator has nonnegative expected bias.",
    "intended_meaning": "The sentences are meant in the large-sample regime of the results they cite: both arms grow, with $M/N\\to p_0\\in(0,1)$, and the potential outcomes have convergent second moments and bounded fourth moments. Freedman (2008a) states Theorem 1 under conditions of this kind, which I read in the IMS reprint of that article, and in that regime the sentences are correct. Let $v_1$ and $v_0$ denote the limiting variances of the potential outcomes and $v_\\tau$ the limiting variance of the unit-level treatment effects, and suppose that $v=v_1/p_0+v_0/(1-p_0)-v_\\tau>0$. Then $N\\,V(\\hat\\beta)\\to v$ and $N\\hat V_N(\\hat\\beta)\\to_p v_1/p_0+v_0/(1-p_0)\\ge v$, and Slutsky's theorem implies that normal intervals have asymptotically correct or conservative coverage. Since the leverages $1/M$ and $1/(N-M)$ tend to zero, HR, HC1 and HC3 agree with HC2 to first order. This deduction is mine. Theorem 1 of Freedman (2008a) is a central limit theorem and does not itself state the coverage result.\n\nThe paper does not state these conditions, and they are needed, since Section 2 assumes only $1<M<N-1$. In a sequence of finite populations with $M=2$, which lies outside the cited regime, the standardized $\\hat\\beta$ has a standard normal limit, the nominal 95\\% interval has limiting coverage of about 69.97\\%, and HR and HC3 equal $1/2$ and $2$ times HC2. Theorems 1--3 and Corollary 1 are finite-sample statements and do not use these sentences."
   },
   "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-E001",
   "work": {
    "arxiv_id": null,
    "doi": "10.1016/j.spl.2011.10.024",
    "title": "On Equivalencies Between Design-Based and Regression-Based Variance Estimators for Randomized Experiments",
    "url": "https://pmaronow.github.io/llm-audit/works/P031/"
   },
   "work_id": "P031"
  },
  {
   "before_review": null,
   "class": "error",
   "date_modified": "2026-10-25",
   "date_published": "2026-10-25",
   "evidence_type": "exact_counterexample",
   "exhibits": [
    {
     "alt": "Crop showing the statement of Theorem 2 and the first sentence of its proof. A red box marks the term sigma(y0, y1), printed without tildes, at the end of the chain sigma-squared(y0-tilde) = sigma-squared(y1-tilde) = sigma(y0, y1).",
     "caption": "Proof of Theorem 2, first sentence, p. 369 (PDF p. 5). The marked covariance is that of the original potential outcomes; the proof needs the covariance of the hypothesized outcomes.",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/exhibits/P031-E002.png"
    },
    {
     "alt": "Crop of the three-line display that ends the proof of Theorem 2 and of the paragraph after it. Red boxes mark the summand e-hat squared, printed without the subscript i, in the first and second lines of the display, and the symbol V CE(beta-hat), printed without a hat, in the sentence ending 'carries over to V CE(beta-hat)'.",
     "caption": "Proof of Theorem 2, final display, and the sentence after the proof, p. 369 (PDF p. 5). The two marked summands lack the index $i$, and the marked estimator lacks its hat.",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/exhibits/P031-E002-b.png"
    },
    {
     "alt": "Crop of the proof of Theorem 3. Red boxes mark V CE(beta-hat), printed without a hat, on the left of the first line of the display, and the two symbols V-hat(y1) and V-hat(y0) in the numerators of the second line.",
     "caption": "Proof of Theorem 3, p. 370 (PDF p. 6). The marked estimator lacks its hat, and the two marked symbols $\\hat V(y_1)$, $\\hat V(y_0)$ are defined nowhere in the paper.",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/exhibits/P031-E002-c.png"
    }
   ],
   "formal_release": null,
   "formal_statements": [
    {
     "id": "P031-T7",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-T7"
    },
    {
     "id": "P031-T8",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-T8"
    },
    {
     "id": "P031-T9",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-T9"
    }
   ],
   "headline": "In the proofs of Theorems 2 and 3, the covariance $\\sigma(y_0,y_1)$ should read $\\sigma(\\tilde y_0,\\tilde y_1)$, two residual sums lack the index $i$, the constant-effects estimator twice lacks its hat, and $\\hat V(y_1)$, $\\hat V(y_0)$ should read $\\hat\\sigma^2(y_1)$, $\\hat\\sigma^2(y_0)$; both theorems hold as stated.",
   "id": "P031-E002",
   "location": "Proof of Theorem 2 and the sentence after it, p. 369 (PDF p. 5); proof of Theorem 3, p. 370 (PDF p. 6)",
   "pdf_page": 5,
   "printed_page": "369",
   "reaches": [],
   "related_entries": [],
   "revisions": [],
   "same_defect_as": [],
   "severity": "Minor",
   "subject": "paper",
   "target_ids": [
    "P031-T7",
    "P031-T8",
    "P031-T9"
   ],
   "text": {
    "as_printed": "(a) Proof of Theorem 2, first sentence (p.~369): ``Proof. Since $\\tilde y_0=\\tilde y_1-\\hat\\beta$, $\\sigma^2(\\tilde y_0)=\\sigma^2(\\tilde y_1)=\\sigma(\\hl{y_0},\\hl{y_1})$. Thus, substituting this into expression (5), randomization yields,''\n\\[\n\\hat V_{CE}(\\hat\\beta)=\\frac{N}{N-1}\\,\\frac{N}{M(N-M)}\\,\\sigma^2(\\tilde y_0).\n\\]\n\n(b) Proof of Theorem 2, final display (p.~369):\n\\[\n\\begin{aligned}\n\\frac{N-2}{N-1}\\hat V_{OLS}(\\hat\\beta)\n&=\\frac{N-2}{N-1}\\,\\frac{\\sum_{i=1}^{N}\\hl{\\hat e^{2}}}{N-2}\\,\\frac{N}{M(N-M)}\\\\\n&=\\frac{N}{N-1}\\,\\frac{\\sum_{i=1}^{N}\\hl{\\hat e^{2}}}{N}\\,\\frac{N}{M(N-M)}\\\\\n&=\\frac{N}{N-1}\\,\\frac{N}{M(N-M)}\\,\\sigma^2(\\tilde y_0)=\\hat V_{CE}(\\hat\\beta).\n\\end{aligned}\n\\]\n\n(c) Sentence after the proof (p.~369): ``As a result, the fact noted above that when $N\\ne 2M$, $\\hat V_{OLS}(\\hat\\beta)$ may be either too large or too small relative to $V(\\hat\\beta)$ carries over to $\\hl{V}_{CE}(\\hat\\beta)$.''\n\n(d) Proof of Theorem 3 (p.~370): ``With $N=2M$ and by Theorems 1 and 2,''\n\\[\n\\begin{aligned}\n\\frac{N-1}{N-2}\\hl{V}_{CE}(\\hat\\beta)\n&=\\hat V_{OLS}(\\hat\\beta)\n=\\frac{\\sum_{i=1}^{N}\\hat e_i^{2}}{2(M-1)}\\,\\frac{2M}{M^{2}}\n=\\frac{\\dfrac{\\sum_{i=1}^{M}\\hat e_i^{2}}{M-1}}{M}+\\frac{\\dfrac{\\sum_{i=M+1}^{N}\\hat e_i^{2}}{M-1}}{M}\\\\\n&=\\frac{\\hl{\\hat V}(y_1)}{M}+\\frac{\\hl{\\hat V}(y_0)}{M}=\\hat V_N(\\hat\\beta)=\\hat V_{HC2}(\\hat\\beta).\n\\end{aligned}\n\\]",
    "corrected": "(a) ``Since $\\tilde y_0=\\tilde y_1-\\hat\\beta$, $\\sigma^2(\\tilde y_0)=\\sigma^2(\\tilde y_1)=\\sigma(\\hl{\\tilde y_0},\\hl{\\tilde y_1})$.''\n\n(b)\n\\[\n\\begin{aligned}\n\\frac{N-2}{N-1}\\hat V_{OLS}(\\hat\\beta)\n&=\\frac{N-2}{N-1}\\,\\frac{\\sum_{i=1}^{N}\\hl{\\hat e_i^{2}}}{N-2}\\,\\frac{N}{M(N-M)}\\\\\n&=\\frac{N}{N-1}\\,\\frac{\\sum_{i=1}^{N}\\hl{\\hat e_i^{2}}}{N}\\,\\frac{N}{M(N-M)}\\\\\n&=\\frac{N}{N-1}\\,\\frac{N}{M(N-M)}\\,\\sigma^2(\\tilde y_0)=\\hat V_{CE}(\\hat\\beta).\n\\end{aligned}\n\\]\n\n(c) ``\\ldots carries over to $\\hl{\\hat V}_{CE}(\\hat\\beta)$.''\n\n(d)\n\\[\n\\begin{aligned}\n\\frac{N-1}{N-2}\\hl{\\hat V}_{CE}(\\hat\\beta)\n&=\\hat V_{OLS}(\\hat\\beta)\n=\\frac{\\sum_{i=1}^{N}\\hat e_i^{2}}{2(M-1)}\\,\\frac{2M}{M^{2}}\n=\\frac{\\dfrac{\\sum_{i=1}^{M}\\hat e_i^{2}}{M-1}}{M}+\\frac{\\dfrac{\\sum_{i=M+1}^{N}\\hat e_i^{2}}{M-1}}{M}\\\\\n&=\\frac{\\hl{\\hat\\sigma^2}(y_1)}{M}+\\frac{\\hl{\\hat\\sigma^2}(y_0)}{M}=\\hat V_N(\\hat\\beta)=\\hat V_{HC2}(\\hat\\beta).\n\\end{aligned}\n\\]\n\nThe corrected identities hold for arbitrary observed outcomes. Let $\\bar Y_T$ and $\\bar Y_C$ denote the means of the observed outcomes in the treatment and control groups, and set $S=\\sum_{i=1}^{N}\\hat e_i^{2}$. By (4), I have $\\hat\\alpha=\\bar Y_C$ and $\\hat\\beta=\\bar Y_T-\\bar Y_C$. Then $\\hat e_i=Y_i-\\bar Y_T$ for $i\\le M$ and $\\hat e_i=Y_i-\\bar Y_C$ for $i>M$. By the definitions of the hypothesized outcomes on p.~368, I have\n\\[\n\\tilde y_{0i}=Y_i-X_i\\hat\\beta=\\hat e_i+\\bar Y_C,\\qquad \\tilde y_{1i}=\\tilde y_{0i}+\\hat\\beta=\\hat e_i+\\bar Y_T.\n\\]\nThe residuals sum to zero within each group. The population means of $\\tilde y_0$ and $\\tilde y_1$ are therefore $\\bar Y_C$ and $\\bar Y_T$, and both centered vectors equal $(\\hat e_i)_{i=1}^{N}$. Using the definitions of the population variance and covariance on p.~366, I obtain\n\\[\n\\sigma^2(\\tilde y_0)=\\sigma^2(\\tilde y_1)=\\sigma(\\tilde y_0,\\tilde y_1)=\\frac{S}{N}.\n\\]\nThis is the corrected sentence (a), and it shows that the indexed sum in (b) equals $N\\sigma^2(\\tilde y_0)$. Substituting it into (5), I find\n\\[\n\\hat V_{CE}(\\hat\\beta)=\\frac{N}{N-1}\\left(\\frac{S}{NM}+\\frac{S}{N(N-M)}\\right)+\\frac{1}{N-1}\\left(\\frac{2S}{N}-\\frac{S}{N}-\\frac{S}{N}\\right)=\\frac{N}{N-1}\\,\\frac{S}{M(N-M)}.\n\\]\nSince the $[2,2]$ element of $(Z'Z)^{-1}$ is $N/(M(N-M))$, I have $\\hat V_{OLS}(\\hat\\beta)=\\frac{S}{N-2}\\,\\frac{N}{M(N-M)}$. Multiplying by $(N-2)/(N-1)$ gives $\\hat V_{CE}(\\hat\\beta)$, which is Theorem 2.\n\nFor Theorem 3, suppose that $N=2M$, so that $N-M=M$ and $N-2=2(M-1)$. By Theorem 2 and the formula for $\\hat V_{OLS}(\\hat\\beta)$, I have\n\\[\n\\frac{N-1}{N-2}\\hat V_{CE}(\\hat\\beta)=\\hat V_{OLS}(\\hat\\beta)=\\frac{S}{2(M-1)}\\,\\frac{2M}{M^{2}}=\\frac{1}{M}\\,\\frac{\\sum_{i=1}^{M}\\hat e_i^{2}}{M-1}+\\frac{1}{M}\\,\\frac{\\sum_{i=M+1}^{N}\\hat e_i^{2}}{M-1}.\n\\]\nBy the proof of Theorem 1, the two quotients on the right are $\\hat\\sigma^2(y_1)$ and $\\hat\\sigma^2(y_0)$. The right side is therefore $\\hat V_N(\\hat\\beta)$, and Theorem 1 implies that it equals $\\hat V_{HC2}(\\hat\\beta)$.",
    "evidence": "This correction rests on a check of the pages, an exact counterexample to the equality in (a) as printed, and a derivation of the corrected identities, given below. For the counterexample, let $N=4$, $M=2$ and $y_0=y_1=(0,2,5,9)$, and suppose that units 1 and 2 are treated. Then $Y=(0,2,5,9)$ and $\\hat\\beta=1-7=-6$, and the hypothesized outcomes are $\\tilde y_0=(6,8,5,9)$ and $\\tilde y_1=(0,2,-1,3)$. A direct computation gives $\\sigma^2(\\tilde y_0)=\\sigma^2(\\tilde y_1)=\\sigma(\\tilde y_0,\\tilde y_1)=5/2$ and $\\sigma(y_0,y_1)=23/2$. In the same example $\\hat V_{CE}(\\hat\\beta)=10/3$ and $\\hat V_{OLS}(\\hat\\beta)=\\hat V_N(\\hat\\beta)=\\hat V_{HC2}(\\hat\\beta)=5$, as Theorems 2 and 3 require.",
    "problem": "There are four kinds of misprint, and one of them makes an equality false as printed.\n\n(a) Since the hypothesized potential outcomes satisfy $\\tilde y_{1i}=\\tilde y_{0i}+\\hat\\beta$ for every unit, their two variances equal their covariance $\\sigma(\\tilde y_0,\\tilde y_1)$. This is the covariance that appears in expression (5). The covariance $\\sigma(y_0,y_1)$ of the original potential outcomes is a different quantity, and the equality with it does not hold in general, even when the true effects are constant.\n\n(b) The summand $\\hat e^{2}$ has no index under a sum over $i$, although the residuals are defined as $\\hat e_i$ on p.~367 and no scalar $\\hat e$ is defined.\n\n(c) The symbol $V_{CE}(\\hat\\beta)$ lacks the hat of the estimator $\\hat V_{CE}(\\hat\\beta)$ defined in (5), and in the paper an unhatted $V$ denotes the true variance of equation (3).\n\n(d) The symbols $\\hat V(y_1)$ and $\\hat V(y_0)$ are not defined, and the quantities meant are the sample variances $\\hat\\sigma^2(y_1)$ and $\\hat\\sigma^2(y_0)$ of p.~366.",
    "what_survives": "Theorems 2 and 3 hold as stated for all observed outcomes when $1<M<N-1$, and no theorem statement changes. Theorem 1 and Corollary 1 do not involve these symbols."
