Skip to content

HTTPS clone URL

Subversion checkout URL

You can clone with HTTPS or Subversion.

Download ZIP
Browse files

tweaks for version 4.0-2

  • Loading branch information...
commit c96b3c9de8fd6714bc91196c06811a1aa9c5fc0a 1 parent f00a601
@mike-lawrence authored
View
5 .Rbuildignore
@@ -1,2 +1,3 @@
-.git/
-.md
+.git*
+.md
+.DS_Store
View
57 CHANGES
@@ -1,34 +1,55 @@
-4.0-0
-- rolled back R version dependency to 2.11-0
+4.0-2
+- updated .Rbuildignore to ignore .gitignore
+- reduced time it takes to check examples by encapsulating unnecessary examples in \dontrun{}
+
+4.0-1
+- All functions
+- Previously, ez used the .() function to permit referral to column names without having to use quotes or the my_data$my_column format. One still needs to use .() when supplying multiple column names, but in cases where an argument is being supplied with a single column name, you no longer even have to type .(); you can simply type the column name.
- ezANOVA
-- fixed bug that caused ezANOVA to return type-2 SS results even when type-3 SS results were requested
-- fixed bug causing error when design is completely between-Ss and unbalanced
-- corrected documentation, which previously reported an interpretation of a p-value as "the probability of the null hypothesis, given the data", when the proper interpretation is (of course) "probability of the data, given the null hypothesis".
+- Added ability to specify covariates (applies to ezPlot and ezStats too)
+- Added "within_full" argument to implement proper automatic collapsing of cell means when values supplied to "within" represent a subset of the full design. (applies to ezPlot and ezStats too)
+- Fixed bug preventing use of returned aov object with stats::TukeyHSD()
+- Fixed bug that caused ezANOVA to return type-2 SS results even when type-3 SS results were requested
+- Fixed bug causing error when design is completely between-Ss and unbalanced (applies to ezPlot and ezStats too)
+- Corrected documentation, which previously reported an interpretation of a p-value as "the probability of the null hypothesis, given the data", when the proper interpretation is (of course) "probability of the data, given the null hypothesis".
+- ezBoot
+- Added "show_progress" argument that permits turning on/off the progress bar
+- Added ability to perform computation in parallel using multiple cores
+- Added ability to perform a residuals bootstrap
+- Switched from "timeCI" progress bar to the simpler/faster "time" progress bar
+- Fixed bug causing error when lmer=TRUE and only 1 predictor variable is supplied
+- ezCor
+- Added ability to apply various corrections for multiple comparisons
- ezMixed
+- Switched to "bits" representation of likelihood ratios
+- Added ability to capture possibly-non-linear effects of numeric predictors via generalized additive modelling (no more polynomials!)
+- Added ability to characterize predictors' effects on the distribution of residuals
- Added ability to estimate models in parallel using multiple cores
+- Added ability to store results to file, saving RAM during computations
+- Added ability to pass-through arguments to mgcv::gam and lme4::lmer/lme4::glmer (useful for modifying the control parameters for example)
- Added the left-hand-side of the formula to the formulas returned by ezMixed (this makes it easier to use the formulas for follow-up exploration)
- Added ability to specify covariates
- Fixed bug that might cause an error with specifying "results_as_progress=TRUE"
- Fixed bug preventing exploration of polynomials greater than 9
-- ezResample
-- Speed improvements achieved by more efficient code
-- Added "resample_between" argument
