Imagine a regression with YEAR (as in 2015 or 2001) predicting SALES (in thousands of dollars) as so: SALES = 100 + 0.5*YEAR And YEAR is statistically significant. What should you predict SALES to be in 2020? (Express your answer as SALES does: in thousands of dollars.)

Develop a scatterplot and explore the correlation between customer age and net sales by each type of customer (regular/promotion).  Use the horizontal axis for the customer age to graph.  Find the linear regression line that models the data by each type of customer.  Round the rate of changes (slopes) to two decimal places and interpret them in terms of the relation between the change in age and the change in net sales.  What can you conclude? Hint: Rate of Change = Vertical Change / Horizontal Change = Change in y  / Change in x

An e-commerce retailer was trying to understand how customer engagement correlates to customer purchases. They built the following regression model: Probability of Purchase = 0.1619 + 0.07 Emails Opened.  If someone opens 5 emails how likely are they to purchase?  If someone has a 75% chance of purchase how many emails have they opened?  If someone opens no emails how likely are they to purchase? What is the slope here and what does it tell us?

Eloise needs to finish a 516-page report on international trade so she can present it at the big conference this weekend. She's been tracking her page count at the end of each business day to see if she's on track. Use Excel to fit a trendline to Eloise's data to create a model of her productivity. According to your model, will Eloise be able to finish her report by the end of the day next Friday? Assume she works only on weekdays. Day Pages Monday 425 Tuesday 431 Wednesday 449 Thursday 464 Friday 471 A: Use Excel to fit a trendline to Eloise's data. What are the slope and intercept for this line? The slope is The intercept is B: Use your model (trendline) to answer the question. Will Eloise finish her report by the end of next friday? Yes