   },
   "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-E002",
   "work": {
    "arxiv_id": null,
    "doi": "10.1016/j.spl.2011.10.024",
    "title": "On Equivalencies Between Design-Based and Regression-Based Variance Estimators for Randomized Experiments",
    "url": "https://pmaronow.github.io/llm-audit/works/P031/"
   },
   "work_id": "P031"
  },
  {
   "before_review": null,
   "class": "error",
   "date_modified": "2026-10-25",
   "date_published": "2026-10-25",
   "evidence_type": "exact_counterexample",
   "exhibits": [
    {
     "alt": "Crop of footnotes 3 and 4 at the bottom of the page. A red box marks the phrase 'the limiting values of the control group mean and average treatment effect' in the second line of footnote 3.",
     "caption": "Footnote 3, p. 369 (PDF p. 5). The marked phrase names two means as the quantities on which the relation depends.",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/exhibits/P031-E003.png"
    }
   ],
   "formal_release": null,
   "formal_statements": [
    {
     "id": "P031-T11",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-T11"
    }
   ],
   "headline": "The asymptotic relation between $\\hat V_{OLS}(\\hat\\beta)$ and $V(\\hat\\beta)$ depends on the treatment fraction and on the limiting variances and covariance of the potential outcomes, not on the control group mean and the average treatment effect.",
   "id": "P031-E003",
   "location": "Footnote 3, p. 369 (PDF p. 5)",
   "pdf_page": 5,
   "printed_page": "369",
   "reaches": [],
   "related_entries": [],
   "revisions": [],
   "same_defect_as": [],
   "severity": "Minor",
   "subject": "paper",
   "target_ids": [
    "P031-T11"
   ],
   "text": {
    "as_printed": "``Freedman (2008b, p. 190) gives the exact asymptotic relation between $\\hat V_{OLS}(\\hat\\beta)$ and $V(\\hat\\beta)$, which depends on the size of the treatment versus control group and \\hl{the limiting values of the control group mean and average treatment effect}.''",
    "corrected": "``Freedman (2008b, p. 190) gives the exact asymptotic relation between $\\hat V_{OLS}(\\hat\\beta)$ and $V(\\hat\\beta)$, which depends on the size of the treatment versus control group and \\hl{the limiting variances and covariance of the treatment and control potential outcomes}.''\n\nThe relation is as follows. Suppose that, along a sequence of finite populations, $M/N\\to p\\in(0,1)$, $\\sigma^2(y_1)\\to v_1$, $\\sigma^2(y_0)\\to v_0$ and $\\sigma(y_1,y_0)\\to c_{10}$. Then\n\\[\n\\lim N\\,V(\\hat\\beta)=\\frac{1-p}{p}\\,v_1+\\frac{p}{1-p}\\,v_0+2c_{10},\n\\qquad\n\\lim N\\,E\\bigl[\\hat V_{OLS}(\\hat\\beta)\\bigr]=\\frac{v_1}{1-p}+\\frac{v_0}{p}.\n\\]\nIf the sample second moments also converge, which holds when the potential outcomes are uniformly bounded, then $N\\hat V_{OLS}(\\hat\\beta)$ converges in probability to the second limit. The second limit minus the first is\n\\[\n\\frac{(2p-1)(v_1-v_0)}{p(1-p)}+v_1+v_0-2c_{10},\n\\]\nwhere $v_1+v_0-2c_{10}$ is the limiting variance of the unit-level treatment effects. No mean of the potential outcomes appears.\n\nI first show that neither variance depends on the two means. Let $\\bar Y_T$ and $\\bar Y_C$ denote the means of the observed outcomes in the treatment and control groups, and set $S=\\sum_{i=1}^{N}\\hat e_i^{2}$. By (4), the residual $\\hat e_i$ equals $Y_i-\\bar Y_T$ for a treated unit and $Y_i-\\bar Y_C$ for a control unit, and\n\\[\n\\hat V_{OLS}(\\hat\\beta)=\\frac{S}{N-2}\\left(\\frac{1}{M}+\\frac{1}{N-M}\\right).\n\\]\nFix constants $c$ and $d$, and replace $y_{0i}$ by $y_{0i}+c$ and $y_{1i}$ by $y_{1i}+c+d$ for every $i$. For a given assignment, $Y_i$ becomes $Y_i+c+dX_i$. Then $\\bar Y_C$ increases by $c$ and $\\bar Y_T$ by $c+d$. Every residual is therefore unchanged, and I conclude that $S$ and $\\hat V_{OLS}(\\hat\\beta)$ are unchanged for every assignment. Further, $\\hat\\beta$ becomes $\\hat\\beta+d$, so $V(\\hat\\beta)$ is unchanged. The control group mean $\\bar y_0$ has moved by $c$ and the average treatment effect $\\beta$ by $d$.\n\nNext, I compute the two limits. Collecting the coefficients of $\\sigma^2(y_1)$ and $\\sigma^2(y_0)$ in (3), I obtain\n\\[\nV(\\hat\\beta)=\\frac{1}{N-1}\\left(\\frac{N-M}{M}\\,\\sigma^2(y_1)+\\frac{M}{N-M}\\,\\sigma^2(y_0)+2\\sigma(y_1,y_0)\\right).\n\\]\nLet $S_T$ and $S_C$ denote the sums of $\\hat e_i^{2}$ over the treated and the control units, so that $S=S_T+S_C$, and let $\\bar y_{1,T}$ denote the mean of $y_1$ over the treated units. I have $S_T=\\sum_{i:X_i=1}(y_{1i}-\\bar y_1)^2-M(\\bar y_{1,T}-\\bar y_1)^2$ and $\\operatorname{Var}(\\bar y_{1,T})=\\frac{N-M}{M(N-1)}\\,\\sigma^2(y_1)$. Taking expectations over the assignments, and arguing in the same way for the control group, I find\n\\[\nE[S_T]=\\frac{N(M-1)}{N-1}\\,\\sigma^2(y_1),\\qquad E[S_C]=\\frac{N(N-M-1)}{N-1}\\,\\sigma^2(y_0).\n\\]\nInserting these into the formula for $\\hat V_{OLS}(\\hat\\beta)$, I obtain\n\\[\nE\\bigl[\\hat V_{OLS}(\\hat\\beta)\\bigr]=\\frac{N}{(N-1)(N-2)}\\Bigl[(M-1)\\,\\sigma^2(y_1)+(N-M-1)\\,\\sigma^2(y_0)\\Bigr]\\left(\\frac{1}{M}+\\frac{1}{N-M}\\right).\n\\]\nMultiplying the expressions for $V(\\hat\\beta)$ and $E[\\hat V_{OLS}(\\hat\\beta)]$ by $N$ and letting $N\\to\\infty$ with $M/N\\to p$ gives the two limits stated above.\n\nFor the sequence in the table, $\\sigma^2(y_0)=1$, $\\sigma^2(y_1)=a^2$ and $\\sigma(y_1,y_0)=a$ for every $k$, and $p=1/4$. The limits are $\\lim N\\,V(\\hat\\beta)=3a^2+2a+1/3$ and $\\operatorname{plim}N\\hat V_{OLS}(\\hat\\beta)=4a^2/3+4$. In this sequence the convergence in probability can be seen directly. With $r$ the mean of $z$ over the treated units, I have $N\\hat V_{OLS}(\\hat\\beta)=\\frac{N}{N-2}\\bigl[4a^2/3+4-(4a^2/3+4/9)\\,r^2\\bigr]$ and $E[r^2]=3/(N-1)$, and Markov's inequality implies that $r^2\\to 0$ in probability.",
    "evidence": "This correction rests on a derivation, given below, and on an exact counterexample. For each integer $k\\ge 2$ let $N=4k$ and $M=k$, let $z_i=-1$ for $i\\le 2k$ and $z_i=1$ for $i>2k$, and set $y_{0i}=z_i$ and $y_{1i}=az_i+2$ for a fixed $a>0$. The outcomes are bounded, and for every $k$ and every $a$ the control group mean is $0$ and the average treatment effect is $2$. The limiting ratio of $\\hat V_{OLS}(\\hat\\beta)$ to $V(\\hat\\beta)$ is $1$, $4/7$ or $52/25$ for $a=1$, $2$ or $1/2$.\n\\begin{audittable}{llllll}{Limits for the sequence above with treatment fraction $1/4$. The two means are the same in every row.}\n$a$ & Control group mean & Average treatment effect & $\\operatorname{plim} N\\hat V_{OLS}(\\hat\\beta)$ & $\\lim N\\,V(\\hat\\beta)$ & Ratio \\\\\n$1$ & $0$ & $2$ & $16/3$ & $16/3$ & $1$ \\\\\n$2$ & $0$ & $2$ & $28/3$ & $49/3$ & $4/7$ \\\\\n$1/2$ & $0$ & $2$ & $13/3$ & $25/12$ & $52/25$ \\\\\n\\end{audittable}\nExact enumeration of all assignments for $N=8$ and $N=12$ agrees with the finite-sample formulas below. In each of the 744 cases enumerated (every assignment, for the three values of $a$), the shift with $c=7$ and $d=-5$ leaves $\\hat V_{OLS}(\\hat\\beta)$ unchanged. I did not read p.~190 of Freedman (2008b), and I do not assess the attribution to that page here.",
    "problem": "The footnote names two first moments, the control group mean and the average treatment effect, as the features of the outcomes that determine how $\\hat V_{OLS}(\\hat\\beta)$ compares with $V(\\hat\\beta)$ in large samples. Neither variance depends on them. If a constant $c$ is added to every $y_{0i}$ and $c+d$ to every $y_{1i}$, then the control group mean changes by $c$ and the average treatment effect by $d$, while $\\hat V_{OLS}(\\hat\\beta)$, for every assignment, and $V(\\hat\\beta)$ do not change. The comparison depends on the treatment fraction and on second moments: the limiting variances of the two potential outcomes and their limiting covariance. The sentence that the footnote supports, that $\\hat V_{OLS}(\\hat\\beta)$ may be too large or too small when $N\\ne 2M$, is correct.",
    "what_survives": "Theorem 2 and its scaling are untouched. The example confirms the warning that the OLS estimator can overstate or understate the variance, and the warning carries over to the constant-effects estimator because $(N-2)/(N-1)\\to 1$. No estimator, theorem or number in the paper is derived from the footnote."
