These methods take objects from various R functions that calculate ANOVA to
create formatted character strings to report the results in accordance with
APA manuscript guidelines. For anova
-objects from model comparisons see
apa_print.list
.
# S3 method for aov
apa_print(
x,
estimate = getOption("papaja.estimate_anova", "ges"),
observed = NULL,
intercept = FALSE,
mse = TRUE,
in_paren = FALSE,
...
)# S3 method for summary.aov
apa_print(
x,
estimate = getOption("papaja.estimate_anova", "ges"),
observed = NULL,
intercept = FALSE,
mse = TRUE,
in_paren = FALSE,
...
)
# S3 method for aovlist
apa_print(
x,
estimate = getOption("papaja.estimate_anova", "ges"),
observed = NULL,
intercept = FALSE,
mse = TRUE,
in_paren = FALSE,
...
)
# S3 method for summary.aovlist
apa_print(
x,
estimate = getOption("papaja.estimate_anova", "ges"),
observed = NULL,
intercept = FALSE,
mse = TRUE,
in_paren = FALSE,
...
)
# S3 method for Anova.mlm
apa_print(
x,
estimate = getOption("papaja.estimate_anova", "ges"),
observed = NULL,
correction = getOption("papaja.sphericity_correction"),
intercept = FALSE,
mse = TRUE,
in_paren = FALSE,
...
)
# S3 method for summary.Anova.mlm
apa_print(
x,
estimate = getOption("papaja.estimate_anova", "ges"),
observed = NULL,
correction = getOption("papaja.sphericity_correction"),
intercept = FALSE,
mse = TRUE,
in_paren = FALSE,
...
)
# S3 method for afex_aov
apa_print(
x,
estimate = getOption("papaja.estimate_anova", "ges"),
observed = NULL,
correction = getOption("papaja.sphericity_correction"),
intercept = FALSE,
mse = TRUE,
in_paren = FALSE,
...
)
# S3 method for anova
apa_print(
x,
estimate = getOption("papaja.estimate_anova", "ges"),
observed = NULL,
intercept = FALSE,
mse = TRUE,
in_paren = FALSE,
...
)
# S3 method for manova
apa_print(x, test = "Pillai", in_paren = FALSE, ...)
# S3 method for summary.manova
apa_print(x, in_paren = FALSE, ...)
apa_print()
-methods return a named list of class apa_results
containing the following elements:
One or more character strings giving point estimates, confidence intervals, and confidence level. A single string is returned in a vector; multiple strings are returned as a named list. If no estimate is available the element is NULL
.
One or more character strings giving the test statistic, parameters (e.g., degrees of freedom), and p-value. A single string is returned in a vector; multiple strings are returned as a named list. If no estimate is available the element is NULL
.
One or more character strings comprised `estimate` and `statistic`. A single string is returned in a vector; multiple strings are returned as a named list.
A data.frame
of class apa_results_table
that contains all elements of estimate
and statistics
. This table can be passed to apa_table()
for reporting.
Column names in apa_results_table
are standardized following the broom glossary (e.g., term
, estimate
conf.int
, statistic
, df
, df.residual
, p.value
). Additionally, each column is labelled (e.g., $\hat{\eta}^2_G$
or $t$
) using the tinylabels package and these labels are used as column names when an apa_results_table
is passed to apa_table()
.
An object containing the results from an analysis of variance ANOVA
Character, function, or data frame. Determines which estimate of effect size is to be used. See details.
Character. The names of the factors that are observed,
i.e., not manipulated. Necessary only for calculating generalized eta
squared; otherwise ignored. If x
is of class afex_aov
, observed
is
automatically deduced from x
.
Logical. Indicates if the intercept term should be included in output.
Logical. Indicates if mean squared errors should be included in
output. The default is TRUE
, but this can be changed either by supplying
a different value in the function call or by changing the global default
via options(papaja.mse = FALSE)
.
Logical. Whether the formatted string is to be reported in
parentheses. If TRUE
, parentheses in the formatted string (e.g., those
enclosing degrees of freedom) are replaced with brackets.
Further arguments that may be passed to apa_num
to format estimates (i.e., columns estimate
and conf.int
).
Character. For repeated-measures ANOVA, the type of
sphericity correction to be used. Possible values are "GG"
for the
Greenhouse-Geisser method (the default), "HF"
for the Huyn-Feldt method,
or "none"
for no correction.
Character. For MANOVA, the multivariate test statistic to be
reported, see summary.manova
.
The factor names are sanitized to facilitate their use as list names (see
Value section). Parentheses are omitted and other non-word characters are
replaced by _
.
Argument estimate
determines which measure of effect size is to be used:
It is currently possible to provide one of three characters to specify the
to-be-calculated effect size: "ges"
for generalized \(eta^2\),
"pes"
for partial \(eta^2\), and "es"
for \(eta^2\).
Note that \(eta^2\) is calculated correctly if and only if the design is
balanced.
It is also possible to provide a data.frame
with columns estimate
,
conf.low
, and conf.high
, which allows for including custom effect-
size measures.
A third option is to provide a function from the effectsize package
that will be used to calculate effect-size measures from x
. If
effectsize is installed (and papaja is loaded), this is the
new default. This default can be changed via
options(papaja.estimate_anova = ...)
.
Bakeman, R. (2005). Recommended effect size statistics for repeated measures designs. Behavior Research Methods , 37 (3), 379--384. doi: tools:::Rd_expr_doi("10.3758/BF03192707")
aov()
, car::Anova()
, apa_print.list()
Other apa_print:
apa_print.BFBayesFactor()
,
apa_print.emmGrid()
,
apa_print.glht()
,
apa_print.htest()
,
apa_print.list()
,
apa_print.lme()
,
apa_print.lm()
,
apa_print.merMod()
,
apa_print()
## From Venables and Ripley (2002) p. 165.
npk_aov <- aov(yield ~ block + N * P * K, npk)
apa_print(npk_aov)
# Use the effectsize package to calculate partial eta-squared with
# confidence intervals
apa_print(npk_aov, estimate = effectsize::omega_squared)
Run the code above in your browser using DataLab