Question Answered step-by-step The data in the Excel file Electronic Sales contains quarterly sales plus the advertising expenditures for a large firm’s popular product line. You should develop a multiple regression model that could be used to forecast future sales. This regression is for time series data which is data collected over regular intervals of time. This type of analysis is very common in business situations for obvious reasons. Time series present different types of challenges from cross-sectional data. One big challenge is autocorrelation. Whenever you work with time series data and regression, you always have to make sure that you minimize the effects of autocorrelation. Based on this data, develop a regression model that will predict the quantity of sales. As you develop this model, you have to take into consideration all the assumptions that a regression is built upon. There are several issues that you need to look at. The first thing you should do is graph the data to determine what is happening to the sales. Are there any trends, upwards or downwards? If so, how do you account for that? Is there any seasonality present? If so, how will you take care of it? Are there any unusual points? Next, are there any additional variables you can create? These could be dummy variables or lagged variables. Finally, when you perform the regressions, are there any statistical issues you need to take care of? For consistency, do not use lag variables beyond one time period for the dependent variable or any of the independent variables. Indicate on the solution, your sales predictions for the next four quarters. Be sure to have an equation for this, not just numbers. QuarterYearSalesAdvert $ (in thousands)Q119971897.798.9Q219972473.1103.0Q319972721.4216.3Q419972348.2488.2Q119981626.6100.9Q219982211.1121.5Q319982143.4247.2Q419982122.1502.6Q119991964.0118.5Q219992510.1149.4Q319992307.9257.5Q419992149.2527.4Q120002030.9126.7Q220002526.7160.7Q320002361.5288.4Q420002322.1566.5Q120012348.9145.2Q220012999.3188.5Q320012939.5319.3Q420012777.6587.1Q120022691.8184.4Q220023303.8196.7Q320023356.5339.9Q420023077.0648.9Q120033022.9203.9Q220033872.2214.2Q320033788.7370.8Q420033452.7669.5Q120043337.1226.6Q220044136.7227.6Q320043864.1412.0Q420043692.5731.3Q120053522.5245.1Q220054714.5250.3Q320054912.9432.6Q420054356.0803.4Q120064194.8257.5Q220065437.4266.8Q320065261.2463.5Q420064676.0865.2Q120074522.0286.3Q220075588.0289.4Q320075132.5463.5Q420074782.4916.7Q120084385.6288.4Q220085381.7296.6Q320085210.8494.4Q420085163.5968.2Q120094769.7309.0Q220095548.9308.0Q320095058.3503.7Q420094866.2999.1Q120104652.9314.2Q220105882.3320.3Q320105617.3494.4Q420105287.81030.0Q120114761.3324.5Q220116128.0330.6Q320116109.2504.7Q420115323.91030.0Q120124851.3339.9Q220126379.3349.2Q320126162.1539.7Q420125703.91040.3Q120135474.3257.5Q220136852.5270.9Q320136300.7463.5Q420135867.2865.2Q120145380.1286.3Q220146626.0289.4Q320146558.4463.5Q420146271.3916.7Q120155630.2288.4Q220157407.1296.6Q320157180.3494.4Q420157108.9968.2Q120166009.8324.5Q220167426.4330.6Q320167366.1504.7Q420166985.71009.4 Math BUKD C520
