, Aslam Muhammad [aut,
ctb]| Title: | Multicollinearity Diagnostic Measures |
|---|---|
| Description: | Package computes popular and widely used multicollinearity diagnostic measures <doi:10.17576/jsm-2019-4809-26> and <doi:10.32614/RJ-2016-062> . Package also indicates which regressors may be the reason of collinearity among regressors. |
| Authors: | Imdad Ullah Muhammad [aut, cre]
, Aslam Muhammad [aut,
ctb] |
| Maintainer: | Imdad Ullah Muhammad <[email protected]> |
| License: | GPL (>= 2) |
| Version: | 1.3.1 |
| Built: | 2024-11-01 05:39:21 UTC |
| Source: | https://github.com/cran/mctest |
R package for computing popular and widely used multicollinearity diagnostic measures.
This package contains functions for computing overall and individual multicollinearity diagnostic measures. The overall multicollinearity diagnostic measures are Determinant of correlation matrix, R-squared from regression of all 's on , Farrar and Glauber chi-square test for detecting the strength of collinearity over the complete set of regressors, Condition Index, Sum of reciprocal of Eigenvalues, Theil's and Red indicator. The individual multicollinearity diagnostic measures are Klein's rule, variance inflation factor (VIF), Tolerance (TOL), Corrected VIF (CVIF), Leamer's method, F & relation, Farrar & Glauber F-test, and IND1 & IND2 indicators proposed by the author. The package also indicates which regressors may be the reason of collinearity among regressors. The VIF values and eigenvalues can also be plotted. Some other statistics such as correlation matrix, Eigenvalues and condition indexes are also available in the package.
For a complete list of functions, use library(help="mctest").
Muhammad Imdad Ullah, Muhammad Aslam
Computes eigenvalues, condition indices and variance decomposition proportions of or its related correlation matrix (see Belsley et al. (1980) <doi: 10.1007/BF00426854> ; Belsley, 1991; Kendall, 1957 and Silvey , 1969).
eigprop(mod, na.rm = TRUE, Inter = TRUE, prop = 0.5, ...)eigprop(mod, na.rm = TRUE, Inter = TRUE, prop = 0.5, ...)
mod |
A model object, not necessarily type |
na.rm |
Whether to remove missing observations. |
Inter |
Whether to include or exclude Intercept term, by default |
prop |
variance proportion default threshold, |
... |
Extra argument(s) if used will be ignored. |
The eigprop function can be used to detect the existence of multicollinearity among regressors. The function computes eigenvalues, condition indices and variance decomposition proportions of regression coefficients. To check the linear dependencies associated with the corresponding eigenvalue, the eigprop compares variance proportion with threshold value (default is 0.5) and displays the proportions greater than given threshold from each row and column, if any. If Inter = TRUE, eigenvalues, condition indices and variance proportions are computed without intercept term. A list object of class "eigp" is returned:
The eigprop objects are:
ev |
A vector of eigenvalues. By default |
ci |
A vector of condition indices. By default |
call |
The matched call. |
Inter |
logical, if |
pi |
A matrix of variance decomposition proportions. By default |
prop |
Default threshold proportion for comparison purpose. |
Missing values in data will be removed by default. There is no method for the detection of multicollinearity, if missing values exists in the data set.
Muhammad Imdad Ullah, Muhammad Aslam
Belsely, D. A. A Guide to Using the Collinearity Diagnostics. Computer Science in Economics and Management, 4(1): 33–50, 1991.
Belsley, D. A., Kuh, E., and Welsch, R. E. Regression Diagnostics: Identifying Influential Data and Sources of Collinearity. John Wiley \& Sons, New York, 1980.
Imdad, M. U. Addressing Linear Regression Models with Correlated Regressors: Some Package Development in R (Doctoral Thesis, Department of Statistics, Bahauddin Zakariya University, Multan, Pakistan), 2017.
