For the purposes of the summary judgment motion that we review today, several tobacco companies (Tobacco) conceded that they conspired to mislead the public as to the health risks of smoking. As the district court2 did, we consider whether three Minnesota nonprofit health maintenance organizations (HMOs) have presented sufficient evidence of causation of harm and damages to recoup certain health-care costs of their members that resulted from tobacco use. For the reasons expressed below, we affirm the summary judgment entered in favor of Tobacco on the HMOs’ damages claims, but we remand for further consideration of the HMOs’ suit for injunctive relief.
I.
This case involves the question of what a plaintiff must show to prove causation of harm, injury in fact, and damages under three Minnesota misrepresentation statutes (unlawful trade practices, see Minn. Stat. § 325D.13, false statement in advertising, see Minn.Stat. § 325F.67, and prevention of consumer fraud, see Minn.Stat. § 325F.69, subd. 1) and under Minnesota’s antitrust statutes (Minn.Stat. § 325D.49-.66). We have the advantage of some recent guidance from the Minnesota Supreme Court on the question.
Following Tobacco’s motion to dismiss for failure to state a claim upon which relief can be granted, see Fed. R. Civ. Proc. 12(b)(6), the district court certified two questions to the Minnesota Supreme Court. Only the second question is currently relevant, namely, whether the HMOs must “prove individual purchaser reliance on the defendants’ statements or conduct in order to be eligible for relief in the form of damages under [the misrepresentation statutes],” Group Health Plan, Inc. v. Philip Morris Inc., 621 N.W.2d 2, 6 (Minn.2001). The Minnesota Supreme Court responded that although proof of “traditional common law reliance” was not necessary for a private plaintiff to recover damages, “causation remains an element of such a claim.” Id. at 13. Although the Minnesota Supreme Court declined to delineate exactly what constituted proof of causation, it stated that the relevant statutes require “some legal nexus between the injury and the defendants’ wrongful conduct” before a recovery may be had, id. at 14 (internal quotation omitted), and that it was the HMOs’ burden to prove that nexus, id. at 15. The court also directed the district court to look to cases under the Lanham Act, 15 U.S.C. § 1125(a), for guidance, because those cases, in its view, “reflect the appropriate sensitivity to the remedial goals of the statute that are paralleled in the [misrepresentation] statutes at issue here.” Id. at 15 n. 11.
As the district court recognized, the requisite proof of the “legal nexus between *757the injury and the defendants’ wrongful conduct” to recover damages entails proof of causation of harm, injury in fact, and damages resulting from Tobacco’s conceded actions. The district court held that the HMOs’ evidence of causation and damages was insufficient to raise a genuine issue of material fact and thus granted Tobacco summary judgment on the damages claims. See Group Health Plan, Inc. v. Philip Morris Inc., 188 F.Supp.2d 1122, 1126 (D.Minn.2002). We affirm this part of the judgment of the district court because we conclude that the HMOs have not made out a submissible case on the issue of damages.
II.
A.
To determine what evidence will support an award of damages under the Minnesota misrepresentation statutes, we look to Lanham Act cases, as the Minnesota Supreme Court has indicated we should. We have held that before a case under that act can proceed to a jury, the district court “ ‘must ensure that the record adequately supports all items of damages claimed and establishes a causal link between the damages and the defendant’s conduct, lest the award become speculative or violate section 35(a)’s prohibition against punishment.’ ” Porous Media Corp. v. Pall Corp., 110 F.3d 1329, 1336 (8th Cir.1997) (quoting ALPO Petfoods, Inc. v. Ralston Purina Co., 913 F.2d 958, 969 (D.C.Cir.1990)); see also Xoom, Inc. v. Imageline, Inc., 323 F.3d 279, 286 (4th Cir.2003). A damage figure set “arbitrarily or through pure guesswork is impermissible.” Broan Mfg. Co. v. Associated Distribs., Inc., 923 F.2d 1232, 1236 (6th Cir.1991) (internal quotations omitted); see also BASF Corp. v. Old World Trading Co., 41 F.3d 1081, 1096 (7th Cir.1994). Before damages are awarded, we require “ ‘substantial evidence in the record to permit a factfinder to draw reasonable inferences and make a fair and reasonable assessment of the amount of damages.’ ” Broan, 923 F.2d at 1236 (quoting Grantham & Mann, Inc. v. American Safety Prods., Inc., 831 F.2d 596, 602 (6th Cir.1987)); see BASF, 41 F.3d at 1095; cf. Cardinal Consulting Co. v. Circo Resorts, Inc., 297 N.W.2d 260, 267 (Minn.1980).
