卡方分布英文课件.ppt

Pearson Chi-Square: Frequencies No mean and SD ?2 statisticsNo assumption of normality Chi-Square test for goodness of fit 50 30 30 10 Observed Frequencies Suppose we have 50 blue balls, 30 orange balls, 30 yellow balls and 10 green balls. -Is the frequency of balls with different colors equal in our bag? 25% 25% 25% 25% Expected Frequencies Chi-Square test for goodness of fit 50 30 30 10 Observed Frequencies 25% 25% 25% 25% Expected Frequencies 120 120 Total ? = 30 30 30 30 Expected Frequencies H0 Chi-Square test for goodness of fit 50 30 30 10 Observed Frequencies 30 30 30 30 Expected Frequencies Difference Normalize Chi-Square test for goodness of fit Chi-Square test for goodness of fit Critical value = 7.81 26.6 ?2(3,n=120) = 26.66, p 0.001 Chi-Square test for Goodness of fit You can test your sample against any possible expected values 25% 25% 25% 25% 10% 10% 10% 70% H0 H0 Example A new casino game involves rolling 3 dice. The winnings are directly proportional to the total number of sixes rolled. Suppose a gambler plays the game 101 times, with the following observed counts: The casino becomes suspicious of the gambler and wishes to determine whether the dice are fair. Do the observed number of rolls fit the expected ones? What do they conclude? Solution Theoretical distribution No of sixes 0 1 2 3 No of Rolls 58 35 7 1 Reject the Null ! Example A game involves flipping 3 times a coin (having a tail and a head). Suppose a gambler plays the game 80 times, with the following observed counts: Do the observed number of results fit the expected ones at 5% level? What can we conclude? No. of head 0 1 2 3 No. of times 4 32 38 6 Solution Theoretical distribution No. of heads 0 1 2 3 No. of times 10 30 30 10 ACCEPT the Null ! We can conclude that the coin is regular and the game is fair Chi-Square test for independence When we have two or more sets of categorical data the Chi-square test works 10 50 35 15 60 40 Male Female Others