Data analysis is a useful component of outcome measurement because it helps you quantify your support and provides a much more compelling message when communicating your investment to stakeholders. One way you can communicate your results to important stakeholders is by giving presentations. And using visual representations to present your data makes your analysis easier to understand. One visualization that is useful for presenting you data is using geometric tiles to showcase missing data in R.


For example, the code below downloads the bank dataset from the UCI machine learning and changes the values for few of the variables to NA to showcase the plot_Missing function. The initial data set has no missing values.



The for functions change random values for the 'age', 'job','loan','campaign', 'default', 'housing', 'day_of_week', and 'previous' variables to NA to denote missing values.


And then the missing values are plotted using the plot_Missing function resulting in the following visualization. The white bars denote missing values, while the black bars denote non missing values.




















The code for the full demonstration is given below.