Judge Dyk Excludes Valuation Opinion Premised on Multivariate Hedonic Regression Analysis

The court granted defendant's renewed motion to exclude plaintiff's damages expert's multivariate hedonic regression analysis. "In assessing the appropriateness of the benchmark rates against the Georgia-Pacific factors, [the expert] . . . used multivariate hedonic regression to 'estimate the value of the accused feature’s contribution to the overall prices realized by [defendant] on the 5 Accused Products.' . . . Even assuming that hedonic regression analysis could properly be used to calculate the value of the accused feature, I conclude that [plaintiff's expert's] methodology relies on arbitrary assumptions that have no basis in the facts of this case or hedonic analysis in general. [His] attribution of equal value to all 19 RAS features is not based on any theory that meets the Daubert criteria of verifiability, peer review or publication, an acceptable error rate, or general acceptance in the scientific community. Indeed, [he] admitted that he could not separately estimate the value of the accused feature because all 19 RAS features were present in the same processor models.. . . . Utilizing guesswork is precisely what [plaintiff] is attempting to do here with [its expert's] guess as to the value of the accused feature in connection with his hedonic analysis. . . . [The expert's] opinion that 2.2% of the price of the accused products is attributable to the 8 accused feature lacks the 'valid scientific connection to the pertinent inquiry' that is required 'as a precondition to admissibility' under Rule 702."

Stragent, LLC et al v. Intel Corporation, 6-11-cv-00421 (TXED March 6, 2014, Order) (Dyk, C.J.)