Sykes, Circuit Judge.

We are again asked to decide whether an aspect of Indiana's alcohol regulation system violates the Equal Protection Clause. Two years ago we upheld an Indiana law that prohibits grocery and convenience stores from selling chilled beer. See Indiana Petroleum Marketers & Convenience Store Ass'n v. Cook, 808 F.3d 318 (7th Cir. 2015). In this case Monarch Beverage Company challenges a feature of Indiana's "prohibited interest" law that separates beer and liquor wholesaling by prohibiting beer wholesalers from holding an interest in a liquor-distribution permit. See IND. CODE §§ 7.1-3-3-19, 7.1-5-9-3, 7.1-5-9-6. Monarch contends that this component of the prohibited-interest law lacks a rational basis. A district judge rejected this argument and upheld the law. We affirm that judgment. Indiana's policy of separating beer and liquor wholesaling survives review for rationality.

I. Background

Indiana's alcohol regulatory scheme, like that of many other states, divides the market along two dimensions: three tiers of the distribution chain (producers, wholesalers, and retailers) and three kinds of alcohol (beer, liquor, and wine). A permit is required to do business in any part of this market. See id. §§ 7.1-3-2-1 to -5-5 (beer producer, wholesaler, and retailer permits); 7.1-3-7-1 to -10-13 (liquor); 7.1-3-12-1 to -15-3 (wine). With limited exceptions, Indiana prohibits any person who holds a permit in one tier of the distribution chain from also holding an interest in a permit in another tier. For example, anyone holding an interest in a beer producer's permit may not also hold an interest in a beer wholesaler's permit. See id. § 7.1-5-9-2. And anyone who holds an interest in any kind of retailing permit is generally prohibited from having any interest in a manufacturer's or wholesaler's permit of any type. See id. § 7.1-5-9-10(a). (Small-scale brewers and distillers are exempt from this restriction. See id. § 7.1-5-9-10(b).)

In addition to restricting permits across the vertical tiers of the distribution chain, Indiana also restricts the issuance of permits within the wholesaling tier by type of alcohol. The law allows some wholesaling permits to be combined: a beer wholesaler can get a permit to wholesale wine; a liquor wholesaler can also get a permit to wholesale wine. See id. § 7.1-3-13-1. But the prohibited-interest law requires the separation of beer and liquor wholesaling: a beer wholesaler may not acquire an interest in a liquor-wholesaling permit and vice versa.1 See id. § 7.1-5-9-3, -6. This aspect of Indiana's regulatory scheme is apparently unique to the state.

Monarch holds permits to wholesale both beer and wine and would like to expand its business to include liquor. Indiana doesn't allow that combination of permits, so Monarch sued members of Indiana's Alcohol and Tobacco Commission to invalidate the law. (The defendants are sued in their official capacities, so we'll refer to them collectively as "Indiana.") The suit alleges that this aspect of the prohibited-interest law facially discriminates against beer wholesalers in violation of the Fourteenth Amendment's equal-protection guarantee. U.S. CONST. amend. XIV, § 1.

On cross-motions for summary judgment, the district court rejected Monarch's challenge and upheld the law. The judge's decision proceeds along two lines of reasoning. First, she ruled that the equal-protection claim failed at the starting gate because Monarch could not identify a similarly situated class of persons that receives better treatment under the statute. Second, she applied rational-basis review and upheld the law as a rational regulatory measure. Monarch appealed.

Meanwhile, separate litigation against the Commission is ongoing in state court on a related question testing how the prohibited-interest law applies to corporate alcohol distributors with overlapping ownership interests. While Monarch's appeal in this case has been pending, a Marion County judge issued a ruling rejecting the Commission's interpretation of the statute. Spirited Sales, LLC v. Indiana Alcohol & Tobacco Comm'n, No. 49D01-1502-PL-5520 (Marion Cty. Super. Ct. Aug. 24, 2016). The case is now before the Indiana Supreme Court, which heard argument on February 23, 2017. Though the cases involve the same statutory provisions, the question here is distinct and seems unlikely to be affected by the outcome of Spirited Sales, so we proceed to decision.