   },
   "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-E003",
   "work": {
    "arxiv_id": null,
    "doi": "10.1016/j.spl.2011.10.024",
    "title": "On Equivalencies Between Design-Based and Regression-Based Variance Estimators for Randomized Experiments",
    "url": "https://pmaronow.github.io/llm-audit/works/P031/"
   },
   "work_id": "P031"
  },
  {
   "before_review": null,
   "class": "error",
   "date_modified": "2026-10-25",
   "date_published": "2026-10-25",
   "evidence_type": "page_check",
   "exhibits": [
    {
     "alt": "Crop of footnote 1 at the bottom of the page, with the line of text it is attached to. A red box marks the word 'Schwartz' in 'Cauchy-Schwartz inequality'.",
     "caption": "Footnote 1, p. 366 (PDF p. 2). The marked name is misspelled.",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/exhibits/P031-E004.png"
    },
    {
     "alt": "Crop of the reference list from the Cochran entry to the Rosenbaum 2009 entry. Red boxes mark 'ed..' in the Cochran (1977) entry, 'ed..' in the Freedman, Pisani and Purves (1998) entry, the word 'heteroskedastiticy' in the MacKinnon and White (1985) entry, and 'ed..' in the Rosenbaum (2002b) entry.",
     "caption": "References, p. 370 (PDF p. 6). The marked word in the MacKinnon and White entry is misspelled, and each of the three marked abbreviations “ed.” is followed by a second full stop.",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/exhibits/P031-E004-b.png"
    }
   ],
   "formal_release": null,
   "formal_statements": [],
   "headline": "“Cauchy–Schwartz” should read “Cauchy–Schwarz”, “heteroskedastiticy” should read “heteroskedasticity”, and “ed..” should read “ed.” in three reference entries.",
   "id": "P031-E004",
   "location": "Footnote 1, p. 366 (PDF p. 2); References, p. 370 (PDF p. 6)",
   "pdf_page": 2,
   "printed_page": "366",
   "reaches": [],
   "related_entries": [],
   "revisions": [],
   "same_defect_as": [],
   "severity": "Minor",
   "subject": "paper",
   "target_ids": [],
   "text": {
    "as_printed": "\\begin{itemize}\n\\item Footnote 1: ``This is due to $\\sigma^2(y_0)+\\sigma^2(y_1)-2\\sqrt{\\sigma^2(y_0)}\\sqrt{\\sigma^2(y_1)}=(\\sqrt{\\sigma^2(y_0)}-\\sqrt{\\sigma^2(y_1)})^2\\geq 0$, and $2\\sqrt{\\sigma^2(y_0)}\\sqrt{\\sigma^2(y_1)}\\geq 2\\sigma(y_0,y_1)$ by the Cauchy--\\hl{Schwartz} inequality.''\n\\item ``MacKinnon, J.G., White, H., 1985. Some \\hl{heteroskedastiticy}-consistent covariance matrix estimators with improved finite sample properties. Journal of Econometrics 29, 305--325.''\n\\item ``Cochran, W.G., 1977. Sampling Techniques, third \\hl{ed..} John Wiley, New York.''\n\\item ``Freedman, D., Pisani, R., Purves, R., 1998. Statistics, third \\hl{ed..} W.W. Norton, New York.''\n\\item ``Rosenbaum, P.R., 2002b. Observational Studies, second \\hl{ed..} Springer, New York.''\n\\end{itemize}",
    "corrected": "\\begin{itemize}\n\\item Footnote 1: ``\\ldots by the Cauchy--\\hl{Schwarz} inequality.''\n\\item ``MacKinnon, J.G., White, H., 1985. Some \\hl{heteroskedasticity}-consistent covariance matrix estimators \\ldots''\n\\item ``Sampling Techniques, third \\hl{ed.} John Wiley, New York.''\n\\item ``Statistics, third \\hl{ed.} W.W. Norton, New York.''\n\\item ``Observational Studies, second \\hl{ed.} Springer, New York.''\n\\end{itemize}",
    "evidence": "This is a check of the page. The inequality in footnote 1 is the Cauchy--Schwarz bound on a covariance and holds as printed, and the correct spelling ``heteroskedasticity-consistent'' appears in the entry for White (1980) on the same page.",
    "problem": "The name of the inequality and one word of a reference title are misspelled, and in three entries ``ed.'' is followed by a second full stop. The meaning is clear in each case.",
    "what_survives": "Everything else is unaffected, since no statement of the paper depends on these words."
   },
   "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-E004",
   "work": {
    "arxiv_id": null,
    "doi": "10.1016/j.spl.2011.10.024",
    "title": "On Equivalencies Between Design-Based and Regression-Based Variance Estimators for Randomized Experiments",
    "url": "https://pmaronow.github.io/llm-audit/works/P031/"
   },
   "work_id": "P031"
  },
  {
   "before_review": null,
   "class": "clarity_note",
   "date_modified": "2026-10-25",
   "date_published": "2026-10-25",
   "evidence_type": "exact_counterexample",
   "exhibits": [
    {
     "alt": "Crop of the abstract on the first page. A red box marks the words 'equivalent to' in the sentence saying that the Neyman and constant-effects estimators are equivalent to a variant of the White estimator and the homoskedastic OLS estimator, respectively.",
     "caption": "Abstract, p. 365 (PDF p. 1). The marked words state the equivalence of the constant-effects and OLS estimators without the finite-sample factor.",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/exhibits/P031-A001.png"
    },
    {
     "alt": "Crop of the end of the second paragraph of the introduction. A red box marks the words 'We also show that all four of these estimators are equivalent under a balanced design'. The preceding sentence, not marked, contains the words 'subject to a finite-sample scaling coefficient'.",
     "caption": "Introduction, second paragraph, p. 365 (PDF p. 1). The marked sentence follows the one that says “subject to a finite-sample scaling coefficient”.",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/exhibits/P031-A001-b.png"
    }
   ],
   "formal_release": null,
   "formal_statements": [],
   "headline": "The abstract and the balanced-design sentence of the introduction call the estimators equivalent without repeating the finite-sample factor $(N-2)/(N-1)$ of Theorems 2 and 3.",
   "id": "P031-A001",
   "location": "Abstract and Introduction, second paragraph, p. 365 (PDF p. 1)",
   "pdf_page": 1,
   "printed_page": "365",
   "reaches": [],
   "related_entries": [],
   "revisions": [],
   "same_defect_as": [],
   "severity": null,
   "subject": "paper",
   "target_ids": [],
   "text": {
    "as_printed": "\\emph{Abstract.} This paper demonstrates that the randomization-based ``Neyman'' and constant-effects estimators for the variance of estimated average treatment effects are \\hl{equivalent to} a variant of the White ``heteroskedasticity-robust'' estimator and the homoskedastic ordinary least squares (OLS) estimator, respectively.\n\n\\emph{Introduction.} We also show that \\hl{all four of these estimators are equivalent} under a balanced design, suggesting that, in many cases, the choice of variance estimator is irrelevant.",
    "corrected": "\\emph{Abstract.} This paper demonstrates that the randomization-based ``Neyman'' and constant-effects estimators for the variance of estimated average treatment effects are equivalent to a variant of the White ``heteroskedasticity-robust'' estimator and, \\hl{up to the finite-sample factor} $\\hl{(N-2)/(N-1)}$, the homoskedastic ordinary least squares (OLS) estimator, respectively. That is,\n\\[\n\\hat V_{CE}(\\hat\\beta)=\\frac{N-2}{N-1}\\,\\hat V_{OLS}(\\hat\\beta),\n\\]\nwhere $N$ is the number of units.\n\n\\emph{Introduction.} \\hl{After the constant-effects estimator is multiplied by} $\\hl{(N-1)/(N-2)}$, all four of these estimators \\hl{coincide} under a balanced design.",
    "intended_meaning": "The two sentences mean equivalence up to the finite-sample scaling. The sentence before the second one says ``subject to a finite-sample scaling coefficient'', and Theorems 2 and 3 and the Discussion state the factor. Theorem 2 states that $\\hat V_{CE}(\\hat\\beta)=\\frac{N-2}{N-1}\\hat V_{OLS}(\\hat\\beta)$, and Theorem 3 states that $\\frac{N-1}{N-2}\\hat V_{CE}(\\hat\\beta)=\\hat V_{OLS}(\\hat\\beta)=\\hat V_N(\\hat\\beta)=\\hat V_{HC2}(\\hat\\beta)$ when $N=2M$. Both hold as printed. The raw estimates are not all equal. For $N=4$, $M=2$, $X=(1,1,0,0)$ and $Y=(0,2,0,4)$, I find in exact arithmetic that $\\hat V_{CE}(\\hat\\beta)=10/3$ and $\\hat V_{OLS}(\\hat\\beta)=\\hat V_N(\\hat\\beta)=\\hat V_{HC2}(\\hat\\beta)=5$. No theorem or formula changes."