Imdadullah, M., Aslam, M., and Altaf, S. mctest: An R Package for Detection of Collinearity Among Regressors. The R Journal, 8(2):499–509, 2016.
Silvey, S. D. Multicollinearity and imprecise estimation. Journal of the Royal Statistical Society, Series B (Methodological), 31(3):539–552, 1969.
Overall collinearity diagnostics omcdiag, Individual collinearity diagnostics imcdiag
## Hald Cement data data(Hald) model <- lm(y~X1+X2+X3+X4, data = as.data.frame(Hald)) # with Intercept term eigprop(model) # without Intercept term eigprop(model, Inter = FALSE) # different proportion threshold eigprop(model, prop = 0.45) # only variance proportions eigprop(model)$pi # only condition indices eigprop(model)$ci # only eigenvalues eigprop(model)$ev## Hald Cement data data(Hald) model <- lm(y~X1+X2+X3+X4, data = as.data.frame(Hald)) # with Intercept term eigprop(model) # without Intercept term eigprop(model, Inter = FALSE) # different proportion threshold eigprop(model, prop = 0.45) # only variance proportions eigprop(model)$pi # only condition indices eigprop(model)$ci # only eigenvalues eigprop(model)$ev
Heat evolved during setting of 13 cement mixtures of four basic ingredients. Each ingredient percentage appears to be rounded down to a full integer. The sum of the four mixture percentages varies from a maximum of 99% to a minimum of 95%. If all four regressor X-variables always summed to 100%, the centered X-matrix would then be of rank only 3. Thus, the regression of heat on four X-percentages is ill-conditioned, with an approximate rank deficiency of MCAL = 1. The first column is the response and the remaining four columns are the predictors.
The Hald data as used by Hoerl, Kennard and Baldwin (1975). These data are also in package wle.
data(Hald)data(Hald)
A data frame with 13 observations on the following 5 variables.
YHeat (cals/gm) evolved in setting, recorded to nearest tenth.
X1Integer percentage of 3CaO.Al2O3 in the mixture.
X2Integer percentage of 3CaO.SiO2 in the mixture.
X3Integer percentage of 4CaO.Al2O3.Fe2O3 in the mixture.
X4Integer percentage of 2CaO.SiO2 in the mixture.
Woods H, Steinour HH, Starke HR. "Effect of composition of Portland cement on heat evolved during hardening. Industrial Engineering and Chemistry 1932; 24: 1207-1214.
Ridge Regression: some simulations, Hoerl, A. E. et al, 1975, Comm Stat Theor Method 4:105
data(Hald) y <- Hald[ , 1] x <- Hald[ , -1]data(Hald) y <- Hald[ , 1] x <- Hald[ , -1]
Computes different measures of multicollinearity diagnostics for each regressor in the design matrix . Individual measures includes variance Inflation factor (VIF) (Marquardt, 1970), Farrar F-test for determination of multicollinearity (Farrar and Glauber, 1967), Auxiliary F-test for relationship between F and R-square(Gujarati and Porter, 2008), Leamer's method (Greene, 2002), Corrected VIF (CVIF) Curto and Pinto (2011) <doi: 10.1080/02664763.2010.505956>, Klein's rule Klein (1962), and IND1 & IND2 (Imdad, et. al., 2019) <https://doi.org/10.17576/jsm-2019-4809-26> proposed by the researchers.
imcdiag(mod, method = NULL, na.rm = TRUE, corr = FALSE, vif = 10, tol = 0.1, conf = 0.95, cvif = 10, ind1 = 0.02, ind2 = 0.7, leamer = 0.1, all = FALSE, ...)imcdiag(mod, method = NULL, na.rm = TRUE, corr = FALSE, vif = 10, tol = 0.1, conf = 0.95, cvif = 10, ind1 = 0.02, ind2 = 0.7, leamer = 0.1, all = FALSE, ...)