II. Discussion

We review a summary judgment de novo. Life Plans, Inc. v. Sec. Life of Denver Ins. Co., 800 F.3d 343, 348-49 (7th Cir. 2015). Indiana's prohibited-interest law doesn't draw lines based on race or any other suspect classification, it doesn't burden a fundamental right, and it raises no federalism concerns under the Supreme Court's dormant commerce-clause doctrine. So Monarch's equal-protection challenge triggers only the most lenient form of judicial review: the law is valid unless it lacks a rational basis. Fitzgerald v. Racing Ass'n of Cent. Iowa, 539 U.S. 103, 107, 123 S.Ct. 2156, 156 L.Ed.2d 97 (2003); Indiana Petroleum Marketers, 808 F.3d at 322. This deferential standard of review is a notoriously "heavy legal lift for the challenger[ ]." Indiana Petroleum Marketers, 808 F.3d at 322.

Monarch devotes considerable attention to the origins of Indiana's prohibited-interest laws, arguing that the "uncontested historical evidence suggests that the prohibition was enacted to protect and promote a patronage system that operated to the benefit of state and local politicians." That may be true; Indiana doesn't put much effort into contesting Monarch's historiography. But any disagreement about the genesis of this law can be left unresolved. The Supreme Court has made it clear that under rational-basis review, the challenger must "negative every conceivable basis" that might support the challenged law, and "it is entirely irrelevant ... whether the conceived reason for the challenged distinction actually motivated the legislature." FCC v. Beach Commc'ns, Inc., 508 U.S. 307, 314-15, 113 S.Ct. 2096, 124 L.Ed.2d 211 (1993).

The parties also dispute, this time more vigorously, whether certain threshold difficulties doom Monarch's claim from the start. Indiana contends that we don't need to decide whether the prohibited-interest law has a rational basis because (1) Monarch has not identified a similarly situated class of persons that is treated more favorably; and (2) Monarch chose to be a beer wholesaler and therefore cannot "complain of unequal treatment compared with those who made a different choice within the same system of limited permits." These contentions are mistaken; no threshold obstacles to rational-basis review exist here.

It is of course true, as the Supreme Court has often said, that the Equal Protection Clause "is essentially a direction that all persons similarly situated should be treated alike." City of Cleburne v. Cleburne Living Ctr., 473 U.S. 432, 439, 105 S.Ct. 3249, 87 L.Ed.2d 313 (1985) (citing Plyler v. Doe, 457 U.S. 202, 216, 102 S.Ct. 2382, 72 L.Ed.2d 786 (1982)). Relying entirely on "class of one" equal-protection cases, Indiana argues that the prohibited-interest law is not subject to any judicial review unless Monarch first identifies a similarly situated comparator class that receives preferential treatment under the statute.

Indiana's reliance on the class-of-one line of cases is misplaced. In that kind of equal-protection litigation, the plaintiff doesn't challenge a statute or ordinance but argues instead that a public official (or group of officials) has treated him differently than other persons similarly situated for an illegitimate or irrational reason.2 The difference in treatment can take the form of selective enforcement of a criminal law, LaBella Winnetka, Inc. v. Village of Winnetka, 628 F.3d 937 (7th Cir. 2010), or selective withholding of government benefits or services, Village of Willowbrook v. Olech, 528 U.S. 562, 120 S.Ct. 1073, 145 L.Ed.2d 1060 (2000) (failure to provide water service); Harvey v. Town of Merrillville, 649 F.3d 526 (7th Cir. 2011) (ignoring complaints about mosquito-infested pond); Srail v. Village of Lisle, 588 F.3d 940 (7th Cir. 2009) (failure to provide water service); RJB Props., Inc. v. Bd. of Educ. of City of Chi., 468 F.3d 1005 (7th Cir. 2006) (denial of government contract to provide janitorial services); Vision Church v. Village of Long Grove, 468 F.3d 975 (7th Cir. 2006) (denial of special land-use application); Smith v. City of Chicago, 457 F.3d 643 (7th Cir. 2006) (failure to reimburse attorney's fees); Racine Charter One, Inc. v. Racine Unified Sch. Dist., 424 F.3d 677 (7th Cir. 2005) (failure to bus students).

