*YOU JUST NEED CONTINUING TO STEP 3,8 – FINISH AS I ALREADY DONE STEP 1,2,4,5,6,7*
The purpose of this research is to identify the best combination of independent variables (drivers of the key performance indicator) to predict the dependent variable (key performance indicator). The dependent variable in this case is job performance however you will need decide which one variable (from those in the table below see Table 1) is the best measure of job performance. The statistical technique you need to use is regression analysis (multiple linear regression OR logistic regression). In the SPSS data file you will notice a column labelled data_type (0= training data, 1= test data). You need to refine your model using the training data then test your final model with the test data. There are many metrics for model validation, we’ll use one known as Mean Absolute Error (also called MAE). With the MAE metric, we take the absolute value of each error (error=actualpredicted). This converts each error to a positive number. We then take the average of those absolute errors