Employee Survey
Lawrence Houston III
2025-05-01
# Load required package
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(apaTables)
library(interactions)## Warning: package 'interactions' was built under R version 4.3.3library(haven)
library(lme4)## Loading required package: Matrixlibrary(lmerTest)##
## Attaching package: 'lmerTest'## The following object is masked from 'package:lme4':
##
## lmer## The following object is masked from 'package:stats':
##
## steplibrary(modelsummary)## Warning: package 'modelsummary' was built under R version 4.3.3## `modelsummary` 2.0.0 now uses `tinytable` as its default table-drawing
## backend. Learn more at: https://vincentarelbundock.github.io/tinytable/
##
## Revert to `kableExtra` for one session:
##
## options(modelsummary_factory_default = 'kableExtra')
## options(modelsummary_factory_latex = 'kableExtra')
## options(modelsummary_factory_html = 'kableExtra')
##
## Silence this message forever:
##
## config_modelsummary(startup_message = FALSE)# Set working directory
setwd("/Users/lawrencehouston/Library/CloudStorage/Box-Box/NOD data/Employee survey")
# Load data
df <- read_sav("Employee Engagement Survey Data.sav")Create New Variables for Disability Status
# Create MentalHealth_status (Yes-No) and MentalHealth_severity (i.e., Mental Health Status Continuous Variable) (0-2)
# Create PhysicalHealth_status (Yes-No) and PhysicalHealth_severity (i.e., Physical Health Status Continuous Variable) (0-2)
df <- df %>%
mutate(
MentalHealth_status_binary = case_when(
MentalHealthCondition == "No" ~ 0,
MentalHealthCondition == "Yes - one condition" ~ 1,
MentalHealthCondition == "Yes - more than one condition" ~ 1,
MentalHealthCondition == "I prefer not to answer" ~ NA_real_
),
MentalHealth_status_cont = case_when(
MentalHealthCondition == "No" ~ 0,
MentalHealthCondition == "Yes - one condition" ~ 1,
MentalHealthCondition == "Yes - more than one condition" ~ 2,
MentalHealthCondition == "I prefer not to answer" ~ NA_real_
),
PhysicalHealth_status_binary = case_when(
PhysicalHealthCondition == "No" ~ 0,
PhysicalHealthCondition == "Yes - one condition" ~ 1,
PhysicalHealthCondition == "Yes - more than one condition" ~ 1,
PhysicalHealthCondition == "I prefer not to answer" ~ NA_real_
),
PhysicalHealth_status_cont = case_when(
PhysicalHealthCondition == "No" ~ 0,
PhysicalHealthCondition == "Yes - one condition" ~ 1,
PhysicalHealthCondition == "Yes - more than one condition" ~ 2,
PhysicalHealthCondition == "I prefer not to answer" ~ NA_real_
)
)
df <- df %>%
mutate(
Disability_severity = case_when(
MentalHealth_status_cont == 2 & PhysicalHealth_status_cont == 2 ~ 4,
MentalHealth_status_cont == 2 & PhysicalHealth_status_cont == 1 ~ 3,
MentalHealth_status_cont == 1 & PhysicalHealth_status_cont == 2 ~ 3,
MentalHealth_status_binary == 1 & PhysicalHealth_status_binary == 1 ~ 2,
MentalHealth_status_binary == 1 & PhysicalHealth_status_binary == 0 ~ 1,
MentalHealth_status_binary == 0 & PhysicalHealth_status_binary == 1 ~ 1,
MentalHealth_status_binary == 0 & PhysicalHealth_status_binary == 0 ~ 0,
TRUE ~ NA_real_
)
)
# Convert variables to factors
df <- df %>%
mutate(
MentalHealth_status_binary = factor(MentalHealth_status_binary, levels = c(0, 1)),
PhysicalHealth_status_binary = factor(PhysicalHealth_status_binary, levels = c(0, 1)),
Leadership_Status = factor(Leadership_Status, levels = c(0, 1)),
DisabilityStatus = factor(DisabilityStatus, levels = c(0, 1))
)Correlations
# Define the list of variables to include in Correlation Matrix
vars_to_include <- c("DisabilityStatus", "Disability_severity",
"MentalHealth_status_binary", "MentalHealth_status_cont",
"PhysicalHealth_status_binary", "PhysicalHealth_status_cont",
"Engagement", "TO_Intent", "Accessibility", "Accommodation",
"PsychSafety", "PeoplePractices", "OrgCommitment",
"ManagerEffectiveness", "LeadershipCommitment", "CareerExperience"
)
# Create dataframe to include only key variables
df_subset <- df[ , vars_to_include]
