SUMMARY ORDER

UPON DUE CONSIDERATION, IT IS HEREBY ORDERED, ADJUDGED AND DECREED that the judgment of the district court is AFFIRMED.

Defendant-counter-claimant-appellant Procter & Gamble Co. (“P&G”) appeals from (i) the judgment and order of permanent injunction of the district court of the Southern District of New York (Pauley, J.), entered on May 29, 2003, following a nine-day jury trial, (ii) the order entered on July 26, 2004 denying P&G’s motion for judgment as a matter of law pursuant to Fed.R.Civ.P. 50(b), Playtex Products, Inc. v. Procter & Gamble, Co., No. 02 Civ. 8046, 2004 WL 1658377 (S.D.N.Y. July 26, 2004), and (iii) the order entered on May 28, 2003, denying in relevant part P&G’s motion in limine to preclude expert testimony on damages offered by plaintiff-counter-defendant-appellee Playtex Products, Inc. (“Playtex”), Playtex Products, Inc. v. Procter & Gamble, Co., No. 02 Civ. 8046, 2003 WL 21242769 (S.D.N.Y. May 28, 2003). We assume the parties’ familiarity *34with the facts and procedural background of this action.

We review de novo a denial of a Rule 50(b) motion, Yunnan Design, Inc. v. PAJ, Inc., 262 F.3d 101, 108 (2d Cir. 2001), applying the “same standard as the district court itself was required to apply,” Diesel v. Town of Lewisboro, 232 F.3d 92, 103 (2d Cir. 2000). We may only grant the motion where the record demonstrates “such a complete absence of evidence supporting the verdict that the jury’s findings could only have been the result of sheer surmise and conjecture, or such an overwhelming amount of evidence in favor of the movant that reasonable and fair minded men could not arrive at a verdict” against the moving party. Id. (internal quotation marks omitted).

We need not reach the question of whether the district court erred in finding that P&G waived its right to raise the issue of unpowered product testing in its Fed.R.Civ.P. 50(b) motion to set aside the jury findings by purportedly failing to raise the issue in its prior Fed.R.Civ.P. 50(a) motion. Similarly, we need not decide whether an unpowered product test alone would suffice to meet a plaintiffs burden in a claim that a competitor falsely advertised the superiority of its product. In light of the plaintiffs evidence as a whole, we are satisfied that Playtex adduced sufficient probative evidence to support the jury’s verdict that P&G falsely advertised superior leakage protection. See This is Me, Inc. v. Taylor, 157 F.3d 139, 142 (2d Cir. 1998) (‘Weakness of the evidence does not justify judgment as a matter of law; as in the case of a grant of summary judgment, the evidence must be such that a reasonable juror would have been compelled to accept the view of the moving party.” (internal citations and quotation marks omitted)).

At the very minimum, the challenged AUT tests and accompanying testimony in combination were probative of the leakage protection claim. Cf. Castrol, Inc. v. Quaker State Corp., 977 F.2d 57, 64 (2d Cir. 1992) (holding standard for challenging reliability of defendant’s tests purportedly supporting advertised claims of test-proven superiority “merely establishes plaintiffs burden of proof with respect to defendant’s tests. It in no way limits the evidence which plaintiff may use in meeting this burden. Such evidence is governed by the usual standards of admissibility”). In addition, Playtex also presented evidence of laboratory testing using the syngina, an instrument “designed to be an in-body simulation.” J.A. at 625-26; see generally J.A. at 577-88, 622-25. The tests demonstrated how (1) the Pearl leaked significantly faster than the Gentle Glide, J.A. at 586-87, and (2) the Pearl’s absorbent braid became “full of syngina fluid” before the primary absorbent reached saturation. J.A. at 586. While this test was also unpowered, it corroborated the results of the AUT tests because a rational juror could have inferred that, in light of the inferior performance in laboratory conditions simulating human use, the Pearl tampons were unlikely to perform in a superior manner in less controlled conditions. Supporting this inference was testimony on the structure of the Pearl’s absorbent braid in relation to the tampon’s overall absorbency, and on how the braid undermined the main pledget’s absorbency. J.A. at [587] 573-74. The powered HPT tests before the jury, unchallenged on this appeal, further corroborate an inference of the Pearl’s nonsuperiority, as the HPT tests demonstrated that consumers perceived no statistically significant differences between the two tampons with respect to leakage protection. J.A. at 470, 472, 749; see also J.A. at 642. P&G vigorously and ably cross-examined each of Playtex’s witnesses on the probative weight of the *35leakage protection evidence. The jury was instructed to evaluate the product testing in light of “the real world” and to “give the product testing evidence such weight, if any ... it deserves in light of all the evidence” and that the jury could “reject the evidence, in whole or in part, if [the jury did] not believe that the tests [were] rehable.” J.A. at 1611-13. The jury charge is not challenged in this appeal. In sum, P&G has not met the “high threshold for disturbing a jury verdict.” Toporoff Eng’rs, P.C. v. Fireman’s Fund Ins. Co., 371 F.3d 105, 108 (2d Cir. 2004).

