APPENDIX A Tables and Formulas 743 TABLE A-9 Critical Values of Spearman’s Rank Correlation Coefficient rs n a = 0.10 a = 0.05 a = 0.02 a = 0.01 5 .900 — — — 6 .829 .886 .943 — 7 .714 .786 .893 .929 8 .643 .738 .833 .881 9 .600 .700 .783 .833 10 .564 .648 .745 .794 11 .536 .618 .709 .755 12 .503 .587 .678 .727 13 .484 .560 .648 .703 14 .464 .538 .626 .679 15 .446 .521 .604 .654 16 .429 .503 .582 .635 17 .414 .485 .566 .615 18 .401 .472 .550 .600 19 .391 .460 .535 .584 20 .380 .447 .520 .570 21 .370 .435 .508 .556 22 .361 .425 .496 .544 23 .353 .415 .486 .532 24 .344 .406 .476 .521 25 .337 .398 .466 .511 26 .331 .390 .457 .501 27 .324 .382 .448 .491 28 .317 .375 .440 .483 29 .312 .368 .433 .475 30 .306 .362 .425 .467 NOTES: 1. For n 7 30 use rs = {z>1n - 1, where z corresponds to the level of significance. For example, if a = 0.05, then z = 1.96. 2. If the absolute value of the test statistic rs is greater than or equal to the positive critical value, then reject H0: rs = 0 and conclude that there is sufficient evidence to support the claim of a correlation. Based on data from Biostatistical Analysis, 4th edition © 1999, by Jerrold Zar, Prentice Hall, Inc., Upper Saddle River, New Jersey, and “Distribution of Sums of Squares of Rank Differences to Small Numbers with Individuals,” The Annals of Mathematical Statistics, Vol. 9, No. 2. rs 1 21 2rs a 2 a 2
RkJQdWJsaXNoZXIy NjM5ODQ=