| Title: | Influential Case Detection Methods for Factor Analysis and Structural Equation Models |
|---|---|
| Description: | Tools for detecting and summarize influential cases that can affect exploratory and confirmatory factor analysis models as well as structural equation models more generally (Chalmers, 2015, <doi:10.1177/0146621615597894>; Flora, D. B., LaBrish, C. & Chalmers, R. P., 2012, <doi:10.3389/fpsyg.2012.00055>). |
| Authors: | Phil Chalmers [aut, cre] |
| Maintainer: | Phil Chalmers <[email protected]> |
| License: | GPL (>= 2) |
| Version: | 0.7.7 |
| Built: | 2024-11-11 03:29:23 UTC |
| Source: | https://github.com/philchalmers/faoutlier |
Influential case detection methods for factor analysis and SEM
Implements robust Mahalanobis methods, generalized Cook's distances, likelihood ratio tests, model implied residuals, and various graphical methods to help detect and summarize influential cases that can affect exploratory and confirmatory factor analyses.
Phil Chalmers [email protected]
Chalmers, R. P. & Flora, D. B. (2015). faoutlier: An R Package for Detecting Influential Cases in Exploratory and Confirmatory Factor Analysis. Applied Psychological Measurement, 39, 573-574. doi:10.1177/0146621615597894
Flora, D. B., LaBrish, C. & Chalmers, R. P. (2012). Old and new ideas for data screening and assumption testing for exploratory and confirmatory factor analysis. Frontiers in Psychology, 3, 1-21. doi:10.3389/fpsyg.2012.00055
The forward search algorithm begins by selecting a homogeneous subset of cases based on a maximum likelihood criteria and continues to add individual cases at each iteration given an acceptance criteria. By default the function will add cases that contribute most to the likelihood function and that have the closest robust Mahalanobis distance, however model implied residuals may be included as well.
forward.search( data, model, criteria = c("GOF", "mah"), n.subsets = 1000, p.base = 0.4, print.messages = TRUE, ... ) ## S3 method for class 'forward.search' print(x, ncases = 10, stat = "GOF", ...) ## S3 method for class 'forward.search' plot( x, y = NULL, stat = "GOF", main = "Forward Search", type = c("p", "h"), ylab = "obs.resid", ... )forward.search( data, model, criteria = c("GOF", "mah"), n.subsets = 1000, p.base = 0.4, print.messages = TRUE, ... ) ## S3 method for class 'forward.search' print(x, ncases = 10, stat = "GOF", ...) ## S3 method for class 'forward.search' plot( x, y = NULL, stat = "GOF", main = "Forward Search", type = c("p", "h"), ylab = "obs.resid", ... )
data |
matrix or data.frame |
model |
if a single numeric number declares number of factors to extract in
exploratory factor analysis. If |
criteria |
character strings indicating the forward search method
Can contain |
n.subsets |
a scalar indicating how many samples to draw to find a homogeneous starting base group |
p.base |
proportion of sample size to use as the base group |
print.messages |
logical; print how many iterations are remaining? |
... |
additional parameters to be passed |
x |
an object of class |
ncases |
number of final cases to print in the sequence |
stat |
type of statistic to use. Could be 'GOF', 'RMR', or 'gCD' for the model chi squared value, root mean square residual, or generalized Cook's distance, respectively |
y |
a |
main |
the main title of the plot |
type |
type of plot to use, default displays points and lines |
ylab |
the y label of the plot |
Note that forward.search is not limited to confirmatory factor analysis and
can apply to nearly any model being studied
where detection of influential observations is important.