# Create the APA-style correlation matrix
apa.cor.table(df_subset)##
##
## Means, standard deviations, and correlations with confidence intervals
##
##
## Variable M SD 1 2
## 1. Disability_severity 0.52 0.97
##
## 2. MentalHealth_status_cont 0.27 0.60 .82**
## [.81, .82]
##
## 3. PhysicalHealth_status_cont 0.32 0.64 .82** .42**
## [.81, .83] [.40, .44]
##
## 4. Engagement 4.16 0.73 -.13** -.13**
## [-.16, -.11] [-.15, -.10]
##
## 5. TO_Intent 3.19 0.52 -.09** -.09**
## [-.11, -.06] [-.12, -.07]
##
## 6. Accessibility 3.95 0.72 -.16** -.11**
## [-.19, -.14] [-.14, -.09]
##
## 7. Accommodation 3.13 0.93 -.19** -.16**
## [-.22, -.17] [-.18, -.13]
##
## 8. PsychSafety 3.84 0.88 -.22** -.18**
## [-.24, -.19] [-.21, -.16]
##
## 9. PeoplePractices 3.62 0.81 -.21** -.18**
## [-.24, -.19] [-.20, -.15]
##
## 10. OrgCommitment 3.54 0.78 -.20** -.17**
## [-.23, -.18] [-.19, -.14]
##
## 11. ManagerEffectiveness 4.10 0.86 -.18** -.15**
## [-.21, -.16] [-.17, -.12]
##
## 12. LeadershipCommitment 3.38 0.81 -.24** -.21**
## [-.26, -.21] [-.23, -.18]
##
## 13. CareerExperience 3.88 0.85 -.17** -.13**
## [-.20, -.15] [-.16, -.10]
##
## 3 4 5 6 7 8
##
##
##
##
##
##
##
##
## -.09**
## [-.12, -.07]
##
## -.06** .33**
## [-.08, -.03] [.30, .35]
##
## -.16** .53** .19**
## [-.18, -.13] [.51, .55] [.17, .22]
##
## -.17** .40** .11** .56**
## [-.19, -.14] [.38, .42] [.09, .14] [.54, .58]
##
## -.19** .61** .28** .65** .58**
## [-.22, -.17] [.59, .62] [.26, .30] [.64, .67] [.57, .60]
##
## -.19** .54** .25** .64** .62** .71**
## [-.21, -.16] [.52, .55] [.22, .27] [.62, .65] [.60, .63] [.69, .72]
##
## -.19** .49** .17** .60** .68** .68**
## [-.21, -.16] [.47, .51] [.15, .20] [.58, .62] [.66, .69] [.67, .69]
##
## -.16** .56** .29** .55** .46** .74**
## [-.18, -.13] [.54, .57] [.26, .31] [.53, .56] [.44, .48] [.72, .75]
##
## -.20** .48** .21** .58** .63** .66**
## [-.23, -.18] [.46, .50] [.19, .24] [.56, .59] [.61, .64] [.65, .68]
##
## -.15** .65** .36** .54** .48** .65**
## [-.18, -.13] [.63, .66] [.34, .38] [.52, .56] [.46, .50] [.64, .67]
##
## 9 10 11 12
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
##
## .68**
## [.67, .70]
##
## .61** .58**
## [.59, .62] [.56, .59]
##
## .65** .77** .58**
## [.64, .67] [.76, .78] [.56, .60]
##
## .60** .57** .60** .59**
## [.58, .61] [.55, .58] [.59, .62] [.57, .61]
##
##
## Note. M and SD are used to represent mean and standard deviation, respectively.
## Values in square brackets indicate the 95% confidence interval.
## The confidence interval is a plausible range of population correlations
## that could have caused the sample correlation (Cumming, 2014).
## * indicates p < .05. ** indicates p < .01.
## Disability Status (yes-no) x Leadership Status –> All Outcomes
# Leadership Status modeled as moderator: Disability Status (yes-no) --> All Outcomes
model_LeadershipStatus <- lm(cbind(Engagement,Accessibility,Accommodation,PsychSafety,PeoplePractices,OrgCommitment,ManagerEffectiveness,LeadershipCommitment,CareerExperience) ~ DisabilityStatus * Leadership_Status, data = df)
summary(model_LeadershipStatus) # no significant interactions, except when predicting LeadershipCommitment## Response Engagement :
##
## Call:
## lm(formula = Engagement ~ DisabilityStatus * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.2306 -0.3693 -0.0360 0.6307 0.9640
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.35059 0.02216 196.334 <2e-16 ***
## DisabilityStatus1 -0.12004 0.06898 -1.740 0.0819 .
## Leadership_Status1 -0.21245 0.02498 -8.505 <2e-16 ***
## DisabilityStatus1:Leadership_Status1 0.01785 0.07483 0.239 0.8115
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7156 on 5733 degrees of freedom
