# Question: For testing independence most software also reports another chi squared statistic

For testing independence, most software also reports another chi-squared statistic, called likelihood-ratio chi-squared. It equals

G2 = 2 ∑ [observed count × log (observed count / expected count)]

It has similar properties as the X2 statistic, such as

df = (r - 1) × (c - 1).

a. Show that G2 = X2 = 0 when each observed count = expected count.

b. Explain why in practice you would not expect to get exactly G2 = X2 = 0, even if the variables are truly independent.

G2 = 2 ∑ [observed count × log (observed count / expected count)]

It has similar properties as the X2 statistic, such as

df = (r - 1) × (c - 1).

a. Show that G2 = X2 = 0 when each observed count = expected count.

b. Explain why in practice you would not expect to get exactly G2 = X2 = 0, even if the variables are truly independent.

**View Solution:**## Answer to relevant Questions

How large a X2 test statistic value provides a P-value of 0.05 for testing independence for the following table dimensions? a. 2 × 2 b. 2 × 3 c. 2 × 5 d. 5 × 5 e. 3 × 9 A study about the effect of the swing on putting in golf showed a very strong linear relationship between y = putting distance and the square of x = club’s impact velocity (r2 is in the range 0.985 to 0.999). a. For the ...Although the slope does not measure association, it is useful for comparing effects for two variables that have the same units. For the Internet Use data file of 33 nations on the text CD, let x = GDP (thousands of dollars ...For the Georgia Student Survey data file on the text CD, the table shows the correlation matrix for college GPA, high school GPA, and daily time spent watching TV. a. Interpret r and r2 between time spent watching TV and ...Use software to analyze the U.S. Statewide Crime data file on the text CD on y = violent crime rate and x = percentage of single parent families. a. Construct a scatter-plot. What does it show? b. One point is quite far ...Post your question