Phil Chalmers [email protected]
Chalmers, R. P. & Flora, D. B. (2015). faoutlier: An R Package for Detecting Influential Cases in Exploratory and Confirmatory Factor Analysis. Applied Psychological Measurement, 39, 573-574. doi:10.1177/0146621615597894
Flora, D. B., LaBrish, C. & Chalmers, R. P. (2012). Old and new ideas for data screening and assumption testing for exploratory and confirmatory factor analysis. Frontiers in Psychology, 3, 1-21. doi:10.3389/fpsyg.2012.00055
Mavridis, D., & Moustaki, I. (2008). Detecting Outliers in Factor Analysis Using the Forward Search Algorithm. Multivariate Behavioral Research, 43, 453-475, doi:10.1080/00273170802285909
gCD, GOF, LD,
robustMD, setCluster
## Not run: #run all internal gCD and GOF functions using multiple cores setCluster() #Exploratory nfact <- 3 (FS <- forward.search(holzinger, nfact)) (FS.outlier <- forward.search(holzinger.outlier, nfact)) plot(FS) plot(FS.outlier) #Confirmatory with sem model <- sem::specifyModel() F1 -> Remndrs, lam11 F1 -> SntComp, lam21 F1 -> WrdMean, lam31 F2 -> MissNum, lam41 F2 -> MxdArit, lam52 F2 -> OddWrds, lam62 F3 -> Boots, lam73 F3 -> Gloves, lam83 F3 -> Hatchts, lam93 F1 <-> F1, NA, 1 F2 <-> F2, NA, 1 F3 <-> F3, NA, 1 (FS <- forward.search(holzinger, model)) (FS.outlier <- forward.search(holzinger.outlier, model)) plot(FS) plot(FS.outlier) #Confirmatory with lavaan model <- 'F1 =~ Remndrs + SntComp + WrdMean F2 =~ MissNum + MxdArit + OddWrds F3 =~ Boots + Gloves + Hatchts' (FS <- forward.search(holzinger, model)) (FS.outlier <- forward.search(holzinger.outlier, model)) plot(FS) plot(FS.outlier) ## End(Not run)## Not run: #run all internal gCD and GOF functions using multiple cores setCluster() #Exploratory nfact <- 3 (FS <- forward.search(holzinger, nfact)) (FS.outlier <- forward.search(holzinger.outlier, nfact)) plot(FS) plot(FS.outlier) #Confirmatory with sem model <- sem::specifyModel() F1 -> Remndrs, lam11 F1 -> SntComp, lam21 F1 -> WrdMean, lam31 F2 -> MissNum, lam41 F2 -> MxdArit, lam52 F2 -> OddWrds, lam62 F3 -> Boots, lam73 F3 -> Gloves, lam83 F3 -> Hatchts, lam93 F1 <-> F1, NA, 1 F2 <-> F2, NA, 1 F3 <-> F3, NA, 1 (FS <- forward.search(holzinger, model)) (FS.outlier <- forward.search(holzinger.outlier, model)) plot(FS) plot(FS.outlier) #Confirmatory with lavaan model <- 'F1 =~ Remndrs + SntComp + WrdMean F2 =~ MissNum + MxdArit + OddWrds F3 =~ Boots + Gloves + Hatchts' (FS <- forward.search(holzinger, model)) (FS.outlier <- forward.search(holzinger.outlier, model)) plot(FS) plot(FS.outlier) ## End(Not run)
Compute generalize Cook's distances (gCD's) for exploratory and confirmatory FA. Can return DFBETA matrix if requested. If mirt is used, then the values will be associated with the unique response patterns instead.
gCD(data, model, vcov_drop = FALSE, progress = TRUE, ...) ## S3 method for class 'gCD' print(x, ncases = 10, DFBETAS = FALSE, ...) ## S3 method for class 'gCD' plot( x, y = NULL, main = "Generalized Cook Distance", type = c("p", "h"), ylab = "gCD", ... )gCD(data, model, vcov_drop = FALSE, progress = TRUE, ...) ## S3 method for class 'gCD' print(x, ncases = 10, DFBETAS = FALSE, ...) ## S3 method for class 'gCD' plot( x, y = NULL, main = "Generalized Cook Distance", type = c("p", "h"), ylab = "gCD", ... )
data |
matrix or data.frame |
model |
if a single numeric number declares number of factors to extract in
exploratory factor analysis (requires complete dataset, i.e., no missing).
If |
vcov_drop |
logical; should the variance-covariance matrix of the parameter
estimates be based on the unique |
progress |
logical; display the progress of the computations in the console? |
... |
additional parameters to be passed |
x |
an object of class |
ncases |
number of extreme cases to display |
DFBETAS |
logical; return DFBETA matrix in addition to gCD? If TRUE, a list is returned |
y |
a |
main |
the main title of the plot |
type |
type of plot to use, default displays points and lines |
ylab |
the y label of the plot |
Note that gCD is not limited to confirmatory factor analysis and
can apply to nearly any model being studied
where detection of influential observations is important.
Phil Chalmers [email protected]
Chalmers, R. P. & Flora, D. B. (2015). faoutlier: An R Package for Detecting Influential Cases in Exploratory and Confirmatory Factor Analysis. Applied Psychological Measurement, 39, 573-574. doi:10.1177/0146621615597894
Flora, D. B., LaBrish, C. & Chalmers, R. P. (2012). Old and new ideas for data screening and assumption testing for exploratory and confirmatory factor analysis. Frontiers in Psychology, 3, 1-21. doi:10.3389/fpsyg.2012.00055
Pek, J. & MacCallum, R. C. (2011). Sensitivity Analysis in Structural Equation Models: Cases and Their Influence. Multivariate Behavioral Research, 46(2), 202-228.
LD, obs.resid, robustMD, setCluster
## Not run: #run all gCD functions using multiple cores setCluster() #Exploratory nfact <- 3 (gCDresult <- gCD(holzinger, nfact)) (gCDresult.outlier <- gCD(holzinger.outlier, nfact)) plot(gCDresult) plot(gCDresult.outlier) #------------------------------------------------------------------- #Confirmatory with sem model <- sem::specifyModel() F1 -> Remndrs, lam11 F1 -> SntComp, lam21 F1 -> WrdMean, lam31 F2 -> MissNum, lam41 F2 -> MxdArit, lam52 F2 -> OddWrds, lam62 F3 -> Boots, lam73 F3 -> Gloves, lam83 F3 -> Hatchts, lam93 F1 <-> F1, NA, 1 F2 <-> F2, NA, 1 F3 <-> F3, NA, 1 (gCDresult2 <- gCD(holzinger, model)) (gCDresult2.outlier <- gCD(holzinger.outlier, model)) plot(gCDresult2) plot(gCDresult2.outlier) #------------------------------------------------------------------- #Confirmatory with lavaan model <- 'F1 =~ Remndrs + SntComp + WrdMean F2 =~ MissNum + MxdArit + OddWrds F3 =~ Boots + Gloves + Hatchts' (gCDresult2 <- gCD(holzinger, model, orthogonal=TRUE)) (gCDresult2.outlier <- gCD(holzinger.outlier, model, orthogonal=TRUE)) plot(gCDresult2) plot(gCDresult2.outlier) # categorical data with mirt library(mirt) data(LSAT7) dat <- expand.table(LSAT7) model <- mirt.model('F = 1-5') result <- gCD(dat, model) plot(result) mod <- mirt(dat, model) res <- mirt::residuals(mod, type = 'exp') cbind(res, gCD=round(result$gCD, 3)) ## End(Not run)## Not run: #run all gCD functions using multiple cores setCluster() #Exploratory nfact <- 3 (gCDresult <- gCD(holzinger, nfact)) (gCDresult.outlier <- gCD(holzinger.outlier, nfact)) plot(gCDresult) plot(gCDresult.outlier) #------------------------------------------------------------------- #Confirmatory with sem model <- sem::specifyModel() F1 -> Remndrs, lam11 F1 -> SntComp, lam21 F1 -> WrdMean, lam31 F2 -> MissNum, lam41 F2 -> MxdArit, lam52 F2 -> OddWrds, lam62 F3 -> Boots, lam73 F3 -> Gloves, lam83 F3 -> Hatchts, lam93 F1 <-> F1, NA, 1 F2 <-> F2, NA, 1 F3 <-> F3, NA, 1 (gCDresult2 <- gCD(holzinger, model)) (gCDresult2.outlier <- gCD(holzinger.outlier, model)) plot(gCDresult2) plot(gCDresult2.outlier) #------------------------------------------------------------------- #Confirmatory with lavaan model <- 'F1 =~ Remndrs + SntComp + WrdMean F2 =~ MissNum + MxdArit + OddWrds F3 =~ Boots + Gloves + Hatchts' (gCDresult2 <- gCD(holzinger, model, orthogonal=TRUE)) (gCDresult2.outlier <- gCD(holzinger.outlier, model, orthogonal=TRUE)) plot(gCDresult2) plot(gCDresult2.outlier) # categorical data with mirt library(mirt) data(LSAT7) dat <- expand.table(LSAT7) model <- mirt.model('F = 1-5') result <- gCD(dat, model) plot(result) mod <- mirt(dat, model) res <- mirt::residuals(mod, type = 'exp') cbind(res, gCD=round(result$gCD, 3)) ## End(Not run)
Compute Goodness of Fit distances between models when removing the case.
