Assign 3- The Disadvantage and Hidden Social Class in Australia
Ka Ho Jacky, Wong
October 20, 2018
set working directory
setwd("C:/Users/jacky/Desktop/Study/Statistical Thinking for Data Science/Assign 3")
getwd()## [1] "C:/Users/jacky/Desktop/Study/Statistical Thinking for Data Science/Assign 3"Get Data
semdata=read.csv("SEM_data_V8.csv")Check the data
str(semdata)## 'data.frame': 2454 obs. of 11 variables:
## $ Postcode : int 2000 2007 2008 2009 2010 2011 2015 2016 2017 2018 ...
## $ IEO : int 1128 1082 1180 1139 1171 1162 1182 1128 1132 852 ...
## $ AverageIncome : num 52595 47486 53977 75281 77911 ...
## $ pro_Carer.Allowance : num 0.351 1.025 0.564 1.096 0.867 ...
## $ pro_Sickness.Allowance : num 0 0 0 0 0.0291 ...
## $ pro_Youth.Allowance..other. : num 0.0413 0.205 0.1162 0.1127 0.189 ...
## $ pro_Newstart.Allowance : num 0.0702 0.1435 0.0996 0.1639 0.0775 ...
## $ pro_Low.Income.Card : num 1.11 2.09 2.76 1.67 4.59 ...
## $ pro_Disability.Support.Pension: num 1.34 3.18 1.81 3.01 1.31 ...
## $ pro_Family.Tax.Benefit.Part.A : num 1.09 2.58 1.58 2.69 1.13 ...
## $ pro_Family.Tax.Benefit.Part.B : num 2.04 5.76 5.41 2.96 4.86 ...names(semdata)## [1] "Postcode" "IEO"
## [3] "AverageIncome" "pro_Carer.Allowance"
## [5] "pro_Sickness.Allowance" "pro_Youth.Allowance..other."
## [7] "pro_Newstart.Allowance" "pro_Low.Income.Card"
## [9] "pro_Disability.Support.Pension" "pro_Family.Tax.Benefit.Part.A"
## [11] "pro_Family.Tax.Benefit.Part.B"summary(semdata)## Postcode IEO AverageIncome pro_Carer.Allowance
## Min. : 800 Min. : 683.0 Min. : 24560 Min. : 0.000
## 1st Qu.:2832 1st Qu.: 932.0 1st Qu.: 45217 1st Qu.: 2.721
## Median :3863 Median : 982.0 Median : 51335 Median : 4.320
## Mean :4089 Mean : 990.3 Mean : 53793 Mean : 4.904
## 3rd Qu.:5163 3rd Qu.:1048.0 3rd Qu.: 59632 3rd Qu.: 6.374
## Max. :7470 Max. :1234.0 Max. :129467 Max. :29.200
## pro_Sickness.Allowance pro_Youth.Allowance..other. pro_Newstart.Allowance
## Min. :0.00000 Min. : 0.0000 Min. : 0.0000
## 1st Qu.:0.00000 1st Qu.: 0.0000 1st Qu.: 0.0000
## Median :0.00000 Median : 0.3835 Median : 0.4226
## Mean :0.02026 Mean : 0.6932 Mean : 0.6842
## 3rd Qu.:0.00000 3rd Qu.: 0.9397 3rd Qu.: 0.8935
## Max. :0.76336 Max. :39.6825 Max. :31.7460
## pro_Low.Income.Card pro_Disability.Support.Pension
## Min. : 0.000 Min. : 0.000
## 1st Qu.: 3.266 1st Qu.: 8.371
## Median : 5.340 Median : 11.806
## Mean : 6.682 Mean : 12.286
## 3rd Qu.: 8.110 3rd Qu.: 15.015
## Max. :215.873 Max. :134.921
## pro_Family.Tax.Benefit.Part.A pro_Family.Tax.Benefit.Part.B
## Min. : 0.000 Min. : 0.000
## 1st Qu.: 6.419 1st Qu.: 7.771
## Median : 9.246 Median : 10.782
## Mean : 9.920 Mean : 12.556
## 3rd Qu.: 12.068 3rd Qu.: 14.458
## Max. :128.571 Max. :440.278Exploratory Factor Analysis
library('psych')## Warning: package 'psych' was built under R version 3.4.4library("GPArotation")Parallel Analysis
parallel <- fa.parallel(semdata, fm = 'minres', fa = 'fa')
## Parallel analysis suggests that the number of factors = 4 and the number of components = NAParallel Analysis Scree plots
locate the point of inflection – the point where the gap between simulated data and actual data tends to be minimum.