As for the proof required for an award of damages under Minnesota antitrust law, we observe that “Minnesota courts have consistently held that Minnesota antitrust law is to be interpreted consistently with the federal courts’ construction of federal antitrust law.” State by Humphrey v. Alpine Air Prods., 490 N.W.2d 888, 894 (Minn.Ct.App.1992), aff'd 500 N.W.2d 788 (Minn.1993). As we have indicated with respect to federal antitrust law, “‘[o]nce causation of damages has been established, the amount of damages may be determined by a just and reasonable estimate as long as the jury verdict is not the product of speculation or guess work.’” Amerinet, Inc. v. Xerox Corp., 972 F.2d 1483, 1494 (8th Cir.1992), cert. denied, 506 U.S. 1080, 113 S.Ct. 1048, 122 L.Ed.2d 356 (1993) (quoting MCI Communications Corp. v. AT &T Co., 708 F.2d 1081, 1161 (7th Cir.1983), cert. denied, 464 U.S. 891, 104 S.Ct. 234, 78 L.Ed.2d 226 (1983)); see also Admiral Theatre Corp. v. Douglas Theatre Co., 585 F.2d 877, 893 (8th Cir.1978). We believe that a “fair and reasonable” estimate and a “just and reasonable” one amount to one and the same thing, and thus we hold that the required showings under the misrepresentation statutes and the antitrust statutes are identical.
B.
As the district court noted, the HMOs “have only one expert, Dr. [Jeffrey] Harris, who purports to provide the necessary *758causal link between Defendants’ alleged misconduct and Plaintiffs’ claimed damages.” Group Health Plan, 188 F.Supp.2d at 1130. The district court, however, excluded Dr. Harris’s testimony as inadmissible under Daubert v. Merrell Dow Pharm., Inc., 509 U.S. 579, 113 S.Ct. 2786, 125 L.Ed.2d 469 (1993), because it was “speculative, inconsistent, and therefore unreliable.” Group Health Plan, 188 F.Supp.2d. at 1131. We review the application of Daubert for an abuse of discretion. United States v. Bahena, 223 F.3d 797, 809 (8th Cir.2000), cert. denied, 531 U.S. 1181, 121 S.Ct. 1163, 148 L.Ed.2d 1023 (2001).
The HMOs’ allegations of conspiracy are of two sorts: Tobacco conspired to conceal the truth about the adverse health effects of smoking, and Tobacco conspired to refrain from developing safer tobacco products. Dr. Harris, an economics professor at the Massachusetts Institute of Technology and a treating physician at Massachusetts General Hospital, postulated a “coun-terfactual” world in which smoking would have been safer and fewer people would have smoked because Tobacco would not have so conspired. He utilized “the well-accepted doctrine of attributional-risk theory” to calculate what the HMOs’ health care expenditures attributable to smoking would have been in this counterfactual world. See Group Health Plan, 188 F.Supp.2d. at 1132. The damages to the HMOs would equal the difference between current expenditures attributable to smoking and those that would have occurred in the counterfactual world.
To measure how much safer smoking would have become, Dr. Harris sought to determine the rate at which Tobacco’s introduction of less hazardous products would have increased absent the alleged misconduct, something he calls the “retardation-of-innovation effect.” To measure how many fewer people would have smoked, Dr. Harris sought to determine how the prevalence of smoking rates would have changed over time if there had been no concealment of health-related information, both in terms of the rate at which individuals began smoking (initiation rates) and of the rate at which they quit (quit rates), something he calls the “disinformation effect.” The overall decline in the HMOs’ expenditures attributable to smoking in this counterfactual world is based on a composite of these effects and their actual expenditures today.
