Survey
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Today • Today: More Chapter 5 • Reading: – Important Sections in Chapter 5: 5.1-5.11 • • – – – Only material covered in class Note we have not, and will not cover moment/probability generating functions Suggested problems: 5.1, 5.2, 5.3, 5.15, 5.25, 5.33, 5.38, 5.47, 5.53, 5.62 Exam will be returned in Discussion Session Important Sections in Chapter 5 Example • Suppose X and Y have joint pdf f(x,y)=x+y for 0<x<1, 0<y<1 • Find the marginal distributions of X and Y • Is there a linear relationship between X and Y? Covariance and Correlation • Recall, the covariance between tow random variables is: • The covariance is: Properties • Cov(X,Y)=E(XY)-μXμY • Cov(X,Y)=Cov(Y,X) • Cov(aX,bY)=abCov(X,Y) • Cov(X+Y,Z)=Cov(X,Z)+Cov(Y,Z) Example • Suppose X and Y have joint pdf f(x,y)=x+y for 0<x<1, 0<y<1 • Is there a linear relationship between X and Y? • What is Cov(3X,-4Y)? • What is the correlation between 3X and -4Y Independence • In the discrete case, two random variables are independent if: • In the continuous case, X and Y are independent if: • If two random variables are independent, their correlation (covariance) is: Example • Suppose X and Y have joint pdf f(x,y)=x+y for 0<x<1, 0<y<1 • Are X and Y independent? Example • Suppose X and Y have joint pdf f(x,y)=x+y for 0<x<1, 0<y<1 • Are X and Y independent? Hard Example • Suppose X and Y have joint pdf f(x,y)=45x2y2 for |x|+|y|<1 • Are X and Y independent? • What is their covariance? Conditional Distributions • Similar to the discrete case, we can update our probability function if one of the random variables has been observed • In the discrete case, the conditional probability function is: • In the continuous case, the conditional pdf is: Example • Suppose X and Y have joint pdf f(x,y)=x+y for 0<x<1, 0<y<1 • What is the conditional distribution of X given Y=y? • Find the probability that X<1/2 given Y=1/2 Normal Distribution • One of the most important distributions is the Normal distribution • This is the famous bell shaped distribution • The pdf of the normal distribution is: f ( x) • 1 2 1 ( x )2 2 2 e Where the mean and variance are: Normal Distribution • A common reference distribution (as we shall see later in the course) is the standard normal distribution, which has mean 0 and variance of 1 • The pdf of the standard normal is: f ( z) • 1 2 z2 2 e 2 Note, we denote the standard normal random variable by Z CDF of the Normal Distribution • The cdf of a continuous random variable,Z, is F(z)=P(Z<=z) • For the standard normal distribution this is z ( z ) 1 2 u 2 2 e 2 du Relating the Standard Normal to Other Normal Distributions • Can use the standard normal distribution to help compute probabilities from other normal distributions • This can be done using a z-score: Z • (X ) A random variable X with mean μ and variance σ has a normal distribution only if the z-score has a standard normal Relating the Standard Normal to Other Normal Distributions • If the z-score has a standard normal distribution, can use the standard normal to compute probabilities • Table II gives values for the cdf of the standard normal Example: • The height of female students at a University follows a normal distribution with mean of 65 inches and standard deviation of 2 inches • Find the probability that a randomly selected female student has a height less than 58 inches • What is the 99th percentile of this distribution? Finding a Percentile • Can use the relationship between Z and the random variable X to compute percentiles for the distribution of X • The 100pth percentile of normally distributed random variable X with mean μ and variance σ can be found using the standard normal distribution Example: • The height of female students at a University follows a normal distribution with mean of 65 inches and standard deviation of 2 inches • What is the 99th percentile of this distribution?