"ggplot2 is a plotting system for R, based on the grammar of graphics, which tries to take the good parts of base and lattice graphics and none of the bad parts.
R Programming Tutorial: Make Scatterplots with Ggplot2
Make Scatterplots with Ggplot2 is an excerpt from, R Programming LiveLessons (Video Training): Fundamentals to Advanced: ...
Thanks for the nice video. Seeing that most of the points were far outside
the confidence interval of the smoothers, made me wonder how to interpret
this.
Does this mean that if I´d repeat the experiment with the same number of
observations, I ll have a 95% chance of having a regression within the
confidence interval? What if I´d look at only one random Baltimore child (1
observation), would the probability that its NocturnalSymp would be in the
confidence interval, still be 95%?
No. With smoothing you are sacrificing some statistical accuracy in order to get a trend line in form of a smoothed function (instead of points). The confidence intervals represent how sure you can be about this general trend based on some simplifying assumptions (these vary for each method) and the data. That is why the CI widens dramaticly when you have less observations.
你好,我这个版本的R里面貌似没有diamonds这个自带的数据。我用mtcars的数据来仿照你的步骤走,到qplot basic
use里面的第三步,有x*y*z的这一步时就没办法做出你这样的图了。报错是 Error in eval(expr,envir,enclos):
dims [products 72] do not match the length of object [100].