# Then e y x u is the mean of the conditional density fy

This preview shows page 1. Sign up to view the full content.

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: hen: lim P n→∞ Sn − nµ √ ≤c nσ 2 = Φ(c). The practical implication of the central limit theorem is the same as that of the DeMoivre-Laplace limit theorem. That is, the CLT gives evidence that the Gaussian approximation, discussed in Section 3.6.3, is a good one, for sums of independent, identically distributed random variables. Figure 4.23 illustrates the CLT for the case the Xk ’s are uniformly distributed on the interval [0, 1]. The approximation in this case is so good that some simulation programs generate Gaussian random variables by generating six uniformly distributed random variables and adding them together to produce one approximately Gaussian random variable. Example 4.9.5 Let S denote the sum of the numbers showing in 1000 rolls of a fair die. By the law of large numbers, S is close to 3500 with high probability. Find the number L so that P {|S − 3500| ≤ L} ≈ 0.9. To be deﬁnite, use the continuity correction. 160 CHAPTER 4. JOINTLY DISTRIBUTED RANDOM VARIABLES Figure 4.23: Comparison of the pdf of Sn to the Gaussian pdf with the same mean an...
View Full Document

## This note was uploaded on 02/09/2014 for the course ISYE 2027 taught by Professor Zahrn during the Spring '08 term at Georgia Institute of Technology.

Ask a homework question - tutors are online