   },
   "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-A001",
   "work": {
    "arxiv_id": null,
    "doi": "10.1016/j.spl.2011.10.024",
    "title": "On Equivalencies Between Design-Based and Regression-Based Variance Estimators for Randomized Experiments",
    "url": "https://pmaronow.github.io/llm-audit/works/P031/"
   },
   "work_id": "P031"
  },
  {
   "before_review": null,
   "class": "error",
   "date_modified": "2026-10-25",
   "date_published": "2026-10-25",
   "evidence_type": "exact_counterexample",
   "exhibits": [
    {
     "alt": "Listing of lines 1 to 9 of the function omni.ate in monospaced type with line numbers. A red box marks line 6, 'prob is assigned genprob(perms)', and line 7, 'ate is assigned estate(Y,Z,prob=prob)'.",
     "caption": "Package ri, file R/omni.ate.R, lines 1–9, typeset from the source file with line numbers added. The marked lines estimate the assignment probabilities from the permutation matrix and use them as weights in the point estimate.",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/exhibits/P031-N002.png"
    },
    {
     "alt": "Listing of lines 19 to 22 of the function omni.ate in monospaced type with line numbers. Red boxes mark line 20, 'distA is assigned gendist(YsA,perms) inside suppressWarnings', and line 22, 'se is assigned Pse(distA)'.",
     "caption": "Package ri, file R/omni.ate.R, lines 19–22, typeset from the source file with line numbers added. The marked lines compute the standard error as the dispersion of the generated distribution.",
     "url": "https://pmaronow.github.io/llm-audit/works/P031/exhibits/P031-N002-b.png"
    }
   ],
   "formal_release": null,
   "formal_statements": [],
   "headline": "With the default approximate permutation matrix under complete randomization, omni.ate weights units by sampled assignment frequencies, so its point estimate and standard error can differ from the difference in means of equation (2) and the square root of expression (5).",
   "id": "P031-N002",
   "location": "R package ri (version 0.9), function omni.ate, file R/omni.ate.R, lines 6–7 and 20–22; no passage of the article",
   "pdf_page": null,
   "printed_page": null,
   "reaches": [],
   "related_entries": [],
   "revisions": [],
   "same_defect_as": [],
   "severity": "Minor",
   "subject": "paper",
   "target_ids": [],
   "text": {
    "as_printed": "File \\texttt{R/omni.ate.R}, lines 6 and 7:\n\n\\texttt{prob <- \\hl{genprob(perms)}}\n\n\\texttt{ate <- estate(Y,Z,\\hl{prob=prob})}\n\nLines 20 and 22:\n\n\\texttt{suppressWarnings(distA <- gendist(YsA,perms))}\n\n\\texttt{se <- Pse(distA)}",
    "corrected": "Under complete randomization the probability of treatment is known to equal $\\hl{M/N}$ for every unit, and \\texttt{genprobexact(Z)} returns it. If \\texttt{omni.ate} passes these probabilities to \\texttt{estate} and to both calls of \\texttt{gendist}, its point estimate is the difference in means $\\hat\\beta$ of equation (2). The standard error computed from a sampled distribution remains approximate. The standard error of the paper is the \\hl{closed form}\n\\[\n\\sqrt{\\frac{N}{N-1}\\,\\frac{N}{M(N-M)}\\,\\sigma^2(\\tilde y_0)},\\qquad \\tilde y_{0i}=Y_i-X_i\\hat\\beta .\n\\]\nProbabilities supplied by the user for other designs should be kept.",
    "evidence": "This correction rests on an exact counterexample and on runs of the unmodified package. For $N=16$, $M=8$, $Y=(1,0,\\ldots,0)$ and units 1--8 treated, the difference in means of equation (2) is $1/8$ and the variance of expression (5) is $7/480$. One admissible sample of 10,000 assignments makes the package's estimate exactly $1/5$, and two runs with fixed seeds return about $0.1272$ and $0.1263$. With all 12,870 assignments enumerated, the package returns $1/8$ and, to floating-point accuracy, a squared standard error of $7/480$.",
    "problem": "Under complete randomization, when a design has more than 10,000 possible assignments and \\texttt{maxiter} is left at its default, \\texttt{genperms} announces an approximate method and returns 10,000 random assignments. The function \\texttt{omni.ate} then estimates each unit's probability of treatment from those draws and uses the estimates as inverse-probability weights, although under complete randomization the probability is known to be $M/N$. The reported \\texttt{ate} can then differ from the difference in means of equation (2) and can change from call to call for the same data. The reported \\texttt{se} is the dispersion of the sampled distribution, not the square root of expression (5).",
    "what_survives": "The equations of the paper and Theorem 2 are untouched, and no number in the article comes from the package. Under complete randomization, with all assignments enumerated, the package agrees with equation (2) and expression (5)."
   },
   "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-N002",
   "work": {
    "arxiv_id": null,
    "doi": "10.1016/j.spl.2011.10.024",
    "title": "On Equivalencies Between Design-Based and Regression-Based Variance Estimators for Randomized Experiments",
    "url": "https://pmaronow.github.io/llm-audit/works/P031/"
   },
   "work_id": "P031"
  }
 ],
 "lean": {
  "applicable": true,
  "guide": "https://github.com/pmaronow/llm-audit-lean/blob/b9e9df44831afed4f2b8f63be5c0cc9169a5fda4/docs/works/P031.md",
  "repository": "https://github.com/pmaronow/llm-audit-lean",
  "targets": [
   {
    "declarations": [
     {
      "claim_revision_id": "catalog:0ed05de99284ed7b0b91b888a3a06037a82b28a777c487035a89768bf8677004",
      "conditional_on": [],
      "credit_reason": "Every real observed vector is realizable by taking both fixed potential-outcome schedules equal to that vector, so quantifying directly over Y loses no cases.",
      "credit_status": "ok",
      "fidelity_status_baseline": "ok",
      "lean_name": "AronowAudit.P031.hc2_eq_neyman",
      "manifest_use": "used",
      "named_axioms": [],
      "says": null,
      "source": "https://github.com/pmaronow/llm-audit-lean/blob/b9e9df44831afed4f2b8f63be5c0cc9169a5fda4/AronowAudit/P031/P031_Variance.lean#L186",
      "status": "proved",
      "support_scope": "historical declaration",
      "used_in_solution": true
     }
    ],
    "formalization": {
     "claim_revision_id": "catalog:0ed05de99284ed7b0b91b888a3a06037a82b28a777c487035a89768bf8677004",
     "crosswalk_url": "../../data/lean-crosswalk.json#/targets/P031-T1",
     "decision": "whole",
     "release_id": "sap-2026-11-08-assured-release",
     "target_id": "P031-T1"
    },
    "html": {
     "body": "<p>Theorem 1, p. 367 (PDF p. 3), proof p. 368 (PDF p. 4). For every admissible assignment and observed outcome vector, HC2 equals Neyman&#x27;s estimator.</p>",
     "headline": "Theorem 1",
     "location": "p. 367 (PDF p. 3); proof on p. 368 (PDF p. 4)"
    },
    "id": "P031-T1",
    "text": {
     "body": "Theorem 1, p. 367 (PDF p. 3), proof p. 368 (PDF p. 4). For every admissible assignment and observed outcome vector, HC2 equals Neyman's estimator.",
     "headline": "Theorem 1",
     "location": "p. 367 (PDF p. 3); proof on p. 368 (PDF p. 4)"
    },
    "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-T1"
   },
   {
    "declarations": [
     {
      "claim_revision_id": "catalog:06cd025683444fc7a32c7c84988353949147ed67bc1693055f68eba3b9bdb8fc",
      "conditional_on": [],
      "credit_reason": "This certifies expectation conservativeness, with no assertion of assignmentwise conservativeness or confidence-interval coverage.",
      "credit_status": "ok",
      "fidelity_status_baseline": "ok",
      "lean_name": "AronowAudit.P031.hc2_conservative",
      "manifest_use": "used",
      "named_axioms": [],
      "says": null,
      "source": "https://github.com/pmaronow/llm-audit-lean/blob/b9e9df44831afed4f2b8f63be5c0cc9169a5fda4/AronowAudit/P031/P031_Variance.lean#L797",
      "status": "proved",
      "support_scope": "historical declaration",
      "used_in_solution": true
     }
    ],
    "formalization": {
     "claim_revision_id": "catalog:06cd025683444fc7a32c7c84988353949147ed67bc1693055f68eba3b9bdb8fc",
     "crosswalk_url": "../../data/lean-crosswalk.json#/targets/P031-T2",
     "decision": "whole",
     "release_id": "sap-2026-11-08-assured-release",
     "target_id": "P031-T2"
    },
    "html": {
     "body": "<p>Corollary 1, p. 368 (PDF p. 4), displays p. 367 (PDF p. 3). Over uniform fixed-size assignments, expected HC2 is at least the actual randomization variance.</p>",
     "headline": "Corollary 1",
     "location": "p. 368 (PDF p. 4); supporting displays on p. 367 (PDF p. 3)"
    },
    "id": "P031-T2",
    "text": {
     "body": "Corollary 1, p. 368 (PDF p. 4), displays p. 367 (PDF p. 3). Over uniform fixed-size assignments, expected HC2 is at least the actual randomization variance.",
     "headline": "Corollary 1",
     "location": "p. 368 (PDF p. 4); supporting displays on p. 367 (PDF p. 3)"
    },
    "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-T2"
   },
   {
    "declarations": [
     {
      "claim_revision_id": "catalog:dbb2a34ac066c27b5e155a3a3cf25b5e21dd3706064b571d974e215a87c993d8",
      "conditional_on": [],
