商务统计-C15商务统计.pdf

Chapter 15 Chi-Square Applicat ions GOALS 1.List the characterist ics of the chi-square d istribut ion. 2.Conduct a test of hypothesis comparing an observed set of frequenc ies to an expected d istribut ion. 3.Conduct a test of hypothesis to determ ine whether two c lassificat ion criteria are re lated. Characterist ics of the Chi-Square Distribut ion The major characterist ics of the chi-square d istribut ion are: 1.It is posit ive ly skewed. 2.It is non-negat ive. 3.It is based on degrees of freedom. 4.When the degrees of freedom change a new d istribut ion is created. Characterist ics of the Chi-Square Distribut ion Goodness-of-Fit Test : Equal Expected Frequenc ies • Let f and f be the observed and expected 0 e frequenc ies respect ive ly. • H : There is no d ifference between the observed 0 and expected frequenc ies. • H : There is a d ifference between the observed 1 and the expected frequenc ies. Goodness-of-fit Test : Equal Expected Frequenc ies The test stat ist ic is: 2  f o  f e 2      f e    The crit ical value is a chi-square value w ith (k-1) degrees of freedom, where k is the number of categories Goodness-of-Fit Example Ms. Jan Kilpatrick is the market ing manager for a manufacturer of sports cards. She plans to begin se lling a series of cards w ith pictures and play ing stat ist ics of former Major League Baseball players. One of the problems is the se lect ion of the former players. At a baseball card show at Southwyck Mall last weekend, she set up a booth and offered cards of the fo llow ing six Hall of Fame baseball players: Tom Seaver, No lan Ryan, Ty Cobb, George Brett, Hank Aaron, and Johnny Bench. Goodness-of-Fit Example A