Final Option

I really like this jitter plot because it allows me to show the raw data points, while also providing annotations that allow me to communicate the main point of the graph (average salaries are lower for women) that is understandable by a public audience. I also added the caption including the data source.

Earlier Option 1

This is the first boxplot that I started out with. I like that this shows the mean and spread of the distributions, but I don’t like that you can’t see the actual data points and that you can’t really get a sense of the discrepancy in the number of female and male professors. Boxplots are also less understandable by the public.

Earlier Option 2

I like this boxplot better because I can see the raw data points. I overlayed the actual datapoints with the boxplot, but it is still not really appropriate for a public audience.

Final Option

I like this version histogram the best because it is more concise and easy to see the distributions, even though they are on top of each other, allowing the space for annotations. This one might be better for a public audience, as well, as means are clearly denoted.

Earlier Option 1

Earlier Option 2

I like this histogram because it gives you a sense of numbers (there are not enough female professors), and also a sense of how much less they are paid, but it’s probably not for a public audience.

Final Option

I like this Waffle plot the best just because it’s the most visually appealing, and I feel like a public audience and the scientific community could understand! The next step would be to try to use glyphs, but there’s something wrong with the fonts on my computer that I can’t quite figure out. Also, I am a bit reluctant to use stereotypical images/graphics representing men and women- something to think about for the future!

Earlier Option 1

This is just a simple stacked bar graph, but as we talked about in class, these kind of stink because they are hard to compare across groups.

Earlier Option 2

The dodged bar graph with coord flip allows for easier comparisons, but it’s not totally special looking, which brought me to the Waffle plot!

Final Option

This is a little bit different take on the same idea, and also adds a different element. It looks at the proportion of men’s salaries that the women’s salaries represent in the different professor ranks, but ALSO adds another piece of information- the discipline that they are working in (either theoretical or applied). Thus, this graph highlights that the problem is really in the theoretical disciplines. I also like that the data is represented as a proportion, and I liked to play around with the annotations and geom_segment.

Earlier Option 1

I started with the most traditional way of representing this kind of data - a bar graph. However, apparantly dynamite plots are bad…..! In addition to often misrepresenting data, this type of bar graph with error bars is mostly used only for a scientific audience.

Earlier Option 2

This is a similar type of plot as the prior bar graph, but uses dots instead, circumventing the issue with the dynamite plot. However, it still isn’t that exciting, and I would like a plot that is understandable to both scholarly and lay audiences.

Bonus Plot 1

This is my favorite type of regression/scattorplot because I can see the raw data over the regression line.

Bonus Plot 2

This is my variation of Plot 1, but I don’t like it as much because really only scholarly audiences know what the se ribbon represent. I love data points!!

Bonus Plot 3

Another regression/scattorplot with the raw data points over it.

Bonus Plot 4

This is my variation of Plot 3, but, again, I don’t like it as much because really only scholarly audiences know what the se ribbon represent.