plot(parallel)
Factor Analysis
Exploratory Factor Analysis (EFA) is a statistical technique that is used to identify the latent relational structure among a set of variables and narrow down to smaller number of variables. This essentially means that the variance of large number of variables can be described by few summary variables
## 2 Factors analysis
twofactor <- fa(semdata,nfactors = 2,rotate = "oblimin",fm="minres")
print(twofactor)## Factor Analysis using method = minres
## Call: fa(r = semdata, nfactors = 2, rotate = "oblimin", fm = "minres")
## Standardized loadings (pattern matrix) based upon correlation matrix
## MR1 MR2 h2 u2 com
## Postcode -0.08 -0.17 0.023 0.977 1.4
## IEO -0.04 0.76 0.606 0.394 1.0
## AverageIncome 0.07 0.69 0.438 0.562 1.0
## pro_Carer.Allowance 0.21 -0.57 0.483 0.517 1.3
## pro_Sickness.Allowance 0.19 -0.09 0.060 0.940 1.5
## pro_Youth.Allowance..other. 0.97 0.16 0.813 0.187 1.1
## pro_Newstart.Allowance 0.90 0.11 0.724 0.276 1.0
## pro_Low.Income.Card 0.90 -0.03 0.844 0.156 1.0
## pro_Disability.Support.Pension 0.72 -0.38 0.936 0.064 1.5
## pro_Family.Tax.Benefit.Part.A 0.79 -0.30 0.940 0.060 1.3
## pro_Family.Tax.Benefit.Part.B 0.77 0.02 0.580 0.420 1.0
##
## MR1 MR2
## SS loadings 4.58 1.87
## Proportion Var 0.42 0.17
## Cumulative Var 0.42 0.59
## Proportion Explained 0.71 0.29
## Cumulative Proportion 0.71 1.00
##
## With factor correlations of
## MR1 MR2
## MR1 1.00 -0.48
## MR2 -0.48 1.00
##
## Mean item complexity = 1.2
## Test of the hypothesis that 2 factors are sufficient.
##
## The degrees of freedom for the null model are 55 and the objective function was 10.25 with Chi Square of 25104.97
## The degrees of freedom for the model are 34 and the objective function was 1.62
##
## The root mean square of the residuals (RMSR) is 0.04
## The df corrected root mean square of the residuals is 0.05
##
## The harmonic number of observations is 2454 with the empirical chi square 447.56 with prob < 1.3e-73
## The total number of observations was 2454 with Likelihood Chi Square = 3963.28 with prob < 0
##
## Tucker Lewis Index of factoring reliability = 0.746
## RMSEA index = 0.217 and the 90 % confidence intervals are 0.211 0.223
## BIC = 3697.89
## Fit based upon off diagonal values = 0.99
## Measures of factor score adequacy
## MR1 MR2
## Correlation of (regression) scores with factors 0.98 0.93
## Multiple R square of scores with factors 0.97 0.86
## Minimum correlation of possible factor scores 0.93 0.71## Visualise the factor anaysis
fa.diagram(twofactor)
3 Factors analysis