Regarding the “retardation-of-innovation effect,” Dr. Harris posited that the conspiracy hampered the rate of innovation by a factor of two-and-a-half. To reach this conclusion, Dr. Harris assumed that the relative risk to smoking adhered to a simple proportional decay formula, and then estimated how a coefficient in that logarithmic formula would have changed absent the conspiracy. In doing so, he pointed to facts such as the one that the average yield of tar in a cigarette had dropped from 37 milligrams to 12 milligrams from 1953 to 1994, estimating that this drop would have been achievable in no more than twelve to sixteen years had Tobacco spent more money on researching and developing safer products. (Dr. Harris noted that “the cigarette industry’s actual research-and-development spending per dollar of sales during 1953 to 1980 was less than one-quarter of that of the chemical industry and less than one-sixth of that of the pharmaceutical industry during the same period.” He then attempted to estimate how long it would have taken to achieve and market the drop in tar had Tobacco spent comparable amounts on research and development). The district court noted that this analysis was unduly speculative, particularly “Dr. Harris’s bald speculation about the connection between money and innovation.” Id. at 1133.
*759Regarding the “disinformation effect,” Dr. Harris estimated that initiation rates for smoking would have declined by nine percent annually for approximately the last fifty years and that four-and-a-half percent of smokers would have quit annually (as opposed to the real world rate of two to four percent a year). As for initiation rates, Dr. Harris noted that while those rates for young men appeared to be dropping in the 1950s and 1960s, they rose among young women from 1967 to 1974 because of advertising that targeted them. He theorized that Tobacco’s success in recruiting new smokers was attributable to “the disinformation campaign promulgated jointly by Defendants; the failure of Defendants to disclose what they knew about the additive effects of nicotine; and the concerted use of lifestyle advertising aimed at youth, especially young women.” As for quit rates, Dr. Harris based his estimations on surveys and studies pertaining to the impact of several current anti-smoking campaigns on such rates.
The district court criticized the estimations pertaining to initiation rates as being nothing but an “inspired guess,” noting that “[w]hile it is possible that the decline in initiation rates was slowed by Defendants’ misconduct, it is equally possible that [that decline was] slowed by a host of other sociological factors.” Id. at 1134. Further, the district court found that the quit-rate estimations were faulty because the anti-smoking campaigns entailed more than simply providing, better health information and thus the “surveys and studies do not focus on the disinformation effect of Defendants’ alleged misconduct” and were “irrelevant to the issue of causation.” Id.
The district court also found Dr. Harris’s methodology to be internally inconsistent because it failed to account for “the relationship between the innovation effect and the information effect in his counter-factual world.” Id. In particular, the court criticized Dr, Harris for not considering that if “improved safety was communicated to consumers, the decline in initiation rates might well slow and quit rates might well fall.” Id. In the district court’s view, therefore, Dr. Harris’s expert report was simply too flawed and speculative to be admitted. Id.
The HMOs concede that Dr. Harris’s report involves some speculation, but they argue that the need to speculate is inherent in long-duration conspiracy cases because plaintiffs cannot actually undo the conspiracy and see what would have happened if it had not existed. They point out that Dr. Harris derived his various estimations from real-life examples and data points and argue that this is the best that can be expected. Any deficiencies, they contend, go to the weight to be given to the report and not to its admissibility, cf. Hurst v. United States, 882 F.2d 306, 311 (8th Cir.1989), and doubts about the admissibility of expert testimony should be resolved in favor of its admission, see Clark by Clark v. Heidrick, 150 F.3d 912, 915 (8th Cir.1998). They call our attention to Dr. Harris’s eminent qualifications and publication record, and the fact that every other court that has considered the admissibility of Dr. Harris’s testimony under Daubert has admitted it. See, e.g., Falise v. American Tobacco Co., 107 F.Supp.2d 200, 205-06 (E.D.N.Y.2000).
Tobacco responds by pointing to many of the same flaws and speculative estimations that the district court did, arguing that the total amount of speculation here is clearly beyond any reasonable limit. It also directs our attention to comments from a Canadian trial court that were highly critical of Dr. Harris’s credibility and notes that no version of Dr. Harris’s analysis on this issue has ever been pub*760lished or submitted to other experts for review outside the litigation context.
