HW2
Гугнина Дарья, Соколова Анна, Королик Ирина
загрузка библиотек
Загрузка переменных
ltu <- read_sav("/Users/dariagugnina/Desktop/Даша/BSGLTUM6.sav")
names(ltu)## [1] "IDCNTRY" "IDBOOK" "IDSCHOOL" "IDCLASS" "IDSTUD"
## [6] "IDGRADE" "ITSEX" "ITADMINI" "ITLANG" "BSBG01"
## [11] "BSBG03" "BSBG04" "BSBG05" "BSBG06A" "BSBG06B"
## [16] "BSBG06C" "BSBG06D" "BSBG06E" "BSBG06F" "BSBG06G"
## [21] "BSBG06H" "BSBG06I" "BSBG06J" "BSBG06K" "BSBG07A"
## [26] "BSBG07B" "BSBG08" "BSBG09A" "BSBG09B" "BSBG10A"
## [31] "BSBG10B" "BSBG11" "BSBG12" "BSBG13A" "BSBG13B"
## [36] "BSBG13C" "BSBG14A" "BSBG14B" "BSBG14C" "BSBG14D"
## [41] "BSBG14E" "BSBG14F" "BSBG15A" "BSBG15B" "BSBG15C"
## [46] "BSBG15D" "BSBG15E" "BSBG15F" "BSBG15G" "BSBG16A"
## [51] "BSBG16B" "BSBG16C" "BSBG16D" "BSBG16E" "BSBG16F"
## [56] "BSBG16G" "BSBG16H" "BSBG16I" "BSBM17A" "BSBM17B"
## [61] "BSBM17C" "BSBM17D" "BSBM17E" "BSBM17F" "BSBM17G"
## [66] "BSBM17H" "BSBM17I" "BSBM18A" "BSBM18B" "BSBM18C"
## [71] "BSBM18D" "BSBM18E" "BSBM18F" "BSBM18G" "BSBM18H"
## [76] "BSBM18I" "BSBM18J" "BSBM19A" "BSBM19B" "BSBM19C"
## [81] "BSBM19D" "BSBM19E" "BSBM19F" "BSBM19G" "BSBM19H"
## [86] "BSBM19I" "BSBM20A" "BSBM20B" "BSBM20C" "BSBM20D"
## [91] "BSBM20E" "BSBM20F" "BSBM20G" "BSBM20H" "BSBM20I"
## [96] "BSBS21A" "BSBS21B" "BSBS21C" "BSBS21D" "BSBS21E"
## [101] "BSBS21F" "BSBS21G" "BSBS21H" "BSBS21I" "BSBS22A"
## [106] "BSBS22B" "BSBS22C" "BSBS22D" "BSBS22E" "BSBS22F"
## [111] "BSBS22G" "BSBS22H" "BSBS22I" "BSBS22J" "BSBS23A"
## [116] "BSBS23B" "BSBS23C" "BSBS23D" "BSBS23E" "BSBS23F"
## [121] "BSBS23G" "BSBS23H" "BSBS24A" "BSBS24B" "BSBS24C"
## [126] "BSBS24D" "BSBS24E" "BSBS24F" "BSBS24G" "BSBS24H"
## [131] "BSBS24I" "BSBM25AA" "BSBS25AB" "BSBM25BA" "BSBS25BB"
## [136] "BSBM26AA" "BSBS26AB" "BSBM26BA" "BSBS26BB" "BSBB21"
## [141] "BSBB22A" "BSBB22B" "BSBB22C" "BSBB22D" "BSBB22E"
## [146] "BSBB22F" "BSBB22G" "BSBB22H" "BSBB22I" "BSBB23A"
## [151] "BSBB23B" "BSBB23C" "BSBB23D" "BSBB23E" "BSBB23F"
## [156] "BSBB23G" "BSBB23H" "BSBB23I" "BSBB23J" "BSBB24A"
## [161] "BSBB24B" "BSBB24C" "BSBB24D" "BSBB24E" "BSBB24F"
## [166] "BSBB24G" "BSBB24H" "BSBE25" "BSBE26A" "BSBE26B"
## [171] "BSBE26C" "BSBE26D" "BSBE26E" "BSBE26F" "BSBE26G"
## [176] "BSBE26H" "BSBE26I" "BSBE27A" "BSBE27B" "BSBE27C"
## [181] "BSBE27D" "BSBE27E" "BSBE27F" "BSBE27G" "BSBE27H"
## [186] "BSBE27I" "BSBE27J" "BSBE28A" "BSBE28B" "BSBE28C"
## [191] "BSBE28D" "BSBE28E" "BSBE28F" "BSBE28G" "BSBE28H"
## [196] "BSBC29" "BSBC30A" "BSBC30B" "BSBC30C" "BSBC30D"
## [201] "BSBC30E" "BSBC30F" "BSBC30G" "BSBC30H" "BSBC30I"
## [206] "BSBC31A" "BSBC31B" "BSBC31C" "BSBC31D" "BSBC31E"
