Learn R Programming

orddom (version 3.1)

delta_gr: Cliff's delta Graphics and Interpretation

Description

Returns a graphical representation and interpretation of Cliff's delta

Usage

delta_gr(x,y, ... ,dv=2)

Arguments

x
A 1-column matrix with optional column name containing all $n_x$ values or scores of group X or 1 (e.g. control or pretest group.).
y
A 1-column matrix with optional column name containing all $n_y$ values of group Y or 2 (e.g. experimental or post-test group). For paired comparisons (e.g. pre-post), $n_x = n_y$ is required. See orddom for details.
...
Other arguments to be passed on to the orddom function, such as (for example): - paired: to compare dependent data (e.g. pre-post) set to paired=TRUE , - alpha for the respective significance level to be used, e.g.alpha=.01 for 1 - onetailed to generate one-sided testing p and confidence interval (CI) values set to onetailed=TRUE , - studdist to obtain CI based on normal distribution z values (instead of Student distribution t) set to studdist=FALSE for 1 - symmetric to obtain symmetric rather than asymmetric CIs (see orddom for details) set to symmetric=TRUE . - onetailed for one-sided rather than the default two-tailed testing. - x.name to assign an individual label to group x (i.e. 1st or control or pretest group). - y.name to label the y input matrix or group y (i.e. 2nd or experimental or posttest group). - description This argument allows for assigning a string (as title or description) for the ordinal comparison outputs.
dv
(For paired comparisons (dv=3) only.) Determines which ordinal $\delta$ statistics are to be returned. Set to: - dv=1 [within] to return an analysis for the $n_x=n_y$ within-pair changes, - dv=2 [between] to return an analysis for the overall distribution changes, based on all $n^2-n = n(n-1)$ score comparisons between y and x where $i \ne j$, - dv=3 [combined] to return an analysis for the combined inference $d_w + d_b$. It is advisable to use dv=3 in combination with symmetric=TRUE.

Value

See Also

orddom