-- eliminated superfluous "dv" argument
-- ezBoot
-- Added "show_progress" argument that permits turning on/off the progress bar
+- ezPerm
- Added ability to perform computation in parallel using multiple cores
-- Added ability to perform a residuals bootstrap
-- Switched from "timeCI" progress bar to the simpler/faster "time" progress bar
-- Fixed bug causing error when lmer=TRUE and only 1 predictor variable is supplied
-- ezBootPlot
+- ezPlot
+- Added ability to print code to create the ggplot2 plot object (useful for learning ggplot2 or applying more nuanced tweaks than would be available from simply modifying the ggplot2 object typically returned)
+- ezPlot2 (previously ezBootPlot)
- Added ability to suppress creating a plot object (useful when simply trying to obtain the bootstrap stats)
+- Added a number of arguments to tweak the aesthetics
+- Added ability to print code to create the ggplot2 plot object (useful for learning ggplot2 or applying more nuanced tweaks than would be available from simply modifying the ggplot2 object typically returned)
- Fixed bug that ignored the "alarm" argument
-- ezPerm
-- Added ability to perform computation in parallel using multiple cores
- ezPredict
+- Added ability to compute parametric bootstrap samples, yielding output visualizable via ezPlot2
- Fixed bug that prevented obtaining predictions when the name of one variable appeared in the name of other variables.
- Fixed bug preventing custom specification of to_predict
-- Added ability to compute parametric bootstrap samples, yielding output visualizable via ezBootPlot
+- ezResample
+- Speed improvements achieved by more efficient code
+- Added "resample_between" argument
+- eliminated superfluous "dv" argument
+- progress_time_CI
+- Removed
3.0-0
- added urls in all documentation pointing to the bug-report/feature-request site (https://github.com/mike-lawrence/ez/issues) and the discussion group (http://groups.google.com/group/ez4r).
View
4 DESCRIPTION
@@ -1,6 +1,6 @@
Package: ez
-Version: 4.0-1
-Date: 2012-08-06
+Version: 4.0-2
+Date: 2012-08-07
Title: Easy analysis and visualization of factorial experiments.
Author: Michael A. Lawrence <Mike.Lawrence@dal.ca>
Maintainer: Michael A. Lawrence <Mike.Lawrence@dal.ca>
View
2  R/ez-internal.R
@@ -241,7 +241,7 @@ function(data, dv, wid, within, within_full, within_covariates, between, between
return(to_return)
}
)
- wid_temp = data.frame(table(temp$wid))
+ wid_temp = data.frame(table(temp[,names(temp)==wid]))
if(any(wid_temp$Freq>1)){
warning(paste('The column supplied as the wid variable contains non-unique values across levels of the supplied between-Ss variables. Automatically fixing this by generating unique wid labels.',sep=''),immediate.=TRUE,call.=FALSE)
data[,names(data)==wid] = as.character(data[,names(data)==wid])
View
13 man/ezANOVA.Rd
@@ -116,6 +116,7 @@ for the bug/issue tracker and the link to the mailing list.
\code{\link{ezBoot}}, \code{\link{ezMixed}}, \code{\link{ezPerm}}, \code{\link{ezPlot}}, \code{\link{ezStats}}
}
\examples{
+
#Read in the ANT data (see ?ANT).
data(ANT)
head(ANT)
@@ -134,7 +135,8 @@ rt_anova = ezANOVA(
#Show the ANOVA and assumption tests.
print(rt_anova)
-#Run an ANOVA on the mean_rt data, ignoring group.
+\dontrun{
+#Run an ANOVA on the mean correct RT data, ignoring group.
rt_anova2 = ezANOVA(
data = ANT[ANT$error==0,]
, dv = rt
@@ -144,6 +146,7 @@ rt_anova2 = ezANOVA(
#Show the ANOVA and assumption tests.
print(rt_anova2)
+}
#Run a purely between-Ss ANOVA on the mean_rt data.
#NOTE use of within_full to ensure that the data are
@@ -163,6 +166,7 @@ print(rt_anova3)
#add a within-Ss effect to be used as a covariate
