Social impact project
1 PREPARATION
1.1 Merge
#- Within variables
Wdata=import("C:/Users/Eason Zhang/Dropbox/social impact project/Final analysis/employeedata.sav")%>%as.data.table()
numerical_variable_names <- names(Wdata)[sapply(Wdata, is.numeric)]
Wdata=group_mean_center(Wdata, numerical_variable_names,by="FactoryAssessedID", add.suffix=".GroC")
added(Wdata, {
wage.SD = sd(wage, na.rm = TRUE)
stress.SD = sd(stress, na.rm = TRUE)
mentalhealth.SD = sd(mentalhealth, na.rm = TRUE)},by=FactoryAssessedID)
#-- Within data check
matching_variables.W <- cc("mentalhealth,stress,wage,migrant10.GroC,
mentalhealth.SD,stress.SD,wage.SD")
contains_variables.W <- names(Wdata) %in% matching_variables.W
matching_variables.W <- names(Wdata)[contains_variables.W]
matching_variables.W
#- Between variables
#-- BA data
BAdata=import("C:/Users/Eason Zhang/Dropbox/social impact project/Final analysis/BA20.1920.finalanalysis.sav")%>%as.data.table()
#-- BM data
BMdata<- import("C:/Users/Eason Zhang/Dropbox/social impact project/Final analysis/managerdata.sav")%>%as.data.table()
BMdata1=BMdata[year == 2019]
BMdata2=BMdata[year == 2020]
BMdata_mean <- BMdata[, .SD, .SDcols = sapply(BMdata, is.numeric)]
BMdata_mean <- BMdata_mean[, lapply(.SD, mean, na.rm = TRUE), by = .(FactoryAssessedID)]
B.Aggregated <- unique(Wdata[, .(FactoryAssessedID, mentalhealth_mean, stress_mean, wage_mean, mentalhealth.SD, stress.SD, wage.SD)], by = "FactoryAssessedID")
#--- Cobmine BM data
setnames(BMdata1, old = names(BMdata1), new = paste0("BM19.", names(BMdata1)))
setnames(BMdata2, old = names(BMdata2), new = paste0("BM20.", names(BMdata2)))
setnames(BMdata_mean, old = names(BMdata_mean), new = paste0("BM.", names(BMdata_mean)))
setnames(BMdata_mean, "BM.FactoryAssessedID", "FactoryAssessedID")
setnames(BMdata1, "BM19.FactoryAssessedID", "FactoryAssessedID")
setnames(BMdata2, "BM20.FactoryAssessedID", "FactoryAssessedID")
Bdata<- Reduce(function(x, y) merge(x, y, by = "FactoryAssessedID", all = TRUE),list(BMdata_mean, BMdata1, BMdata2))
Bdata <- merge(BAdata, Bdata, by = "FactoryAssessedID", all = T)
Bdata2 <- merge(Bdata, B.Aggregated, by = "FactoryAssessedID", all = T)
#-- Between data check
matching_variables.B <- cc("BM.responsiblesourcing,BM19.responsiblesourcing,BM20.responsiblesourcing,BA1920FOApractices,BA20FOApractices,BA1920discriminate4prac,BA20discriminate4prac,BA1920targetedpractices,BA20targetedpractices,FactoryAssessedID, mentalhealth_mean, stress_mean, wage_mean, mentalhealth.SD, stress.SD, wage.SD")
contains_variables.B <- names(Bdata2) %in% matching_variables.B
matching_variables.B <- names(Bdata2)[contains_variables.B]
matching_variables.B
#- Full data
Bdata2=Bdata2[, c("mentalhealth_mean", "stress_mean", "wage_mean",
"mentalhealth.SD", "stress.SD", "wage.SD") := NULL]
BWdata2 <- merge(Bdata2, Wdata, by = "FactoryAssessedID", all = T)
BWdata2$clus <- BWdata2$FactoryAssessedID