In litigation of that type, if the plaintiff can't identify a similarly situated person or group for comparison purposes, it's normally unnecessary to take the analysis any further; the claim simply fails. Harvey, 649 F.3d at 532. It's easy to see why. The equal-protection guarantee is "concerned with governmental classifications that `affect some groups of citizens differently than others.'" Engquist v. Oregon Dep't of Agric., 553 U.S. 591, 601, 128 S.Ct. 2146, 170 L.Ed.2d 975 (2008) (quoting McGowan v. Maryland, 366 U.S. 420, 425, 81 S.Ct. 1101, 6 L.Ed.2d 393 (1961)). In a class-of-one equal-protection case, it may not be clear that the challenged governmental action entails any classification at all. Identifying a similarly situated comparator is a way to show that disparate treatment in fact has occurred and sets "a clear standard against which departures, even for a single plaintiff, [can] be readily assessed." Id. at 602, 128 S.Ct. 2146. In contrast, where (as here) the plaintiff challenges a statute or ordinance that by its terms imposes regulatory burdens on a specific class of persons (in this case, beer distributors), there's no need to identify a comparator; the classification appears in the text of the statute itself.

Indiana also contends that Monarch cannot challenge the prohibited-interest law because it knew the consequences of becoming a beer wholesaler — namely, that doing so would put liquor distribution off limits — and chose to become one anyway. This argument is hard to square with our decision in Indiana Petroleum Marketers. There we reviewed Indiana's law prohibiting grocery and convenience stores from selling chilled beer. 808 F.3d at 322-25. Though no one thought to mention it, the beer sellers were no doubt aware of the "no cold beer" restriction before they applied for a beer dealer's permit, yet we reviewed the claim on the merits. Monarch's situation is no different.

Indiana insists that Indiana Petroleum Marketers is distinguishable because the ban on cold-beer sales was "ancillary" to the statutorily defined class, while the law separating beer and liquor distribution is part of the class definition. It's not at all clear why this distinction (if it is one) should make any difference in the analysis. Indiana cites no cases to support this proposed ancillary/definitional dichotomy. It's not even clear that the restriction Monarch is challenging is definitional rather than ancillary.

In an effort to illustrate the distinction and explain why it matters, Indiana points to laws prohibiting fishing without a license and says that a system in which only fishing license holders may fish can't be challenged on equal-protection grounds because the difference in treatment (license holders v. nonlicense holders) precisely defines the class. We're not so sure about that conclusion, but the analogy is inapt in any event. Monarch is not challenging Indiana's law that prohibits liquor wholesaling without a permit; it is challenging the law prohibiting beer wholesalers from obtaining liquor-wholesaling permits. This restriction is not inherent in the tripartite permitting scheme; after all, wine wholesalers are allowed to have liquor-wholesaling permits.

The rule Indiana proposes is unsupported and unworkable. It's also wholly unjustified. The only demand the Equal-Protection Clause places on a nonsuspect statutory classification is that it be rational. We see no reason to limit application of this basic constitutional requirement as Indiana proposes.

Moving to the merits of Monarch's claim, Indiana's prohibited-interest law comes to us with "a strong presumption of validity." Beach Commc'ns, 508 U.S. at 314, 113 S.Ct. 2096. Monarch must shoulder the heavy burden "to negative every conceivable basis which might support it." Id. at 315, 113 S.Ct. 2096 (quoting Lehnhausen v. Lake Shore Auto Parts Co., 410 U.S. 356, 364, 93 S.Ct. 1001, 35 L.Ed.2d 351 (1973)). And Indiana does not need to present actual evidence to support its proffered rationale for the law, which can be "based on rational speculation unsupported by evidence or empirical data." Id.

In the district court, Indiana offered three reasons for its policy choice to separate beer and liquor wholesaling; it repeats those justifications here. The first is essentially a temperance rationale: Indiana argues that it has a legitimate interest in discouraging alcohol consumption, especially the consumption of hard liquor, which has higher alcohol content. The separation of beer and liquor wholesaling rationally serves this interest by making distribution more expensive, which in turn increases prices for consumers.3 Second, Indiana points to its interest in maintaining tax revenue, arguing that separating the beer- and liquor-wholesaling markets helps to maintain the number of independent liquor wholesalers that in turn pay alcohol excise taxes. Finally, Indiana relies on its interest in market stability, arguing that market upheaval would ensue if the prohibited-interest law is invalidated.

The first of these reasons is stronger than the others. Indeed, Indiana makes little effort to defend the tax-revenue rationale other than to note that it was endorsed by the district judge. The market-upheaval justification is briefly outlined in Indiana's brief but not really defended.4 So we'll limit our discussion to the temperance rationale.

Everyone agrees that reducing liquor consumption is a legitimate governmental interest. Monarch argues that it's irrational to think that the prohibited-interest law furthers this interest in any meaningful way. We disagree. It's certainly not the most direct way of achieving this aim (a tax is the most direct way), but it's hardly irrational to think that separating beer and liquor wholesaling is likely to impose higher distribution costs than if beer and liquor wholesaling were combined. That, in turn, keeps liquor prices higher, with the salutary corresponding effect of reducing consumption.

More specifically, rational regulators could believe that Indiana's beer wholesalers — with their robust franchise protections and existing distribution infrastructures (warehouses, drivers, relationships with retailers, etc.) — would vigorously compete with liquor wholesalers if allowed to hold permits to distribute both kinds of alcohol.5 Rational regulators might also believe that this increased competition could drive down liquor prices for consumers and thereby increase consumption. See, e.g., Christopher T. Conlon & Nirupama Rao, The Price of Liquor is Too Damn High: Alcohol Taxation and Market Structure 17 (Kilts Booth Marketing series, Paper No. 2-009, 2015) (https://papers. ssrn.com/sol3/papers.cfm?abstract_id= 2610118) (finding that requiring wholesalers to publicly list prices "promote[s] non-competitive pricing behavior among wholesalers, potentially leading to higher prices"); Alexander C. Wagenaar, et al., Effects of Beverage Alcohol Price and Tax Levels on Drinking: A Meta-analysis of 1003 Estimates from 112 Studies, 104 ADDICTION 179 (2009) (concluding that higher prices reduce consumption).

Monarch's response is to argue that there are far more direct and effective ways for Indiana to increase liquor prices and thus reduce consumption — most obviously, through taxation.6 Monarch insists that the attenuated connection between the prohibited-interest law and Indiana's temperance objective and the obvious availability of a more direct alternative call the rationality of this law into question.

The Supreme Court has on limited occasions been willing to infer irrationality from the availability of an alternative policy that more directly and effectively furthers the government's asserted interest. For example, in United States Department of Agriculture v. Moreno, 413 U.S. 528, 93 S.Ct. 2821, 37 L.Ed.2d 782 (1973), the Court invalidated a statute that prohibited households of unrelated individuals from receiving food stamps. The government justified the law on fraud-prevention grounds. Applying rational-basis review, the Court rejected that rationale because other statutory provisions were aimed "specifically at the problems of fraud, ... [and the] existence of these provisions necessarily casts considerable doubt upon the proposition that the [challenged provision] could rationally have been intended to prevent those very same abuses." Id. at 536-37, 93 S.Ct. 2821; see also City of Cleburne, 473 U.S. at 446, 105 S.Ct. 3249 (relying on Moreno, 413 U.S. at 535, 93 S.Ct. 2821, and explaining that the government "may not rely on a classification whose relationship to an asserted goal is so attenuated as to render the distinction arbitrary or irrational").

The Supreme Court's broader rational-basis jurisprudence, however, points in the opposite direction. The Court has repeatedly said that "[t]he fact that other means are better suited to the achievement of governmental ends ... is of no moment under rational basis review." Tuan Anh Nguyen v. INS, 533 U.S. 53, 77, 121 S.Ct. 2053, 150 L.Ed.2d 115 (2001); see also Gregory v. Ashcroft, 501 U.S. 452, 473, 111 S.Ct. 2395, 115 L.Ed.2d 410 (1991) ("[A] State `does not violate the Equal Protection Clause merely because the classifications made by its laws are imperfect.'" (quoting Massachusetts Bd. of Ret. v. Murgia, 427 U.S. 307, 316, 96 S.Ct. 2562, 49 L.Ed.2d 520 (1976))). Against this backdrop, Moreno and City of Cleburne are better understood as extraordinary rather than exemplary rational-basis cases. The Supreme Court has never invalidated an economic regulation on rational-basis review because a more direct or effective policy alternative was available. Neither have we, and Monarch has given us no reason to change course.

