Module # 7 assignment

Create your own visual analytics based on Distribution analysis. The visual will follow our textbook recommendation to use grid to enhance the comparisons between scatter plots or your variables. Attached is data set

I used in my presentation. Another popular  data set is taken from R mtcarsLinks to an external site..  You can retrieve this data set from R by typing> mtcars
Testing one of these two data sets regarding visual distributions as discussed in this module, and post on your blog the results and express your opinion about Few's recommendations in your testing.
How to import the data to RStudio?
Follow this guideline: https://support.rstudio.com/hc/en-us/articles/218611977-Importing-Data-with-RStudioLinks to an external site.
Another great resource from Distribution is the blog by Nathan Yau - the author of our textbook Visualize This. This blog posting title: How to Visualize and Compare Distributions in R.
https://flowingdata.com/2012/05/15/how-to-visualize-and-compare-distributions/Links to an external site.
Your assignment
Test one of these two data sets ( Download data setor mtcarsLinks to an external site.) regarding visual distributions as discussed in this module. Post in your blog the results and address how in your opinion, how Few's recommendations help or disputable.



According to Few, three characteristics summarize the distribution of a set of values when the distribution is displayed visually. They are spread, center, and shape. Spread is a simple measure of dispersion. Center is the central tendency of a set of values. Shape shows where the values are located throughout the spread. 


The first visualizations I produced were scatterplots. I incorporated regression lines as well as grids to allow the viewer to understand trends between these respective variables. I used the mtcars dataset. I showed the relationship between variables such as weight, mpg, horsepower, and quarter-mile time. 






The next visualization is a scatterplot matrix between the variables mpg, hp, wt, and disp. 


According to Few, this visualization would not meet his criteria. This chart is much more complex than the standard scatterplot. This creates confusion and uncertainty which leads against Few's principles. The individual scatterplots that were shown above (scroll up) would fall under Few's recommendations as they are easy to read while showcasing relationships between variables. These individual scatterplots use an appropriate variety of color to not only catch the attention of the audience, but also maintain clearness and effectiveness. 

Comments

Popular posts from this blog

Final Project

Module # 12

Module # 13