#- Export
export(Bdata2,"Bdata3.sav")
export(BWdata2,"BWdata3.sav")
2 OVERVIEW
## Frequency Statistics:
## ───────────────
## N %
## ───────────────
## 1 1730 33.5
## 2 1666 32.3
## 3 1756 34.0
## (NA) 12 0.2
## ───────────────
## Total N = 5,164
## Valid N = 5,152One-round analysis: A. 3; B. 2 C. 1
Two-round analysis: D. 3&2; E. 3&1; F. 2&1
Three-round analysis: G. 3&2&1
3 A. 3rd ROUND DATA
3.1 I check for cw2: Cross-level interaction of M
3.1.1 BA1920FOApractices
mentalhealth.BA1920FOApractices=lmer(mentalhealth~BA1920FOApractices*migrant10+migrant10_mean*BA1920FOApractices+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
stress.BA1920FOApractices=lmer(stress~BA1920FOApractices*migrant10+migrant10_mean*BA1920FOApractices+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
wage.BA1920FOApractices=lmer(wage~BA1920FOApractices*migrant10+migrant10_mean*BA1920FOApractices+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
model_summary(list(mentalhealth.BA1920FOApractices, stress.BA1920FOApractices, wage.BA1920FOApractices))##
## Model Summary
##
## ────────────────────────────────────────────────────────────────────────────
## (1) mentalhealth (2) stress (3) wage
## ────────────────────────────────────────────────────────────────────────────
## (Intercept) 3.098 3.745 378.106 *
## (1.701) (2.417) (147.512)
## BA1920FOApractices 0.011 -0.034 -7.288
## (0.086) (0.123) (7.477)
## migrant10 6.805 * -2.403 281.488 *
## (2.750) (2.570) (125.870)
## migrant10_mean -4.163 -0.669 -506.045
## (3.615) (4.352) (286.715)
## BA1920FOApractices:migrant10 -0.346 * 0.157 -15.141 *
## (0.141) (0.132) (6.467)
## BA1920FOApractices:migrant10_mean 0.205 0.009 24.703
## (0.183) (0.222) (14.500)
## ────────────────────────────────────────────────────────────────────────────
## Marginal R^2 0.012 0.030 0.040
## Conditional R^2 0.181 0.060 0.360
## AIC 3933.788 6059.325 17848.612
## BIC 3985.815 6113.650 17902.788
## Num. obs. 1343 1690 1665
## Num. groups: clus 66 66 66
## Var: clus (Intercept) 0.021 0.173 695.328
## Var: clus migrant10 0.388 0.298 1264.509
## Cov: clus (Intercept) migrant10 -0.055 -0.223 -288.457
## Var: Residual 0.999 2.026 2389.298
## ────────────────────────────────────────────────────────────────────────────
## Note. * p < .05, ** p < .01, *** p < .001.
3.1.2 BA20FOApractices
mentalhealth.BA20FOApractices=lmer(mentalhealth~BA20FOApractices*migrant10+migrant10_mean*BA20FOApractices+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
stress.BA20FOApractices=lmer(stress~BA20FOApractices*migrant10+migrant10_mean*BA20FOApractices+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
wage.BA20FOApractices=lmer(wage~BA20FOApractices*migrant10+migrant10_mean*BA20FOApractices+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
model_summary(list(mentalhealth.BA20FOApractices, stress.BA20FOApractices, wage.BA20FOApractices))##
## Model Summary
##
## ───────────────────────────────────────────────────────────────────────────
## (1) mentalhealth (2) stress (3) wage
## ───────────────────────────────────────────────────────────────────────────
## (Intercept) 4.988 ** 3.701 337.226 *
## (1.838) (2.855) (168.468)
## BA20FOApractices -0.088 -0.035 -5.244
## (0.092) (0.145) (8.489)
## migrant10 12.968 ** -6.416 * 396.245 *
## (4.925) (3.131) (155.001)
## migrant10_mean -11.243 * 3.366 -432.188
## (4.472) (5.656) (384.388)
## BA20FOApractices:migrant10 -0.650 ** 0.361 * -20.503 **
## (0.247) (0.158) (7.841)
## BA20FOApractices:migrant10_mean 0.566 * -0.191 20.901
## (0.224) (0.285) (19.243)
## ───────────────────────────────────────────────────────────────────────────
## Marginal R^2 0.028 0.052 0.051
## Conditional R^2 0.264 0.094 0.434
## AIC 2246.304 3465.962 10086.196
## BIC 2292.948 3514.735 10134.855
## Num. obs. 784 970 959
## Num. groups: clus 44 44 44
## Var: clus (Intercept) 0.017 0.218 789.517
## Var: clus migrant10 0.601 0.338 1318.768
## Cov: clus (Intercept) migrant10 -0.050 -0.271 -255.259
## Var: Residual 0.909 1.967 1910.987
## ───────────────────────────────────────────────────────────────────────────
## Note. * p < .05, ** p < .01, *** p < .001.
3.1.3 BA1920discriminate4prac
mentalhealth.BA1920discriminate4prac=lmer(mentalhealth~BA1920discriminate4prac*migrant10+migrant10_mean*BA1920discriminate4prac+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
stress.BA1920discriminate4prac=lmer(stress~BA1920discriminate4prac*migrant10+migrant10_mean*BA1920discriminate4prac+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
wage.BA1920discriminate4prac=lmer(wage~BA1920discriminate4prac*migrant10+migrant10_mean*BA1920discriminate4prac+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
model_summary(list(mentalhealth.BA1920discriminate4prac, stress.BA1920discriminate4prac, wage.BA1920discriminate4prac))##
## Model Summary
##
## ──────────────────────────────────────────────────────────────────────────────────
## (1) mentalhealth (2) stress (3) wage
## ──────────────────────────────────────────────────────────────────────────────────
## (Intercept) 1.126 2.163 406.518 **
## (1.789) (1.778) (141.449)
## BA1920discriminate4prac 0.552 0.219 -43.798
## (0.452) (0.454) (35.815)
## migrant10 -0.138 0.956 29.345
## (1.326) (1.261) (62.273)
## migrant10_mean 2.834 0.550 -280.043
## (2.834) (2.481) (207.741)
## BA1920discriminate4prac:migrant10 0.045 -0.084 -11.093
## (0.342) (0.328) (16.211)
## BA1920discriminate4prac:migrant10_mean -0.752 -0.230 65.974
## (0.716) (0.637) (52.670)
## ──────────────────────────────────────────────────────────────────────────────────
## Marginal R^2 0.002 0.027 0.032
## Conditional R^2 0.186 0.058 0.368
## AIC 3932.120 6056.879 17846.788
## BIC 3984.147 6111.204 17900.964
## Num. obs. 1343 1690 1665
## Num. groups: clus 66 66 66
## Var: clus (Intercept) 0.031 0.169 714.091
## Var: clus migrant10 0.443 0.282 1391.197
## Cov: clus (Intercept) migrant10 -0.076 -0.211 -316.643
## Var: Residual 0.998 2.028 2389.350
## ──────────────────────────────────────────────────────────────────────────────────
## Note. * p < .05, ** p < .01, *** p < .001.interact_plot(mentalhealth.BA1920discriminate4prac, modx = BA1920discriminate4prac, pred = migrant10)
3.1.4 BA20discriminate4prac
mentalhealth.BA20discriminate4prac=lmer(mentalhealth~BA20discriminate4prac*migrant10+migrant10_mean*BA20discriminate4prac+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
stress.BA20discriminate4prac=lmer(stress~BA20discriminate4prac*migrant10+migrant10_mean*BA20discriminate4prac+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
wage.BA20discriminate4prac=lmer(wage~BA20discriminate4prac*migrant10+migrant10_mean*BA20discriminate4prac+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
model_summary(list(mentalhealth.BA20discriminate4prac, stress.BA20discriminate4prac, wage.BA20discriminate4prac))##