Indiana's law separating beer and liquor wholesaling is rationally related to the state's interest in encouraging temperance; that it serves this purpose indirectly does not make the law irrational.

AFFIRMED.

Easterbrook, Circuit Judge, concurring in the judgment.

I agree with my colleagues that Indiana's law is constitutionally valid. Monarch says that state law cuts down competition, injuring consumers. But so did the laws in Exxon Corp. v. Governor of Maryland, 437 U.S. 117, 98 S.Ct. 2207, 57 L.Ed.2d 91 (1978); New Orleans v. Dukes, 427 U.S. 297, 96 S.Ct. 2513, 49 L.Ed.2d 511 (1976); and The Slaughter-House Cases, 83 U.S. (16 Wall.) 36, 21 S.Ct. 394 (1873). The Supreme Court has facilitated anticompetitive legislation by creating an exception to antitrust principles when states curtail competition as part of a regulatory program. See Parker v. Brown, 317 U.S. 341, 63 S.Ct. 307, 87 S.Ct. 315 (1943), and its successors. State limits on the extent of competition thus have a long pedigree, and regulation of the liquor industry receives an additional boost from § 2 of the Twenty-First Amendment.

My colleagues say that Indiana prevails because its law has a rational basis. That's the standard under the Equal Protection Clause for classifications that do not entail race or other suspect criteria. But like the district judge I do not see any classification. Indiana does not treat any person differently from any other. No one, directly or through a corporation or other business, can have all three alcohol wholesale licenses. That may be sensible or silly, but it does not discriminate. Beer wholesalers can get one other license type, just as wine or liquor wholesalers may, but not two others. A beer-liquor license combination is forbidden to everyone by Ind. Code § 7.1-5-9-3 and § 7.1-5-9-6.

Monarch says that this understanding of discrimination would eliminate rational-basis review of statuses (such as beer wholesaler) that people assume voluntarily, and so it would. My colleagues think this dispositive against Indiana's position, but I do not.

Monarch's demand that the liquor-distribution scheme be adequately justified even though it does not treat any person differently from any other person is a substantive-due-process claim in disguise. And the Supreme Court has held that only persons whose "fundamental" rights have been abridged can maintain substantive-due-process claims. See Washington v. Glucksberg, 521 U.S. 702, 117 S.Ct. 2258, 138 L.Ed.2d 772 (1997). No one would be so bold as to contend that holding three kinds of alcohol wholesale licenses simultaneously is a fundamental right. Litigants should not be allowed to evade the limits on substantive due process by characterizing substantive objections to state-law rules as equal-protection claims.

Back in 1868, when the Fourteenth Amendment was ratified, the sort of argument Monarch presents would not have been seen as either an equal-protection or a substantive-due-process theory. It would have been conceived as a request for relief under the Privileges or Immunities Clause. A bare majority of the Court in Slaughter-House drained that clause of force, but calls to overrule Slaughter-House have not succeeded. See McDonald v. Chicago, 561 U.S. 742, 130 S.Ct. 3020, 177 L.Ed.2d 894 (2010). Recasting a privileges-or-immunities theory as an equal-protection theory has the benefit (for plaintiffs) of evading both Slaughter-House and Glucksberg, but it lacks a constitutional footing.

Perhaps the Supreme Court has given this portfolio to the Equal Protection Clause despite the lack of historical provenance and textual support. That's what my colleagues think. If they are right, judges of the courts of appeals must fall into line. But the Justices consistently write about the Equal Protection Clause as if it operates on discriminatory classifications. Because I don't see any classification at all in Indiana's scheme, I would treat Monarch's contention as a substantive objection that fails at the threshold under Slaughter-House and Glucksberg.