mod |
A model object, not necessarily type |
na.rm |
Whether to remove missing observations. |
method |
Specific individual measure of collinearity such as VIF, CVIF, and Leamer, etc. For example, |
corr |
Whether to display correlation matrix or not, by default |
vif |
Default threshold for VIF measure, |
tol |
Default threshold for TOL measure, |
conf |
Default confidence level for Farrar's Wi test, |
cvif |
Default threshold for CVIF measure, |
ind1 |
Default threshold for IND1 indicator, |
ind2 |
Default threshold for IND2 indicator, |
leamer |
Default threshold for Leamer's method, |
all |
Returns all individual measure of collinearity in a matrix of 0 (not detected) or 1 (detected). |
... |
Extra argument(s) if used will be ignored. |
The imcdiag function detects the existence of multicollinearity due to -variable. That's why named as individual measures of diagnostics. This includes VIF, TOL, Klein's rule, Farrar and Glauber F-test, F and relation, Leamer's method, CVIF, IND1, and IND2 diagnostic measures of multicollinearity. If method argument is used (method="VIF"), the VIF values for each regressor will be displayed with decision of either collinearity exists or not which is indicated by 0 (collinearity is not detected by method for regressor) and 1 (collinearity is detected by the method for regressor). If argument all=TRUE all individual measures of collinearity will be displayed in a matrix of 0 (collinearity is not detected) or 1 (collinearity is detected).
This function detects the existence of multicollinearity by using different available diagnostic measures already available in literature. The function returns the value of diagnostic measures with decision of either collinearity is detected by the diagnostic measure or not. Value of 1 indicates that collinearity is detected and 0 indicates that measure could not detect the existence of collinearity. A list object of class "imc" is returned:
x |
A numeric matrix of regressors. |
y |
A vector of response variable. |
idiags |
Listing of specific individual measure such as |
method |
Specific individual collinearity measure, such as VIF, TOL, CVIF, IND1, and IND2 etc. |
corr |
Logical, if |
R2 |
R-square from regression of all regressors |
call |
The matched call. |
pval |
Returns significant regressor as number after comparing the p-value of regressors from |
all |
If |
alldiag |
Matrix of all individual collinearity measures indicated as either 0 (collinearity not detected) or 1 (collinearity detected) for each diagnostic measure and each regressor. |
Missing values in data will be removed by default. There is no method for the detection of multicollinearity, if missing values exists in the data set.
Muhammad Imdad Ullah, Muhammad Aslam
Belsely, D. A. A Guide to Using the Collinearity Diagnostics. Computer Science in Economics and Management, 4(1): 33–50, 1991.
Belsley, D. A., Kuh, E., and Welsch, R. E. Regression Diagnostics: Identifying Influential Data and Sources of Collinearity. John Wiley \& Sons, New York, 1980.
Chatterjee, S. and Hadi, A. S. Regression Analysis by Example. John Wiley \& Sons, 4th edition, New York, 2006.
Curto, J. D. and Pinto, J. C. The Corrected VIF (CVIF). Journal of Applied Statistics, 38(7), 1499–1507.
Greene, W. H. Econometric Analysis. Prentice–Hall, Upper Saddle River, New Jersey, 4th edition, 2000.
Imdad, M. U. Addressing Linear Regression Models with Correlated Regressors: Some Package Development in R (Doctoral Thesis, Department of Statistics, Bahauddin Zakariya University, Multan, Pakistan), 2017.
Imdadullah, M., Aslam, M., and Altaf, S. mctest: An R Package for Detection of Collinearity Among Regressors. The R Journal, 8(2):499–509, 2016.
Imdad, M. U., Aslam, M., Altaf, S., and Ahmed, M. Some New Diagnostics of Multicollinearity in Linear Regression Model. Sains Malaysiana, 48(2): 2051–2060, 2019.
