This preview shows pages 1–15. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Prob & Stat 1 PROBABILITY AND STATISTICS Some Basic Definitions Random variable large set of possible values only one will occur The set of possible values and their probabilities = the probability distribution Prob & Stat 2 Continuous random variable has a probability density function (pdf) f X such that P ( X A ) = Z A f X ( x ) dx for all sets A Prob & Stat 3 CDFs cumulative distribution function (CDF) of X is F X ( x ) := P ( X x ) If X has a pdf then F X ( x ) := Z x f X ( u ) du Prob & Stat 4 Quantiles if the CDF of X is continuous and strictly increasing then it has a inverse function F 1 for q between 0 and 1, F 1 ( q ) is called the q th quantile or 100 q th percentile Prob & Stat 5 probability X is below its q th quantile is q : P { X F 1 ( q ) } = q also called the lower quantile the q th upper quantile is the 1 q th lower quantile 0.2 0.4 0.6 0.8 1 0.2 0.4 0.6 0.8 1 q F1 (q) 0.2 0.4 0.6 0.8 1 0.2 0.4 0.6 0.8 1 q F1 (q) 0.2 0.4 0.6 0.8 1 0.2 0.4 0.6 0.8 1 q F1 (q) Prob & Stat 6 median is the 50% percentile or .5 quantile 25% and 75% percentiles (.25 and .75 quantiles) are called the first and third quartiles for 95% confidence intervals we use the 0.025 and 0.975 quantiles, i.e., the 0.025 lower and 0.025 upper quantiles. Prob & Stat 7 Expectations and Variances The expectation of X is E ( X ) := Z +  xf X ( x ) dx variance of X is 2 X := Z { x E ( X ) } 2 f X ( x ) dx = E { X E ( X ) } 2 Useful formula: 2 X = E ( X 2 ) { E ( X ) } 2 standard deviation is the square root of the variance: X := p E { X E ( X ) } 2 Prob & Stat 8 If X 1 ,...,X n is a sample from a prob distn, then expectation estimated by sample mean X = n 1 n X i =1 X i the variance estimated by sample variance s 2 X = n i =1 ( X i X ) 2 n 1 Prob & Stat 9 Correlation and Covariance XY = E { X E ( X ) }{ Y E ( Y ) } If ( X,Y ) are continuously distributed, then XY = Z { x E ( X ) }{ y E ( Y ) } f XY ( x,y ) dxdy Prob & Stat 10 Useful formulas: XY = E ( XY ) E ( x ) E ( y ) XY = E [ { X E ( X ) } Y ] XY = E [ { Y E ( Y ) } X ] XY = E ( XY ) if E ( X ) = 0 or E ( Y ) = 0 Prob & Stat 11 Correlation coefficient between X and Y : XY := XY / X Y for any ( X,Y ) it is true that 1 XY 1 Prob & Stat 12 Given a bivariate sample { ( X i ,Y i ) } n i =1 , the sample correlation coefficient is n 1 n i =1 ( X i X )( Y i Y ) s X s Y (1) where X and Y are the sample means s X and s Y are the sample standard deviations Prob & Stat 135 5321 1 2 3 r = 0.55 5321 1 2 3 r = 0.255 5321 1 2 3 r = 0.955 521 1 2 3 4 r = 0.115 542 2 4 6 r = 0.835 5321 1 2 3 r = 0.015 54321 1 2 3 r = 0.895 5321 1 2 3 r = 1 Prob & Stat 14 an absolute correlation of .25 is very weak an absolute correlation of .5 is only moderate an absolute correlation of .95 is rather strong...
View
Full
Document
 Spring '07
 ANDERSON

Click to edit the document details