If mirt is used, then the values will be associated with the unique response patterns instead.
GOF(data, model, M2 = TRUE, progress = TRUE, ...) ## S3 method for class 'GOF' print(x, ncases = 10, digits = 5, ...) ## S3 method for class 'GOF' plot( x, y = NULL, main = "Goodness of Fit Distance", type = c("p", "h"), ylab = "GOF", absolute = FALSE, ... )GOF(data, model, M2 = TRUE, progress = TRUE, ...) ## S3 method for class 'GOF' print(x, ncases = 10, digits = 5, ...) ## S3 method for class 'GOF' plot( x, y = NULL, main = "Goodness of Fit Distance", type = c("p", "h"), ylab = "GOF", absolute = FALSE, ... )
data |
matrix or data.frame |
model |
if a single numeric number declares number of factors to extract in
exploratory factor analysis (requires complete dataset, i.e., no missing).
If |
M2 |
logical; use the M2 statistic for when using mirt objects instead of G2? |
progress |
logical; display the progress of the computations in the console? |
... |
additional parameters to be passed |
x |
an object of class |
ncases |
number of extreme cases to display |
digits |
number of digits to round in the printed result |
y |
a |
main |
the main title of the plot |
type |
type of plot to use, default displays points and lines |
ylab |
the y label of the plot |
absolute |
logical; use absolute values instead of deviations? |
Note that GOF is not limited to confirmatory factor analysis and
can apply to nearly any model being studied
where detection of influential observations is important.
Phil Chalmers [email protected]
Chalmers, R. P. & Flora, D. B. (2015). faoutlier: An R Package for Detecting Influential Cases in Exploratory and Confirmatory Factor Analysis. Applied Psychological Measurement, 39, 573-574. doi:10.1177/0146621615597894
Flora, D. B., LaBrish, C. & Chalmers, R. P. (2012). Old and new ideas for data screening and assumption testing for exploratory and confirmatory factor analysis. Frontiers in Psychology, 3, 1-21. doi:10.3389/fpsyg.2012.00055
gCD, LD, obs.resid,
robustMD, setCluster
## Not run: #run all GOF functions using multiple cores setCluster() #Exploratory nfact <- 3 (GOFresult <- GOF(holzinger, nfact)) (GOFresult.outlier <- GOF(holzinger.outlier, nfact)) plot(GOFresult) plot(GOFresult.outlier) ## include a progress bar GOFresult <- GOF(holzinger, nfact, progress = TRUE) #------------------------------------------------------------------- #Confirmatory with sem model <- sem::specifyModel() F1 -> Remndrs, lam11 F1 -> SntComp, lam21 F1 -> WrdMean, lam31 F2 -> MissNum, lam42 F2 -> MxdArit, lam52 F2 -> OddWrds, lam62 F3 -> Boots, lam73 F3 -> Gloves, lam83 F3 -> Hatchts, lam93 F1 <-> F1, NA, 1 F2 <-> F2, NA, 1 F3 <-> F3, NA, 1 (GOFresult <- GOF(holzinger, model)) (GOFresult.outlier <- GOF(holzinger.outlier, model)) plot(GOFresult) plot(GOFresult.outlier) #------------------------------------------------------------------- #Confirmatory with lavaan model <- 'F1 =~ Remndrs + SntComp + WrdMean F2 =~ MissNum + MxdArit + OddWrds F3 =~ Boots + Gloves + Hatchts' (GOFresult <- GOF(holzinger, model, orthogonal=TRUE)) (GOFresult.outlier <- GOF(holzinger.outlier, model, orthogonal=TRUE)) plot(GOFresult) plot(GOFresult.outlier) # categorical data with mirt library(mirt) data(LSAT7) dat <- expand.table(LSAT7) model <- mirt.model('F = 1-5') result <- GOF(dat, model) plot(result) ## End(Not run)## Not run: #run all GOF functions using multiple cores setCluster() #Exploratory nfact <- 3 (GOFresult <- GOF(holzinger, nfact)) (GOFresult.outlier <- GOF(holzinger.outlier, nfact)) plot(GOFresult) plot(GOFresult.outlier) ## include a progress bar GOFresult <- GOF(holzinger, nfact, progress = TRUE) #------------------------------------------------------------------- #Confirmatory with sem model <- sem::specifyModel() F1 -> Remndrs, lam11 F1 -> SntComp, lam21 F1 -> WrdMean, lam31 F2 -> MissNum, lam42 F2 -> MxdArit, lam52 F2 -> OddWrds, lam62 F3 -> Boots, lam73 F3 -> Gloves, lam83 F3 -> Hatchts, lam93 F1 <-> F1, NA, 1 F2 <-> F2, NA, 1 F3 <-> F3, NA, 1 (GOFresult <- GOF(holzinger, model)) (GOFresult.outlier <- GOF(holzinger.outlier, model)) plot(GOFresult) plot(GOFresult.outlier) #------------------------------------------------------------------- #Confirmatory with lavaan model <- 'F1 =~ Remndrs + SntComp + WrdMean F2 =~ MissNum + MxdArit + OddWrds F3 =~ Boots + Gloves + Hatchts' (GOFresult <- GOF(holzinger, model, orthogonal=TRUE)) (GOFresult.outlier <- GOF(holzinger.outlier, model, orthogonal=TRUE)) plot(GOFresult) plot(GOFresult.outlier) # categorical data with mirt library(mirt) data(LSAT7) dat <- expand.table(LSAT7) model <- mirt.model('F = 1-5') result <- GOF(dat, model) plot(result) ## End(Not run)
A sample of 100 simulated cases from the infamous Holzinger dataset using 9 variables.
Phil Chalmers [email protected]
Chalmers, R. P. & Flora, D. B. (2015). faoutlier: An R Package for Detecting Influential Cases in Exploratory and Confirmatory Factor Analysis. Applied Psychological Measurement, 39, 573-574. doi:10.1177/0146621615597894
Flora, D. B., LaBrish, C. & Chalmers, R. P. (2012). Old and new ideas for data screening and assumption testing for exploratory and confirmatory factor analysis. Frontiers in Psychology, 3, 1-21. doi:10.3389/fpsyg.2012.00055
A sample of 100 simulated cases from the infamous Holzinger dataset using 9 variables, but with 1 outlier added to the dataset. The first row was replaced by adding 2 to five of the observed variables (odd-numbered items) and subtracting 2 from the other four observed variables (even-numbered items).
Phil Chalmers [email protected]
Chalmers, R. P. & Flora, D. B. (2015). faoutlier: An R Package for Detecting Influential Cases in Exploratory and Confirmatory Factor Analysis. Applied Psychological Measurement, 39, 573-574. doi:10.1177/0146621615597894
Flora, D. B., LaBrish, C. & Chalmers, R. P. (2012). Old and new ideas for data screening and assumption testing for exploratory and confirmatory factor analysis. Frontiers in Psychology, 3, 1-21. doi:10.3389/fpsyg.2012.00055
Compute likelihood distances between models when removing the case. If there are no
missing data then the GOF will often provide equivalent results. If mirt is used,
then the values will be associated with the unique response patterns instead.
LD(data, model, progress = TRUE, ...) ## S3 method for class 'LD' print(x, ncases = 10, digits = 5, ...) ## S3 method for class 'LD' plot( x, y = NULL, main = "Likelihood Distance", type = c("p", "h"), ylab = "LD", absolute = FALSE, ... )LD(data, model, progress = TRUE, ...) ## S3 method for class 'LD' print(x, ncases = 10, digits = 5, ...) ## S3 method for class 'LD' plot( x, y = NULL, main = "Likelihood Distance", type = c("p", "h"), ylab = "LD", absolute = FALSE, ... )
data |
matrix or data.frame |
model |
if a single numeric number declares number of factors to extract in
exploratory factor analysis (requires complete dataset, i.e., no missing).
