You should build a causal regression model, where your dependent variable (outcome) is avocado demand. You can build as many regression models as you’d like to see how your adjusted R^2 improves, but you should report on the main tab the results based on the best model that you choose.
Instructions MGSC 778 Causal Forecasting Assignment Instructions: 1. Build a causal regression model to predict the weekly demand for Avocados from the weeks of Dec 6th 2015 to Sep 9th 2018. Your model will be measured against its adjusted R-squared fit versus the actual data of this same time period. The criteria for evaluation is the size of the adjusted R-squared value. You can choose any independent variables you want as long as you only use the data provided in this worksheet. Examples of possible independent variables include price, some time-based measure such as month, special holidays, etc. You should also follow the guidelines document included with the assignment for consistency across the teams to make the adjusted R^2 comparable. 2. Include your answers on this page in the blocks provided. The specifics of your solution may be saved as separate worksheets on this spreadsheet. Place your model fit statistics in the yellow blocks below. 3. Name your file using the following format: CausalProjectLast name of each team member.xlsx. Also, please fill out the main results in the appropriate boxes on this spreadsheet. Regression Statistics Multiple R R Square Adjusted R Square Standard Error Observations Include your last five forecast in the yellow cells below PeriodActualForecastError 12-Aug-1840,901,95040,901,950 19-Aug-1840,735,73340,735,733 26-Aug-1836,867,97536,867,975 2-Sep-1836,169,16236,169,162 9-Sep-1837,484,25437,484,254 Grade: Your grade will be based on your Adjusted R Square value relative to the Adjusted R Square values of the other teams. Actual vs. Forecast Actuals433244333143338433454335240901950.00999999840735732.6836867974.57999999836169161.5737484253.75Forecasts4332443331433384334543352 Units Sold Put your names here Raw Data DateTotal VolumeAveragePrice 6-Dec-1528,800,3970.89 13-Dec-1528,041,3350.93 20-Dec-1525,083,6470.98 27-Dec-1527,297,9840.95 3-Jan-1638,142,0880.86 10-Jan-1635,264,3360.93 17-Jan-1634,426,3420.94 24-Jan-1632,787,0790.95 31-Jan-1634,721,2500.93 7-Feb-1652,288,6980.76 14-Feb-1636,476,4420.88 21-Feb-1632,804,7330.94 28-Feb-1636,801,8180.91 6-Mar-1635,064,5060.95 13-Mar-1636,374,5160.93 20-Mar-1636,335,4840.93 27-Mar-1635,930,1960.94 3-Apr-1633,668,4510.94 10-Apr-1636,584,0290.9 17-Apr-1637,467,8850.9 24-Apr-1639,607,6950.87 1-May-1642,867,6090.84 8-May-1646,324,5300.82 15-May-1639,914,9970.89 22-May-1636,958,0360.93 29-May-1640,019,0750.94 5-Jun-1640,231,2600.97 12-Jun-1635,580,8201.04 19-Jun-1638,489,9361.02 26-Jun-1636,617,0241.04 3-Jul-1639,993,1861.06 10-Jul-1635,567,5681.1 17-Jul-1632,656,1241.15 24-Jul-1632,339,3771.2 31-Jul-1631,201,5901.23 7-Aug-1633,819,9091.15 14-Aug-1634,386,1771.12 21-Aug-1633,592,0981.1 28-Aug-1633,993,9311.09 4-Sep-1637,130,6891.04 11-Sep-1634,126,7311.08 18-Sep-1631,346,0911.15 25-Sep-1630,305,1131.22 2-Oct-1629,615,0081.23 9-Oct-1628,857,5821.27 16-Oct-1627,707,0471.3 23-Oct-1624,753,5141.34 30-Oct-1621,009,7301.43 6-Nov-1622,534,6981.44 13-Nov-1624,075,1261.36 20-Nov-1624,989,7031.27 27-Nov-1622,923,0631.21 4-Dec-1631,621,2221 11-Dec-1630,093,5410.98 18-Dec-1629,583,8830.96 25-Dec-1630,287,8541 1-Jan-1738,879,7170.89 8-Jan-1738,049,8030.99 15-Jan-1738,295,4880.98 22-Jan-1742,140,3930.94 29-Jan-1739,373,5790.96 5-Feb-1761,034,4570.77 12-Feb-1741,077,4710.87 19-Feb-1733,905,8550.99 26-Feb-1737,007,7980.99 5-Mar-1733,684,1751.13 12-Mar-1732,020,5741.22 19-Mar-1731,595,1251.25 26-Mar-1732,555,1191.24 2-Apr-1734,468,0171.21 9-Apr-1734,785,7131.21 16-Apr-1735,182,3211.23 23-Apr-1735,729,0141.18 30-Apr-1738,315,5001.18 7-May-1747,293,9221.09 14-May-1736,634,2691.19 21-May-1734,397,6511.26 28-May-1737,030,8941.28 4-Jun-1737,352,3611.24 11-Jun-1737,039,8541.21 18-Jun-1738,247,6691.18 25-Jun-1737,305,3081.17 2-Jul-1738,010,4261.21 9-Jul-1739,367,3361.17 16-Jul-1732,455,0471.33 23-Jul-1732,608,3021.31 30-Jul-1731,756,0971.32 6-Aug-1732,529,9201.33 13-Aug-1732,817,2541.33 20-Aug-1729,913,7441.41 27-Aug-1728,785,2801.47 3-Sep-1726,808,4111.57 10-Sep-1726,385,0811.56 17-Sep-1725,394,9031.57 