Lesson 7: Case: We see that some viewstyles dominate the market. We would like to understand what a buyer might expect for particular styles or quality of view. 3. Create and attach a Crosstab table and corresponding side-by-side bar chart and 100% stacked column chart for the variables STYLE and VIEW by creating a pivot table. Consider selecting a home in the data set at random (uniformly). Explain how you would compute the following statistics and interpret the results. Always provide the specific statistics in your answer e.g. if discussing the most frequent thing, state what the frequency is and any comparison frequencies if needed. a. Most likely a house will have what quality of view? b. How likely will it not have this (the most frequent) quality of view? Why is this different than the least frequent quality of view? c. What is the most likely quality of view and style? d. How likely will a home have that quality of view or be that style? Make a table of the expected frequencies if STYLE were independent of VIEW by multiplying all combinations of the marginals (totals). Copy the % of Total table and paste as values. In the cell for the first joint row and column, multiply the row and column totals. Add a $ to the reference for the column to the row total and a $ to the reference to row for the column total. Copy this cell to the other joint row and columns. a. Explain why these are the expected frequencies if STYLE were independent of VIEW. b. What is the highest and lowest expected frequencies(fe) of style and views? What are the observed most likely and least likely (fo) style and views (from the % of Totals table)? Are they the same? c. What might your results in (b) imply? What do we need to take care to note about this implication