## Model Summary
##
## ────────────────────────────────────────────────────────────────────────────────
## (1) mentalhealth (2) stress (3) wage
## ────────────────────────────────────────────────────────────────────────────────
## (Intercept) 1.263 3.424 578.933 **
## (2.418) (2.209) (183.368)
## BA20discriminate4prac 0.495 -0.124 -87.203
## (0.608) (0.562) (46.228)
## migrant10 1.418 -1.023 109.091
## (2.429) (1.818) (85.307)
## migrant10_mean 0.851 1.269 -557.822
## (4.114) (3.150) (290.183)
## BA20discriminate4prac:migrant10 -0.361 0.445 -30.599
## (0.619) (0.469) (22.017)
## BA20discriminate4prac:migrant10_mean -0.186 -0.398 136.462
## (1.035) (0.807) (73.253)
## ────────────────────────────────────────────────────────────────────────────────
## Marginal R^2 0.005 0.045 0.056
## Conditional R^2 0.271 0.092 0.431
## AIC 2246.134 3465.777 10080.336
## BIC 2292.778 3514.550 10128.995
## Num. obs. 784 970 959
## Num. groups: clus 44 44 44
## Var: clus (Intercept) 0.034 0.209 765.758
## Var: clus migrant10 0.757 0.405 1515.093
## Cov: clus (Intercept) migrant10 -0.107 -0.288 -356.668
## Var: Residual 0.909 1.972 1911.968
## ────────────────────────────────────────────────────────────────────────────────
## Note. * p < .05, ** p < .01, *** p < .001.
3.1.5 BA1920targetedpractices
mentalhealth.BA1920targetedpractices=lmer(mentalhealth~BA1920targetedpractices*migrant10+migrant10_mean*BA1920targetedpractices+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
stress.BA1920targetedpractices=lmer(stress~BA1920targetedpractices*migrant10+migrant10_mean*BA1920targetedpractices+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
wage.BA1920targetedpractices=lmer(wage~BA1920targetedpractices*migrant10+migrant10_mean*BA1920targetedpractices+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
model_summary(list(mentalhealth.BA1920targetedpractices, stress.BA1920targetedpractices, wage.BA1920targetedpractices))##
## Model Summary
##
## ────────────────────────────────────────────────────────────────────────────────────
## (1) mentalhealth (2) stress (3) wage
## ────────────────────────────────────────────────────────────────────────────────────
## (Intercept) 1.592 3.605 ** 380.477 ***
## (1.359) (1.327) (103.053)
## BA1920targetedpractices 0.176 -0.061 -15.080
## (0.138) (0.137) (10.543)
## migrant10 1.267 -0.030 78.992
## (1.285) (1.075) (53.297)
## migrant10_mean 1.524 -0.624 -283.339
## (2.422) (2.015) (168.036)
## BA1920targetedpractices:migrant10 -0.133 0.071 -10.023
## (0.137) (0.116) (5.765)
## BA1920targetedpractices:migrant10_mean -0.166 0.025 27.323
## (0.249) (0.210) (17.305)
## ────────────────────────────────────────────────────────────────────────────────────
## Marginal R^2 0.006 0.027 0.043
## Conditional R^2 0.188 0.057 0.367
## AIC 3936.054 6062.975 17849.806
## BIC 3988.081 6117.300 17903.982
## Num. obs. 1343 1690 1665
## Num. groups: clus 66 66 66
## Var: clus (Intercept) 0.023 0.157 681.623
## Var: clus migrant10 0.444 0.268 1317.940
## Cov: clus (Intercept) migrant10 -0.072 -0.197 -289.455
## Var: Residual 0.998 2.029 2389.709
## ────────────────────────────────────────────────────────────────────────────────────
## Note. * p < .05, ** p < .01, *** p < .001.interact_plot(mentalhealth.BA1920targetedpractices, modx = BA1920targetedpractices, pred = migrant10)
3.1.6 BA20targetedpractices
mentalhealth.BA20targetedpractices=lmer(mentalhealth~BA20targetedpractices*migrant10+migrant10_mean*BA20targetedpractices+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
stress.BA20targetedpractices=lmer(stress~BA20targetedpractices*migrant10+migrant10_mean*BA20targetedpractices+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
wage.BA20targetedpractices=lmer(wage~BA20targetedpractices*migrant10+migrant10_mean*BA20targetedpractices+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
model_summary(list(mentalhealth.BA20targetedpractices, stress.BA20targetedpractices, wage.BA20targetedpractices))##
