Page: 30 case of fraud from which an inference may be drawn that the results were affected and that, [74] The Supreme Court’s reference to a prima facie case arose in the specific context where the applicant could not directly prove that a non-entitled person voted. The Court recognized that prima facie proof that an irregularity occurred may be sufficient to permit the necessary factual inferences to be drawn to meet the civil standard of proof. In those circumstances, the respondent bears the risk of annulment if it can not be established that an ineligible vote was not cast or that it did not affect the results. Absent a statutory direction to the contrary, which is not present here, the burden of proof never shifts to the responding party and the standard remains that of the balance of probabilities: FH v McDougall, 2008 SCC 53 at para 40. [75] In Opitz, the Supreme Court used the “magic number” test to determine whether the application judge should have annulled the result. The test was explained at paras 71-73: 71 To date, the only approach taken by Canadian courts in assessing contested election applications has been the "magic number" test referred to in O'Brien (p. 93). On this test, the election must be annulled if the rejected votes are equal to or outnumber the winner's plurality (Blanchard, at p. 320). 72 The "magic number" test is simple. However, it inherently favours the challenger. It assumes that all of the rejected votes were cast for the successful candidate. In reality, this is highly improbable. However, no alternative test has been developed. No evidence has been presented in this case to support any form of statistical test that would be reliable and that would not compromise the secrecy of the ballot. 73 Accordingly, for the purposes of this application, we would utilize the magic number test. The election should be annulled when the number of rejected votes is equal to or greater than the successful candidate's margin of victory. However, we do not rule out the possibility that another, more realistic method for assessing 2013 FC 525 (CanLII) having done so, the burden of proof then shifts to the respondents.