This function calculates representative values of a vector, like minimum/maximum values or lower, median and upper quartile etc., which can be used for numeric vectors to plot adjusted predictions at these representative values.
values_at(x, values = "meansd")representative_values(x, values = "meansd")
A numeric vector of length two or three, representing the required
values from x
, like minimum/maximum value or mean and +/- 1 SD. If
x
is missing, a function, pre-programmed with n
and
length
is returned. See examples.
A numeric vector.
Character vector, naming a pattern for which representative values should be calculcated.
"minmax":
(default) minimum and maximum values (lower and upper bounds)
of the moderator are used to plot the interaction between independent
variable and moderator.
"meansd"
: uses the mean value of the moderator as well as one standard
deviation below and above mean value to plot the effect of the moderator
on the independent variable.
"zeromax"
: is similar to the "minmax"
option, however, 0
is always
used as minimum value for the moderator. This may be useful for predictors
that don't have an empirical zero-value, but absence of moderation should
be simulated by using 0 as minimum.
"fivenum":
calculates and uses the Tukey's five number summary (minimum,
lower-hinge, median, upper-hinge, maximum) of the moderator value.
"quart"
: calculates and uses the quartiles (lower, median and upper) of
the moderator value, including minimum and maximum value.
"quart2"
: calculates and uses the quartiles (lower, median and upper) of
the moderator value, excluding minimum and maximum value.
"terciles"
: calculates and uses the terciles (lower and upper third) of
the moderator value, including minimum and maximum value.
"terciles2"
: calculates and uses the terciles (lower and upper third)
of the moderator value, excluding minimum and maximum value.
an option to compute a range of percentiles is also possible, using
"percentile"
, followed by the percentage of the range. For example,
"percentile95"
will calculate the 95% range of the variable.
"all"
: uses all values of the moderator variable.
data(efc)
values_at(efc$c12hour)
values_at(efc$c12hour, "quart2")
mean_sd <- values_at(values = "meansd")
mean_sd(efc$c12hour)
Run the code above in your browser using DataLab