threefactor <- fa(semdata,nfactors = 3,rotate = "oblimin",fm="minres")
print(threefactor)## Factor Analysis using method = minres
## Call: fa(r = semdata, nfactors = 3, rotate = "oblimin", fm = "minres")
## Standardized loadings (pattern matrix) based upon correlation matrix
## MR1 MR2 MR3 h2 u2 com
## Postcode 0.05 -0.22 -0.54 0.31 0.688 1.3
## IEO -0.07 0.77 0.12 0.63 0.374 1.1
## AverageIncome 0.04 0.67 0.06 0.42 0.578 1.0
## pro_Carer.Allowance 0.10 -0.61 0.32 0.62 0.383 1.6
## pro_Sickness.Allowance 0.12 -0.10 0.24 0.11 0.890 1.8
## pro_Youth.Allowance..other. 0.97 0.15 -0.01 0.81 0.186 1.0
## pro_Newstart.Allowance 0.88 0.10 0.07 0.72 0.277 1.0
## pro_Low.Income.Card 0.93 -0.04 -0.09 0.87 0.129 1.0
## pro_Disability.Support.Pension 0.70 -0.38 0.09 0.93 0.067 1.6
## pro_Family.Tax.Benefit.Part.A 0.76 -0.30 0.09 0.94 0.060 1.3
## pro_Family.Tax.Benefit.Part.B 0.79 0.02 -0.05 0.59 0.411 1.0
##
## MR1 MR2 MR3
## SS loadings 4.50 1.93 0.53
## Proportion Var 0.41 0.18 0.05
## Cumulative Var 0.41 0.58 0.63
## Proportion Explained 0.65 0.28 0.08
## Cumulative Proportion 0.65 0.92 1.00
##
## With factor correlations of
## MR1 MR2 MR3
## MR1 1.00 -0.48 0.24
## MR2 -0.48 1.00 -0.14
## MR3 0.24 -0.14 1.00
##
## Mean item complexity = 1.3
## Test of the hypothesis that 3 factors are sufficient.
##
## The degrees of freedom for the null model are 55 and the objective function was 10.25 with Chi Square of 25104.97
## The degrees of freedom for the model are 25 and the objective function was 1.5
##
## The root mean square of the residuals (RMSR) is 0.02
## The df corrected root mean square of the residuals is 0.03
##
## The harmonic number of observations is 2454 with the empirical chi square 147.71 with prob < 2.2e-19
## The total number of observations was 2454 with Likelihood Chi Square = 3667.58 with prob < 0
##
## Tucker Lewis Index of factoring reliability = 0.68
## RMSEA index = 0.244 and the 90 % confidence intervals are 0.237 0.25
## BIC = 3472.44
## Fit based upon off diagonal values = 1
## Measures of factor score adequacy
## MR1 MR2 MR3
## Correlation of (regression) scores with factors 0.98 0.93 0.73
## Multiple R square of scores with factors 0.97 0.86 0.53
## Minimum correlation of possible factor scores 0.93 0.73 0.05## Visualise the factor anaysis
fa.diagram(threefactor)
## 4 Factors analysis
fourfactor <- fa(semdata,nfactors = 4,rotate = "oblimin",fm="minres")## The estimated weights for the factor scores are probably incorrect. Try a different factor extraction method.print(fourfactor)## Factor Analysis using method = minres