## (293 observations deleted due to missingness)
## Multiple R-squared: 0.01716, Adjusted R-squared: 0.01664
## F-statistic: 33.36 on 3 and 5733 DF, p-value: < 2.2e-16
##
##
## Response Accessibility :
##
## Call:
## lm(formula = Accessibility ~ DisabilityStatus * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.96072 -0.46072 0.03928 0.53928 1.21300
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.104267 0.021787 188.385 < 2e-16 ***
## DisabilityStatus1 -0.177183 0.067825 -2.612 0.00902 **
## Leadership_Status1 -0.143542 0.024560 -5.844 5.36e-09 ***
## DisabilityStatus1:Leadership_Status1 0.003457 0.073577 0.047 0.96252
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7036 on 5733 degrees of freedom
## (293 observations deleted due to missingness)
## Multiple R-squared: 0.01505, Adjusted R-squared: 0.01454
## F-statistic: 29.21 on 3 and 5733 DF, p-value: < 2.2e-16
##
##
## Response Accommodation :
##
## Call:
## lm(formula = Accommodation ~ DisabilityStatus * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4041 -0.6178 -0.1178 0.5959 2.1328
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.40412 0.02841 119.837 < 2e-16 ***
## DisabilityStatus1 -0.33746 0.08843 -3.816 0.000137 ***
## Leadership_Status1 -0.28636 0.03202 -8.942 < 2e-16 ***
## DisabilityStatus1:Leadership_Status1 0.08691 0.09593 0.906 0.364975
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9174 on 5733 degrees of freedom
## (293 observations deleted due to missingness)
## Multiple R-squared: 0.02605, Adjusted R-squared: 0.02554
## F-statistic: 51.12 on 3 and 5733 DF, p-value: < 2.2e-16
##
##
## Response PsychSafety :
##
## Call:
## lm(formula = PsychSafety ~ DisabilityStatus * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1032 -0.5096 0.1571 0.5634 1.4242
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.10323 0.02660 154.242 < 2e-16 ***
## DisabilityStatus1 -0.37823 0.08282 -4.567 5.05e-06 ***
## Leadership_Status1 -0.26033 0.02999 -8.681 < 2e-16 ***
## DisabilityStatus1:Leadership_Status1 0.11117 0.08984 1.237 0.216
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8591 on 5733 degrees of freedom
## (293 observations deleted due to missingness)
## Multiple R-squared: 0.02829, Adjusted R-squared: 0.02778
## F-statistic: 55.63 on 3 and 5733 DF, p-value: < 2.2e-16
##
##
## Response PeoplePractices :
##
## Call:
## lm(formula = PeoplePractices ~ DisabilityStatus * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.74167 -0.54167 0.00904 0.60904 1.61770
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.947651 0.024388 161.868 < 2e-16 ***
## DisabilityStatus1 -0.205984 0.075924 -2.713 0.00669 **
## Leadership_Status1 -0.356688 0.027493 -12.974 < 2e-16 ***
## DisabilityStatus1:Leadership_Status1 -0.002683 0.082362 -0.033 0.97401
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7876 on 5733 degrees of freedom
## (293 observations deleted due to missingness)
## Multiple R-squared: 0.04226, Adjusted R-squared: 0.04176
## F-statistic: 84.32 on 3 and 5733 DF, p-value: < 2.2e-16
##
##
## Response OrgCommitment :
##
## Call:
## lm(formula = OrgCommitment ~ DisabilityStatus * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.78308 -0.54213 -0.04213 0.45787 1.69433
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.78308 0.02385 158.607 < 2e-16 ***
## DisabilityStatus1 -0.30808 0.07425 -4.149 3.39e-05 ***
## Leadership_Status1 -0.24095 0.02689 -8.961 < 2e-16 ***
## DisabilityStatus1:Leadership_Status1 0.07162 0.08055 0.889 0.374
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7703 on 5733 degrees of freedom
## (293 observations deleted due to missingness)
## Multiple R-squared: 0.02872, Adjusted R-squared: 0.02822
## F-statistic: 56.52 on 3 and 5733 DF, p-value: < 2.2e-16
##
##
## Response ManagerEffectiveness :
##
## Call:
## lm(formula = ManagerEffectiveness ~ DisabilityStatus * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.3320 -0.3410 0.0958 0.6680 1.0958
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.33198 0.02620 165.341 < 2e-16 ***