      "credit_reason": "The imputation imposes a hypothesized effect equal to the estimate; actual effects need not be constant.",
      "credit_status": "ok",
      "fidelity_status_baseline": "ok",
      "lean_name": "AronowAudit.P031.scaled_ols_eq_constantEffects",
      "manifest_use": "used",
      "named_axioms": [],
      "says": null,
      "source": "https://github.com/pmaronow/llm-audit-lean/blob/b9e9df44831afed4f2b8f63be5c0cc9169a5fda4/AronowAudit/P031/P031_Variance.lean#L265",
      "status": "proved",
      "support_scope": "historical declaration",
      "used_in_solution": true
     }
    ],
    "formalization": {
     "claim_revision_id": "catalog:dbb2a34ac066c27b5e155a3a3cf25b5e21dd3706064b571d974e215a87c993d8",
     "crosswalk_url": "../../data/lean-crosswalk.json#/targets/P031-T3",
     "decision": "whole",
     "release_id": "sap-2026-11-08-assured-release",
     "target_id": "P031-T3"
    },
    "html": {
     "body": "<p>Theorem 2, p. 369 (PDF p. 5). Multiplying OLS variance by (N-2)/(N-1) gives the constant-effects imputation variance.</p>",
     "headline": "Theorem 2",
     "location": "p. 369 (PDF p. 5)"
    },
    "id": "P031-T3",
    "text": {
     "body": "Theorem 2, p. 369 (PDF p. 5). Multiplying OLS variance by (N-2)/(N-1) gives the constant-effects imputation variance.",
     "headline": "Theorem 2",
     "location": "p. 369 (PDF p. 5)"
    },
    "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-T3"
   },
   {
    "declarations": [
     {
      "claim_revision_id": "catalog:7d51e5759a712f173626b9380b0d4274148896b70a3be804ef8acf1d69f1a960",
      "conditional_on": [],
      "credit_reason": "The CE scaling factor is part of the conclusion and must not be dropped when describing the four estimators as equal.",
      "credit_status": "ok",
      "fidelity_status_baseline": "ok",
      "lean_name": "AronowAudit.P031.balanced_equivalences",
      "manifest_use": "used",
      "named_axioms": [],
      "says": null,
      "source": "https://github.com/pmaronow/llm-audit-lean/blob/b9e9df44831afed4f2b8f63be5c0cc9169a5fda4/AronowAudit/P031/P031_Variance.lean#L283",
      "status": "proved",
      "support_scope": "historical declaration",
      "used_in_solution": true
     }
    ],
    "formalization": {
     "claim_revision_id": "catalog:7d51e5759a712f173626b9380b0d4274148896b70a3be804ef8acf1d69f1a960",
     "crosswalk_url": "../../data/lean-crosswalk.json#/targets/P031-T4",
     "decision": "whole",
     "release_id": "sap-2026-11-08-assured-release",
     "target_id": "P031-T4"
    },
    "html": {
     "body": "<p>Theorem 3, p. 369 (PDF p. 5), proof p. 370 (PDF p. 6). In a balanced design the scaled constant-effects, OLS, Neyman, and HC2 estimators agree.</p>",
     "headline": "Theorem 3",
     "location": "p. 369 (PDF p. 5); proof on p. 370 (PDF p. 6)"
    },
    "id": "P031-T4",
    "text": {
     "body": "Theorem 3, p. 369 (PDF p. 5), proof p. 370 (PDF p. 6). In a balanced design the scaled constant-effects, OLS, Neyman, and HC2 estimators agree.",
     "headline": "Theorem 3",
     "location": "p. 369 (PDF p. 5); proof on p. 370 (PDF p. 6)"
    },
    "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-T4"
   },
   {
    "declarations": [
     {
      "claim_revision_id": "source-claim-import-2026-11-08:P031-T5:1",
      "conditional_on": [],
      "credit_reason": "Historical normality-only refutation does not address the repaired cited-regime effective claim. Preserve its original ok judgment as history; withdraw current claim credit. It is absent from the new manifest lists; no proof-dependency use is inferred.",
      "credit_status": "wrong_credit",
      "fidelity_status_baseline": "ok",
      "lean_name": "AronowAudit.P031.Wave1.printed_large_sample_contract_refuted",
      "manifest_use": "not_listed",
      "named_axioms": [],
      "says": null,
      "source": "https://github.com/pmaronow/llm-audit-lean/blob/b9e9df44831afed4f2b8f63be5c0cc9169a5fda4/AronowAudit/P031/Wave1/LargeSampleRefutation.lean#L29",
      "status": "counterexample_proved",
      "support_scope": "withdrawn",
      "used_in_solution": false
     }
    ],
    "formalization": {
     "claim_revision_id": "source-claim-import-2026-11-08:P031-T5:1",
     "crosswalk_url": "../../data/lean-crosswalk.json#/targets/P031-T5",
     "decision": "restricted",
     "release_id": "sap-2026-11-08-assured-release",
     "target_id": "P031-T5"
    },
    "html": {
     "body": "<p>pp. 367-368 (PDF pp. 3-4), including footnote 2. The cited regular finite-population regime gives the nonnegative finite Neyman bias, exact HC2 equality, asymptotic robust equivalences, and conservative normal-interval coverage. Restriction: the statement assumes strictly positive limiting N-times-true-variance contrast D; it does not formalize the D=0 coverage case. Allocation and moment conditions come from the cited regime, not from routine measure-theoretic defaults. A separate normality-only counterexample is retained as auxiliary evidence.</p>",
     "headline": "Unnumbered large-sample coverage statement (Section 3), its extension to HC2 after Corollary 1, and footnote 2",
     "location": "p. 367 (PDF p. 3); p. 368 (PDF p. 4), including footnote 2"
    },
    "id": "P031-T5",
    "text": {
     "body": "pp. 367-368 (PDF pp. 3-4), including footnote 2. The cited regular finite-population regime gives the nonnegative finite Neyman bias, exact HC2 equality, asymptotic robust equivalences, and conservative normal-interval coverage. Restriction: the statement assumes strictly positive limiting N-times-true-variance contrast D; it does not formalize the D=0 coverage case. Allocation and moment conditions come from the cited regime, not from routine measure-theoretic defaults. A separate normality-only counterexample is retained as auxiliary evidence.",
     "headline": "Unnumbered large-sample coverage statement (Section 3), its extension to HC2 after Corollary 1, and footnote 2",
     "location": "p. 367 (PDF p. 3); p. 368 (PDF p. 4), including footnote 2"
    },
    "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-T5"
   },
   {
    "declarations": [
     {
      "claim_revision_id": "source-claim-import-2026-11-08:P031-T6:1",
      "conditional_on": [],
      "credit_reason": "Historical positive variance-direction result is related partial evidence, without the repaired universal cited-regime Neyman/HC2 coverage contrast. It is absent from the new manifest lists; no actual proof-dependency use or nonuse is inferred.",
      "credit_status": "narrower",
      "fidelity_status_baseline": "ok",
      "lean_name": "AronowAudit.P031.Wave1.ols_ce_may_be_too_small_or_large_proof",
      "manifest_use": "not_listed",
      "named_axioms": [],
      "says": null,
      "source": "https://github.com/pmaronow/llm-audit-lean/blob/b9e9df44831afed4f2b8f63be5c0cc9169a5fda4/AronowAudit/P031/Wave1/Gap/GLP027P016P031P031B1.lean#L335",
      "status": "proved",
      "support_scope": "limited related evidence",
      "used_in_solution": false
     }
    ],
    "formalization": {
     "claim_revision_id": "source-claim-import-2026-11-08:P031-T6:1",
     "crosswalk_url": "../../data/lean-crosswalk.json#/targets/P031-T6",
     "decision": "restricted",
     "release_id": "sap-2026-11-08-assured-release",
     "target_id": "P031-T6"
    },
    "html": {
     "body": "<p>Section 4, p. 369 (PDF p. 5). Within the cited regular finite-population regime, unbalanced OLS and CE variance estimates can have either sign of asymptotic error and can yield undercoverage. Neyman and HC2 retain conservative normal-interval coverage. Restriction: the positive contrast assumes strictly positive limiting N-times-true-variance D and does not formalize the D=0 case. A separate normality-only counterexample is retained as auxiliary evidence. The once-unhatted CE quantity is the imputation estimator.</p>",
     "headline": "Unnumbered statements on the homoskedastic OLS and constant-effects estimators when N is not 2M (Section 4)",
     "location": "p. 369 (PDF p. 5)"
    },
    "id": "P031-T6",
    "text": {
     "body": "Section 4, p. 369 (PDF p. 5). Within the cited regular finite-population regime, unbalanced OLS and CE variance estimates can have either sign of asymptotic error and can yield undercoverage. Neyman and HC2 retain conservative normal-interval coverage. Restriction: the positive contrast assumes strictly positive limiting N-times-true-variance D and does not formalize the D=0 case. A separate normality-only counterexample is retained as auxiliary evidence. The once-unhatted CE quantity is the imputation estimator.",
     "headline": "Unnumbered statements on the homoskedastic OLS and constant-effects estimators when N is not 2M (Section 4)",
     "location": "p. 369 (PDF p. 5)"
    },
    "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-T6"
   },
   {
    "declarations": [
     {
      "claim_revision_id": "catalog:93b8391d1f0f059f427f493bdf84d6dc5c86234f341ca826f11369120d849d2a",
      "conditional_on": [],
      "credit_reason": "This is an exact witness against the untilded proof equality, and does not refute Theorem 2.",