## Call: fa(r = semdata, nfactors = 4, rotate = "oblimin", fm = "minres")
## Standardized loadings (pattern matrix) based upon correlation matrix
## MR1 MR4 MR2 MR3 h2 u2 com
## Postcode 0.24 -0.15 -0.21 -0.48 0.21 0.7930 2.1
## IEO 0.00 -0.33 -0.21 0.50 0.61 0.3926 2.2
## AverageIncome 0.13 -0.33 -0.18 0.42 0.42 0.5809 2.5
## pro_Carer.Allowance 0.05 -0.01 0.99 0.01 1.00 0.0046 1.0
## pro_Sickness.Allowance -0.18 0.38 0.14 0.18 0.12 0.8849 2.3
## pro_Youth.Allowance..other. 0.82 0.10 0.02 0.10 0.83 0.1742 1.1
## pro_Newstart.Allowance 0.41 0.52 -0.07 0.18 0.73 0.2687 2.2
## pro_Low.Income.Card 0.91 0.01 0.08 -0.09 0.91 0.0895 1.0
## pro_Disability.Support.Pension 0.01 0.96 0.02 -0.05 1.00 0.0014 1.0
## pro_Family.Tax.Benefit.Part.A 0.15 0.84 0.04 -0.01 0.97 0.0262 1.1
## pro_Family.Tax.Benefit.Part.B 0.72 0.05 0.03 -0.03 0.61 0.3923 1.0
##
## MR1 MR4 MR2 MR3
## SS loadings 2.60 2.71 1.29 0.79
## Proportion Var 0.24 0.25 0.12 0.07
## Cumulative Var 0.24 0.48 0.60 0.67
## Proportion Explained 0.35 0.37 0.17 0.11
## Cumulative Proportion 0.35 0.72 0.89 1.00
##
## With factor correlations of
## MR1 MR4 MR2 MR3
## MR1 1.00 0.81 0.35 0.00
## MR4 0.81 1.00 0.56 -0.20
## MR2 0.35 0.56 1.00 -0.28
## MR3 0.00 -0.20 -0.28 1.00
##
## Mean item complexity = 1.6
## Test of the hypothesis that 4 factors are sufficient.
##
## The degrees of freedom for the null model are 55 and the objective function was 10.25 with Chi Square of 25104.97
## The degrees of freedom for the model are 17 and the objective function was 0.33
##
## The root mean square of the residuals (RMSR) is 0.02
## The df corrected root mean square of the residuals is 0.03
##
## The harmonic number of observations is 2454 with the empirical chi square 74.36 with prob < 3.8e-09
## The total number of observations was 2454 with Likelihood Chi Square = 797.81 with prob < 1.3e-158
##
## Tucker Lewis Index of factoring reliability = 0.899
## RMSEA index = 0.137 and the 90 % confidence intervals are 0.129 0.145
## BIC = 665.12
## Fit based upon off diagonal values = 1## Visualise the factor anaysis
fa.diagram(fourfactor)
SEM Modelling
Load lavaan
library(lavaan)## Warning: package 'lavaan' was built under R version 3.4.4## This is lavaan 0.6-3## lavaan is BETA software! Please report any bugs.##
## Attaching package: 'lavaan'## The following object is masked from 'package:psych':
##
## cor2covlibrary(semPlot)## Warning: package 'semPlot' was built under R version 3.4.4build latent variable model
model <- '
# latent variable model
SC =~ IEO + AverageIncome
DIS =~ pro_Youth.Allowance..other. + pro_Low.Income.Card + pro_Newstart.Allowance + pro_Disability.Support.Pension + pro_Family.Tax.Benefit.Part.A + pro_Family.Tax.Benefit.Part.B
# regressions
SC ~ DIS
'fitting the data to the model
fit <- sem(model, data=semdata)## Warning in lav_data_full(data = data, group = group, cluster = cluster, :
## lavaan WARNING: some observed variances are (at least) a factor 1000 times
## larger than others; use varTable(fit) to investigate## Warning in lav_data_full(data = data, group = group, cluster = cluster, : lavaan WARNING: some observed variances are larger than 1000000
## lavaan NOTE: use varTable(fit) to investigate## Warning in lav_model_vcov(lavmodel = lavmodel, lavsamplestats = lavsamplestats, : lavaan WARNING:
## Could not compute standard errors! The information matrix could
## not be inverted. This may be a symptom that the model is not
## identified.## Warning in lav_object_post_check(object): lavaan WARNING: some estimated ov
## variances are negativeevaluation
summary(fit, standardized=TRUE, fit.measures=TRUE)## lavaan 0.6-3 ended normally after 118 iterations