## DisabilityStatus1 -0.29239 0.08157 -3.585 0.00034 ***
## Leadership_Status1 -0.24096 0.02954 -8.158 4.14e-16 ***
## DisabilityStatus1:Leadership_Status1 0.10559 0.08848 1.193 0.23276
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8461 on 5733 degrees of freedom
## (293 observations deleted due to missingness)
## Multiple R-squared: 0.02005, Adjusted R-squared: 0.01954
## F-statistic: 39.1 on 3 and 5733 DF, p-value: < 2.2e-16
##
##
## Response LeadershipCommitment :
##
## Call:
## lm(formula = LeadershipCommitment ~ DisabilityStatus * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.6352 -0.3910 -0.1352 0.5833 1.8804
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.63519 0.02438 149.078 < 2e-16 ***
## DisabilityStatus1 -0.46852 0.07591 -6.172 7.21e-10 ***
## Leadership_Status1 -0.24418 0.02749 -8.883 < 2e-16 ***
## DisabilityStatus1:Leadership_Status1 0.19716 0.08235 2.394 0.0167 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7875 on 5733 degrees of freedom
## (293 observations deleted due to missingness)
## Multiple R-squared: 0.03299, Adjusted R-squared: 0.03248
## F-statistic: 65.19 on 3 and 5733 DF, p-value: < 2.2e-16
##
##
## Response CareerExperience :
##
## Call:
## lm(formula = CareerExperience ~ DisabilityStatus * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1166 -0.5304 0.1362 0.5500 1.3241
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.11665 0.02576 159.808 < 2e-16 ***
## DisabilityStatus1 -0.21943 0.08019 -2.736 0.00623 **
## Leadership_Status1 -0.25289 0.02904 -8.709 < 2e-16 ***
## DisabilityStatus1:Leadership_Status1 0.03156 0.08700 0.363 0.71680
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8319 on 5733 degrees of freedom
## (293 observations deleted due to missingness)
## Multiple R-squared: 0.02202, Adjusted R-squared: 0.0215
## F-statistic: 43.02 on 3 and 5733 DF, p-value: < 2.2e-16# Plot significant interaction showing that leaders (vs individual contributors) with disability viewed leadership more negatively
model_lead <- lm(LeadershipCommitment ~ DisabilityStatus * Leadership_Status, data = df)
interact_plot(model_lead, pred = DisabilityStatus, modx = Leadership_Status,
main.title = "Interaction: Disability Status × Leadership Status on Leadership Commitment")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
Disability Severity (range: 0 to 4) x Leadership Status –> All Outcomes
# Leadership Status modeled as moderator: Disability Severity (range: 0 to 4) --> All Outcomes
model_LeadershipStatus <- lm(cbind(Engagement,Accessibility,Accommodation,PsychSafety,PeoplePractices,OrgCommitment,ManagerEffectiveness,LeadershipCommitment,CareerExperience) ~ Disability_severity * Leadership_Status, data = df)
summary(model_LeadershipStatus) # no significant interactions, except when predicting OrgCommitment and LeadershipCommitment## Response Engagement :
##
## Call:
## lm(formula = Engagement ~ Disability_severity * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1724 -0.3771 -0.0438 0.6229 1.1861
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.37713 0.02309 189.543 < 2e-16 ***
## Disability_severity -0.10123 0.02556 -3.961 7.56e-05 ***
## Leadership_Status1 -0.20477 0.02606 -7.856 4.70e-15 ***
## Disability_severity:Leadership_Status1 0.01160 0.02764 0.420 0.675
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7112 on 5653 degrees of freedom
## (373 observations deleted due to missingness)
## Multiple R-squared: 0.02964, Adjusted R-squared: 0.02912
## F-statistic: 57.55 on 3 and 5653 DF, p-value: < 2.2e-16
##
##
## Response Accessibility :
##
## Call:
## lm(formula = Accessibility ~ Disability_severity * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.02428 -0.38947 0.00225 0.50225 1.47995
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.11914 0.02272 181.306 < 2e-16 ***