Overall collinearity diagnostic omcdiag, collinearity plot mc.plot
## Hald Cement data data(Hald) model <- lm(y~X1+X2+X3+X4, data = as.data.frame(Hald)) ## all Individual measures id<-imcdiag(model); id$idiags[,1] # VIF measure with custom VIF threshold imcdiag(model, method = "VIF", vif = 5) # IND1 measure with custom IND1 threshold and correlation matrix imcdiag(model, method="IND1", ind1=0.01, corr=TRUE) # CVIF measure with custom CVIF threshold and correlation matrix imcdiag(model, method = "CVIF", cvif = 5, corr = TRUE) # Collinearity Diagnostic measures in matrix of 0 or 1 imcdiag(model, all = TRUE) imcdiag(model, method = "VIF", all = TRUE) ## only VIF values without collinearity detection indication imcdiag(model, method = "VIF")[[1]][,1] plot(imcdiag(model, method = "VIF")[[1]][,1]) # vif plot## Hald Cement data data(Hald) model <- lm(y~X1+X2+X3+X4, data = as.data.frame(Hald)) ## all Individual measures id<-imcdiag(model); id$idiags[,1] # VIF measure with custom VIF threshold imcdiag(model, method = "VIF", vif = 5) # IND1 measure with custom IND1 threshold and correlation matrix imcdiag(model, method="IND1", ind1=0.01, corr=TRUE) # CVIF measure with custom CVIF threshold and correlation matrix imcdiag(model, method = "CVIF", cvif = 5, corr = TRUE) # Collinearity Diagnostic measures in matrix of 0 or 1 imcdiag(model, all = TRUE) imcdiag(model, method = "VIF", all = TRUE) ## only VIF values without collinearity detection indication imcdiag(model, method = "VIF")[[1]][,1] plot(imcdiag(model, method = "VIF")[[1]][,1]) # vif plot
Plot of VIF and Eigenvalues for detection of multicollinearity among regressors. The VIF and Eigenvalues are also displayed on graph. Eigenvalues plot can be displayed with or without inclusion of intercept term.
mc.plot(mod, Inter = FALSE, vif = 10, ev = 0.01, ...)mc.plot(mod, Inter = FALSE, vif = 10, ev = 0.01, ...)
mod |
A model object, not necessarily type |
Inter |
Whether to include or exclude Intercept term, by default |
vif |
Threshold of VIF and will appear as horizontal line on VIF plot. The default value is |
ev |
Threshold of Eigenvalues and will appear as horizontal line on Eigenvalues plot. The default value is |
... |
Extra argument(s) if used will be ignored. |
mc.plot function draw graphs of VIF and Eigenvalues for graphical detection of collinearity among regression. Horizontal line for VIF and Eigenvalues is drawn as indication of threshold values of both VIF and Eigenvalues for testing the multicollinearity.
Don't return any thing, it displays plot.
Muhammad Imdad Ullah, Muhammad Aslam
Belsely, D. A. A Guide to Using the Collinearity Diagnostics. Computer Science in Economics and Management, 4(1): 33–50, 1991.
Belsley, D. A., Kuh, E., and Welsch, R. E. Regression Diagnostics: Identifying Influential Data and Sources of Collinearity. John Wiley \& Sons, New York, 1980.
Chatterjee, S. and Hadi, A. S. Regression Analysis by Example. John Wiley \& Sons, 4th edition, New York, 2006.
Greene, W. H. Econometric Analysis. Prentice–Hall, Upper Saddle River, New Jersey, 4th edition, 2000.
Imdad, M. U. Addressing Linear Regression Models with Correlated Regressors: Some Package Development in R (Doctoral Thesis, Department of Statistics, Bahauddin Zakariya University, Multan, Pakistan), 2017.
Imdadullah, M., Aslam, M., and Altaf, S. mctest: An R Package for Detection of Collinearity Among Regressors. The R Journal, 8(2):499–509, 2016.
