Question

Suppose that we wish to predict which candidate a person will vote for in this election (“R”-Republican, “D”-Democrat, “I”-Independent) based on , household income. We use the data from a pollster who surveyed a large number of people in Ohio and discover that the mean value of  for people who said they would vote “R” was , the mean of those who said they would vote “D” was , and the mean of those who said they would vote “I” was . In addition, the variance of for these three groups of people was  = 16,000,000. Finally, 46% of people who participated in the polling said that they would vote “R” and 44% said that they would vote “D”.

1) Assume that all necessary assumptions for LDA are satisfied and  follows a normal distribution.  Fill in the blanks for these parameters for LDA

__________________

__________________

__________________

__________________

__________________

___________________

2) Predict the probability that a person with a household income of  will vote “D”.

Answer 1

Two ways to increase the statistical power of an experiment overlap in the two sampling distributions for null hypothesis and alternative hypothesis Larger the sample size, the higher the power 2. Decrease random error - Reduce the variance: smaller variance yields higher power. Power is higher when the standard deviation is smaller than when it applied consistently.