varRegressors
(Package: lmSupport) :
Adds actual numeric regressors for factor to dataframe as new variables
Adds new variables/columns in dataframe to represent numeric regressors for a factor. Factors are coded using their currently defined contrast codes. This function is useful for control of a factor covariate when graphing and ignoring this factor and/or other lower-level control variables. For this purpose, POC coding will typically be set for factor prior to using lm.codeRegressor
● Data Source:
CranContrib
● Keywords: regression
● Alias: varRegressors
●
0 images
|
modelPredictions
(Package: lmSupport) :
Provides predicted values for sample or new data. New predictions include SEs
If no data are provided, modelPredictions returns a numeric vector predicted values for the sample, functioning as a simple wrapper for fitted.values(). If a dataframe with new values for Xs are provided, modelPredictions adds prediced values and SEs for these new data to the dataframe using predict() from car package.
● Data Source:
CranContrib
● Keywords: regression
● Alias: modelPredictions
●
0 images
|
modelErrors
(Package: lmSupport) :
Returns model errors (residuals) from lm object
Simple wrapper to return model errors using residuals() function. Implemented simply to match terminology to 610/710 GLM course. Also prints(but does not return) model SSE
● Data Source:
CranContrib
● Keywords: manip
● Alias: modelErrors
●
0 images
|
|
Calculates F-test to compare two models to determine if ModelA significantly reduces SSE from ModelC. Also reports Partial eta2 and Delta R2 for this model comparison. ModelC should contain subset of ModelA regressors.
● Data Source:
CranContrib
● Keywords: regression
● Alias: modelCompare
●
0 images
|
|
Removes cases from dataframe. Cases can be numeric or character. If numeric, rownames must be able to be converted to numeric. Returns warning if cases not found in dataframe.
● Data Source:
CranContrib
● Keywords: manip
● Alias: dfRemoveCases
●
0 images
|
modelEffectSizes
(Package: lmSupport) :
Calculates effect size indices based on Sums of Squares
Calculates unique SSRs, SSE, SST. Based on these SSs, it calculates partial eta2 and delta R2 for all effects in a linear model object. For categorical variables coded as factors, it calculates these for multi-df effect. Manually code regressors to get 1 df effects Uses car::Anova() with Type 3 error
● Data Source:
CranContrib
● Keywords: regression
● Alias: modelEffectSizes
●
0 images
|
dfWriteDat
(Package: lmSupport) :
Saves dataframe as tab-delimited text file with typical Curtin lab parameters
Saves a dataframe as a tab-delimited data file with standard Curtin lab format. Will add rownames as a first column in .dat file and label this column with SubID
● Data Source:
CranContrib
● Keywords: manip
● Alias: dfWriteDat
●
0 images
|
varDescribe
(Package: lmSupport) :
Provides typical descriptive statistics for data frame
Provides three levels of detail regarding descriptive statistics for a data frame. Based on describe() function from psych package
● Data Source:
CranContrib
● Keywords: manip
● Alias: varDescribe
●
0 images
|
varPlot
(Package: lmSupport) :
Creates histogram, optional rug/strip and density plots, and generates univariate descriptive statistics
Represents important aspects of a variable/vector both visually (histogram, rug or strip, and density plots) and with descriptive statistics of varying detail
● Data Source:
CranContrib
● Keywords: descriptives
● Alias: varPlot
●
0 images
|
varOdd
(Package: lmSupport) :
Tests if Number is Odd
Returns result of test if Number is Odd.
● Data Source:
CranContrib
● Keywords: manip
● Alias: varOdd
●
0 images
|
providing 
.