Trade Court Says Commerce Answered CAFC's Questions Over Use of 'd' Test to Root Out Masked Dumping

The test is used to root out "targeted" or masked dumping by finding if a subset of an exporter's sales is significantly different from the comparison group. If it is, Commerce applies a "ratio test" to see if the ratio of significantly different transactions warrants using an average-to-transaction method, rather than the average-to-average comparison it normally uses. Exporter SeAH Steel Corp. challenged the use of the test, claiming that the agency failed to satisfy certain statistical assumptions required for the test's use.

In a July 2021 decision, the Federal Circuit questioned whether the test could be used without a normal distribution, with few data points and where there is minimal variance in a respondent's sales (see 2107150032).

The appellate court raised concerns that the use of small sample sizes without normal distributions could "exaggerate" dumping margins by introducing an "upward bias" to effect size. In response, Commerce said that the d test works with the ratio test and a meaningful difference test to "compensate for inaccuracies." The only point of the d test is to find whether prices differ greatly across region, time period or customer, Commerce said. Kelly upheld the agency's threshold of 33% positives before any potential effect on a respondent's margins is enacted.

The Federal Circuit raised another question over Commerce's use of a threshold identified by Dr. Jacob Cohen, the test's founder, as a measure of a significant price difference despite the fact that the agency's data does not meet certain statistical assumptions. Commerce said the assumptions do not matter since it uses the entire population of data and not just a sample and that the use of the threshold "represents a difference which is 'grossly perceptible.'" Kelly, citing the Statement of Administrative Action to the Uruguay Round Agreements Act, said that the choice of measurement as a uniform approach to identify differences as significant is "reasonable" since it leads to a limited use of the average-to-transaction method.

"Commerce’s decision to adopt Cohen’s 0.8 (“large”) threshold as a measure of significance because it is widely accepted in the statistical literature does not undermine the reasonableness of that choice, if it is based on Commerce’s expertise and Commerce demonstrates the reasonableness of that choice with reference to the impact it has on the differential pricing analysis," the opinion said. "Thus, Commerce’s reference to Cohen’s work does not circumscribe its discretion to choose the same values in a new context, because that choice is itself reasonable."

Commerce also addressed the Federal Circuit's concern over prices with small variances that hover around the same value. The appeals court thought this would produce inaccurate results on the test and that an objective examiner looking at a group of sales where prices differed by only a few cents would be unlikely to find that they show a pattern of prices that “'differ significantly' under the statute," a sign of masked dumping. Commerce said that this does not matter -- an examiner would indeed conclude that there was no pattern -- since the agency does not look for a pattern at this stage of the DPA, as the Cohen's d test only looks for significant price differences.

"Thus, Cohen’s test would need to generate enough 'false positives' to overcome the 33% threshold, at minimum, and there is no evidence on the record suggesting that price patterns, such as that proposed by the Court of Appeals, occur with frequency in SeAH’s sales," the judge said.

(Stupp Corp., et al. v. United States, Slip Op. 23-23, CIT Consol. # 15-00334, dated 02/24/23, Judge Claire Kelly; Attorneys: Jeffrey Winton of Winton and Chapman for plaintiff SeAH Steel Corporation; Robert Kiepura for defendant U.S. government; Jeffrey Gerrish of Schagrin Associates for plaintiff Welspun Tubular)