This function provides descriptive statistics for a quantitative variable (unquoted). If no keyword arguments for statistics are provided, default values are used. Default stats: c(“n”, “mean”, “sd”)
dstats(oil,operator) #> n mean sd #> 1 53 11522.05 7250.68
You supply statistics argument with the “stats” parameter. You can pass single statistic or multiple statistics as a list object. Singe statistic:
Multiple statistics:
You can supply as many grouping variables as needed.
dstats(soils, pH, Group, Contour, Depth) #> Group Contour Depth n mean sd #> 1 1 Top 0-10 4 5.33 0.24 #> 2 2 Top 10-30 4 4.85 0.33 #> 3 3 Top 30-60 4 4.20 0.23 #> 4 4 Top 60-90 4 3.89 0.14 #> 5 5 Slope 0-10 4 5.51 0.31 #> 6 6 Slope 10-30 4 5.28 0.95 #> 7 7 Slope 30-60 4 4.27 0.49 #> 8 8 Slope 60-90 4 3.93 0.09 #> 9 9 Depression 0-10 4 5.35 0.22 #> 10 10 Depression 10-30 4 4.88 0.37 #> 11 11 Depression 30-60 4 4.36 0.31 #> 12 12 Depression 60-90 4 4.17 0.25
You can pass multiple statistics and multiple grouping variable at the same time.
dstats(soils, pH, Group, Contour, stats=c("mean", "median", "sd")) #> Group Contour mean median sd #> 1 1 Top 5.33 5.27 0.24 #> 2 2 Top 4.85 4.90 0.33 #> 3 3 Top 4.20 4.27 0.23 #> 4 4 Top 3.89 3.88 0.14 #> 5 5 Slope 5.51 5.54 0.31 #> 6 6 Slope 5.28 4.94 0.95 #> 7 7 Slope 4.27 4.06 0.49 #> 8 8 Slope 3.93 3.95 0.09 #> 9 9 Depression 5.35 5.27 0.22 #> 10 10 Depression 4.88 4.85 0.37 #> 11 11 Depression 4.36 4.43 0.31 #> 12 12 Depression 4.17 4.23 0.25
User-defined functions can also be used as the ‘statistic’. It’s passed using the statistic parameter:
#custom statistic my_n <- function(xs) length(xs) #calling the custom statistic dstats(soils, pH, stats = c("my_n")) #> my_n #> 1 48
User-defined functioned can also be passed alongside other statistics:
dstats(soils, pH, Group, Contour, Depth, stats=c("my_n","mean")) #> Group Contour Depth my_n mean #> 1 1 Top 0-10 4 5.33 #> 2 2 Top 10-30 4 4.85 #> 3 3 Top 30-60 4 4.20 #> 4 4 Top 60-90 4 3.89 #> 5 5 Slope 0-10 4 5.51 #> 6 6 Slope 10-30 4 5.28 #> 7 7 Slope 30-60 4 4.27 #> 8 8 Slope 60-90 4 3.93 #> 9 9 Depression 0-10 4 5.35 #> 10 10 Depression 10-30 4 4.88 #> 11 11 Depression 30-60 4 4.36 #> 12 12 Depression 60-90 4 4.17
Other optionalinputs into the function include the ‘na.rm’ parameter. When TRUE, NAs are removed. Default is TRUE
dstats(soils, pH, Depth, stats=c("mean","median","sd"), na.rm=FALSE) #> Depth mean median sd #> 1 0-10 5.40 5.35 0.25 #> 2 10-30 5.00 4.85 0.60 #> 3 30-60 4.28 4.26 0.33 #> 4 60-90 4.00 3.95 0.20
Another optional input is digit, which is the number of decimal points to print. Default = 2.