## Model Summary
##
## ──────────────────────────────────────────────────────────────────────────────────
## (1) mentalhealth (2) stress (3) wage
## ──────────────────────────────────────────────────────────────────────────────────
## (Intercept) 2.035 4.195 ** 412.932 ***
## (1.429) (1.435) (113.736)
## BA20targetedpractices 0.122 -0.131 -18.422
## (0.145) (0.149) (11.630)
## migrant10 0.725 -0.779 86.650
## (1.710) (1.206) (57.923)
## migrant10_mean 0.142 -1.169 -346.382
## (2.647) (2.256) (195.737)
## BA20targetedpractices:migrant10 -0.078 0.163 -10.611
## (0.185) (0.132) (6.385)
## BA20targetedpractices:migrant10_mean 0.005 0.088 34.247
## (0.273) (0.239) (20.293)
## ──────────────────────────────────────────────────────────────────────────────────
## Marginal R^2 0.008 0.047 0.051
## Conditional R^2 0.275 0.093 0.434
## AIC 2252.242 3471.949 10088.206
## BIC 2298.886 3520.722 10136.865
## Num. obs. 784 970 959
## Num. groups: clus 44 44 44
## Var: clus (Intercept) 0.027 0.212 749.745
## Var: clus migrant10 0.785 0.364 1469.150
## Cov: clus (Intercept) migrant10 -0.111 -0.272 -294.527
## Var: Residual 0.909 1.970 1913.017
## ──────────────────────────────────────────────────────────────────────────────────
## Note. * p < .05, ** p < .01, *** p < .001.
3.2 II check for ab2: Main effect of M on W (Mplus approach)
3.2.1 BM.responsiblesourcing
BA1920FOApractices.BM.responsiblesourcing=lmer(BA1920FOApractices~BM.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
BA20FOApractices.BM.responsiblesourcing=lmer(BA20FOApractices~BM.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
BA1920discriminate4prac.BM.responsiblesourcing=lmer(BA1920discriminate4prac~BM.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
BA20discriminate4prac.BM.responsiblesourcing=lmer(BA20discriminate4prac~BM.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
BA1920targetedpractices.BM.responsiblesourcing=lmer(BA1920targetedpractices~BM.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
BA20targetedpractices.BM.responsiblesourcing=lmer(BA20targetedpractices~BM.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
model_summary(list(BA1920FOApractices.BM.responsiblesourcing, BA20FOApractices.BM.responsiblesourcing, BA1920discriminate4prac.BM.responsiblesourcing, BA20discriminate4prac.BM.responsiblesourcing, BA1920targetedpractices.BM.responsiblesourcing, BA20targetedpractices.BM.responsiblesourcing))##
## Model Summary
##
## ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## (1) BA1920FOApractices (2) BA20FOApractices (3) BA1920discriminate4prac (4) BA20discriminate4prac (5) BA1920targetedpractices (6) BA20targetedpractices
## ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## (Intercept) 19.055 *** 18.910 *** 3.813 *** 3.874 *** 9.121 *** 8.859 ***
## (0.055) (0.065) (0.021) (0.022) (0.060) (0.081)
## BM.responsiblesourcing 0.185 *** 0.333 *** 0.023 ** 0.012 0.081 *** 0.094 ***
## (0.019) (0.023) (0.007) (0.008) (0.021) (0.029)
## ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Marginal R^2 0.693 0.870 0.190 0.070 0.266 0.247
## Conditional R^2 1.000 1.000 1.000 1.000 1.000 1.000
## AIC -20816.929 -17259.765 -22545.406 -14159.220 -20827.300 -17284.903
## BIC -20796.968 -17241.844 -22525.445 -14141.300 -20807.339 -17266.983
## Num. obs. 1086 652 1086 652 1086 652
## Num. groups: clus 46 31 46 31 46 31
## Var: clus (Intercept) 0.033 0.035 0.005 0.004 0.040 0.057
## Var: Residual 0.000 0.000 0.000 0.000 0.000 0.000
## ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Note. * p < .05, ** p < .01, *** p < .001.3.2.2 BM19.responsiblesourcing
BA1920FOApractices.BM19.responsiblesourcing=lmer(BA1920FOApractices~BM19.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
BA20FOApractices.BM19.responsiblesourcing=lmer(BA20FOApractices~BM19.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
BA1920discriminate4prac.BM19.responsiblesourcing=lmer(BA1920discriminate4prac~BM19.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
BA20discriminate4prac.BM19.responsiblesourcing=lmer(BA20discriminate4prac~BM19.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
BA1920targetedpractices.BM19.responsiblesourcing=lmer(BA1920targetedpractices~BM19.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
BA20targetedpractices.BM19.responsiblesourcing=lmer(BA20targetedpractices~BM19.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
model_summary(list(BA1920FOApractices.BM19.responsiblesourcing, BA20FOApractices.BM19.responsiblesourcing, BA1920discriminate4prac.BM19.responsiblesourcing, BA20discriminate4prac.BM19.responsiblesourcing, BA1920targetedpractices.BM19.responsiblesourcing, BA20targetedpractices.BM19.responsiblesourcing))##