##
## Optimization method NLMINB
## Number of free parameters 17
##
## Number of observations 2454
##
## Estimator ML
## Model Fit Test Statistic 3219.343
## Degrees of freedom 19
## P-value (Chi-square) 0.000
##
## Model test baseline model:
##
## Minimum Function Test Statistic 23001.346
## Degrees of freedom 28
## P-value 0.000
##
## User model versus baseline model:
##
## Comparative Fit Index (CFI) 0.861
## Tucker-Lewis Index (TLI) 0.795
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -74438.405
## Loglikelihood unrestricted model (H1) -72828.733
##
## Number of free parameters 17
## Akaike (AIC) 148910.810
## Bayesian (BIC) 149009.503
## Sample-size adjusted Bayesian (BIC) 148955.490
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.262
## 90 Percent Confidence Interval 0.254 0.270
## P-value RMSEA <= 0.05 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.082
##
## Parameter Estimates:
##
## Information Expected
## Information saturated (h1) model Structured
## Standard Errors Standard
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv
## SC =~
## IEO 1.000 71.088
## AverageIncome 107.038 NA 7609.115
## DIS =~
## pr_Yth.Allw... 1.000 1.092
## pr_Lw.Incm.Crd 5.909 NA 6.451
## pr_Nwstrt.Allw 0.978 NA 1.068
## pr_Dsblty.Sp.P 6.421 NA 7.010
## pr_Fml.T.B.P.A 5.963 NA 6.510
## pr_Fml.T.B.P.B 8.314 NA 9.077
## Std.all
##
## 0.832
## 0.603
##
## 0.776
## 0.849
## 0.783
## 0.986
## 1.001
## 0.669
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv
## SC ~
## DIS -41.534 NA -0.638
## Std.all
##
## -0.638
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv
## .IEO 2245.595 NA 2245.595
## .AverageIncome 101417086.960 NA 101417086.960
## .pr_Yth.Allw... 0.789 NA 0.789
## .pr_Lw.Incm.Crd 16.098 NA 16.098
## .pr_Nwstrt.Allw 0.721 NA 0.721
## .pr_Dsblty.Sp.P 1.408 NA 1.408
## .pr_Fml.T.B.P.A -0.092 NA -0.092
## .pr_Fml.T.B.P.B 101.745 NA 101.745
## .SC 2997.402 NA 0.593
## DIS 1.192 NA 1.000
## Std.all
## 0.308
## 0.637
## 0.398
## 0.279
## 0.387
## 0.028
## -0.002
## 0.553
## 0.593
## 1.000The lavInspect() and lavTech() functions can be used to inspect/extract information that is stored inside (or can be computed from) a fitted lavaan object. Note: the (older) inspect() function is now simply a shortcut for lavInspect() with default arguments.
lavInspect(fit, what="estimates")## $lambda
## SC DIS
## IEO 1.000 0.000
## AverageIncome 107.038 0.000
## pro_Youth.Allowance..other. 0.000 1.000
## pro_Low.Income.Card 0.000 5.909
## pro_Newstart.Allowance 0.000 0.978
## pro_Disability.Support.Pension 0.000 6.421
## pro_Family.Tax.Benefit.Part.A 0.000 5.963
## pro_Family.Tax.Benefit.Part.B 0.000 8.314
##
## $theta
## IEO AvrgIn p_Y.A.
## IEO 2245.595
## AverageIncome 0.000 101417086.960
## pro_Youth.Allowance..other. 0.000 0.000 0.789
## pro_Low.Income.Card 0.000 0.000 0.000
## pro_Newstart.Allowance 0.000 0.000 0.000
## pro_Disability.Support.Pension 0.000 0.000 0.000
## pro_Family.Tax.Benefit.Part.A 0.000 0.000 0.000
## pro_Family.Tax.Benefit.Part.B 0.000 0.000 0.000
## p_L.I. pr_N.A p_D.S.
## IEO
## AverageIncome
## pro_Youth.Allowance..other.
## pro_Low.Income.Card 16.098
## pro_Newstart.Allowance 0.000 0.721
## pro_Disability.Support.Pension 0.000 0.000 1.408
## pro_Family.Tax.Benefit.Part.A 0.000 0.000 0.000
## pro_Family.Tax.Benefit.Part.B 0.000 0.000 0.000
## p_F.T.B.P.A p_F.T.B.P.B
## IEO
## AverageIncome
## pro_Youth.Allowance..other.
## pro_Low.Income.Card
## pro_Newstart.Allowance
## pro_Disability.Support.Pension
## pro_Family.Tax.Benefit.Part.A -0.092
## pro_Family.Tax.Benefit.Part.B 0.000 101.745
##
## $psi
## SC DIS
## SC 2997.402
## DIS 0.000 1.192
##
## $beta
## SC DIS
## SC 0 -41.534
## DIS 0 0.000visualise the weightings in a diagram
semPaths(fit, what = "stand", rotation = 4)
##visualise the difference between the implied and observed fits of the correlations in our model vs the data.