If |
progress |
logical; display the progress of the computations in the console? |
... |
additional parameters to be passed |
x |
an object of class |
ncases |
number of extreme cases to display |
digits |
number of digits to round in the printed result |
y |
a |
main |
the main title of the plot |
type |
type of plot to use, default displays points and lines |
ylab |
the y label of the plot |
absolute |
logical; use absolute values instead of deviations? |
Note that LD is not limited to confirmatory factor analysis and
can apply to nearly any model being studied
where detection of influential observations is important.
Phil Chalmers [email protected]
Chalmers, R. P. & Flora, D. B. (2015). faoutlier: An R Package for Detecting Influential Cases in Exploratory and Confirmatory Factor Analysis. Applied Psychological Measurement, 39, 573-574. doi:10.1177/0146621615597894
Flora, D. B., LaBrish, C. & Chalmers, R. P. (2012). Old and new ideas for data screening and assumption testing for exploratory and confirmatory factor analysis. Frontiers in Psychology, 3, 1-21. doi:10.3389/fpsyg.2012.00055
gCD, GOF, obs.resid,
robustMD, setCluster
## Not run: #run all LD functions using multiple cores setCluster() #Exploratory nfact <- 3 (LDresult <- LD(holzinger, nfact)) (LDresult.outlier <- LD(holzinger.outlier, nfact)) plot(LDresult) plot(LDresult.outlier) ## add a progress meter LDresult <- LD(holzinger, nfact, progress = TRUE) #------------------------------------------------------------------- #Confirmatory with sem model <- sem::specifyModel() F1 -> Remndrs, lam11 F1 -> SntComp, lam21 F1 -> WrdMean, lam31 F2 -> MissNum, lam42 F2 -> MxdArit, lam52 F2 -> OddWrds, lam62 F3 -> Boots, lam73 F3 -> Gloves, lam83 F3 -> Hatchts, lam93 F1 <-> F1, NA, 1 F2 <-> F2, NA, 1 F3 <-> F3, NA, 1 (LDresult <- LD(holzinger, model)) (LDresult.outlier <- LD(holzinger.outlier, model)) plot(LDresult) plot(LDresult.outlier) #------------------------------------------------------------------- #Confirmatory with lavaan model <- 'F1 =~ Remndrs + SntComp + WrdMean F2 =~ MissNum + MxdArit + OddWrds F3 =~ Boots + Gloves + Hatchts' (LDresult <- LD(holzinger, model, orthogonal=TRUE)) (LDresult.outlier <- LD(holzinger.outlier, model, orthogonal=TRUE)) plot(LDresult) plot(LDresult.outlier) # categorical data with mirt library(mirt) data(LSAT7) dat <- expand.table(LSAT7) model <- mirt.model('F = 1-5') LDresult <- LD(dat, model) plot(LDresult) ## End(Not run)## Not run: #run all LD functions using multiple cores setCluster() #Exploratory nfact <- 3 (LDresult <- LD(holzinger, nfact)) (LDresult.outlier <- LD(holzinger.outlier, nfact)) plot(LDresult) plot(LDresult.outlier) ## add a progress meter LDresult <- LD(holzinger, nfact, progress = TRUE) #------------------------------------------------------------------- #Confirmatory with sem model <- sem::specifyModel() F1 -> Remndrs, lam11 F1 -> SntComp, lam21 F1 -> WrdMean, lam31 F2 -> MissNum, lam42 F2 -> MxdArit, lam52 F2 -> OddWrds, lam62 F3 -> Boots, lam73 F3 -> Gloves, lam83 F3 -> Hatchts, lam93 F1 <-> F1, NA, 1 F2 <-> F2, NA, 1 F3 <-> F3, NA, 1 (LDresult <- LD(holzinger, model)) (LDresult.outlier <- LD(holzinger.outlier, model)) plot(LDresult) plot(LDresult.outlier) #------------------------------------------------------------------- #Confirmatory with lavaan model <- 'F1 =~ Remndrs + SntComp + WrdMean F2 =~ MissNum + MxdArit + OddWrds F3 =~ Boots + Gloves + Hatchts' (LDresult <- LD(holzinger, model, orthogonal=TRUE)) (LDresult.outlier <- LD(holzinger.outlier, model, orthogonal=TRUE)) plot(LDresult) plot(LDresult.outlier) # categorical data with mirt library(mirt) data(LSAT7) dat <- expand.table(LSAT7) model <- mirt.model('F = 1-5') LDresult <- LD(dat, model) plot(LDresult) ## End(Not run)
Compute model predicted residuals for each variable using regression estimated factor scores.