There is no doubt, in our estimation, that Dr. Harris’s expert testimony-entails a great deal of speculation, for although his estimations are oriented in real-world examples and data points, his use of them often involves inferences that approach leaps of faith. Cf. Glastetter v. Novartis Pharm. Corp., 252 F.3d 986, 991 (8th Cir.2001) (per curiam). But the Dau-bert inquiry does not end there, for while the cases are legion that assert that expert testimony is inadmissible when it is based on speculative assumptions, see, e.g., J.B. Hunt Transport, Inc. v. General Motors Corp., 243 F.3d 441, 444 (8th Cir.2001); Boucher v. U.S. Suzuki Motor Corp., 73 F.3d 18, 21-22 (2d Cir.1996), that does not mean that testimony must be excluded if an expert occasionally speculates (which is inevitable). What is required is that when experts “testify in court they adhere to the same standards of intellectual rigor that are demanded in their professional work.” Rosen v. Ciba-Geigy Corp., 78 F.3d 316, 319 (7th Cir.1996) (Posner, J.), cert. denied, 519 U.S. 819, 117 S.Ct. 73, 136 L.Ed.2d 33 (1996). Although courts cast their assessment of how much speculation is permissible in various verbal forms, their conclusions in cases involving coun-terfactual estimations essentially come down to this: A certain amount of speculation is necessary, an even greater amount is permissible (and goes to the weight of the testimony), but too much is fatal to admission. Cf. United States v. Cavely, 318 F.3d 987, 997-98 (10th Cir.2003), cert. denied, — U.S.-, 123 S.Ct. 2653, 156 L.Ed.2d 659 (2003); Amorgianos v. National R.R. Passenger Corp., 303 F.3d 256, 270 (2d Cir.2002); Joy v. Bell Helicopter Textron, Inc., 999 F.2d 549, 569-70 (D.C.Cir.1993).
This formulation of the inquiry may be accurate but it is not too helpful in any particular case. But it is critical to bear in mind that the district court is the “gatekeeper,” and we owe significant deference to its determination that expert testimony is excessively speculative. See Peitzmeier v. Hennessy Ind., Inc., 97 F.3d 293, 296-97 (8th Cir.1996), cert. denied, 520 U.S. 1196, 117 S.Ct. 1552, 137 L.Ed.2d 701 (1997). Even if we believe that we might have come to a different conclusion as an original matter from the one that the district court did, we can reverse only if “we are convinced that the District Court made a clear error of judgment” on the basis of the record before it. See Bahena, 223 F.3d at 809. When, as here, the essence of the appeal is merely that the district court chose too strict a threshold, we will be hardpressed to conclude that such an error exists.
Having carefully reviewed the record and Dr. Harris’s expert report, we believe that the issue is closer than the district court thought, for Dr. Harris’s work is thorough, sophisticated, and often well-grounded in the relevant scientific literature. But we are nonetheless unable to conclude that the district court committed a clear error of judgment in excluding the testimony, for predictions like the estimated nine percent annual decline in initiation rates strike us as inspired guesses at best.
We note, moreover, that excessive speculation is not the only (or most significant) difficulty that we have with Dr. Harris’s testimony. That testimony also is inconsistent with one of the main premises underlying the HMOs’ theory of conspiratorial liability, namely, that Tobacco fraudulently marketed “low tar” and “light” cigarettes as allegedly healthier alternatives to normal cigarettes, while knowing that they were not safer because smokers would find ways to compensate *761for the decreased nicotine levels (such as puffing more frequently, increasing the duration of smoke inhalation, smoking more cigarettes per day, smoking cigarettes to a shorter length, and pinching filters to decrease their effectiveness). Dr. Harris’s calculations regarding the “retardation-of-innovation effect” are predicated on the belief that, absent the conspiracy, smoking would have become safer because low-tar cigarettes would have been on the market sooner and smokers would have switched to lower-tar brands, a proposition that was directly contrary to the HMOs’ theory of the case.
While we recognize that a proponent may call a witness to .testify on its behalf and not endorse everything that the witness says, see, e.g., United States v. Logan, 121 F.3d 1172, 1174-75 (8th Cir.1997), we believe that the disconnect between Dr. Harris’s work and the HMOs’ theory of liability weighs heavily against the admission of his testimony under Dau-bert because it undermines the existence of a “legal nexus between the injury and the defendants’ wrongful conduct” and thus does not properly “fit” the HMOs’ case. Cf. Amorgianos, 303 F.3d at 270. Based on all the appropriate considerations, we conclude that the district court did not abuse its discretion in excluding Dr. Harris’s testimony.3
Because the HMOs do not have any other evidence demonstrating the amount of damages caused by Tobacco’s alleged misconduct, a factfinder in this case would have to act arbitrarily to set a damage amount. We thus conclude that the HMOs’ proof of damages is insufficient to allow them to proceed to trial on their damages claims.