## Model Summary
##
## ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## (1) BA1920FOApractices (2) BA20FOApractices (3) BA1920discriminate4prac (4) BA20discriminate4prac (5) BA1920targetedpractices (6) BA20targetedpractices
## ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## (Intercept) 19.154 *** 19.199 *** 3.636 *** 3.608 *** 8.506 *** 8.335 ***
## (0.060) (0.068) (0.023) (0.026) (0.068) (0.083)
## BM19.responsiblesourcing 0.155 *** 0.232 *** 0.089 *** 0.103 *** 0.277 *** 0.292 ***
## (0.018) (0.021) (0.007) (0.008) (0.021) (0.026)
## ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Marginal R^2 0.674 0.821 0.838 0.893 0.837 0.834
## Conditional R^2 1.000 1.000 1.000 1.000 1.000 1.000
## AIC -13646.961 -14321.831 -21765.239 -15856.399 -19141.811 -9889.651
## BIC -13628.611 -14304.725 -21746.889 -15839.292 -19123.461 -9872.544
## Num. obs. 726 532 726 532 726 532
## Num. groups: clus 33 24 33 24 33 24
## Var: clus (Intercept) 0.035 0.034 0.005 0.004 0.046 0.050
## Var: Residual 0.000 0.000 0.000 0.000 0.000 0.000
## ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Note. * p < .05, ** p < .01, *** p < .001.3.2.3 BM20.responsiblesourcing
BA1920FOApractices.BM20.responsiblesourcing=lmer(BA1920FOApractices~BM20.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
BA20FOApractices.BM20.responsiblesourcing=lmer(BA20FOApractices~BM20.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
BA1920discriminate4prac.BM20.responsiblesourcing=lmer(BA1920discriminate4prac~BM20.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
BA20discriminate4prac.BM20.responsiblesourcing=lmer(BA20discriminate4prac~BM20.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
BA1920targetedpractices.BM20.responsiblesourcing=lmer(BA1920targetedpractices~BM20.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
BA20targetedpractices.BM20.responsiblesourcing=lmer(BA20targetedpractices~BM20.responsiblesourcing+ (1|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
model_summary(list(BA1920FOApractices.BM20.responsiblesourcing, BA20FOApractices.BM20.responsiblesourcing, BA1920discriminate4prac.BM20.responsiblesourcing, BA20discriminate4prac.BM20.responsiblesourcing, BA1920targetedpractices.BM20.responsiblesourcing, BA20targetedpractices.BM20.responsiblesourcing))##
## Model Summary
##
## ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## (1) BA1920FOApractices (2) BA20FOApractices (3) BA1920discriminate4prac (4) BA20discriminate4prac (5) BA1920targetedpractices (6) BA20targetedpractices
## ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## (Intercept) 19.465 *** 19.410 *** 3.934 *** 3.994 *** 9.499 *** 9.273 ***
## (0.051) (0.070) (0.018) (0.021) (0.055) (0.082)
## BM20.responsiblesourcing 0.032 0.135 *** -0.035 *** -0.055 *** -0.092 *** -0.127 ***
## (0.017) (0.023) (0.006) (0.007) (0.018) (0.027)
## ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Marginal R^2 0.078 0.500 0.426 0.625 0.373 0.403
## Conditional R^2 1.000 1.000 1.000 1.000 1.000 1.000
## AIC -21942.217 -12184.716 -24583.388 -13828.546 -15297.566 -12491.709
## BIC -21923.365 -12168.114 -24564.537 -13811.943 -15278.714 -12475.107
## Num. obs. 823 469 823 469 823 469
## Num. groups: clus 35 23 35 23 35 23
## Var: clus (Intercept) 0.037 0.049 0.005 0.005 0.044 0.065
## Var: Residual 0.000 0.000 0.000 0.000 0.000 0.000
## ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Note. * p < .05, ** p < .01, *** p < .001.3.3 III check for cw1: Cross-level interaction of W
3.3.1 BM.responsiblesourcing
mentalhealth.BM.responsiblesourcing=lmer(mentalhealth~BM.responsiblesourcing*migrant10+migrant10_mean*BM.responsiblesourcing+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
stress.BM.responsiblesourcing=lmer(stress~BM.responsiblesourcing*migrant10+migrant10_mean*BM.responsiblesourcing+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
wage.BM.responsiblesourcing=lmer(wage~BM.responsiblesourcing*migrant10+migrant10_mean*BM.responsiblesourcing+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
model_summary(list(mentalhealth.BM.responsiblesourcing, stress.BM.responsiblesourcing, wage.BM.responsiblesourcing))##
