****

Normal Approximation to the Sign Test As a consequence of the central limit theorem, the normal distribution can be used to approximate the binomial distribution of the sample size is large. Experts differ on the exact definition of large" We suggest that the normal approximation is acceptable if the sample size exceeds 20. A continuity correction factor in the tent statistic compensates for estimating dis- crete data with a continuous distribution and provides a closer approximation to the pualue The Sign Test: Normal Approximation (Large Samples) If the number of nonzero sample observations is large, then the sign test is based on the normal approximation to the binomial with the following mean and standard deviation: meant p0.5 standard deviationer - Vape - V0.251-os The test statistici S-0.5 (14.14) 05V where S* in the test statistic corrected for continuity, defined as follows: For a two-tail test: $* = 5 +0.5 S