C.
The HMOs argue, however, that it is Tobacco that is obligated to differentiate between damages caused by the alleged misconduct and lawful or innocent causes of their injury, relying both on an Eighth Circuit antitrust case, National Farmers’ Org., Inc. v. Associated Milk Producers, Inc., 850 F.2d 1286 (8th Cir.1988), cert. denied, 489 U.S. 1081, 109 S.Ct. 1535, 103 L.Ed.2d 840 (1989), and on the Minnesota “indivisible injury” doctrine. We disagree for the reasons that follow.
In National Farmers, the plaintiff had produced evidence that could serve as a “yardstick” of the amount of damages caused by the defendants’ antitrust violations, but this evidence did not account for exactly which parts of the defendants’ al*762leged misconduct caused which part of the damages. National Farmers, 850 F.2d at 1297, 1307. As part of an explanation that a plaintiff needed only to “present evidence as to the amount of its damages sufficient to allow the finder of fact to make a just and reasonable estimate [of damages],” id. at 1306-07, we said that even if on remand some of the alleged misconduct turned out not to be an antitrust violation, the “yardstick” estimate would still suffice; that was so because “the fact that the [defendants’] illegal conspiracy was composed of lawful and unlawful conduct so tightly intertwined as to make it difficult to determine which portion of the damages claimed were caused by the unlawful conduct should not diminish the recovery.” Id. at 1307. We went on to observe that the district court “should recognize that the harmful consequences of certain unlawful conduct may have been exacerbated by otherwise lawful conduct. In such a situation, the fact that lawful conduct contributed to additional injury should not prohibit recovery for that injury.” Id. As we believe is readily apparent, this passage from National Farmers simply means that a “yardstick” estimate can be “just and reasonable” even if it does not “prove with precision” which damages were caused by which aspects of the alleged misconduct. See id. at 1306. More importantly, we do not interpret National Farmers as relieving the HMOs of the duty to set forth a “yardstick” estimate of the damages caused by Tobacco’s alleged misconduct in the first place.
The HMOs submit that their total health care costs attributable to smoking is an acceptable “yardstick,” but this argument strains credulity because selling tobacco is not a strict liability activity. The HMOs’ primary “yardstick” was Dr. 'Harris’s expert testimony, but that, as we explained above, is simply out of the case.
The Minnesota indivisible injury rule does not help the HMOs either. “The single indivisible injury rule can be traced back to Flaherty v. Northern Pac. Ry. Co., 39 Minn. 328, 40 N.W. 160 (1888), and holds that tortfeasors whose separate negligent acts operate together to cause damage to another are each liable for the whole amount of the resulting damage.” Morlock v. St. Paul Guardian Ins. Co., 650 N.W.2d 154, 164 (Minn.2002) (emphasis added) (Anderson, J., dissenting); cf. Canada by Landy v. McCarthy, 567 N.W.2d 496, 507 (Minn.1997). When the harm to the plaintiff is caused by a combination of the conduct of more than one tortfeasor, the “burden of proving that the harm is capable of being separated lies with each defendant who contends it can be divided.” Canada, 567 N.W.2d at 507; see Mathews v. Mills, 288 Minn. 16, 22, 178 N.W.2d 841, 845 (1970). The purpose of the doctrine is to allow a plaintiff to recover damages even if it cannot prove exactly which damages were caused by which tort-feasor, as it is more fair for the loss to fall “on defendants who are clearly proved to have been at fault” than on an “innocent plaintiff.” See Mathews, 288 Minn, at 22, 178 N.W.2d at 845; see also Edmonds v. Compagnie Generate Transatlantique, 443 U.S. 256, 260 n. 8, 99 S.Ct. 2753, 61 L.Ed.2d 521 (1979); Restatement (Second) Torts § 433(B)(2) cmt. d (1965). This doctrine, however, is plainly inapposite where, as here, plaintiffs have not set forth any evidence of the amount of damages caused by the misconduct, because the issue of whether (and how) to apportion the damages “among at-fault defendants,” see Blatz v. Allina Health Sys., 622 N.W.2d, 376, 390-92 (Minn.Ct.App.2001) (emphasis added); see also Mathews, 288 Minn, at 24, 178 N.W.2d at 846, is simply never reached. Where there is no reasonable estimate of damages, we need not consider *763whether the injury is indivisible or capable of being apportioned (and who has the burden there), for there is no amount of damages to apportion among the defendants.
