ORDER AND JUDGMENT*
After examining the briefs and appellate record, this panel has determined unanimously that oral argument would not materially assist the determination of this appeal. See Fed. R.App. P. 34(a)(2); 10th Cir. R. 34.1(G). The case is therefore ordered submitted without oral argument.
Plaintiffs appeal the district court’s grant of summary judgment dismissing their age discrimination complaint against Ruhrpumpen, Inc. We affirm.
The parties are familiar with the facts, which are accurately and fully set forth in the district court’s thorough opinion as well as this court’s prior decision in this case. See Foster v. Ruhrpumpen, Inc., 365 F.3d 1191, 1192 (10th Cir.2004) (reversing the district court’s initial grant of summary judgment on the grounds that plaintiffs failed to exhaust their administrative remedies). Thus, we briefly recite only those facts necessary to explain this decision.
Ruhrpumpen acquired a pump manufacturing plant from Flowserve, Inc. Flow-serve terminated all of its employees, including plaintiffs. Ruhrpumpen invited the former Flowserve employees to apply for employment, and plaintiffs were among those who applied. Ruhrpumpen asked Flowserve’s Superintendent of Production, Mike Brantley, to evaluate the skill level, work habits, and on-the-job attitude of all of the terminated Flowserve employees. Ruhrpumpen hired fifty-seven of the former Flowserve employees, not including plaintiffs. Plaintiffs then filed a complaint alleging Ruhrpumpen had violated their rights under the Age Discrimination in Employment Act (ADEA), 29 U.S.C. §§ 621-634. Id.
The district court granted Ruhrpumpen’s motion for summary judgment. It ruled that plaintiffs failed to present evidence establishing a prima facie case of ADEA discrimination. See Kendrick v. Penske Transp. Servs., Inc., 220 F.3d 1220, 1226 (10th Cir.2000) (describing elements of prima facie failure-to-hire ADEA claim). It further ruled that even if plaintiffs had made out a prima facie case, Ruhrpumpen *391had presented legitimate, non-discriminatory reasons for not hiring them, and plaintiffs had failed to present evidence that Ruhrpumpen’s reasons for not hiring them were pretext for discrimination. See id. at 1226, 1230 (describing burden-shifting analysis of circumstantial-evidence ADEA claim, and holding that plaintiff can withstand summary judgment if he presents evidence that employer’s reason for the employment decision is “pretextual-i.e. unworthy of belief’).
We review the grant of summary judgment de novo, applying the same standard as did the district court. MacKenzie v. City & County of Denver, 414 F.3d 1266, 1273 (10th Cir.2005). Summary judgment is proper where “the pleadings, depositions, answers to interrogatories, and admissions on file, together with the affidavits, if any, show that there is no genuine issue as to any material fact and the moving party is entitled to a judgment as a matter of law.” Fed.R.Civ.P. 56(c). We review the record and any reasonable inferences therefrom in the light most favorable to the nonmoving parties. MacKenzie, 414 F.3d at 1273.
On appeal, plaintiffs contend that the district court erred in ruling that they failed to establish a prima facie case or to raise a genuine issue of fact as to the element of pretext. We are doubtful that plaintiffs demonstrated all of the elements necessary to establish a prima facie case of age discrimination. Even if plaintiffs did establish a prima facie case of discrimination, however, their discrimination claim still fails because they did not proffer evidence showing that defendant’s reasons for not hiring them were simply a pretext for age discrimination.
Plaintiff does not dispute that Ruhrpumpen produced evidence of legitimate, nondiscriminatory reasons for not hiring plaintiffs, namely, that after determining the number of workers it needed, it selected the most qualified applicants based upon their skills, work habits, and on-the-job attitude of the applicants, as determined from their employment applications and the objective evaluations by Mike Brantley, the former Flowserve supervisor. The burden then shifted to plaintiffs to present evidence that Ruhrpumpen’s prof-erred reason for the employment decision was unworthy of belief. Kendrick, 220 F.3d at 1230.
Pretext may be demonstrated by revealing “such weaknesses, implausibilities, inconsistencies, incoherencies, or contradictions in the employer’s proffered legitimate reasons for its action that a reasonable factfinder could rationally find them unworthy of credence and hence infer that the employer did not act for the asserted non-discriminatory reasons.” Morgan v. Hilti, Inc., 108 F.3d 1319, 1323 (10th Cir.1997) (quotation omitted). Evidence of pretext may include “prior treatment of plaintiff; the employer’s policy and practice regarding minority employment (including statistical data); disturbing procedural irregularities (e.g., falsifying or manipulating ... criteria); and the use of subjective criteria.” Garrett v. Hewlett-Packard Co., 305 F.3d 1210, 1217 (10th Cir.2002) (quotation omitted).
Plaintiffs made several arguments in support of their claim that Ruhrpumpen’s justification for not hiring them is pretextual. First, they point to a remark make by Don McCourt, the current president of Ruhrpumpen and former operations manager for Flowserve. Two weeks before Flowserve sold the pumping plant to Ruhrpumpen, McCourt told one of the plaintiffs that “some old dogs will need to learn new tricks.” Aplt.App., Vol. I at 52. We agree with the district court that this remark is too isolated and ambiguous to demonstrate any nexus between it and *392Ruhrpumpen’s subsequent hiring decisions. See Stone v. Autoliv ASP, Inc., 210 F.3d 1132, 1140 (10th Cir.2000) (concluding that isolated, ambiguous remarks may be too abstract to support an inference of age discrimination); see also Cone v. Longmont United Hosp. Ass’n, 14 F.3d 526, 531 (10th Cir.1994) (“Isolated comments, unrelated to the challenged action, are insufficient to show discriminatory animus in termination decisions.”). The circumstances of McCourt’s remark are unclear; the only evidence is his testimony that he was referring to a management employee’s treatment of employees, and had nothing to do with any plaintiff or with any employee’s age. The remark is ambiguous, in the sense that it is susceptible to more than one interpretation; isolated, in the sense that it was only made once; and stray, in the sense that plaintiff has not shown an adequate nexus between the remark and Ruhrpumpen’s decision not to hire plaintiffs. See Stone, 210 F.3d at 1140.