obs.resid(data, model, ...) ## S3 method for class 'obs.resid' print(x, restype = "obs", ...) ## S3 method for class 'obs.resid' plot( x, y = NULL, main = "Observed Residuals", type = c("p", "h"), restype = "obs", ... )obs.resid(data, model, ...) ## S3 method for class 'obs.resid' print(x, restype = "obs", ...) ## S3 method for class 'obs.resid' plot( x, y = NULL, main = "Observed Residuals", type = c("p", "h"), restype = "obs", ... )
data |
matrix or data.frame |
model |
if a single numeric number declares number of factors to extract in
exploratory factor analysis. If |
... |
additional parameters to be passed |
x |
an object of class |
restype |
type of residual used, either |
y |
a |
main |
the main title of the plot |
type |
type of plot to use, default displays points and lines |
Phil Chalmers [email protected]
Chalmers, R. P. & Flora, D. B. (2015). faoutlier: An R Package for Detecting Influential Cases in Exploratory and Confirmatory Factor Analysis. Applied Psychological Measurement, 39, 573-574. doi:10.1177/0146621615597894
Flora, D. B., LaBrish, C. & Chalmers, R. P. (2012). Old and new ideas for data screening and assumption testing for exploratory and confirmatory factor analysis. Frontiers in Psychology, 3, 1-21. doi:10.3389/fpsyg.2012.00055
## Not run: data(holzinger) data(holzinger.outlier) #Exploratory nfact <- 3 (ORresult <- obs.resid(holzinger, nfact)) (ORresult.outlier <- obs.resid(holzinger.outlier, nfact)) plot(ORresult) plot(ORresult.outlier) #------------------------------------------------------------------- #Confirmatory with sem model <- sem::specifyModel() F1 -> Remndrs, lam11 F1 -> SntComp, lam21 F1 -> WrdMean, lam31 F2 -> MissNum, lam41 F2 -> MxdArit, lam52 F2 -> OddWrds, lam62 F3 -> Boots, lam73 F3 -> Gloves, lam83 F3 -> Hatchts, lam93 F1 <-> F1, NA, 1 F2 <-> F2, NA, 1 F3 <-> F3, NA, 1 (ORresult <- obs.resid(holzinger, model)) (ORresult.outlier <- obs.resid(holzinger.outlier, model)) plot(ORresult) plot(ORresult.outlier) #------------------------------------------------------------------- #Confirmatory with lavaan model <- 'F1 =~ Remndrs + SntComp + WrdMean F2 =~ MissNum + MxdArit + OddWrds F3 =~ Boots + Gloves + Hatchts' (obs.resid2 <- obs.resid(holzinger, model, orthogonal=TRUE)) (obs.resid2.outlier <- obs.resid(holzinger.outlier, model, orthogonal=TRUE)) plot(obs.resid2) plot(obs.resid2.outlier) ## End(Not run)## Not run: data(holzinger) data(holzinger.outlier) #Exploratory nfact <- 3 (ORresult <- obs.resid(holzinger, nfact)) (ORresult.outlier <- obs.resid(holzinger.outlier, nfact)) plot(ORresult) plot(ORresult.outlier) #------------------------------------------------------------------- #Confirmatory with sem model <- sem::specifyModel() F1 -> Remndrs, lam11 F1 -> SntComp, lam21 F1 -> WrdMean, lam31 F2 -> MissNum, lam41 F2 -> MxdArit, lam52 F2 -> OddWrds, lam62 F3 -> Boots, lam73 F3 -> Gloves, lam83 F3 -> Hatchts, lam93 F1 <-> F1, NA, 1 F2 <-> F2, NA, 1 F3 <-> F3, NA, 1 (ORresult <- obs.resid(holzinger, model)) (ORresult.outlier <- obs.resid(holzinger.outlier, model)) plot(ORresult) plot(ORresult.outlier) #------------------------------------------------------------------- #Confirmatory with lavaan model <- 'F1 =~ Remndrs + SntComp + WrdMean F2 =~ MissNum + MxdArit + OddWrds F3 =~ Boots + Gloves + Hatchts' (obs.resid2 <- obs.resid(holzinger, model, orthogonal=TRUE)) (obs.resid2.outlier <- obs.resid(holzinger.outlier, model, orthogonal=TRUE)) plot(obs.resid2) plot(obs.resid2.outlier) ## End(Not run)
Obtain Mahalanobis distances using the robust
computing methods found in the MASS package. This function is generally only applicable
to models with continuous variables.
robustMD(data, method = "mve", ...) ## S3 method for class 'robmah' print(x, ncases = 10, digits = 5, ...) ## S3 method for class 'robmah' plot(x, y = NULL, type = "xyplot", main, ...)robustMD(data, method = "mve", ...) ## S3 method for class 'robmah' print(x, ncases = 10, digits = 5, ...) ## S3 method for class 'robmah' plot(x, y = NULL, type = "xyplot", main, ...)
data |
matrix or data.frame |
method |
type of estimation for robust means and covariance
(see |
... |
additional arguments to pass to |
x |
an object of class |
ncases |
number of extreme cases to print |
digits |
number of digits to round in the final result |
y |
empty parameter passed to |
type |
type of plot to display, can be either |
main |
title for plot. If missing titles will be generated automatically |
Phil Chalmers [email protected]
Chalmers, R. P. & Flora, D. B. (2015). faoutlier: An R Package for Detecting Influential Cases in Exploratory and Confirmatory Factor Analysis. Applied Psychological Measurement, 39, 573-574. doi:10.1177/0146621615597894
Flora, D. B., LaBrish, C. & Chalmers, R. P. (2012). Old and new ideas for data screening and assumption testing for exploratory and confirmatory factor analysis. Frontiers in Psychology, 3, 1-21. doi:10.3389/fpsyg.2012.00055
## Not run: data(holzinger) output <- robustMD(holzinger) output plot(output) plot(output, type = 'qqplot') ## End(Not run)## Not run: data(holzinger) output <- robustMD(holzinger) output plot(output) plot(output, type = 'qqplot') ## End(Not run)
This function defines a object that is placed in a relevant internal environment defined in faoutlier.
Internal functions will utilize this object automatically to capitalize on parallel
processing architecture. The object defined is a call from parallel::makeCluster(). Note that
if you are defining other parallel objects (for simulation designs, for example) it is not recommended
to define a cluster.
setCluster(spec, ..., remove = FALSE)setCluster(spec, ..., remove = FALSE)
spec |
input that is passed to |
... |
additional arguments to pass to |
remove |
logical; remove previously defined cluster object? |
Phil Chalmers [email protected]
Chalmers, R. P. & Flora, D. B. (2015). faoutlier: An R Package for Detecting Influential Cases in Exploratory and Confirmatory Factor Analysis. Applied Psychological Measurement, 39, 573-574. doi:10.1177/0146621615597894
Flora, D. B., LaBrish, C. & Chalmers, R. P. (2012). Old and new ideas for data screening and assumption testing for exploratory and confirmatory factor analysis. Frontiers in Psychology, 3, 1-21. doi:10.3389/fpsyg.2012.00055
## Not run: #make 4 cores available for parallel computing setCluster(4) #' #stop and remove cores setCluster(remove = TRUE) #use all available cores setCluster() ## End(Not run)## Not run: #make 4 cores available for parallel computing setCluster(4) #' #stop and remove cores setCluster(remove = TRUE) #use all available cores setCluster() ## End(Not run)