Scenario There are many universities and colleges and many state-funded institutions that are public and private, providing tertiary education in the United States. Eduresearch is an organization that researches different aspects of the United States' education sector. You are Angelo De Focatis, a business analyst who works for Eduresearch in one of their research projects. You have been asked by the General Manager, Aaron Byner, to analyse a sample of data collected from a recent survey of 150 randomly selected tertiary education providers. The email request together with guidelines (shown in purple) is presented below. Consider these guidelines carefully. To: Angelo De Focatis From: Aaron Byner - General Manager Subject: Analysis of Offers, Fees and Expenditure Dear Angelo, The senior management team is awaiting reports on the following projects: Project 1: Academics' weekly earnings analysis The data set includes a random sample of 150 academics teaching in a sample of selected universities. Build a multiple regression model to predict the amount earned per week. Your model should provide insights into what factors influence the academics' weekly earnings as well as the ability to predict their earnings per week for various scenarios (Age, experience, course type, consultation, contribution to profit, weekly earnings). For this analysis, you will need to build a multiple regression model using weekly earnings as the dependent variable. You should follow the model building process introduced in the lecture and tutorial. To select variables to include in the model, start with transforming categorical variables into dummy variables. When transforming course type into dummy variables, consider Marketing as the baseline category. This means that, the created dummy variables for course type should only include Accounting, Art and Law. Then, create scatter diagrams and calculate relevant model summary coefficients. Afterwards, run the multiple regression analysis and assess the model for overall significance (F test with alpha set at 0.05). In the next step(s), if the overall model is found to be significant, in a stepwise fashion, remove variables that are least likely to be contributing to any significant change in the dependent variable one at a time (if there are any), by conducting a series of t-tests with alpha set at 0.05. Project 2: Tertiary education providers' profit analysis Average profits of the selected sample of tertiary education providers from August 2011 to July 2020 is provided. The management team is interested in forecasting profit, as they believe there is a time-based pattern in the income and expenses of the sector. Implement a proper forecasting model to address this request and provide your interpretation. For this study, you need to consider several forecasting models and evaluate model performance in terms of forecasting accuracy and model fit. You should consider the following: (a) Both 3 and 5 periods centred moving average models. (b) Exponential smoothing models with alpha weights set to 0.4, 0.5 and 0.6. (c) Fitting linear, logarithmic, polynomial (order 2), and power trend lines to the original data. i. What do the errors say about the usefulness of the forecasting models? ii. What are the R2 values of the models? iii. What would be the forecasted profit for the next five-time periods (August 2020 to December 2020) using each of the models you have built? I look forward to your response. Sincerely, Aaron Byner General Manager