Plaintiffs next make two statistical arguments. First, plaintiffs contend that if one compares the hired to not-hired applicants by job classification, the average age difference is lower for the hired workers in every category, with a low of 2.5 years to a high of 27.2 years. Second, they contend that the average age of the fifty-seven workers hired by Ruhrpumpen was 47.8 years old, whereas the average age of the workers not hired was 52.8 years old. Ruhrpumpen disputes the number of not-hired applicants used by plaintiffs in their comparison, and presents contrary evidence showing that the average age of the fifty-seven hired applicants was 48 years old, and the average age of the forty-nine applicants not hired was 48.55 years, a difference of only six months.1
We agree with the district court that, even using the comparison propounded by plaintiffs, plaintiffs’ evidence is inadequate to demonstrate pretext. While “Statistical data showing an employer’s pattern of conduct toward a protected class can create an inference that an employer discriminated against individual members of the class,” Fallis v. Kerr-McGee Corp., 944 F.2d 743, 746 (10th Cir.1991) (citation omitted), this court has also cautioned against its usage. “Statistics taken in isolation are generally not probative of age discrimination.” Jones v. Unisys Corp., 54 F.3d 624, 632 (10th Cir.1995). To create an inference of discrimination, statistical evidence “must show a significant disparity and eliminate nondiscriminatory explanations for the disparity.” Fallis, 944 F.2d at 746 (citation omitted). Plaintiffs’ statistical evidence does neither: it does not show a significant disparity, and it fails to eliminate nondiscriminatory reasons for the numerical disparities.
“[A] plaintiffs statistical evidence must focus on eliminating nondiscriminatory explanations for the disparate treatment by showing disparate treatment between comparable individuals.” Id. (citation and emphasis omitted). “Statistical evidence which fails to properly take into account nondiscriminatory explanations does not permit an inference of pretext.” Martinez v. Wyo., Dep’t of Family Servs., 218 F.3d 1133, 1139 (10th Cir.2000). In this case, plaintiffs’ comparisons of the overall ages of the hired and not-hired applicants are too simplistic; they fail to take into account individual differences in skill or qual*393ifieations and fail to eliminate nondiscriminatory reasons for any age difference. Therefore, this evidence is insufficient to raise a genuine issue of material fact as to pretext. Cf. Doan v. Seagate Tech., Inc., 82 F.3d 974, 979 (10th Cir.1996); Jones, 54 F.3d at 632.
As to the “significant disparity” requirement, it is true that this court has declined to adopt a bright-line rule that a difference of five years is an insignificant difference as a matter of law under the ADEA. Whittington v. Nordam Group Inc., 429 F.3d 986, 995 (10th Cir.2005). Nevertheless, where a plaintiff relies on statistical evidence, he “must show ‘gross statistical disparities.’ ” Denison v. Swaco Geolograph Co., 941 F.2d 1416, 1424 (10th Cir.1991) (quoting Hazelwood Sch. Dist. v. United States, 433 U.S. 299, 307-08, 97 S.Ct. 2736, 53 L.Ed.2d 768 (1977)). We agree with the district court that plaintiffs’ evidence in this case does not reliably demonstrate such a gross disparity as to create an inference of discrimination. Cone, 14 F.3d at 532 (finding plaintiffs statistics invalid because they-did not “demonstrate a significant disparity in the treatment of younger workers”). We further agree with the district court that the small number of employees within each of the eleven job classifications is too small in this case to provide reliable statistical results. Cf. Fallis, 944 F.2d at 746 (holding that statistical analysis of nine employees too small to have any probative force to show discrimination).
Plaintiffs perfunctorily list two other reasons why they believe Ruhrpumpen’s explanation for not hiring them is pretext: that those not hired were, “by and large,” more qualified than those hired and that Ruhrpumpen did not ask all Flowserve employees to complete an employment application. Aplt. Br. at 18-19. The district court concluded that the evidence plaintiffs presented relative to these claims failed to demonstrate pretext. Plaintiffs do not put forward any reason, argument, or legal authority showing why they believe the district court erred in so ruling. See id. at 18-21. “[S]uch perfunctory complaints fail to frame and develop an issue sufficient to invoke appellate review.” Murrell v. Shalala, 43 F.3d 1388, 1389 n. 2 (10th Cir.1994). “It is insufficient merely to state in one’s brief that one is appealing an adverse ruling below without advancing reasoned argument as to the grounds for the appeal.” Am. Airlines v. Christensen, 967 F.2d 410, 415 n. 8 (10th Cir.1992); see also Fed. R.App. P. 28(a)(9)(A) (“The appellant’s brief must contain ... appellant’s contentions and the reasons for them, with citations to the authorities and parts of the record on which the appellant relies.”).
The judgment of the district court is AFFIRMED.