In this module, you’ll learn how to use Tableau to do with data what spies do when observing their surroundings: get an overview of the data, narrow in on certain aspects of the data that seem abnormal, and then analyze the data. Tableau is a great tool for facilitating the overview, zoom, then filter details-on-demand approach. Tableau is a lot like a more powerful version of Excel's pivot table and pivot chart functionality.

In this module, you'll be guided through a mini-case study that will illustrate the first three parts of the FACT model, with a focus on the C, or calculations part of the FACT model. First, you will perform a correlation analysis to identify two-way relationships, and analyze correlations using a correlation matrix and scatter plots. You will then build on your knowledge of correlations and learn how to perform regression analysis in Excel. Finally, you will learn how to interpret and evaluate the diagnostic metrics and plots of a regression analysis.

In this module, you’ll learn how the regression algorithm can be applied to fit a wide variety of relationships among data. Specifically, you’ll learn how to set up the data and run a regression to estimate the parameters of nonlinear relationships, categorical independent variables. You’ll also investigate if the effect of an independent variable depends on the level of another independent variable by including interaction terms in the multiple regression model. Another aspect of this module is learning how to evaluate models, regression or otherwise, to find the most favorable levels of the independent variables. For models that explain revenue, the most favorable levels of the independent variables will maximize revenue. In contrast, if you have a model that describes costs, like a budget, then the most favorable levels of the independent variables will minimize costs. Optimizing models can be difficult because there are so many inputs and constraints that need to be managed. In this module, you’ll learn how to use the Solver Add-In to find the optimal level of inputs. For some models, the dependent variable is a binary variable that has only two values, such as true/false, win/lose, or invest/not invest. In these situations, a special type of regression, called logistic regression, is used to predict how each observation should be classified. You’ll learn about the logit transformation that’s used to convert a binary outcome to a linear relationship with the independent variables. Excel doesn’t have a built-in logistic regression tool, so you’ll learn how to manually design a logistic regression model, and then optimize the parameters using the Solver Add-In tool.

The lessons in this module are organized around several useful tasks, including stacking multiple dataframes together into one dataframe, creating multiple histograms to accompany the descriptive statistics, and learning how to perform k-means clustering. After going through this module, you’ll not only gain a foundation to help you understand coding, but you’ll also learn more about analyzing financial data. Along the way, I hope that you’ll also pick up on a few other useful Excel functions.