Playtex also adduced sufficient evidence to support the jury’s conclusion that P&G’s false advertising caused it to lose profits. Playtex pointed to its market share before and after the advertising campaign, the nature of the tampon market, strong brand loyalty among its customers, and the stated goals of P&G’s campaign. This evidence may be circumstantial, but “[e]ircumstantial evidence is of no less value than direct evidence,” 4 Leonard B. Sand, et al., Modern Federal Jury Instructions, Instruction 74r-2 (rev. Oct. 1999), and it can be sufficient to prove causation in a false advertising case just as it can be to prove other propositions. See EFCO Corp. v. Symons Corp., 219 F.3d 734, 740 (8th Cir. 2000); BASF Corp. v. Old World Trading Co., 41 F.3d 1081, 1093 & n. 11 (7th Cir. 1994).

We review a district court’s admission of an expert’s testimony for abuse of discretion, Amorgianos v. Nat’l R.R. Passenger Corp., 303 F.3d 256, 264-65 (2d Cir. 2002), and will not overturn a decision to admit expert testimony unless it is “manifestly erroneous.” Id. at 265 (internal citations, quotation marks, and emphasis omitted). Under Fed.R.Evid. 702, expert testimony must be the “product of rehable principles and methods.” “Significantly, the abuse of discretion standard apphes as much to the trial court’s decisions about how to determine reliability as to its ultimate conclusion.” Id. (internal citation and quotation marks omitted). The district court has broad discretion in determining what method for determining reliability is appropriate for evaluating reliability under the circumstances of each case. Id. Given the unique characteristics of this product market, as well as the other evidence of causation before the jury, the district court’s decision to permit Dr. Lynde’s testimony on damages was not manifestly erroneous.

Dr. Lynde’s methodology did not purport to attribute the whole of Playtex’s profit losses to false advertising, but denominated a substantial fraction of that loss to the entry of a viable competitor into the marketplace. J.A. at 899. In the absence of sufficient data to conduct a regression analysis, Dr. Lynde’s method of discerning the “residual impact” of P&G’s advertising when the two products were in oligopolistic competition, see J.A. at 878-99, 926, 940, sufficed as a reliable proxy for the jury to evaluate in order to calculate lost profit damages. Cf. Burndy Corp. v. Teledyne Indus., Inc., 748 F.2d 767, 771 (2d Cir. 1984) (holding district court as fact-finder could “engage in some degree of speculation in computing the amount of [Lanham Act, Sec. 43(a)] damages ... causation must first be established” (internal citations omitted)); see Campbell v. Metro. Prop. & Cas. Ins. Co., 239 F.3d 179, 186 (2d Cir. 2001) (noting that the weight of admissible expert evidence “is a matter to be argued to the trier of fact, not a basis for reversal on appeal”).

For the reasons set forth above, the judgment of the district court is hereby AFFIRMED.