Overall collinearity diagnostic measures omcdiag, Individual collinearity diagnostic measures imcdiag
## Hald Cement data data(Hald) model <- lm(y~X1+X2+X3+X4, data = as.data.frame(Hald)) ## plot with default threshold of VIF and Eigenvalues with no intercept mc.plot(model) ## plot with default threshold of VIF and Eigenvalues with intercept mc.plot(model, Inter = TRUE) ## plot with specific threshold of VIF and Eigenvalues with no intercept mc.plot(model, vif = 5, ev = 20) ## plot with specific threshold of VIF and Eigenvalues with intercept mc.plot(model, vif = 5, ev = 20, Inter = TRUE)## Hald Cement data data(Hald) model <- lm(y~X1+X2+X3+X4, data = as.data.frame(Hald)) ## plot with default threshold of VIF and Eigenvalues with no intercept mc.plot(model) ## plot with default threshold of VIF and Eigenvalues with intercept mc.plot(model, Inter = TRUE) ## plot with specific threshold of VIF and Eigenvalues with no intercept mc.plot(model, vif = 5, ev = 20) ## plot with specific threshold of VIF and Eigenvalues with intercept mc.plot(model, vif = 5, ev = 20, Inter = TRUE)
The function mctest display overall, individual or both types of multicollinearity diagnostic measures from omcdiag and imcdiag functions, respectively.
mctest(mod, type=c("o","i","b"), na.rm=TRUE, Inter=TRUE, method=NULL, corr=FALSE, detr=0.01, red=0.5, theil=0.5, cn=30, vif=10, tol=0.1, conf=0.95, cvif=10, ind1=0.02, ind2=0.7, leamer=0.1, all=FALSE, ...)mctest(mod, type=c("o","i","b"), na.rm=TRUE, Inter=TRUE, method=NULL, corr=FALSE, detr=0.01, red=0.5, theil=0.5, cn=30, vif=10, tol=0.1, conf=0.95, cvif=10, ind1=0.02, ind2=0.7, leamer=0.1, all=FALSE, ...)
mod |
A model object, not necessarily type |
na.rm |
Whether to remove missing observations. |
Inter |
Whether to include or exclude Intercept term. By default |
type |
Displays overall, individual or both type of collinearity diagnostics. Overall collinearity diagnostics are displayed by default with eigenvalues and condition indexes, when |
method |
Specific individual measure of collinearity such as VIF, TOL, CVIF, Leamer, IND1, and IND2 etc, when |
corr |
Whether to display correlation matrix or not |
detr |
Determinant default threshold, |
red |
Red indicator default threshold, |
theil |
Theil's indicator default threshold, |
cn |
Condition number default threshold, |
vif |
Default threshold for VIF measure, |
conf |
Default confidence level for Farrar's test, |
cvif |
Default threshold for CVIF measure, |
tol |
Default threshold for TOL measure, |
ind1 |
Default threshold for IND1 indicator, |
ind2 |
Default threshold for IND2 indicator, |
leamer |
Default threshold for Leamer's method, |
all |
Returns all individual measure of collinearity in a matrix of 0 (not detected) or 1 (detected). |
... |
Extra argument(s) if used will be ignored. |
Missing values in data will be removed by default. There is no method for the detection of multicollinearity, if missing values exists in the data set
Muhammad Imdad Ullah, Muhammad Aslam
Belsely, D. A. A Guide to Using the Collinearity Diagnostics. Computer Science in Economics and Management, 4(1): 33–50, 1991.
Belsley, D. A., Kuh, E., and Welsch, R. E. Regression Diagnostics: Identifying Influential Data and Sources of Collinearity. John Wiley \& Sons, New York, 1980.
Chatterjee, S. and Hadi, A. S. Regression Analysis by Example. John Wiley \& Sons, 4th edition, New York, 2006.
Greene, W. H. Econometric Analysis. Prentice–Hall, Upper Saddle River, New Jersey, 4th edition, 2000.
