251greatD 3/31/06 Great Distributions I Have Known Note that F 5 Px 5 . The following distributions are all that are usually used in first-year Statistics. Distribution Uses Formula Mean Variance Discrete Distributions Binomial Gives Px C xn p x q n x np probability of x 2 npq No formula for successes in n F x . tries. p is Never use Px constant formula if a table probability of success on 1 try. is applicable. Use to replace h-g when N 20 n . Binomial Gives See above. Since probability of pq E p p x Var p p or x pn p as n n proportion of successes in n tries Geometric Gives q 1 P( x) q x1 p 2 2 probability that p p F x 1 q x the first success occurs on try x . Poisson Gives e m m x m P x probability of x 2 m x! successes in an m is called the interval in parameter of the which the Poisson average number distribution. of successes is No formula for m. F x . Use to replace Never use Px Binomial with m np when formula if a table is applicable. n 500 . p Hypergeometric Gives the probability of x successes in a sample of n taken from a population of N in which there are M successes. Px C nNxM C xM C nN No formula for F x . To get F x add P x . If p np M , N 2 N n npq N 1 Great Distributions I Have Known (pg. 2) 1 Distribution Continuous Distributions Continuous Uniform Exponential Uses Gives the probability that x Lies on an interval when you are told that the uniform distribution between c and d applies. x is usually the amount of time you have to wait until a success. Formula f x 1 d c for c x d , Mean Variance cd 2 2 1 c d c 2 f x 0 otherwise. xc F x d c for c x d , 12 F x 0 for x c and F x 1 for x d f x ce cx and F x 1 ecx when x 0 and the mean time to a 1 . Both c are zero if x 0 . 1 1 z2 f z e 2 2 x . z 1 c success is Standardized Normal This is the distribution of x when is known. It is used to approximate the binomial dist. when np 5 and nq 5 with np and 0 1 Always use tables once you have values of z . npq . It is used to approximate the Poisson Distribution when m 25 with m and m. t distribution This is the distribution of x when is unknown but s is known. Use tables. 0 DF DF 2 2 Great Distributions I Have Known (Page 3) Distribution Chi-squared 2 distribution F distribution Uses Distribution of s 2 when x is normal and is known. The ratio of 2 two ' s from the same population has the F distribution. It is used to compare variances. Formula Mean Variance Use tables mean DF var iance 2DF Use tables DF2 DF2 1 2DF2 2 DF1 DF2 2 DF1 DF2 22 DF2 4 Remember: (i) If you are looking for numbers of successes when the number of tries is given and the probability of success is constant, you want the Binomial distribution. This distribution can also be used to replace the Hypergeometric when the population size is large N 20 n . (ii) If you are looking for the try on which the first success occurs out of many possible tries when the probability of success is constant, you want the Geometric distribution. (iii) If you are looking for numbers of successes when the average number of successes per unit time or space is given, you want the Poisson distribution. This distribution can be used to replace the binomial when the n population is large and the probability of success is small 500 . p (iv) If you are looking for numbers of successes when the number of tries is given and the probability of success is not constant because the total number of successes in the population is limited, you want the Hypergeometric distribution. (v) If you are interested in the distribution of x and know , use the Normal distribution with a standard deviation of x ; if you are interested in the distribution of x and know s , use the t distribution with a standard deviation of s x . This also works for differences between means. (vi) If you are interested in the distribution of the sample variance and the parent distribution is approximately Normal, use the Chi-squared 2 distribution; If you are comparing two variances, use the F distribution. (vii) The following substitutions are commonly used for distributions. You must show that the conditions for use (under ‘if’) are satisfied. See next page for table. 3 Great Distributions I Have Known (Page 4) Replace Binomial With Poisson with m np Hypergeometric Binomial with p Binomial M N Normal with np , If n 500 p N 20 n np 5 and nq 5 npq Poisson Normal with m , if m 25 m Hypergeometric Normal p , np , M N np 5 and nq 5 , but think about Binomial if N 20 n N n npq N 1 4