24-Sep-1724,637,1481.62 1-Oct-1724,610,6451.64 8-Oct-1724,397,1661.65 15-Oct-1725,031,5891.58 22-Oct-1726,706,9721.44 29-Oct-1730,237,9111.29 5-Nov-1732,051,5941.19 12-Nov-1732,336,2251.15 19-Nov-1729,253,4841.17 26-Nov-1724,686,6751.24 3-Dec-1733,824,2531.09 10-Dec-1735,634,9131.03 17-Dec-1730,757,7671.07 24-Dec-1729,102,3491.18 31-Dec-1738,267,3420.98 7-Jan-1836,703,1571.13 14-Jan-1837,299,9451.2 21-Jan-1842,939,8221.08 28-Jan-1840,171,6411.09 4-Feb-1862,505,6470.87 11-Feb-1843,167,8060.97 18-Feb-1836,709,8871.08 25-Feb-1840,021,5291.06 4-Mar-1840,741,2141.07 11-Mar-1840,449,6031.09 18-Mar-1841,386,3141.05 25-Mar-1843,409,8361.03 1-Apr-1841,109,6891.1 8-Apr-1842,964,0681.04 15-Apr-1847,098,6781.03 22-Apr-1844,313,9791.04 29-Apr-1843,856,7591.07 6-May-1863,716,1440.89 13-May-1846,371,2461 20-May-1844,458,7981.02 27-May-1847,105,3141.03 3-Jun-1844,705,0391.07 10-Jun-1845,613,3721.03 17-Jun-1844,009,0851.09 24-Jun-1844,742,7501.04 1-Jul-1845,572,7391.05 8-Jul-1847,848,1901.03 15-Jul-1843,126,7731.07 22-Jul-1841,906,9171.1 29-Jul-1840,512,7821.12 5-Aug-1839,427,6671.15 12-Aug-1840,901,9501.12 19-Aug-1840,735,7331.13 26-Aug-1836,867,9751.22 2-Sep-1836,169,1621.29 9-Sep-1837,484,2541.24 Avocado prices and sales for U.S. market Total Volume4234442351423584236542372423794238642393424004240742414424214242842435424424244942456424634247042477424844249142498425054251242519425264253342540425474255442561425684257542582425894259642603426104261742624426314263842645426524265942666426734268042687426944270142708427154272242729427364274342750427574276442771427784278542792427994280642813428204282742834428414284842855428624286942876428834289042897429044291142918429254293242939429464295342960429674297442981429884299543002430094301643023430304303743044430514305843065430724307943086430934310043107431144312143128431354314243149431564316343170431774318443191431984320543212432194322643233432404324743254432614326843275432824328943296433034331043317433244333143338433454335228800396.5728041335.37999999925083647.17000000227297983.67000000238142088.03999999935264336.00999999834426341.86999999732787079.21000000134721249.92000000252288697.89000000136476441.85999999932804733.21999999936801817.6835064506.03999999936374516.14000000136335483.78000000135930195.92000000233668450.54999999736584029.39000000137467885.18999999839607695.29999999742867608.53999999946324529.70000000339914996.74000000236958035.50999999840019075.24000000240231259.6499999993558082038489936.14000000136617023.78999999939993186.03999999935567568.4332656123.62999999932339377.0931201590.21999999933819909.09000000434386177.29999999733592097.71999999933993931.31000000237130688.90999999634126730.95000000331346091.46000000130305112.89000000129615008.48999999828857581.9827707046.8224753513.94999999921009730.21000000122534698.37999999924075126.48999999824989702.7522923062.64999999931621221.89999999930093540.69999999929583882.60999999930287853.69999999938879716.85000000138049802.61999999738295488.31000000242140393.39000000139373579.2561034457.10000000141077470.64999999933905854.57999999837007797.68999999833684175.00999999832020573.94000000131595125.2332555119.3234468017.35999999934785712.54999999735182320.78000000135729013.92000000238315500.4347293921.60000000136634269.03000000134397651.14999999937030893.72999999737352360.59000000437039853.79999999738247669.32999999837305307.6838010426.15999999639367336.1832455047.10999999932608301.51000000231756097.21999999932529920.2332817254.12999999929913744.37000000128785279.7526808410.64999999926385081.35999999925394902.8224637148.37999999924610645.21000000124397166.19000000125031589.0926706971.51000000230237911.2332051594.2399999983233622529253484246866753382425335634913.00999999830757767.03000000129102349.32999999838267341.60999999936703156.71999999937299945.21999999942939821.54999999740171640.84000000462505646.52000000343167806.09000000436709887.49000000240021528.75999999840741214.04999999740449603.11999999741386314.11999999743409835.7541109688.71999999942964067.6847098677.6844313979.29999999743856758.99000000263716144.14999999946371245.84000000444458798.29999999747105314.28000000144705039.04999999745613372.42000000244009084.78000000144742749.88000000345572739.17000000247848189.78999999943126773.21999999941906916.84000000440512782.18999999839427666.53999999940901950.00999999840735732