Monica Guimaraes

In this liveProject series, you’ll take on the role of a data analyst working for the Jones Family Philanthropic Foundation. The board of directors is interested in learning about the life expectancy of Americans so that they can better target their charitable spending.

Your challenges in this series of liveProjects include running a regression analysis on demographic data to find factors related to life expectancy, and answering data-mining questions about the distribution of these demographic variables. To do this, you’ll clean and model your data, assess the accuracy of your findings, and present your results—all with open-source tools from the Python ecosystem.

In this liveProject, you’ll perform a regression analysis on precleaned data to determine factors relating to American life expectancy. You will learn how to do a comprehensive regression analysis and how to select a model in the presence of multicollinearity. You will use the libraries developed in the second and third projects to check the validity of your final model.

In this liveProject, you’ll build your own Python data library to check three of the assumptions of the regression model: normality, linearity, and constant variance. Confidence in your regression models depends on how well you have satisfied these assumptions. Once you’ve developed functions and plots that can check these assumptions, you’ll master techniques for correcting them. With this library, you will expand your data science toolbox with important diagnostics tools that will allow you to be confident in your results.

In this liveProject, you’ll build your own Python data library that can detect unusual data. This data can affect regression analysis, and so your library will help spot it before it can negatively affect results. You’ll program functions to detect high-leverage points, outliers, and influential observations. Through the analysis of multiple examples, you'll gain a deep understanding of the kind of problems that can arise with real data.

In this liveProject, you’ll use the Python data ecosystem to explore how demographic data affects American life expectancy. You’ll use pandas and NumPy to clean and merge a newly collected data set Matplotlib, and seaborn to create a variety of plots that showcase the distribution of the data and expose the relationships between the variables.