III.
The HMOs also contend that the district court should not have granted summary judgment on their suit for in-junctive relief because Tobacco never properly raised the issue in its motions before the district court. Tobacco disagrees, pointing to the last sentence of its motion for summary judgment on causation, injury, and damages, which requests the court to “grant summary judgment for Defendants on Plaintiffs’ remaining causes of action,” and argues that because the HMOs did not raise their contention before the district court, their argument is waived. Tobacco also maintains that in-junctive relief is improper here because the HMOs cannot prove that they were damaged or likely to be injured in the future.
A party moving for summary judgment has a prefatory burden to inform the district court of the basis for its motion, and to identify the part of the summary judgment record that it believes demonstrates the absence of a genuine issue of material fact. See Celotex Corp. v. Catrett, 477 U.S. 317, 323, 106 S.Ct. 2548, 91 L.Ed.2d 265 (1986); Handeen v. Lemaire, 112 F.3d 1339, 1345-46 (8th Cir.1997). It is only after the moving party has fulfilled this burden that the nonmoving party must set forth specific facts showing that there is a genuine issue for trial. Dush v. Appleton Elec. Co., 124 F.3d 957, 963 (8th Cir.1997). Tobacco never satisfied this prefatory burden here, because it never identified those aspects of the record that showed an absence of a genuine issue of material fact with respect to the request for injunctive relief.
We therefore believe that the matter of injunctive relief ought to be remanded to the district court for additional briefing and consideration. Our ruling on the HMOs’ damages claims was bottomed on the utter absence of evidence on the amount of damages, but that does not mean that the record is devoid of evidence supporting the fact of damage itself. Indeed, we believe that the record contains a mountain' of evidence tending to show that advertising generally causes people to begin smoking and causes current smokers to smoke more, which increases costs for the HMOs. If one concedes that a portion of the advertising was fraudulent, which Tobacco has done for the purposes of this motion, a reasonable person could infer that that fraudulent portion caused a part of those costs, even if the HMOs’ participants differed slightly from the populations used to study the effect of advertising generally on the prevalence of smoking. In other words, although the evidence in the case is, as we have said, insufficient to allow a factfinder to arrive at a reasonable estimate of the extent of harm caused, we hold that it was sufficient to raise an inference that harm has in fact been caused.4
IV.
We therefore affirm the judgment of the district court as to the HMOs’ damages claims and remand for further consideration of the HMOs’ injunctive claims.
. The Honorable Paul A. Magnuson, United States District Judge for the District of Minnesota-.
. The HMOs also contend that the district court abused its discretion by failing to hold an evidentiary hearing prior to its Daubert ruling. Although in limine hearings are generally recommended prior to Daubert determinations, see Padillas v. Stork-Gamco, Inc., 186 F.3d 412, 418 (3d Cir.1999), they are not required, see Lauzon v. Senco Prods., Inc., 270 F.3d 681, 685-86 (8th Cir.2001). The only legal requirement is that the parties “have an adequate opportunity to be heard” before the district court makes its decision. See, e.g., Nelson v. Tennessee Gas Pipeline Co., 243 F.3d 244, 249 & n. 3 (6th Cir.2001), cert. denied, 534 U.S. 822, 122 S.Ct. 56, 151 L.Ed.2d 25 (2001); Cortes-Irizarry v. Corporacion Insular De Seguros, 111 F.3d 184, 188 n. 3 (1st Cir.1997). Here, the parties were allowed, to exceed the normal page limits in their briefs on Tobacco's motion for summary judgment, and the district court permitted the HMOs to present written submissions by Dr. Harris and other experts in support of their argument. We thus conclude that the HMOs had an adequate opportunity to be heard on the Daubert matter.
The HMOs also argue that because there was no Daubert hearing we should review the district court’s exclusion of Dr. Harris's testimony de novo. Our case law is clear, however, that we review the exclusion of testimony under Daubert for an abuse of discretion despite the absence of a hearing. Lauzon, 270 F.3d at 685-86.
. Tobacco raises preemption issues pertaining to the Federal Cigarette Labeling Act. We leave it to the district court to consider what effect, if any, these issues have on the HMOs’ prayer for an injunction.