The data team at IndoCabs believes there may be a relationship between bookings, cancellations, and trip start time.To analyze the relationship between these variables, begin by generating a pivot table of the number of bookings

by hour of trip start. Report the number of bookings at hour:

(a) 8, (b) 12, and (c) 16.

2. Continue by generating a pivot table capturing the number of

cancellations by hour of trip start. Report the number of cancellations at hour: (a) 8, (b) 12, and (c) 16.

3. continue your analysis by generating a pivot table of the average of

cancellations ("average" is a value field setting on the pivot table that will output a number between 0 and 1 for each hour) by hour of trip start. Report the proportion of cancellations at hour:(a) 8, (b) 12, and (c) 16.

4. Now that we have summarized some key information by hour of trip start time, provide the following calculations to examine the relationships between key variables.

You should be using the output from the pivot tables, i.e., a maximum

of 24 observations per variable. Report:

a. The correlation between number of bookings and number of cancellations.

b. The R-squared value on a trendline, if you create a scatterplot of the

hourly number of bookings and hourly number of cancellations

c. The correlation between number of bookings and the proportion of cancellations.

d. The correlation between the number of bookings and a new measure of cancellations: create this new measure by converting the proportion of cancellations

to "whole number proportions" by multiplying each number by 100.

E.g., 0.03567 becomes 3.

567 (do not round until the final step). This question is addressing how/if the correlation changes when the underlying units change.