Please help! So for this question I just had to suggest two regression equations that a company could do if it was worried about cancellations. We had car cancellations as dependent variable and could choose from mobile booking, day of cancellation, and hour of cancellation as variables. As you'll read below, I did one equation using just mobile bookings and cancellations but like stated below WOULD THIS GIVE ME A PREDICTION OF HOW MANY CANCELLATIONS WOULD OCCUR WHEN SOMEONE BOOKS MOBILLY? (I tried this in excel and it gave me a decimal which doesn't seem right). Overall, can I do regression equation with a variable that is binomial (0 for no and 1 for yes) and what answer will that give me and for the second equation is that right? Do these equations make sense? ALSO, in the second equation if the hour of day variable was a number between 0 and 23 and 6pm would be 18, do I times that coefficient by 18 then if I want it to output cancellations at 6pm? Thank you and accuracy is really important for this!

Question:Knowing what you know now about regression analyses, describe (in words) at least two regression equations that you think would be useful for a cab company to examine given its goal of reducing cab cancellations. Describe your reasoning for both the outcome and explanatory variables. (limit 200 words)

My answer:Regression analysis proves to be a helpful tool for finding relationships between variables. Two regression equations that I think would be useful for IndoCabs to examine given its goal of reducing cab cancellations include one that is created from the regression table using the dependent variable cancellations (Y), with independent variable mobile bookings, and the regression table with cancellations as (Y) and day of week and hour as the independent variables. I chose these variables because IndoCabs specifically wanted to know the relationship between cancellations and method of booking, day of week, and time of day. The first equation would include setting the dependent variable of cancellations = to the intercept coefficient from the regression table + coefficient of mobile bookings * when it is a mobile booking which is (1). Since this method of bookings was the most popular, this would give a prediction of how many cancellations occur when someone books mobilly.

The second equation would be Cancellations = the intercept coefficient from the regression table+ coefficient of the day of week variable * 1 (because Mondays had the most cancellations) + coefficient of hour of day variable * 18 (because 6pm had the most bookings and it was found that high booking volume is positively correlated with cancellations). This equation would predict how many cancellations occur on the weekday of Monday and the hour of trip start of 6:00 p.m. As this method of day and time are when most bookings and cancellations happen, this can highlight for the company a prediction of the most problematic cancellation time: how many bookings are cancelled on Mondays at that certain time. Using this equation would also let the company predict how many cancellations there will be through picking any day of week and time.