As such, you will notice that with my scatterplots, in particular, I am adamant about plotting the raw data points along linear trends, as I think it is important to recognize that significant associations between variables often still leave much to be explained. Often times, I encounter plots–mainly from regression analyses–where all I can see are the trends (e.g., lines of best fit), with no attempts made to visualize uncertainty or error in the those trends. I think it is important for visualizations of data to plot both signal and noise.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |