This week’s discussion topic allows you to create and clean your own dataset similar to what you will be required to do for your Term Research Project for the course. In Week 4, you will complete the first two sections in the Word Document attached below (Introduction and Purpose, Definition of Variables). You will also insert your formatted descriptive statistics table into the third section. Once you have completed these sections, you should copy and paste these items into the text box provided in the discussion post. You should also attach your formatted dataset along with your completed word document.
To begin, go to the World Bank Data Database and access the Millennium Devlopment Goals using this link:
https://databank.worldbank.org/source/millennium-development-goals
Choose at least 5 independent variables (predictors) and 1 dependent variable (outcome). For your dependent variable, you should choose GNI per capita, Atlas method (current US$). You may choose any other variables as predictors but note that not all countries are surveyed for all variables. You will have missing data as some countries may not have observations for the specific variables that you choose. You will have to delete any country that has too much missing data for any of your variables, so be careful which variables you choose. Your initial dataset will need a sample size of 100 or greater for each variable. To increase the number of countries with acceptable observations, you will program the databank to generate an average value for the span of 2006-2015 rather generating output for any one specific year. There are many variables in this data bank series, so you should try to be unique and capture items of interest to you. If you choose the exact same variables as someone else, I may require you to change at least one. If your sample size is large enough, I may select certain cases for you to analyze so that your results will be unique. I will approve the final data frame in the order that they are originally posted. You are not required to include any references in your descriptions or definitions. The World Bank Dataset that you attach will be sufficient for your reference. Also keep in mind that you will not be graded on your hypotheses, so you do not have to spend hours upon hours trying to come up with a perfect prediction model. You will be graded on your ability to download, clean, and present data. The description and hypothesized relationships are primarily there so that I can determine whether or not you know how to perform and read the results.