I was assigned the following three articles for review:
- Using Graphs To Make the Complex Simple: the Medicare Drug Plan as an Example
- A Rose by Another Name
- Visual Aids When Comparing An Apple to the Stars
You could see my reviews of the first two articles by the following link:
https://docs.google.com/presentation/d/1k85VBoIvT0eEIffOMkIJL0r7eWn74esh420jayOgHGU/edit#slide=id.p
If there is any issue viewing the work, please email me at lyiheng@bgsu.edu.
Just feel free to leave comments and questions.
Thank you!
Hi Yiheng,
You shared some good reviews of Howard Wainer’ s articles. Here are three questions I have for you:
1) What’s the advantages of “the Roses” compared with the pie charts?
2) In slide 6, you mention that the history of “the Roses” might give us some insight on how we could improve dot plots and histograms, or even create a brand-new format. So do you have any idea about how to improve dot plots or histograms? Or what kind of brand-new format can we create in the future?
3) In slide 8, you mention “The previous reference line where the costs are equal is no longer than crucial since it’s exactly the horizontal line at y=0”. What does it mean?
Hi Yiheng,
Nice job on the presentation.
1) My first question is about the roses. Just to clarify, in the “Modern Rose” graph of the respiratory symptoms among coal miners, is the area of the circle quarter proportional to the number of observations in that category? It appears that way and is clearly a better choice than using the radius as the quantitative variable representation. How do you feel about the modern rose method of representing data? At least to my eyes, it is difficult to compare the numbers of coal miners in each category accurately without looking at the number legend. While it is easy to see which groups is the largest, second largest, etc., it is more difficult to tell if one group is twice as big, or perhaps 1.5 times as big is another group. I found myself having to do what Cleveland calls “table look-up” when making these relative comparisons. Do you think this type of graph is the most effective way to display this data?
2) Do you agree with the author that a rose chart has all the advantages over a pie chart? I am not a fan of pie charts, but think I would have had an easier time with the coal miner data if it had been displayed by a pie chart. I think a rose chart that relies on area of a pie slice determined solely by radius is much harder to visually interpret than an area only dependent on angle.
3) Now that you know what you know from this course, which version of the medicare data, graph 1 with the reference line or graph 2 showing savings as a function of current drug expenditure, delivers the “message” of the data more effectively? This topic is very relevant to the US right now, as healthcare reform is sure to be an important topic in the next few elections. For the untrained consumer of graphs, which graph most clearly communicates the information? I would choose the second graph myself, but feel that some less educated readers might freak out when they see negative numbers on the y-axis.