.6836867974.57999999836169161.5737484253.75AveragePrice4234442351423584236542372423794238642393424004240742414424214242842435424424244942456424634247042477424844249142498425054251242519425264253342540425474255442561425684257542582425894259642603426104261742624426314263842645426524265942666426734268042687426944270142708427154272242729427364274342750427574276442771427784278542792427994280642813428204282742834428414284842855428624286942876428834289042897429044291142918429254293242939429464295342960429674297442981429884299543002430094301643023430304303743044430514305843065430724307943086430934310043107431144312143128431354314243149431564316343170431774318443191431984320543212432194322643233432404324743254432610.890.930.980.950.860.930.940.950.930.760.880.940.910.950.930.930.940.940.90.90.870.840.820.890.930.940.971.041.021.041.061.10000000000000011.14999999999999991.21.231.14999999999999991.12000000000000011.10000000000000011.09000000000000011.041.081.14999999999999991.221.231.271.31.341.431.441.361.271.2110.980.9610.890.990.980.940.960.770.870.990.991.12999999999999991.221.251.241.211.211.231.181.181.09000000000000011.191.261.281.241.211.181.171.211.171.331.311.321.331.331.411.471.571.561.571.621.641.651.581.441.291.191.14999999999999991.171.241.09000000000000011.031.071.180.981.12999999999999991.21.081.09000000000000010.870.971.081.061.071.09000000000000011.051.031.10000000000000011.041.031.041.070.8911.021.031.071.031.09000000000000011.041.051.031.071.10000000000000011.12000000000000011.14999999999999991.12000000000000011.12999999999999991.221.291.24 Volume Sold Price USD per Avocado Guidelines for Causal Forecasting Project 1. You should build a causal regression model, where your dependent variable (outcome) is avocado demand. You can build as many regression models as you’d like to see how your adjusted R^2 improves, but you should report on the main tab the results based on the best model that you choose. 2. The historical date (week) and price are the only pieces of data given to you to build your regression model. You can define as many independent variables (predictors) as you’d like but they should be derived based on the date (e.g., trend, seasonality, event) and/or the price. You cannot bring in any external data into your model. However, you can research externally, for example, what might be going on during the dates with “anomalies” (e.g., spikes/dips), and define some indicators if you’d like. You need to explain what the indicator represents, though; you cannot just define a variable called “spike.” Think about this project from the decision maker’s perspective. The goal is to build a prediction model, so all variables that you include in your model should be meaningful variables that can also be included to predict the sales for future periods (e.g., holidays). 3. Here are some examples of independent variables that you could consider: • Price. • Trend, i.e., weekly changes in sales, through a period (time) variable numbering weeks consecutively (1, 2, …, 144). • Seasonality through indicator variables such as monthly or quarterly. • Date-specific special events or holidays through indicator variables. 4. You cannot use any derivations of the quantity (dependent variable) in a given period as an independent variable for that period in the regression equation. You should think about using this equation for future predictions of the quantity; you would not be able to create this variable for the future without knowing the quantity. 5. Your regression models should run on the entire dataset. You cannot use some part of it to report Adjusted R^2 results. You also cannot exclude or change the value of any demand data points. The goal is to find a model that can explain the variability in the entire dataset as much as possible. 6. You can run the regression in Excel. If you prefer to use R, Minitab, SAS or another statistical software for running your regression, that is fine but please make sure to include a screenshot from the full software output and type the required metrics and values in the main tab. 7. I will use Adjusted R^2 as the basis for your grade (instead of R^2) since this metric adjusts for the number of variables you add into the model. The grading will be based on how your Adjusted R^2 compares with the other teams.