1. First, sort the data by the specimen collection date (column A) to make sure they are in chronological order. Then, find the "dailycases_specimen" variable (column C). This variable is the number of new cases reported each day. Graph the time series for this variable over full range of dates in the spreadsheet and do the following: a. Describe the time series pattern, using the terminology we have learned. b. Comment on which of the methods we have learned, if any, would be appropriate for generating a forecast from this time series. 2. Repeat part 1, but this time using only the data from March 10, 2022 through April 20, 2022 (that's 42 days, or six weeks, of data). 3. Using the six weeks of data from the previous question, generate a forecast for the seven day period starting April 21 (i.e., 4/21/22 through 4/28/2022) using three different methods: a. Linear regression assuming a trend, but no seasons. (You can use the date for the time variable, but it may be easier to interpret the slope and intercept if you create a new "time period" variable with just the numbers 1-42). b. Linear regression a weekly seasonal pattern, but no trend (you will need to create dummy variables for the days of the week). c. Linear regression assuming a trend and weekly seasonal pattern