## Model Summary
##
## ────────────────────────────────────────────────────────────────────────────────────
## (1) mentalhealth (2) stress (3) wage
## ────────────────────────────────────────────────────────────────────────────────────
## (Intercept) 3.203 *** 3.323 *** 224.175 ***
## (0.204) (0.308) (14.910)
## BM.responsiblesourcing 0.059 -0.075 3.514
## (0.089) (0.127) (6.743)
## migrant10 0.471 0.303 -0.493
## (0.318) (0.326) (13.732)
## migrant10_mean -0.171 -0.707 -23.138
## (0.370) (0.465) (25.382)
## BM.responsiblesourcing:migrant10 -0.189 0.180 -3.903
## (0.104) (0.108) (4.562)
## BM.responsiblesourcing:migrant10_mean 0.002 -0.002 2.060
## (0.141) (0.174) (10.086)
## ────────────────────────────────────────────────────────────────────────────────────
## Marginal R^2 0.026 0.047 0.021
## Conditional R^2 0.224 0.092 0.381
## AIC 2679.246 4040.290 11802.693
## BIC 2727.468 4090.501 11852.796
## Num. obs. 918 1120 1108
## Num. groups: clus 49 49 49
## Var: clus (Intercept) 0.036 0.280 473.151
## Var: clus migrant10 0.547 0.420 1096.093
## Cov: clus (Intercept) migrant10 -0.112 -0.338 37.356
## Var: Residual 0.964 2.035 2233.244
## ────────────────────────────────────────────────────────────────────────────────────
## Note. * p < .05, ** p < .01, *** p < .001.
3.3.2 BM19.responsiblesourcing
mentalhealth.BM19.responsiblesourcing=lmer(mentalhealth~BM19.responsiblesourcing*migrant10+migrant10_mean*BM19.responsiblesourcing+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
stress.BM19.responsiblesourcing=lmer(stress~BM19.responsiblesourcing*migrant10+migrant10_mean*BM19.responsiblesourcing+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
wage.BM19.responsiblesourcing=lmer(wage~BM19.responsiblesourcing*migrant10+migrant10_mean*BM19.responsiblesourcing+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
model_summary(list(mentalhealth.BM19.responsiblesourcing, stress.BM19.responsiblesourcing, wage.BM19.responsiblesourcing))##
## Model Summary
##
## ─────────────────────────────────────────────────────────────────────────────────────
## (1) mentalhealth (2) stress (3) wage
## ─────────────────────────────────────────────────────────────────────────────────────
## (Intercept) 3.167 *** 3.852 *** 230.417 ***
## (0.250) (0.360) (19.074)
## BM19.responsiblesourcing 0.027 -0.249 * -1.593
## (0.078) (0.114) (5.653)
## migrant10 0.124 0.251 3.874
## (0.335) (0.316) (12.649)
## migrant10_mean 0.098 -1.036 -24.964
## (0.411) (0.536) (30.287)
## BM19.responsiblesourcing:migrant10 -0.084 0.162 -4.218
## (0.105) (0.098) (3.968)
## BM19.responsiblesourcing:migrant10_mean -0.006 0.179 6.848
## (0.125) (0.172) (8.788)
## ─────────────────────────────────────────────────────────────────────────────────────