semCors(fit)
check where the model is performing well and where it is not performing so well
also can see the relationship betwwen variables
semCors(fit, include="difference")
obtain confidence intervals for the estimated coefficients, which also tell us a little bit more about how well the model is working
parameterEstimates(fit, ci = TRUE, level = 0.95)## lhs op rhs
## 1 SC =~ IEO
## 2 SC =~ AverageIncome
## 3 DIS =~ pro_Youth.Allowance..other.
## 4 DIS =~ pro_Low.Income.Card
## 5 DIS =~ pro_Newstart.Allowance
## 6 DIS =~ pro_Disability.Support.Pension
## 7 DIS =~ pro_Family.Tax.Benefit.Part.A
## 8 DIS =~ pro_Family.Tax.Benefit.Part.B
## 9 SC ~ DIS
## 10 IEO ~~ IEO
## 11 AverageIncome ~~ AverageIncome
## 12 pro_Youth.Allowance..other. ~~ pro_Youth.Allowance..other.
## 13 pro_Low.Income.Card ~~ pro_Low.Income.Card
## 14 pro_Newstart.Allowance ~~ pro_Newstart.Allowance
## 15 pro_Disability.Support.Pension ~~ pro_Disability.Support.Pension
## 16 pro_Family.Tax.Benefit.Part.A ~~ pro_Family.Tax.Benefit.Part.A
## 17 pro_Family.Tax.Benefit.Part.B ~~ pro_Family.Tax.Benefit.Part.B
## 18 SC ~~ SC
## 19 DIS ~~ DIS
## est se z pvalue ci.lower ci.upper
## 1 1.000 0 NA NA 1 1
## 2 107.038 NA NA NA NA NA
## 3 1.000 0 NA NA 1 1
## 4 5.909 NA NA NA NA NA
## 5 0.978 NA NA NA NA NA
## 6 6.421 NA NA NA NA NA
## 7 5.963 NA NA NA NA NA
## 8 8.314 NA NA NA NA NA
## 9 -41.534 NA NA NA NA NA
## 10 2245.595 NA NA NA NA NA
## 11 101417086.960 NA NA NA NA NA
## 12 0.789 NA NA NA NA NA
## 13 16.098 NA NA NA NA NA
## 14 0.721 NA NA NA NA NA
## 15 1.408 NA NA NA NA NA
## 16 -0.092 NA NA NA NA NA
## 17 101.745 NA NA NA NA NA
## 18 2997.402 NA NA NA NA NA
## 19 1.192 NA NA NA NA NAsee how the various factors covary with one another
Extract Model Fitted Values
fitted(fit)## $cov
## IEO AvrgIn p_Y.A.
## IEO 7299.128
## AverageIncome 540918.297 159315710.561
## pro_Youth.Allowance..other. -49.504 -5298.816 1.981
## pro_Low.Income.Card -292.508 -31309.346 7.043
## pro_Newstart.Allowance -48.418 -5182.525 1.166
## pro_Disability.Support.Pension -317.850 -34021.927 7.653
## pro_Family.Tax.Benefit.Part.A -295.186 -31595.966 7.107
## pro_Family.Tax.Benefit.Part.B -411.583 -44054.876 9.909
## p_L.I. pr_N.A p_D.S.
## IEO
## AverageIncome
## pro_Youth.Allowance..other.
## pro_Low.Income.Card 57.711
## pro_Newstart.Allowance 6.888 1.861
## pro_Disability.Support.Pension 45.218 7.485 50.544
## pro_Family.Tax.Benefit.Part.A 41.993 6.951 45.632
## pro_Family.Tax.Benefit.Part.B 58.552 9.692 63.625
## p_F.T.B.P.A p_F.T.B.P.B
## IEO
## AverageIncome
## pro_Youth.Allowance..other.
## pro_Low.Income.Card
## pro_Newstart.Allowance
## pro_Disability.Support.Pension
## pro_Family.Tax.Benefit.Part.A 42.286
## pro_Family.Tax.Benefit.Part.B 59.088 184.133compare with the covariance of the original dataset
cov(semdata)## Postcode IEO AverageIncome
## Postcode 2.248282e+06 -2.740917e+04 -2.338663e+06
## IEO -2.740917e+04 7.302068e+03 5.411360e+05
## AverageIncome -2.338663e+06 5.411360e+05 1.593807e+08
## pro_Carer.Allowance -3.650503e+02 -1.539688e+02 -1.826178e+04
## pro_Sickness.Allowance -5.589705e+00 -6.284068e-01 -2.699079e+01
## pro_Youth.Allowance..other. 4.686655e+00 -3.619253e+01 -2.426961e+03
## pro_Newstart.Allowance -5.606835e+01 -3.308921e+01 -2.660158e+03
## pro_Low.Income.Card 9.473737e+02 -2.622096e+02 -2.479028e+04
## pro_Disability.Support.Pension 3.902606e+02 -3.412477e+02 -4.156450e+04
## pro_Family.Tax.Benefit.Part.A 3.534246e+02 -2.960958e+02 -3.198968e+04
## pro_Family.Tax.Benefit.Part.B 2.834043e+02 -3.416264e+02 -4.344709e+04
## pro_Carer.Allowance pro_Sickness.Allowance
## Postcode -3.650503e+02 -5.589704614
## IEO -1.539688e+02 -0.628406754
## AverageIncome -1.826178e+04 -26.990791215
## pro_Carer.Allowance 1.107488e+01 0.038360526
## pro_Sickness.Allowance 3.836053e-02 0.002278902
## pro_Youth.Allowance..other. 1.695698e+00 0.013291843
## pro_Newstart.Allowance 1.567245e+00 0.014155151
## pro_Low.Income.Card 1.196870e+01 0.054529667
## pro_Disability.Support.Pension 1.426177e+01 0.085788314
## pro_Family.Tax.Benefit.Part.A 1.278647e+01 0.081320929
## pro_Family.Tax.Benefit.Part.B 1.540276e+01 0.088894282
## pro_Youth.Allowance..other.
## Postcode 4.686655e+00
## IEO -3.619253e+01
## AverageIncome -2.426961e+03
## pro_Carer.Allowance 1.695698e+00
## pro_Sickness.Allowance 1.329184e-02
## pro_Youth.Allowance..other. 1.982144e+00
## pro_Newstart.Allowance 1.427039e+00
## pro_Low.Income.Card 8.931736e+00
## pro_Disability.Support.Pension 7.419898e+00
## pro_Family.Tax.Benefit.Part.A 7.112249e+00
## pro_Family.Tax.Benefit.Part.B 1.383106e+01
## pro_Newstart.Allowance pro_Low.Income.Card
## Postcode -5.606835e+01 9.473737e+02
## IEO -3.308921e+01 -2.622096e+02
## AverageIncome -2.660158e+03 -2.479028e+04
## pro_Carer.Allowance 1.567245e+00 1.196870e+01
## pro_Sickness.Allowance 1.415515e-02 5.452967e-02
## pro_Youth.Allowance..other. 1.427039e+00 8.931736e+00
## pro_Newstart.Allowance 1.861583e+00 7.958142e+00
## pro_Low.Income.Card 7.958142e+00 5.773426e+01
## pro_Disability.Support.Pension 7.389479e+00 4.427005e+01
## pro_Family.Tax.Benefit.Part.A 6.958410e+00 4.201902e+01
## pro_Family.Tax.Benefit.Part.B 1.175611e+01 7.602636e+01
## pro_Disability.Support.Pension
## Postcode 3.902606e+02
## IEO -3.412477e+02
## AverageIncome -4.156450e+04
## pro_Carer.Allowance 1.426177e+01
## pro_Sickness.Allowance 8.578831e-02
## pro_Youth.Allowance..other. 7.419898e+00
## pro_Newstart.Allowance 7.389479e+00
## pro_Low.Income.Card 4.427005e+01
## pro_Disability.Support.Pension 5.056437e+01
## pro_Family.Tax.Benefit.Part.A 4.564208e+01
## pro_Family.Tax.Benefit.Part.B 6.314294e+01
## pro_Family.Tax.Benefit.Part.A
## Postcode 3.534246e+02
## IEO -2.960958e+02
## AverageIncome -3.198968e+04
## pro_Carer.Allowance 1.278647e+01
## pro_Sickness.Allowance 8.132093e-02
## pro_Youth.Allowance..other. 