## [211] "BSBC31F" "BSBC31G" "BSBC31H" "BSBC31I" "BSBC31J"
## [216] "BSBC32A" "BSBC32B" "BSBC32C" "BSBC32D" "BSBC32E"
## [221] "BSBC32F" "BSBC32G" "BSBC32H" "BSBP33" "BSBP34A"
## [226] "BSBP34B" "BSBP34C" "BSBP34D" "BSBP34E" "BSBP34F"
## [231] "BSBP34G" "BSBP34H" "BSBP34I" "BSBP35A" "BSBP35B"
## [236] "BSBP35C" "BSBP35D" "BSBP35E" "BSBP35F" "BSBP35G"
## [241] "BSBP35H" "BSBP35I" "BSBP35J" "BSBP36A" "BSBP36B"
## [246] "BSBP36C" "BSBP36D" "BSBP36E" "BSBP36F" "BSBP36G"
## [251] "BSBP36H" "BSBS37A" "BSBS37B" "BSBS37C" "BSBS37D"
## [256] "BSBS37E" "BSBS37F" "BSBS37G" "BSBS37H" "BSBS37I"
## [261] "BSBM38AA" "BSBB38AB" "BSBE38AC" "BSBC38AD" "BSBP38AE"
## [266] "BSBM38BA" "BSBB38BB" "BSBE38BC" "BSBC38BD" "BSBP38BE"
## [271] "BSBM39AA" "BSBS39AB" "BSBM39BA" "BSBS39BB" "ITACCOMM1"
## [276] "IDPOP" "IDGRADER" "BSDAGE" "TOTWGT" "HOUWGT"
## [281] "SENWGT" "WGTADJ1" "WGTADJ2" "WGTADJ3" "WGTFAC1"
## [286] "WGTFAC2" "WGTFAC3" "JKZONE" "JKREP" "BSMMAT01"
## [291] "BSMMAT02" "BSMMAT03" "BSMMAT04" "BSMMAT05" "BSSSCI01"
## [296] "BSSSCI02" "BSSSCI03" "BSSSCI04" "BSSSCI05" "BSMALG01"
## [301] "BSMALG02" "BSMALG03" "BSMALG04" "BSMALG05" "BSMDAT01"
## [306] "BSMDAT02" "BSMDAT03" "BSMDAT04" "BSMDAT05" "BSMNUM01"
## [311] "BSMNUM02" "BSMNUM03" "BSMNUM04" "BSMNUM05" "BSMGEO01"
## [316] "BSMGEO02" "BSMGEO03" "BSMGEO04" "BSMGEO05" "BSSCHE01"
## [321] "BSSCHE02" "BSSCHE03" "BSSCHE04" "BSSCHE05" "BSSEAR01"
## [326] "BSSEAR02" "BSSEAR03" "BSSEAR04" "BSSEAR05" "BSSBIO01"
## [331] "BSSBIO02" "BSSBIO03" "BSSBIO04" "BSSBIO05" "BSSPHY01"
## [336] "BSSPHY02" "BSSPHY03" "BSSPHY04" "BSSPHY05" "BSMKNO01"
## [341] "BSMKNO02" "BSMKNO03" "BSMKNO04" "BSMKNO05" "BSMAPP01"
## [346] "BSMAPP02" "BSMAPP03" "BSMAPP04" "BSMAPP05" "BSMREA01"
## [351] "BSMREA02" "BSMREA03" "BSMREA04" "BSMREA05" "BSSKNO01"
## [356] "BSSKNO02" "BSSKNO03" "BSSKNO04" "BSSKNO05" "BSSAPP01"
## [361] "BSSAPP02" "BSSAPP03" "BSSAPP04" "BSSAPP05" "BSSREA01"
## [366] "BSSREA02" "BSSREA03" "BSSREA04" "BSSREA05" "BSMIBM01"
## [371] "BSMIBM02" "BSMIBM03" "BSMIBM04" "BSMIBM05" "BSSIBM01"
## [376] "BSSIBM02" "BSSIBM03" "BSSIBM04" "BSSIBM05" "BSBGHER"
## [381] "BSDGHER" "BSBGSSB" "BSDGSSB" "BSBGSB" "BSDGSB"
## [386] "BSBGSLM" "BSDGSLM" "BSBGEML" "BSDGEML" "BSBGSCM"
## [391] "BSDGSCM" "BSBGSVM" "BSDGSVM" "BSBGSLS" "BSDGSLS"
## [396] "BSBGESL" "BSDGESL" "BSBGSCS" "BSDGSCS" "BSBGSVS"
## [401] "BSDGSVS" "BSBGSLB" "BSDGSLB" "BSBGEBL" "BSDGEBL"
## [406] "BSBGSCB" "BSDGSCB" "BSBGSLE" "BSDGSLE" "BSBGEEL"
## [411] "BSDGEEL" "BSBGSCE" "BSDGSCE" "BSBGSLC" "BSDGSLC"
## [416] "BSBGECL" "BSDGECL" "BSBGSCC" "BSDGSCC" "BSBGSLP"
## [421] "BSDGSLP" "BSBGEPL" "BSDGEPL" "BSBGSCP" "BSDGSCP"
## [426] "BSDG06S" "BSDGEDUP" "BSDMLOWP" "BSDSLOWP" "BSDMWKHW"
## [431] "BSDSWKHS" "BSDBWKHB" "BSDCWKHC" "BSDPWKHP" "BSDEWKHE"
## [436] "VERSION"ltu1 <- ltu[c('BSBM18C', 'BSBM18E', 'BSBM18G', 'BSBM18I', 'BSBM18J','BSBM20A', 'BSBM20B','BSBM20C', 'BSBM20D',
'BSBM20E', 'BSBM19A','BSBM19B','BSBM19C','BSBM19F','BSBM19G','BSBM19H')]Переводим в тип numeric