      "credit_status": "ok",
      "fidelity_status_baseline": "ok",
      "lean_name": "AronowAudit.P031.printed_covariance_counterexample",
      "manifest_use": "used",
      "named_axioms": [],
      "says": null,
      "source": "https://github.com/pmaronow/llm-audit-lean/blob/b9e9df44831afed4f2b8f63be5c0cc9169a5fda4/AronowAudit/P031/P031_Variance.lean#L1237",
      "status": "counterexample_proved",
      "support_scope": "historical declaration",
      "used_in_solution": true
     }
    ],
    "formalization": {
     "claim_revision_id": "catalog:93b8391d1f0f059f427f493bdf84d6dc5c86234f341ca826f11369120d849d2a",
     "crosswalk_url": "../../data/lean-crosswalk.json#/targets/P031-T7",
     "decision": "whole",
     "release_id": "sap-2026-11-08-assured-release",
     "target_id": "P031-T7"
    },
    "html": {
     "body": "<p>first sentence of the proof of Theorem 2, p. 369 (PDF p. 5). The specified four-unit assignment has both imputed variances 5/2 and original potential-outcome covariance 23/2, refuting the printed covariance equality.</p>",
     "headline": "Proof of Theorem 2, first sentence, as printed",
     "location": "p. 369 (PDF p. 5)"
    },
    "id": "P031-T7",
    "text": {
     "body": "first sentence of the proof of Theorem 2, p. 369 (PDF p. 5). The specified four-unit assignment has both imputed variances 5/2 and original potential-outcome covariance 23/2, refuting the printed covariance equality.",
     "headline": "Proof of Theorem 2, first sentence, as printed",
     "location": "p. 369 (PDF p. 5)"
    },
    "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-T7"
   },
   {
    "declarations": [
     {
      "claim_revision_id": "catalog:957da3e23ba7e4d65d076bf73ef9b06ff65e6c6c6295f9a7bfa6fbf938075df2",
      "conditional_on": [],
      "credit_reason": "The corrected target, rather than the false untilded printed proof step, is the assigned component.",
      "credit_status": "ok",
      "fidelity_status_baseline": "ok",
      "lean_name": "AronowAudit.P031.corrected_theorem_two_proof",
      "manifest_use": "used",
      "named_axioms": [],
      "says": null,
      "source": "https://github.com/pmaronow/llm-audit-lean/blob/b9e9df44831afed4f2b8f63be5c0cc9169a5fda4/AronowAudit/P031/P031_Variance.lean#L1292",
      "status": "proved",
      "support_scope": "historical declaration",
      "used_in_solution": true
     }
    ],
    "formalization": {
     "claim_revision_id": "catalog:957da3e23ba7e4d65d076bf73ef9b06ff65e6c6c6295f9a7bfa6fbf938075df2",
     "crosswalk_url": "../../data/lean-crosswalk.json#/targets/P031-T8",
     "decision": "whole",
     "release_id": "sap-2026-11-08-assured-release",
     "target_id": "P031-T8"
    },
    "html": {
     "body": "<p>corrected proof of Theorem 2, p. 369 (PDF p. 5). Every link of the corrected imputed-moment, residual-sum, and scaled-OLS proof chain holds.</p>",
     "headline": "Proof of Theorem 2, corrected",
     "location": "p. 369 (PDF p. 5)"
    },
    "id": "P031-T8",
    "text": {
     "body": "corrected proof of Theorem 2, p. 369 (PDF p. 5). Every link of the corrected imputed-moment, residual-sum, and scaled-OLS proof chain holds.",
     "headline": "Proof of Theorem 2, corrected",
     "location": "p. 369 (PDF p. 5)"
    },
    "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-T8"
   },
   {
    "declarations": [
     {
      "claim_revision_id": "catalog:a39dadb1c9720257e73c249700588c193411fbbc29878d638987e470f27e4092",
      "conditional_on": [],
      "credit_reason": "The corrected target restores the CE hat and the sample-variance notation without changing the mathematical identity.",
      "credit_status": "ok",
      "fidelity_status_baseline": "ok",
      "lean_name": "AronowAudit.P031.corrected_theorem_three_proof",
      "manifest_use": "used",
      "named_axioms": [],
      "says": null,
      "source": "https://github.com/pmaronow/llm-audit-lean/blob/b9e9df44831afed4f2b8f63be5c0cc9169a5fda4/AronowAudit/P031/P031_Variance.lean#L1342",
      "status": "proved",
      "support_scope": "historical declaration",
      "used_in_solution": true
     }
    ],
    "formalization": {
     "claim_revision_id": "catalog:a39dadb1c9720257e73c249700588c193411fbbc29878d638987e470f27e4092",
     "crosswalk_url": "../../data/lean-crosswalk.json#/targets/P031-T9",
     "decision": "whole",
     "release_id": "sap-2026-11-08-assured-release",
     "target_id": "P031-T9"
    },
    "html": {
     "body": "<p>corrected proof of Theorem 3, p. 370 (PDF p. 6). Every link of the balanced-design chain holds, with the CE hat and sample-variance notation restored.</p>",
     "headline": "Proof of Theorem 3, corrected",
     "location": "p. 370 (PDF p. 6)"
    },
    "id": "P031-T9",
    "text": {
     "body": "corrected proof of Theorem 3, p. 370 (PDF p. 6). Every link of the balanced-design chain holds, with the CE hat and sample-variance notation restored.",
     "headline": "Proof of Theorem 3, corrected",
     "location": "p. 370 (PDF p. 6)"
    },
    "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-T9"
   },
   {
    "declarations": [
     {
      "claim_revision_id": "catalog:09cecd529551b564b9284d0ca8112a577ec7cb579a217cff95b7403ff51bfa56",
      "conditional_on": [],
      "credit_reason": "{'source': 'adjudication', 'decision': 'rejected', 'what': 'At AronowAudit/P031/P031_Variance.lean:2376, the conjunction supplies all three specified families, their common allocation and first moments, the distinct probability limits 1, 4/7 and 52/25, and universal invariance of both variances under the specified shifts; FootnoteVarianceWitness is expanded at line 2278. This matches the asymptotic counterexample and variance-invariance component identified by the row, without restricting its populations or assignments. The exact finite formulas, N=8 enumeration and intercept/residual identities are separate supporting components of the expanded target, so their absence from this declaration does not omit a conclusion of the credited component. The additional CE probability limit strengthens the witness harmlessly.'}",
      "credit_status": "ok",
      "fidelity_status_baseline": "ok",
      "lean_name": "AronowAudit.P031.footnote_three_counterexample",
      "manifest_use": "used",
      "named_axioms": [],
      "says": null,
      "source": "https://github.com/pmaronow/llm-audit-lean/blob/b9e9df44831afed4f2b8f63be5c0cc9169a5fda4/AronowAudit/P031/P031_Variance.lean#L2056",
      "status": "counterexample_proved",
      "support_scope": "historical declaration",
      "used_in_solution": true
     }
    ],
    "formalization": {
     "claim_revision_id": "catalog:09cecd529551b564b9284d0ca8112a577ec7cb579a217cff95b7403ff51bfa56",
     "crosswalk_url": "../../data/lean-crosswalk.json#/targets/P031-T10",
     "decision": "whole",
     "release_id": "sap-2026-11-08-assured-release",
     "target_id": "P031-T10"
    },
    "html": {
     "body": "<p>counterexample to footnote 3, p. 369 (PDF p. 5), parts (a)–(c). Shifting all control outcomes by c and all treatment outcomes by c+d shifts the control mean and population effect by c and d. Assignment by assignment, it adds c+dX to the observed vector, shifts the intercept and treatment estimate by c and d, and preserves every residual, OLS variance estimate, and actual randomization variance. For N=4k, M=k, k≥2, the balanced sign schedules y0=z, y1=a z+2, a=1,2,1/2, share allocation 1/4, control mean 0 and effect 2. Their moments and exact N-times-variance and OLS formulas hold, with the treated sign mean r satisfying E[r²]=3/(N-1). Their true leading limits are 16/3,49/3,25/12, their OLS probability and expectation limits are 16/3,28/3,13/3, and their OLS/actual-variance probability-limit ratios are 1,4/7,52/25. At k=2 the printed outcome vectors give 28 assignments, actual variances 16/21,7/3,25/84, expected OLS estimates 16/21,8/7,2/3 and expectation/variance ratios 1,24/49,56/25. Thus allocation and the two first moments do not determine the variance relation. The usual measure-theoretic conditions are assumed.</p>",
     "headline": "Footnote 3, as printed",
     "location": "p. 369 (PDF p. 5), footnote 3"
    },
    "id": "P031-T10",
    "text": {
     "body": "counterexample to footnote 3, p. 369 (PDF p. 5), parts (a)–(c). Shifting all control outcomes by c and all treatment outcomes by c+d shifts the control mean and population effect by c and d. Assignment by assignment, it adds c+dX to the observed vector, shifts the intercept and treatment estimate by c and d, and preserves every residual, OLS variance estimate, and actual randomization variance. For N=4k, M=k, k≥2, the balanced sign schedules y0=z, y1=a z+2, a=1,2,1/2, share allocation 1/4, control mean 0 and effect 2. Their moments and exact N-times-variance and OLS formulas hold, with the treated sign mean r satisfying E[r²]=3/(N-1). Their true leading limits are 16/3,49/3,25/12, their OLS probability and expectation limits are 16/3,28/3,13/3, and their OLS/actual-variance probability-limit ratios are 1,4/7,52/25. At k=2 the printed outcome vectors give 28 assignments, actual variances 16/21,7/3,25/84, expected OLS estimates 16/21,8/7,2/3 and expectation/variance ratios 1,24/49,56/25. Thus allocation and the two first moments do not determine the variance relation. The usual measure-theoretic conditions are assumed.",