Imdad, M. U. Addressing Linear Regression Models with Correlated Regressors: Some Package Development in R (Doctoral Thesis, Department of Statistics, Bahauddin Zakariya University, Multan, Pakistan), 2017.
Imdadullah, M., Aslam, M., and Altaf, S. mctest: An R Package for Detection of Collinearity Among Regressors. The R Journal, 8(2):499–509, 2016.
Imdad, M. U., Aslam, M., Altaf, S., and Ahmed, M. Some New Diagnostics of Multicollinearity in Linear Regression Model. Sains Malaysiana, 48(2): 2051–2060, 2019.
overall collinearity diagnostics omcdiag, individual collinearity diagnostics imcdiag, collinearity plots mc.plot
## Hald Cement data data(Hald) model <- lm(y~X1+X2+X3+X4, data = as.data.frame(Hald)) ## Overall diagnostic measures and eigenvalues with intercept term mctest(model) ## Overall diagnostic measures and eigenvalues without intercept term mctest(model, Inter=FALSE) ## all individual diagnostic measures mctest(model, type="i") ## certain individual diagnostic measures with collinearity detection indication VIF<-mctest(model, type="i", method="VIF") VIF[[1]][,1] # named VIF values only IND1<-mctest(model, type="i", method="IND1") IND1[[1]][,1] # named IND1 values only ## all individual diagnostic measures with correlation matrix mctest(model, type="i", corr=TRUE) ## VIF and correlation matrix with collinearity detection indication mctest(model, type="i", method="VIF", corr=TRUE) ## both overall and individual collinearity diagnostics mctest(model, type="b") mctest(model, type="b", method="VIF", cor=TRUE) ## all overall and vif with correlation matrix ## VIF and CN desired threshold ## eigenvalues without intercept term mctest(model, type="b", method="VIF", Inter=FALSE, vif=15, cn=35) ## Individual collinearity diagnostic measures in matrix of 0 or 1 mctest(model, all = TRUE) mctest(model, method = "VIF", all = TRUE) mctest(model, type="b", all = TRUE)## Hald Cement data data(Hald) model <- lm(y~X1+X2+X3+X4, data = as.data.frame(Hald)) ## Overall diagnostic measures and eigenvalues with intercept term mctest(model) ## Overall diagnostic measures and eigenvalues without intercept term mctest(model, Inter=FALSE) ## all individual diagnostic measures mctest(model, type="i") ## certain individual diagnostic measures with collinearity detection indication VIF<-mctest(model, type="i", method="VIF") VIF[[1]][,1] # named VIF values only IND1<-mctest(model, type="i", method="IND1") IND1[[1]][,1] # named IND1 values only ## all individual diagnostic measures with correlation matrix mctest(model, type="i", corr=TRUE) ## VIF and correlation matrix with collinearity detection indication mctest(model, type="i", method="VIF", corr=TRUE) ## both overall and individual collinearity diagnostics mctest(model, type="b") mctest(model, type="b", method="VIF", cor=TRUE) ## all overall and vif with correlation matrix ## VIF and CN desired threshold ## eigenvalues without intercept term mctest(model, type="b", method="VIF", Inter=FALSE, vif=15, cn=35) ## Individual collinearity diagnostic measures in matrix of 0 or 1 mctest(model, all = TRUE) mctest(model, method = "VIF", all = TRUE) mctest(model, type="b", all = TRUE)
Computes different overall measures of multicollinearity diagnostics for matrix of regressors. Overall measures of collinearity detection includes Determinant of the correlation matrix (Cooley and Lohnes, 1971), Farrar test of chi-square for presence of multicollinearity (Farrar and Glauber, 1967), Red Indicator (Kovacs et al., 2015) <doi: 10.1111/j.1751-5823.2005.tb00156.x>, Sum of lambda inverse Chatterjee and Price (1977) values, Theil's indicator (Theil, 1971) and condition number (Belsley et al., 1980) <doi: 10.1007/BF00426854> with or without intercept term.