ANT$rt2 = ANT$rt + ANT$block*1000 #additive with and independent of the other predictors!
+\dontrun{
#Run an anova that doesn't use the covariate
rt_anova4a = ezANOVA(
data = ANT[ANT$error==0,]
@@ -175,8 +179,9 @@ rt_anova4a = ezANOVA(
#Show the ANOVA and assumption tests.
# Note loss of power to observe the within effects
print(rt_anova4a)
+}
-#Run an anova that doesn't use the covariate
+#Run an anova that does use the covariate
rt_anova4b = ezANOVA(
data = ANT[ANT$error==0,]
, dv = rt2
@@ -195,6 +200,7 @@ print(rt_anova4b)
ANT$bc = as.numeric(as.character(ANT$subnum))\%\%10 #Note that the effect is balanced across groups
ANT$rt3 = ANT$rt + ANT$bc*1000 #additive with and independent of the other predictors!
+\dontrun{
#Run an anova that doesn't use the covariate
rt_anova5a = ezANOVA(
data = ANT[ANT$error==0,]
@@ -207,8 +213,9 @@ rt_anova5a = ezANOVA(
#Show the ANOVA and assumption tests.
# Note loss of power to observe the between effects
print(rt_anova5a)
+}
-#Run an anova that doesn't use the covariate
+#Run an anova that does use the covariate
rt_anova5b = ezANOVA(
data = ANT[ANT$error==0,]
, dv = rt2
View
4 man/ezBoot.Rd
@@ -72,6 +72,7 @@ for the bug/issue tracker and the link to the mailing list.
\code{link{ezANOVA}}, \code{\link{ezMixed}}, \code{\link{ezPerm}}, \code{\link{ezPlot2}}, \code{\link{ezResample}}
}
\examples{
+
#Read in the ANT data (see ?ANT).
data(ANT)
head(ANT)
@@ -87,6 +88,7 @@ rt = ezBoot(
, iterations = 1e1 #1e3 or higher is best for publication
)
+\dontrun{
#plot the full design
p = ezPlot2(
preds = rt
@@ -112,5 +114,5 @@ p = ezPlot2(
, split = cue
)
print(p)
-
+}
}
View
3  man/ezDesign.Rd
@@ -66,6 +66,7 @@ ezDesign(
)
#subnum #7 is missing data from the last half of the experiment
+\dontrun{
ezDesign(
data = ANT2
, x = flank
@@ -86,5 +87,5 @@ ezDesign(
##they made all errors in this condition
#finally, subnum#12 has virtually no data, suggesting that they mistakenly
##swapped responses
-
+}
}
View
3  man/ezPlot.Rd
@@ -152,6 +152,7 @@ head(ANT)
ezPrecis(ANT)
+\dontrun{
#Run an ANOVA on the mean correct RT data.
mean_rt_anova = ezANOVA(
data = ANT[ANT$error==0,]
@@ -163,7 +164,7 @@ mean_rt_anova = ezANOVA(
#Show the ANOVA and assumption tests.
print(mean_rt_anova)
-
+}
#Plot the main effect of group.
group_plot = ezPlot(
View
28 man/ezPredict.Rd
@@ -50,37 +50,25 @@ for the bug/issue tracker and the link to the mailing list.
data(ANT)
head(ANT)
-#fit a mixed effects model to the error rate data
-er_fit = lmer(
- formula = error ~ cue*flank*group + (1|subnum)
- , family = binomial
- , data = ANT
+#fit a mixed effects model to the rt data
+rt_fit = lmer(
+ formula = rt ~ cue*flank*group + (1|subnum)
+ , data = ANT[ANT$error==0,]
)
#obtain the predictions from the model
-er_preds = ezPredict(
- fit = er_fit
+rt_preds = ezPredict(
+ fit = rt_fit
)
#visualize the predictions
ezPlot2(
- preds = er_preds
+ preds = rt_preds
, x = flank
, row = cue
, col = group
- , y_lab = 'Error rate (log-odds)'
+ , y_lab = 'RT (ms)'
)
-#visualize the predictions as a difference
-# score for the group effect
-ezPlot2(
- preds = er_preds
- , x = flank
- , row = cue
- , diff = group
- , y_lab = 'Group effect on\nError rate (log-odds)'
-)
-
-
}
View
4 man/ezResample.Rd
@@ -67,7 +67,7 @@ var_boots = ldply(
, between = .(group)
)
cell_vars = ddply(
- .data = this_resample
+ .data = idata.frame(this_resample)
, .variables = .(subnum,cue,flank,group)
, .fun = function(x){
to_return = data.frame(
@@ -77,7 +77,7 @@ var_boots = ldply(
}
)
mean_cell_vars = ddply(
- .data = cell_vars
+ .data = idata.frame(cell_vars)
, .variables = .(cue,flank,group)
, .fun = function(x){
to_return = data.frame(
Please sign in to comment.
Something went wrong with that request. Please try again.