     "headline": "Footnote 3, as printed",
     "location": "p. 369 (PDF p. 5), footnote 3"
    },
    "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-T10"
   },
   {
    "declarations": [
     {
      "claim_revision_id": "catalog:9b757199f55b3bb9ab4ac3b294c49752a04d15fb339e2007c45b22279b70ff1a",
      "conditional_on": [],
      "credit_reason": "{'source': 'adjudication', 'decision': 'rejected', 'what': 'At AronowAudit/P031/Wave1/FootnoteThreeComplete.lean:10, the hypotheses and deterministic limits match the corrected claim, including the difference and treatment-effect-variance limits, and the conclusion includes the optional probability/ratio limits and exact variance shift invariance. ArmSecondMomentsConverge, defined in P031/P031_Variance.lean:2417, expresses consistency of the centered arm sample variances, the second moments used by the OLS formula. This loses no case under the usual finite raw-second-moment reading either: interior allocation and convergent population variances give sample-mean consistency, and convergent finite raw second moments then give centered sample-variance consistency. Uniform boundedness and positive leading variance are used only where the corrected claim places them, so the note does not identify a material restriction.'}",
      "credit_status": "ok",
      "fidelity_status_baseline": "ok",
      "lean_name": "AronowAudit.P031.Wave1.footnote_three_complete",
      "manifest_use": "used",
      "named_axioms": [],
      "says": null,
      "source": "https://github.com/pmaronow/llm-audit-lean/blob/b9e9df44831afed4f2b8f63be5c0cc9169a5fda4/AronowAudit/P031/Wave1/FootnoteThreeComplete.lean#L10",
      "status": "proved",
      "support_scope": "historical declaration",
      "used_in_solution": true
     },
     {
      "claim_revision_id": "catalog:9b757199f55b3bb9ab4ac3b294c49752a04d15fb339e2007c45b22279b70ff1a",
      "conditional_on": [],
      "credit_reason": "{'source': 'adjudication', 'decision': 'rejected', 'what': 'At AronowAudit/P031/Wave1/FootnoteThreeProbability.lean:18, the theorem proves precisely the stochastic component: uniformly bounded outcomes imply arm-variance consistency, that consistency gives the scaled OLS probability limit, and positive leading true variance gives the ratio limit. These are conclusions and conditions expressly present in the corrected claim, rather than extra assumptions imported from the row description. The centered second-moment formulation in P031/P031_Variance.lean:2417 preserves the ordinary finite raw-second-moment cases as well, because sample means are consistent under the stated allocation and population-variance limits. The deterministic and shift clauses belong to the separately credited complete declaration and need not be repeated in this stochastic component.'}",
      "credit_status": "ok",
      "fidelity_status_baseline": "ok",
      "lean_name": "AronowAudit.P031.Wave1.footnote_three_probability_complete",
      "manifest_use": "used",
      "named_axioms": [],
      "says": null,
      "source": "https://github.com/pmaronow/llm-audit-lean/blob/b9e9df44831afed4f2b8f63be5c0cc9169a5fda4/AronowAudit/P031/Wave1/FootnoteThreeProbability.lean#L18",
      "status": "proved",
      "support_scope": "historical declaration",
      "used_in_solution": true
     }
    ],
    "formalization": {
     "claim_revision_id": "catalog:9b757199f55b3bb9ab4ac3b294c49752a04d15fb339e2007c45b22279b70ff1a",
     "crosswalk_url": "../../data/lean-crosswalk.json#/targets/P031-T11",
     "decision": "restricted",
     "release_id": "sap-2026-11-08-assured-release",
     "target_id": "P031-T11"
    },
    "html": {
     "body": "<p>corrected footnote 3, p. 369 (PDF p. 5). Interior allocation and convergent population second moments give the corrected variance, expected-OLS, bias, treatment-effect-variance, conditional probability, and positive-denominator ratio limits, with bounded-outcome sufficiency and exact shifts. Sample second-moment convergence means consistency of both centered arm sample variances.</p>",
     "headline": "Footnote 3, corrected",
     "location": "p. 369 (PDF p. 5), footnote 3"
    },
    "id": "P031-T11",
    "text": {
     "body": "corrected footnote 3, p. 369 (PDF p. 5). Interior allocation and convergent population second moments give the corrected variance, expected-OLS, bias, treatment-effect-variance, conditional probability, and positive-denominator ratio limits, with bounded-outcome sufficiency and exact shifts. Sample second-moment convergence means consistency of both centered arm sample variances.",
     "headline": "Footnote 3, corrected",
     "location": "p. 369 (PDF p. 5), footnote 3"
    },
    "url": "https://pmaronow.github.io/llm-audit/works/P031/#P031-T11"
   }
  ]
 },
 "missing_sources": [],
 "reproduction": {
  "agreement": "not_applicable",
  "status": "not_applicable",
  "targets": []
 },
 "summary": "The paper asks how design-based variance estimators for the difference in means in a completely randomized experiment relate to regression estimators. It shows by direct algebra that the Neyman estimator equals the HC2 heteroskedasticity-robust estimator (Theorem 1), that the constant-effects estimator equals $(N-2)/(N-1)$ times the homoskedastic OLS estimator (Theorem 2), and that all four agree under a balanced design after that rescaling (Theorem 3). 4 entries are classified as errors (4 Minor), and 2 are clarity notes; 1 item remains undetermined and 2 are outside the scope of my review. No finding is Moderate or above, and none changes a theorem.",
 "what_was_checked": "I checked the following results, which held up subject to the qualifications below.\n\\begin{itemize}\n\\item The estimator of equation (2) is unbiased, and equation (3) equals the variance of $\\hat\\beta$ over all assignments, by exact enumeration in small designs.\n\\item The finite-population variance estimators of p.~366 are unbiased, and the bound of footnote 1 holds.\n\\item Equation (4), the expectation and the bias of the Neyman estimator displayed on p.~367, and the leverages hold as printed, and the HR and HC2 formulas reduce as stated.\n\\item Theorem 1 with its proof, and Corollary 1, hold in the stated finite design.\n\\item Expression (5) equals the variance of the difference in means over all assignments under a constant effect equal to $\\hat\\beta$.\n\\item Theorems 2 and 3 hold, and their proofs are correct once the misprints of \\fid{P031-E002} are repaired.\n\\item For $N\\ne 2M$ the OLS and constant-effects estimators can be too large or too small relative to $V(\\hat\\beta)$, and exact examples show both.\n\\item Footnote 2 holds under the coverage conditions of \\fid{P031-E001}, with both arms growing.\n\\item Under complete randomization with all assignments enumerated, \\texttt{omni.ate} in the \\texttt{ri} package returns the difference in means and a squared standard error equal to $(N-2)/(N-1)$ times the value of the OLS estimator, on the data sets tested.\n\\end{itemize}\nMy checks had the following limits. Pages A32--A34 of Freedman, Pisani and Purves (1998) and journal p.~190 of Freedman (2008b) were not read, and Angrist and Pischke (2009), MacKinnon and White (1985) and Gadbury (2001) were not consulted, so I could not determine whether every cited passage contains the statement attributed to it. I read but did not test \\texttt{invert.ci}, \\texttt{genperms.custom}, or the blocked and clustered branches of \\texttt{genperms} and \\texttt{genprobexact}. I tested \\texttt{estlate} and \\texttt{resresplot} for auxiliary checks of their help pages against the code; those checks do not test implementations of the paper's method. The paper has no tables or figures, and there were no reported numbers to recompute. I had no supplement, correction or replication file other than the article and the package. That this audit records no further corrections is not a finding that the rest of the paper is correct.",
 "work": {
  "arxiv_id": null,
  "audit_complete": true,
  "authors": [
   "Cyrus Samii",
   "P. M. Aronow"
  ],
  "category": "Articles - Theory and Methodology",
  "citation": "Cyrus Samii and P. M. Aronow (2012). On Equivalencies Between Design-Based and Regression-Based Variance Estimators for Randomized Experiments. Statistics and Probability Letters 82(2):365–370.",
  "doi": "10.1016/j.spl.2011.10.024",
  "edition": {
   "pages_in_audited_file": 6,
   "sha256": "84ffa871a17a9dd592c72b1620521d50c37a9a8aa6282bc919f870e0a8bd59d9",
   "source_url": "https://doi.org/10.1016/j.spl.2011.10.024",
   "venue": "Statistics and Probability Letters",
   "year": "2012"
  },
  "id": "P031",
  "later_materials": null,
  "title": "On Equivalencies Between Design-Based and Regression-Based Variance Estimators for Randomized Experiments",
  "type": "Journal article",
  "url": "https://pmaronow.github.io/llm-audit/works/P031/",
  "venue": "Statistics and Probability Letters",
  "year": "2012"
 }
}