ltu2 <- as.data.frame(lapply(ltu1, as.numeric))Матрица корреляции
ltu.cor <- hetcor(ltu2)
ltu.cor<- ltu.cor$correlations
corrgram(ltu.cor)
Определяем количество факторов
fa.parallel(ltu.cor, 4347)
## Parallel analysis suggests that the number of factors = 4 and the number of components = 3Без вращения, 4 фактора
fa <- fa(ltu2, rotate="none", fm="ml", nfactors = 4)
fa## Factor Analysis using method = ml
## Call: fa(r = ltu2, nfactors = 4, rotate = "none", fm = "ml")
## Standardized loadings (pattern matrix) based upon correlation matrix
## ML1 ML2 ML3 ML4 h2 u2 com
## BSBM18C 0.58 0.26 -0.21 0.03 0.45 0.55 1.7
## BSBM18E 0.55 0.34 -0.38 -0.05 0.55 0.45 2.5
## BSBM18G 0.52 0.27 -0.29 0.03 0.43 0.57 2.1
## BSBM18I 0.52 0.41 -0.39 -0.08 0.59 0.41 2.8
## BSBM18J 0.53 0.42 -0.43 -0.08 0.64 0.36 2.9
## BSBM20A 0.51 0.28 0.24 -0.05 0.40 0.60 2.1
## BSBM20B 0.51 0.29 0.24 -0.11 0.41 0.59 2.2
## BSBM20C 0.54 0.29 0.51 -0.06 0.63 0.37 2.6
## BSBM20D 0.54 0.34 0.53 -0.06 0.70 0.30 2.7
## BSBM20E 0.61 0.03 0.23 0.11 0.43 0.57 1.4
## BSBM19A 0.69 -0.33 -0.01 0.12 0.60 0.40 1.5
## BSBM19B -0.45 0.53 0.03 0.31 0.58 0.42 2.6
## BSBM19C -0.55 0.55 0.03 0.24 0.67 0.33 2.4
## BSBM19F 0.68 -0.35 0.00 0.35 0.71 0.29 2.0
## BSBM19G 0.66 -0.20 -0.10 0.25 0.55 0.45 1.5
## BSBM19H -0.50 0.44 0.04 0.23 0.50 0.50 2.4
##
## ML1 ML2 ML3 ML4
## SS loadings 5.06 2.01 1.32 0.46
## Proportion Var 0.32 0.13 0.08 0.03
## Cumulative Var 0.32 0.44 0.52 0.55
## Proportion Explained 0.57 0.23 0.15 0.05
## Cumulative Proportion 0.57 0.80 0.95 1.00
##
## Mean item complexity = 2.2
## Test of the hypothesis that 4 factors are sufficient.
##
## The degrees of freedom for the null model are 120 and the objective function was 6.88 with Chi Square of 29846.93
## The degrees of freedom for the model are 62 and the objective function was 0.22
##
## 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 4276 with the empirical chi square 515.2 with prob < 1.2e-72
## The total number of observations was 4347 with Likelihood Chi Square = 939.02 with prob < 7e-157
##
## Tucker Lewis Index of factoring reliability = 0.943
## RMSEA index = 0.057 and the 90 % confidence intervals are 0.054 0.06
## BIC = 419.63
## Fit based upon off diagonal values = 1
## Measures of factor score adequacy
## ML1 ML2 ML3 ML4
## Correlation of (regression) scores with factors 0.96 0.91 0.88 0.74
## Multiple R square of scores with factors 0.92 0.83 0.77 0.55
## Minimum correlation of possible factor scores 0.85 0.67 0.54 0.10fa.diagram(fa)
Ротация
Ортоганальное вращение, 4 факторов
fa1 <- fa(ltu2, rotate="varimax", fm="ml", nfactors = 4)
fa1## Factor Analysis using method = ml
## Call: fa(r = ltu2, nfactors = 4, rotate = "varimax", fm = "ml")
## Standardized loadings (pattern matrix) based upon correlation matrix
## ML4 ML3 ML2 ML1 h2 u2 com
## BSBM18C 0.58 0.25 -0.10 0.21 0.45 0.55 1.7
## BSBM18E 0.72 0.15 -0.08 0.11 0.55 0.45 1.2
## BSBM18G 0.61 0.16 -0.07 0.18 0.43 0.57 1.4
## BSBM18I 0.75 0.16 -0.04 0.05 0.59 0.41 1.1
## BSBM18J 0.79 0.13 -0.04 0.05 0.64 0.36 1.1
## BSBM20A 0.26 0.57 -0.07 0.11 0.40 0.60 1.5
## BSBM20B 0.27 0.57 -0.09 0.05 0.41 0.59 1.5
## BSBM20C 0.10 0.78 -0.06 0.10 0.63 0.37 1.1
## BSBM20D 0.11 0.82 -0.02 0.09 0.70 0.30 1.1
## BSBM20E 0.17 0.48 -0.20 0.36 0.43 0.57 2.5
## BSBM19A 0.19 0.21 -0.50 0.52 0.60 0.40 2.6
## BSBM19B -0.02 -0.04 0.75 -0.11 0.58 0.42 1.1
## BSBM19C -0.05 -0.08 0.78 -0.23 0.67 0.33 1.2
## BSBM19F 0.14 0.17 -0.38 0.72 0.71 0.29 1.8
## BSBM19G 0.29 0.15 -0.33 0.57 0.55 0.45 2.3
## BSBM19H -0.09 -0.08 0.67 -0.18 0.50 0.50 1.2
##
## ML4 ML3 ML2 ML1
## SS loadings 2.74 2.42 2.21 1.47
## Proportion Var 0.17 0.15 0.14 0.09
## Cumulative Var 0.17 0.32 0.46 0.55
## Proportion Explained 0.31 0.27 0.25 0.17
## Cumulative Proportion 0.31 0.58 0.83 1.00
##
## Mean item complexity = 1.5
## Test of the hypothesis that 4 factors are sufficient.
##
## The degrees of freedom for the null model are 120 and the objective function was 6.88 with Chi Square of 29846.93
## The degrees of freedom for the model are 62 and the objective function was 0.22
##
## 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 4276 with the empirical chi square 515.2 with prob < 1.2e-72
## The total number of observations was 4347 with Likelihood Chi Square = 939.02 with prob < 7e-157
##
## Tucker Lewis Index of factoring reliability = 0.943
## RMSEA index = 0.057 and the 90 % confidence intervals are 0.054 0.06
## BIC = 419.63
## Fit based upon off diagonal values = 1
## Measures of factor score adequacy
## ML4 ML3 ML2 ML1
## Correlation of (regression) scores with factors 0.91 0.90 0.88 0.81
## Multiple R square of scores with factors 0.83 0.82 0.77 0.66
## Minimum correlation of possible factor scores 0.66 0.64 0.55 0.32fa.diagram(fa1, simple = T)
4 factors and oblimin
fa2 <- fa(ltu2, rotate="oblimin", fm="ml", nfactors = 4)
fa.diagram(fa2, simple = T)
fa2## Factor Analysis using method = ml
## Call: fa(r = ltu2, nfactors = 4, rotate = "oblimin", fm = "ml")
## Standardized loadings (pattern matrix) based upon correlation matrix
## ML1 ML3 ML2 ML4 h2 u2 com
## BSBM18C 0.54 0.11 0.02 0.17 0.45 0.55 1.3
## BSBM18E 0.73 -0.01 -0.02 0.03 0.55 0.45 1.0
## BSBM18G 0.59 0.02 0.04 0.14 0.43 0.57 1.1
## BSBM18I 0.78 0.01 -0.01 -0.05 0.59 0.41 1.0
## BSBM18J 0.82 -0.02 0.00 -0.05 0.64 0.36 1.0
## BSBM20A 0.16 0.54 -0.01 0.02 0.40 0.60 1.2
## BSBM20B 0.19 0.56 -0.08 -0.07 0.41 0.59 1.3
## BSBM20C -0.04 0.81 -0.01 0.00 0.63 0.37 1.0
## BSBM20D -0.03 0.85 0.03 -0.01 0.70 0.30 1.0
## BSBM20E 0.02 0.41 -0.01 0.36 0.43 0.57 2.0
## BSBM19A 0.05 0.06 -0.26 0.54 0.60 0.40 1.5
## BSBM19B 0.02 0.01 0.81 0.06 0.58 0.42 1.0
## BSBM19C 0.02 0.00 0.77 -0.08 0.67 0.33 1.0
## BSBM19F -0.04 0.00 -0.01 0.85 0.71 0.29 1.0
## BSBM19G 0.15 -0.02 -0.04 0.65 0.55 0.45 1.1
## BSBM19H -0.04 -0.01 0.67 -0.04 0.50 0.50 1.0
##
## ML1 ML3 ML2 ML4
## SS loadings 2.72 2.32 1.91 1.91
## Proportion Var 0.17 0.14 0.12 0.12
## Cumulative Var 0.17 0.31 0.43 0.55
## Proportion Explained 0.31 0.26 0.22 0.22
## Cumulative Proportion 0.31 0.57 0.78 1.00
##
## With factor correlations of
## ML1 ML3 ML2 ML4
## ML1 1.00 0.38 -0.17 0.37
## ML3 0.38 1.00 -0.18 0.38
## ML2 -0.17 -0.18 1.00 -0.64
## ML4 0.37 0.38 -0.64 1.00
##
## Mean item complexity = 1.2
## Test of the hypothesis that 4 factors are sufficient.
##
## The degrees of freedom for the null model are 120 and the objective function was 6.88 with Chi Square of 29846.93
## The degrees of freedom for the model are 62 and the objective function was 0.22
##
## 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 4276 with the empirical chi square 515.2 with prob < 1.2e-72
## The total number of observations was 4347 with Likelihood Chi Square = 939.02 with prob < 7e-157
##
## Tucker Lewis Index of factoring reliability = 0.943
## RMSEA index = 0.057 and the 90 % confidence intervals are 0.054 0.06
## BIC = 419.63
## Fit based upon off diagonal values = 1
## Measures of factor score adequacy
## ML1 ML3 ML2 ML4
## Correlation of (regression) scores with factors 0.93 0.92 0.91 0.92
## Multiple R square of scores with factors 0.86 0.85 0.84 0.85
## Minimum correlation of possible factor scores 0.72 0.71 0.67 0.69Check alpha
ltu3 <- ltu2[c('BSBM19A','BSBM19F','BSBM19G')]
ltu4 <- ltu2[c('BSBM18C', 'BSBM18E', 'BSBM18G', 'BSBM18I', 'BSBM18J')]
ltu5 <- ltu2[c('BSBM20A', 'BSBM20B','BSBM20C', 'BSBM20D','BSBM20E')]
ltu6 <- ltu2[c('BSBM19B','BSBM19C','BSBM19H')]
alpha(ltu3, check.keys=T)##
## Reliability analysis
## Call: alpha(x = ltu3, check.keys = T)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.82 0.82 0.75 0.6 4.5 0.0048 2.4 0.76 0.61
##
## lower alpha upper 95% confidence boundaries
## 0.81 0.82 0.83
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r med.r
## BSBM19A 0.76 0.76 0.61 0.61 3.1 0.0074 NA 0.61
## BSBM19F 0.73 0.73 0.57 0.57 2.7 0.0083 NA 0.57
## BSBM19G 0.77 0.77 0.63 0.63 3.4 0.0070 NA 0.63
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## BSBM19A 4311 0.85 0.85 0.74 0.67 2.1 0.86
## BSBM19F 4289 0.87 0.87 0.77 0.70 2.6 0.90
## BSBM19G 4270 0.85 0.85 0.72 0.65 2.4 0.90
##
## Non missing response frequency for each item
## 1 2 3 4 miss
## BSBM19A 0.27 0.44 0.23 0.06 0.01
## BSBM19F 0.11 0.35 0.37 0.17 0.01
## BSBM19G 0.17 0.40 0.32 0.12 0.02alpha(ltu4, check.keys=T)##
## Reliability analysis
## Call: alpha(x = ltu4, check.keys = T)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.84 0.84 0.82 0.52 5.4 0.0038 1.8 0.65 0.5
##
## lower alpha upper 95% confidence boundaries
## 0.84 0.84 0.85
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r med.r
## BSBM18C 0.83 0.83 0.79 0.54 4.8 0.0043 0.0037 0.54
## BSBM18E 0.80 0.80 0.76 0.50 4.1 0.0050 0.0050 0.48
## BSBM18G 0.82 0.83 0.79 0.54 4.7 0.0044 0.0046 0.55
## BSBM18I 0.80 0.80 0.76 0.51 4.1 0.0049 0.0021 0.50
## BSBM18J 0.80 0.80 0.75 0.50 3.9 0.0050 0.0020 0.49
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## BSBM18C 4293 0.75 0.74 0.64 0.59 1.9 0.85
## BSBM18E 4300 0.81 0.81 0.74 0.68 1.8 0.85
## BSBM18G 4300 0.75 0.75 0.65 0.60 2.0 0.86
## BSBM18I 4316 0.79 0.80 0.74 0.67 1.6 0.78
## BSBM18J 4309 0.82 0.82 0.77 0.70 1.7 0.83
##
## Non missing response frequency for each item
## 1 2 3 4 miss
## BSBM18C 0.34 0.44 0.16 0.06 0.01
## BSBM18E 0.43 0.38 0.14 0.05 0.01
## BSBM18G 0.31 0.45 0.17 0.06 0.01
## BSBM18I 0.53 0.34 0.09 0.03 0.01
## BSBM18J 0.47 0.37 0.12 0.04 0.01alpha(ltu5, check.keys=T)##
## Reliability analysis
## Call: alpha(x = ltu5, check.keys = T)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.81 0.82 0.8 0.47 4.5 0.0045 1.9 0.63 0.47
##
## lower alpha upper 95% confidence boundaries
## 0.8 0.81 0.82
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r med.r
## BSBM20A 0.78 0.78 0.75 0.47 3.6 0.0055 0.0138 0.47
## BSBM20B 0.78 0.79 0.75 0.48 3.7 0.0054 0.0114 0.45
## BSBM20C 0.76 0.77 0.73 0.45 3.3 0.0059 0.0060 0.47
## BSBM20D 0.75 0.76 0.71 0.44 3.1 0.0063 0.0061 0.42
## BSBM20E 0.81 0.81 0.79 0.52 4.3 0.0047 0.0096 0.48
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## BSBM20A 4313 0.75 0.76 0.67 0.60 1.7 0.81
## BSBM20B 4304 0.72 0.75 0.66 0.58 1.6 0.72
## BSBM20C 4297 0.79 0.79 0.74 0.65 1.7 0.81
## BSBM20D 4297 0.82 0.81 0.78 0.69 1.7 0.84
## BSBM20E 4295 0.72 0.69 0.56 0.51 2.6 0.98
##
## Non missing response frequency for each item
## 1 2 3 4 miss
## BSBM20A 0.48 0.37 0.10 0.04 0.01
## BSBM20B 0.49 0.41 0.08 0.02 0.01
## BSBM20C 0.52 0.34 0.11 0.04 0.01
## BSBM20D 0.52 0.32 0.13 0.04 0.01
## BSBM20E 0.15 0.29 0.35 0.20 0.01alpha(ltu6, check.keys=T)##
## Reliability analysis
## Call: alpha(x = ltu6, check.keys = T)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.8 0.8 0.73 0.57 4.1 0.0052 2.6 0.85 0.58
##
## lower alpha upper 95% confidence boundaries
## 0.79 0.8 0.81
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r med.r
## BSBM19B 0.73 0.73 0.58 0.58 2.8 0.0081 NA 0.58
## BSBM19C 0.69 0.69 0.52 0.52 2.2 0.0095 NA 0.52
## BSBM19H 0.76 0.77 0.62 0.62 3.3 0.0071 NA 0.62
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## BSBM19B 4304 0.84 0.84 0.72 0.64 2.7 0.96
## BSBM19C 4285 0.87 0.87 0.77 0.69 2.5 1.03
## BSBM19H 4298 0.83 0.83 0.68 0.61 2.6 1.03
##
## Non missing response frequency for each item
## 1 2 3 4 miss
## BSBM19B 0.11 0.29 0.35 0.25 0.01
## BSBM19C 0.18 0.33 0.27 0.22 0.01
## BSBM19H 0.18 0.29 0.29 0.23 0.01Adding facors in ltu dataset
fa4 <- fa(ltu2, cor="mixed", fm="ml", nfactors=4, scores=T, rotate="varimax")##
## mixed.cor is deprecated, please use mixedCor.scores <- (fa4$scores)
factores<-cbind(ltu,scores)
names(factores)## [1] "IDCNTRY" "IDBOOK" "IDSCHOOL" "IDCLASS" "IDSTUD"
## [6] "IDGRADE" "ITSEX" "ITADMINI" "ITLANG" "BSBG01"
## [11] "BSBG03" "BSBG04" "BSBG05" "BSBG06A" "BSBG06B"
## [16] "BSBG06C" "BSBG06D" "BSBG06E" "BSBG06F" "BSBG06G"
## [21] "BSBG06H" "BSBG06I" "BSBG06J" "BSBG06K" "BSBG07A"
## [26] "BSBG07B" "BSBG08" "BSBG09A" "BSBG09B" "BSBG10A"
## [31] "BSBG10B" "BSBG11" "BSBG12" "BSBG13A" "BSBG13B"
## [36] "BSBG13C" "BSBG14A" "BSBG14B" "BSBG14C" "BSBG14D"
## [41] "BSBG14E" "BSBG14F" "BSBG15A" "BSBG15B" "BSBG15C"
## [46] "BSBG15D" "BSBG15E" "BSBG15F" "BSBG15G" "BSBG16A"
## [51] "BSBG16B" "BSBG16C" "BSBG16D" "BSBG16E" "BSBG16F"
## [56] "BSBG16G" "BSBG16H" "BSBG16I" "BSBM17A" "BSBM17B"
## [61] "BSBM17C" "BSBM17D" "BSBM17E" "BSBM17F" "BSBM17G"
## [66] "BSBM17H" "BSBM17I" "BSBM18A" "BSBM18B" "BSBM18C"
## [71] "BSBM18D" "BSBM18E" "BSBM18F" "BSBM18G" "BSBM18H"
## [76] "BSBM18I" "BSBM18J" "BSBM19A" "BSBM19B" "BSBM19C"
## [81] "BSBM19D" "BSBM19E" "BSBM19F" "BSBM19G" "BSBM19H"
## [86] "BSBM19I" "BSBM20A" "BSBM20B" "BSBM20C" "BSBM20D"
## [91] "BSBM20E" "BSBM20F" "BSBM20G" "BSBM20H" "BSBM20I"
## [96] "BSBS21A" "BSBS21B" "BSBS21C" "BSBS21D" "BSBS21E"
## [101] "BSBS21F" "BSBS21G" "BSBS21H" "BSBS21I" "BSBS22A"
## [106] "BSBS22B" "BSBS22C" "BSBS22D" "BSBS22E" "BSBS22F"
## [111] "BSBS22G" "BSBS22H" "BSBS22I" "BSBS22J" "BSBS23A"
## [116] "BSBS23B" "BSBS23C" "BSBS23D" "BSBS23E" "BSBS23F"
## [121] "BSBS23G" "BSBS23H" "BSBS24A" "BSBS24B" "BSBS24C"
## [126] "BSBS24D" "BSBS24E" "BSBS24F" "BSBS24G" "BSBS24H"
## [131] "BSBS24I" "BSBM25AA" "BSBS25AB" "BSBM25BA" "BSBS25BB"
## [136] "BSBM26AA" "BSBS26AB" "BSBM26BA" "BSBS26BB" "BSBB21"
## [141] "BSBB22A" "BSBB22B" "BSBB22C" "BSBB22D" "BSBB22E"
## [146] "BSBB22F" "BSBB22G" "BSBB22H" "BSBB22I" "BSBB23A"
## [151] "BSBB23B" "BSBB23C" "BSBB23D" "BSBB23E" "BSBB23F"
## [156] "BSBB23G" "BSBB23H" "BSBB23I" "BSBB23J" "BSBB24A"
## [161] "BSBB24B" "BSBB24C" "BSBB24D" "BSBB24E" "BSBB24F"
## [166] "BSBB24G" "BSBB24H" "BSBE25" "BSBE26A" "BSBE26B"
## [171] "BSBE26C" "BSBE26D" "BSBE26E" "BSBE26F" "BSBE26G"
## [176] "BSBE26H" "BSBE26I" "BSBE27A" "BSBE27B" "BSBE27C"
## [181] "BSBE27D" "BSBE27E" "BSBE27F" "BSBE27G" "BSBE27H"
## [186] "BSBE27I" "BSBE27J" "BSBE28A" "BSBE28B" "BSBE28C"
## [191] "BSBE28D" "BSBE28E" "BSBE28F" "BSBE28G" "BSBE28H"
## [196] "BSBC29" "BSBC30A" "BSBC30B" "BSBC30C" "BSBC30D"
## [201] "BSBC30E" "BSBC30F" "BSBC30G" "BSBC30H" "BSBC30I"
## [206] "BSBC31A" "BSBC31B" "BSBC31C" "BSBC31D" "BSBC31E"
## [211] "BSBC31F" "BSBC31G" "BSBC31H" "BSBC31I" "BSBC31J"
## [216] "BSBC32A" "BSBC32B" "BSBC32C" "BSBC32D" "BSBC32E"
## [221] "BSBC32F" "BSBC32G" "BSBC32H" "BSBP33" "BSBP34A"
## [226] "BSBP34B" "BSBP34C" "BSBP34D" "BSBP34E" "BSBP34F"
## [231] "BSBP34G" "BSBP34H" "BSBP34I" "BSBP35A" "BSBP35B"
## [236] "BSBP35C" "BSBP35D" "BSBP35E" "BSBP35F" "BSBP35G"
## [241] "BSBP35H" "BSBP35I" "BSBP35J" "BSBP36A" "BSBP36B"
## [246] "BSBP36C" "BSBP36D" "BSBP36E" "BSBP36F" "BSBP36G"
## [251] "BSBP36H" "BSBS37A" "BSBS37B" "BSBS37C" "BSBS37D"
## [256] "BSBS37E" "BSBS37F" "BSBS37G" "BSBS37H" "BSBS37I"
## [261] "BSBM38AA" "BSBB38AB" "BSBE38AC" "BSBC38AD" "BSBP38AE"
## [266] "BSBM38BA" "BSBB38BB" "BSBE38BC" "BSBC38BD" "BSBP38BE"
## [271] "BSBM39AA" "BSBS39AB" "BSBM39BA" "BSBS39BB" "ITACCOMM1"
## [276] "IDPOP" "IDGRADER" "BSDAGE" "TOTWGT" "HOUWGT"
## [281] "SENWGT" "WGTADJ1" "WGTADJ2" "WGTADJ3" "WGTFAC1"
## [286] "WGTFAC2" "WGTFAC3" "JKZONE" "JKREP" "BSMMAT01"
## [291] "BSMMAT02" "BSMMAT03" "BSMMAT04" "BSMMAT05" "BSSSCI01"
## [296] "BSSSCI02" "BSSSCI03" "BSSSCI04" "BSSSCI05" "BSMALG01"
## [301] "BSMALG02" "BSMALG03" "BSMALG04" "BSMALG05" "BSMDAT01"
## [306] "BSMDAT02" "BSMDAT03" "BSMDAT04" "BSMDAT05" "BSMNUM01"
## [311] "BSMNUM02" "BSMNUM03" "BSMNUM04" "BSMNUM05" "BSMGEO01"
## [316] "BSMGEO02" "BSMGEO03" "BSMGEO04" "BSMGEO05" "BSSCHE01"
## [321] "BSSCHE02" "BSSCHE03" "BSSCHE04" "BSSCHE05" "BSSEAR01"
## [326] "BSSEAR02" "BSSEAR03" "BSSEAR04" "BSSEAR05" "BSSBIO01"
## [331] "BSSBIO02" "BSSBIO03" "BSSBIO04" "BSSBIO05" "BSSPHY01"
## [336] "BSSPHY02" "BSSPHY03" "BSSPHY04" "BSSPHY05" "BSMKNO01"
## [341] "BSMKNO02" "BSMKNO03" "BSMKNO04" "BSMKNO05" "BSMAPP01"
## [346] "BSMAPP02" "BSMAPP03" "BSMAPP04" "BSMAPP05" "BSMREA01"
## [351] "BSMREA02" "BSMREA03" "BSMREA04" "BSMREA05" "BSSKNO01"
## [356] "BSSKNO02" "BSSKNO03" "BSSKNO04" "BSSKNO05" "BSSAPP01"
## [361] "BSSAPP02" "BSSAPP03" "BSSAPP04" "BSSAPP05" "BSSREA01"
## [366] "BSSREA02" "BSSREA03" "BSSREA04" "BSSREA05" "BSMIBM01"
## [371] "BSMIBM02" "BSMIBM03" "BSMIBM04" "BSMIBM05" "BSSIBM01"
## [376] "BSSIBM02" "BSSIBM03" "BSSIBM04" "BSSIBM05" "BSBGHER"
## [381] "BSDGHER" "BSBGSSB" "BSDGSSB" "BSBGSB" "BSDGSB"
## [386] "BSBGSLM" "BSDGSLM" "BSBGEML" "BSDGEML" "BSBGSCM"
## [391] "BSDGSCM" "BSBGSVM" "BSDGSVM" "BSBGSLS" "BSDGSLS"
## [396] "BSBGESL" "BSDGESL" "BSBGSCS" "BSDGSCS" "BSBGSVS"
## [401] "BSDGSVS" "BSBGSLB" "BSDGSLB" "BSBGEBL" "BSDGEBL"
## [406] "BSBGSCB" "BSDGSCB" "BSBGSLE" "BSDGSLE" "BSBGEEL"
## [411] "BSDGEEL" "BSBGSCE" "BSDGSCE" "BSBGSLC" "BSDGSLC"
## [416] "BSBGECL" "BSDGECL" "BSBGSCC" "BSDGSCC" "BSBGSLP"
## [421] "BSDGSLP" "BSBGEPL" "BSDGEPL" "BSBGSCP" "BSDGSCP"
## [426] "BSDG06S" "BSDGEDUP" "BSDMLOWP" "BSDSLOWP" "BSDMWKHW"
## [431] "BSDSWKHS" "BSDBWKHB" "BSDCWKHC" "BSDPWKHP" "BSDEWKHE"
## [436] "VERSION" "ML3" "ML1" "ML2" "ML4"Regression
Check distribution dependent var(should be normal)
ggplot()+
geom_histogram(data=factores, aes(x = BSMMAT01), fill= "aquamarine3", color= "lavenderblush4")+
xlab("Math achievements")+
ylab("Number of respondents")+
ggtitle("Distribution of math achievements")## Don't know how to automatically pick scale for object of type haven_labelled. Defaulting to continuous.## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
Regression
model <- lm(as.numeric(factores$BSMMAT01) ~ factores$ML1 + factores$ML2+factores$ML3+factores$ML4+factores$ITSEX+factores$BSBG07B+factores$BSBG07A+factores$BSBG10A)
summary(model)##
## Call:
## lm(formula = as.numeric(factores$BSMMAT01) ~ factores$ML1 + factores$ML2 +
## factores$ML3 + factores$ML4 + factores$ITSEX + factores$BSBG07B +
## factores$BSBG07A + factores$BSBG10A)
##
## Residuals:
## Min 1Q Median 3Q Max
## -274.779 -39.278 4.062 43.470 218.156
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 485.465803 9.082078 53.453 < 2e-16 ***
## factores$ML1 -1.181389 1.027414 -1.150 0.25027
## factores$ML2 43.368350 1.092710 39.689 < 2e-16 ***
## factores$ML3 0.007532 1.039237 0.007 0.99422
## factores$ML4 -13.436391 1.255235 -10.704 < 2e-16 ***
## factores$ITSEX -2.029118 2.038464 -0.995 0.31959
## factores$BSBG07B -1.902350 0.634724 -2.997 0.00274 **
## factores$BSBG07A 4.804380 0.685409 7.010 2.8e-12 ***
## factores$BSBG10A 6.817370 7.876064 0.866 0.38677
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 62.87 on 3968 degrees of freedom
## (370 observations deleted due to missingness)
## Multiple R-squared: 0.345, Adjusted R-squared: 0.3437
## F-statistic: 261.3 on 8 and 3968 DF, p-value: < 2.2e-16Check multicollinearity
vif(model)## factores$ML1 factores$ML2 factores$ML3 factores$ML4
## 1.016533 1.062021 1.019644 1.110537
## factores$ITSEX factores$BSBG07B factores$BSBG07A factores$BSBG10A
## 1.044942 1.536362 1.544644 1.003278Diagnostic
par(mfrow=c(2,2)) # to put 4 graphs on 1 screen
layout(matrix(c(1,2,3,4),2,2))
plot(model)