For my project, I’ve chosen to create a scatter plot graph to illustrate my data. I’ve mapped individual plant height on the x axis against the number of berries per plant on the y axis. I divided my data into three subsets: human trimmed plants near trails, untrimmed plants near trails, and untrimmed plants off trail. Together the subsets make up all my data, so I wanted them on the same graph to look at overall patterns. However, I mapped them as different coloured series to help the viewer discern quickly if one subset of plant had significantly different numbers than the others in either variable.
Overall, I’m pleased with how the graph turned out. Its creation did involve some grappling with excel, but at the end of the day my data was not too extensive and was fairly easy to organize. I was unsure about whether to add linear lines of best fit or connect the data points to help viewers better visualize the pattern. I decided not to do either of these things because I felt they made the graph visually cluttered and harder to read.
The data in the figure indicates that there is at least some level of positive correlation between plant height and number of berries. I will have to do some more analysis but this graph is roughly consistent with what I had expected to see, though perhaps not quite as linear. However, I am surprised to see less differences between the subsets than I expected. I really thought the human impacted plants would carry a lot less berries, but this potential relationship does not seem to hold true.