## Marginal R^2 0.008 0.052 0.010
## Conditional R^2 0.240 0.089 0.365
## AIC 1848.897 2728.782 7889.363
## BIC 1893.480 2775.035 7935.537
## Num. obs. 638 754 748
## Num. groups: clus 35 35 35
## Var: clus (Intercept) 0.038 0.132 270.071
## Var: clus migrant10 0.737 0.357 964.767
## Cov: clus (Intercept) migrant10 -0.167 -0.217 178.383
## Var: Residual 0.925 2.042 2027.924
## ─────────────────────────────────────────────────────────────────────────────────────
## Note. * p < .05, ** p < .01, *** p < .001.interact_plot(mentalhealth.BM19.responsiblesourcing, modx = BM19.responsiblesourcing, pred = migrant10)
3.3.3 BM20.responsiblesourcing
mentalhealth.BM20.responsiblesourcing=lmer(mentalhealth~BM20.responsiblesourcing*migrant10+migrant10_mean*BM20.responsiblesourcing+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
stress.BM20.responsiblesourcing=lmer(stress~BM20.responsiblesourcing*migrant10+migrant10_mean*BM20.responsiblesourcing+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
wage.BM20.responsiblesourcing=lmer(wage~BM20.responsiblesourcing*migrant10+migrant10_mean*BM20.responsiblesourcing+ (migrant10|clus), na.action = na.exclude, data = data, control=lmerControl(optimizer="bobyqa"))
model_summary(list(mentalhealth.BM20.responsiblesourcing, stress.BM20.responsiblesourcing, wage.BM20.responsiblesourcing))##
## Model Summary
##
## ─────────────────────────────────────────────────────────────────────────────────────
## (1) mentalhealth (2) stress (3) wage
## ─────────────────────────────────────────────────────────────────────────────────────
## (Intercept) 3.303 *** 3.022 *** 217.620 ***
## (0.182) (0.248) (12.932)
## BM20.responsiblesourcing 0.053 -0.029 9.386
## (0.089) (0.109) (6.932)
## migrant10 0.200 0.730 * -18.140
## (0.325) (0.295) (14.873)
## migrant10_mean -0.184 -0.774 4.946
## (0.361) (0.423) (23.563)
## BM20.responsiblesourcing:migrant10 -0.097 0.106 0.863
## (0.098) (0.094) (4.601)
## BM20.responsiblesourcing:migrant10_mean -0.036 -0.006 -12.944
## (0.145) (0.155) (10.611)
## ─────────────────────────────────────────────────────────────────────────────────────
## Marginal R^2 0.016 0.065 0.040
## Conditional R^2 0.238 0.099 0.426
## AIC 2003.898 3013.138 8811.311
## BIC 2049.118 3060.424 8858.501
## Num. obs. 680 836 828
## Num. groups: clus 37 37 37
## Var: clus (Intercept) 0.069 0.195 559.372
## Var: clus migrant10 0.654 0.255 1615.160
## Cov: clus (Intercept) migrant10 -0.158 -0.214 -137.613
## Var: Residual 0.974 2.019 2204.179
## ─────────────────────────────────────────────────────────────────────────────────────
## Note. * p < .05, ** p < .01, *** p < .001.interact_plot(mentalhealth.BM20.responsiblesourcing, modx = BM20.responsiblesourcing, pred = migrant10)
