Note how the points not only meander about the x=y line,
-but some of the points tail off near the end of the distributions.
The Tukey mean-difference plotA working example
Many datasets will have distributions that differ not only additively
-and/or Multiplicatively, but also by their general shape. This may
+and/or multiplicatively, but also by their general shape. This may
create complex point patterns in your QQ plot. Such cases can be
indicative of different processes at play for different ranges
of values. We’ll explore such a case using wat95 and
@@ -549,7 +549,7 @@
A working example)
The proposed offsets seem to do a good job in characterizing the -differences in temperatures .
+differences in temperatures.The characterization of the differences in normal temperatures between the old and new set of normals can be formalized as follows:
\[ diff --git a/vignettes/qq.Rmd b/vignettes/qq.Rmd index 2044393..bc47a47 100755 --- a/vignettes/qq.Rmd +++ b/vignettes/qq.Rmd @@ -261,7 +261,7 @@ y <- rnorm(100) eda_qq(x, y) ``` -Note how the points not only meander about the `x=y` line, but some of the points tail off near the end of the distributions. +Note how the points not only meander about the `x=y` line, but some of the points tail off near the end of the distribution. # Power transformation @@ -308,7 +308,7 @@ par(OP) # A working example -Many datasets will have distributions that differ not only additively and/or Multiplicatively, but also by their general shape. This may create complex point patterns in your QQ plot. Such cases can be indicative of different *processes* at play for different ranges of values. We'll explore such a case using `wat95` and `wat05` dataframes available in this package. The data represent derived normal temperatures for the 1981-2010 period (`wat95`) and the 1991-2020 period (`wat05`) for the city of Waterville, Maine (USA). We will subset the data to the daily *average* normals, `avg`: +Many datasets will have distributions that differ not only additively and/or multiplicatively, but also by their general shape. This may create complex point patterns in your QQ plot. Such cases can be indicative of different *processes* at play for different ranges of values. We'll explore such a case using `wat95` and `wat05` dataframes available in this package. The data represent derived normal temperatures for the 1981-2010 period (`wat95`) and the 1991-2020 period (`wat05`) for the city of Waterville, Maine (USA). We will subset the data to the daily *average* normals, `avg`: ```{r} old <- wat95$avg # legacy temperature normals @@ -378,7 +378,7 @@ par(OP) ``` -The proposed offsets seem to do a good job in characterizing the differences in temperatures . +The proposed offsets seem to do a good job in characterizing the differences in temperatures. The characterization of the differences in normal temperatures between the old and new set of normals can be formalized as follows: