LD function

Likelihood Distance

Compute likelihood distances between models when removing the $i_{th}$ 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,
  ...
)

Arguments

• 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 class(model) is a sem (semmod), or lavaan (character), then a confirmatory approach is performed instead. Finally, if the model is defined with mirt::mirt.model() then distances will be computed for categorical data with the mirt package
• progress: logical; display the progress of the computations in the console?
• ...: additional parameters to be passed
• x: an object of class LD
• ncases: number of extreme cases to display
• digits: number of digits to round in the printed result
• y: a NULL value ignored by the plotting function
• 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?

Details

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.

Examples

## 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)

References

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. tools:::Rd_expr_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. tools:::Rd_expr_doi("10.3389/fpsyg.2012.00055")

See Also

gCD, GOF, obs.resid, robustMD, setCluster

Author(s)

Phil Chalmers rphilip.chalmers@gmail.com