omcdiag(mod, na.rm = TRUE, Inter = TRUE, detr = 0.01, red = 0.5, conf = 0.95, theil = 0.5, cn = 30,...)omcdiag(mod, na.rm = TRUE, Inter = TRUE, detr = 0.01, red = 0.5, conf = 0.95, theil = 0.5, cn = 30,...)
mod |
A model object, not necessarily type |
na.rm |
Whether to remove missing observations. |
Inter |
Whether to include or exclude Intercept term, by default |
detr |
Determinant default threshold, |
red |
red indicator default threshold, |
conf |
confidence level of Farrar Chi-Square test, |
theil |
Theil's indicator default threshold, |
cn |
condition number default threshold, |
... |
Extra argument(s) if used will be ignored. |
This function detects the existence of multicollinearity by using different available diagnostic measures already available in literature such as Determinant of correlation matrix, Farrar test of chi-square, Red Indicator, Sum of lambda inverse values, Theil's Indicator and Condition Number.
Function also displays diagnostic measures value with the decision of either multicollinearity is detected by the diagnostics or not. The Value of 1 indicate that multicollinearity is detected and 0 indicate measure could not detect by the certain diagnostic measure. A list object of class "omc" is returned:
odiags |
Listing of all overall diagnostic measures. |
Inter |
logical, if |
x |
matrix of regressors. |
call |
The matched call. |
Missing values in data will be removed by default. There is no method for the detection of multicollinearity, if missing values exists in the data set.
Muhammad Imdad Ullah, Muhammad Aslam
Belsely, D. A. A Guide to Using the Collinearity Diagnostics. Computer Science in Economics and Management, 4(1): 33–50, 1991.
Belsley, D. A., Kuh, E., and Welsch, R. E. Regression Diagnostics: Identifying Influential Data and Sources of Collinearity. John Wiley \& Sons, New York, 1980.
Chatterjee, S. and Hadi, A. S. Regression Analysis by Example. John Wiley \& Sons, 4th edition, New York, 2006.
Greene, W. H. Econometric Analysis. Prentice–Hall, Upper Saddle River, New Jersey, 4th edition, 2000.
Imdad, M. U. Addressing Linear Regression Models with Correlated Regressors: Some Package Development in R (Doctoral Thesis, Department of Statistics, Bahauddin Zakariya University, Multan, Pakistan), 2017.
Imdadullah, M., Aslam, M., and Altaf, S. mctest: An R Package for Detection of Collinearity Among Regressors. The R Journal, 8(2):499–509, 2016.
Kovacs, P., Petres, T., and Toth, L. A New Measure of Multicollinearity in Linear Regression Models. International Statistical Review / Revue Internationale de Statistique, 73(3): 405–412, 2005.
Individual collinearity diagnostic measure imcdiag, Eigenvalues and variance decomposition proportion eigprop
## Hald Cement data data(Hald) model <- lm(y~X1+X2+X3+X4, data = as.data.frame(Hald)) ## all oveall diagnostic measures and eigenvalues with intercept od<-omcdiag(model) ## all oveall diagnostic measures and eigenvalues without intercept omcdiag(model, Inter=FALSE) ## all oveall diagnostic measures and eigenvalues with intercept ## with different determinant and confidence level threshold omcdiag(model, detr=0.001, conf=0.99) ## returns the determinant of correlation matrix |X'X| omcdiag(model)[1]## Hald Cement data data(Hald) model <- lm(y~X1+X2+X3+X4, data = as.data.frame(Hald)) ## all oveall diagnostic measures and eigenvalues with intercept od<-omcdiag(model) ## all oveall diagnostic measures and eigenvalues without intercept omcdiag(model, Inter=FALSE) ## all oveall diagnostic measures and eigenvalues with intercept ## with different determinant and confidence level threshold omcdiag(model, detr=0.001, conf=0.99) ## returns the determinant of correlation matrix |X'X| omcdiag(model)[1]