7.112249e+00
## pro_Newstart.Allowance 6.958410e+00
## pro_Low.Income.Card 4.201902e+01
## pro_Disability.Support.Pension 4.564208e+01
## pro_Family.Tax.Benefit.Part.A 4.230370e+01
## pro_Family.Tax.Benefit.Part.B 5.928690e+01
## pro_Family.Tax.Benefit.Part.B
## Postcode 2.834043e+02
## IEO -3.416264e+02
## AverageIncome -4.344709e+04
## pro_Carer.Allowance 1.540276e+01
## pro_Sickness.Allowance 8.889428e-02
## pro_Youth.Allowance..other. 1.383106e+01
## pro_Newstart.Allowance 1.175611e+01
## pro_Low.Income.Card 7.602636e+01
## pro_Disability.Support.Pension 6.314294e+01
## pro_Family.Tax.Benefit.Part.A 5.928690e+01
## pro_Family.Tax.Benefit.Part.B 1.842085e+02Extract Model Residuals
residuals is a generic function which extracts model residuals from objects returned by modeling functions.
resid(fit, type="standardized")## $type
## [1] "standardized"
##
## $cov
## IEO AvrgIn p_Y.A.
## IEO -696299.771
## AverageIncome -0.001 0.000
## pro_Youth.Allowance..other. 10.001 12.745 0.000
## pro_Low.Income.Card 5.108 6.236 22.738
## pro_Newstart.Allowance 11.877 11.776 16.112
## pro_Disability.Support.Pension -10.905 -15.578 -15.187
## pro_Family.Tax.Benefit.Part.A -0.742 -0.857 2.064
## pro_Family.Tax.Benefit.Part.B 4.728 0.260 19.840
## p_L.I. pr_N.A p_D.S.
## IEO
## AverageIncome
## pro_Youth.Allowance..other.
## pro_Low.Income.Card 87906302.395
## pro_Newstart.Allowance 14.677 0.000
## pro_Disability.Support.Pension -15.487 -5.777 176181256.646
## pro_Family.Tax.Benefit.Part.A 1.918 3.627 -21.816
## pro_Family.Tax.Benefit.Part.B 19.633 11.636 -2.528
## p_F.T.B.P.A p_F.T.B.P.B
## IEO
## AverageIncome
## pro_Youth.Allowance..other.
## pro_Low.Income.Card
## pro_Newstart.Allowance
## pro_Disability.Support.Pension
## pro_Family.Tax.Benefit.Part.A 72534369.958
## pro_Family.Tax.Benefit.Part.B 11.889 20640647.400work out the reliability of the fit using a function from the semTools package
library(semTools)## Warning: package 'semTools' was built under R version 3.4.4## ## ################################################################################# This is semTools 0.5-1## All users of R (or SEM) are invited to submit functions or ideas for functions.## #################################################################################
## Attaching package: 'semTools'## The following object is masked from 'package:psych':
##
## skewreliability(fit)## SC DIS total
## alpha 0.01348875 0.8450774 0.005613145
## omega 0.36772900 0.8897506 0.366525067
## omega2 0.36772900 0.8897506 0.366525067
## omega3 0.36772885 0.8508721 0.366503060
## avevar 0.36343575 0.6435319 0.363436343