## Disability_severity -0.09486 0.02514 -3.773 0.000163 ***
## Leadership_Status1 -0.12139 0.02564 -4.734 2.26e-06 ***
## Disability_severity:Leadership_Status1 -0.02456 0.02719 -0.903 0.366435
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6997 on 5653 degrees of freedom
## (373 observations deleted due to missingness)
## Multiple R-squared: 0.03253, Adjusted R-squared: 0.03202
## F-statistic: 63.37 on 3 and 5653 DF, p-value: < 2.2e-16
##
##
## Response Accommodation :
##
## Call:
## lm(formula = Accommodation ~ Disability_severity * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4461 -0.6719 -0.1583 0.5539 2.5129
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.44614 0.02950 116.803 < 2e-16 ***
## Disability_severity -0.20934 0.03265 -6.412 1.56e-10 ***
## Leadership_Status1 -0.27424 0.03330 -8.235 < 2e-16 ***
## Disability_severity:Leadership_Status1 0.03815 0.03531 1.080 0.28
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9086 on 5653 degrees of freedom
## (373 observations deleted due to missingness)
## Multiple R-squared: 0.04978, Adjusted R-squared: 0.04927
## F-statistic: 98.71 on 3 and 5653 DF, p-value: < 2.2e-16
##
##
## Response PsychSafety :
##
## Call:
## lm(formula = PsychSafety ~ Disability_severity * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.14742 -0.48075 0.09577 0.61091 1.82297
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.14742 0.02750 150.818 < 2e-16 ***
## Disability_severity -0.22804 0.03043 -7.493 7.76e-14 ***
## Leadership_Status1 -0.24319 0.03104 -7.835 5.55e-15 ***
## Disability_severity:Leadership_Status1 0.04624 0.03291 1.405 0.16
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8469 on 5653 degrees of freedom
## (373 observations deleted due to missingness)
## Multiple R-squared: 0.05846, Adjusted R-squared: 0.05796
## F-statistic: 117 on 3 and 5653 DF, p-value: < 2.2e-16
##
##
## Response PeoplePractices :
##
## Call:
## lm(formula = PeoplePractices ~ Disability_severity * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.65053 -0.45053 0.01473 0.54947 2.01893
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.98527 0.02519 158.225 < 2e-16 ***
## Disability_severity -0.15463 0.02787 -5.547 3.03e-08 ***
## Leadership_Status1 -0.33474 0.02843 -11.775 < 2e-16 ***
## Disability_severity:Leadership_Status1 -0.01274 0.03015 -0.423 0.673
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7757 on 5653 degrees of freedom
## (373 observations deleted due to missingness)
## Multiple R-squared: 0.07376, Adjusted R-squared: 0.07327
## F-statistic: 150.1 on 3 and 5653 DF, p-value: < 2.2e-16
##
##
## Response OrgCommitment :
##
## Call:
## lm(formula = OrgCommitment ~ Disability_severity * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.82884 -0.57884 -0.07884 0.41084 2.00948
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.82884 0.02465 155.322 < 2e-16 ***
## Disability_severity -0.20958 0.02728 -7.682 1.83e-14 ***
## Leadership_Status1 -0.23968 0.02782 -8.614 < 2e-16 ***
## Disability_severity:Leadership_Status1 0.06155 0.02951 2.086 0.037 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7592 on 5653 degrees of freedom
## (373 observations deleted due to missingness)
## Multiple R-squared: 0.05448, Adjusted R-squared: 0.05398
## F-statistic: 108.6 on 3 and 5653 DF, p-value: < 2.2e-16
##
##
## Response ManagerEffectiveness :
##
## Call:
## lm(formula = ManagerEffectiveness ~ Disability_severity * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.3723 -0.3946 0.1054 0.6277 1.4435
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.37234 0.02709 161.408 < 2e-16 ***
## Disability_severity -0.18953 0.02998 -6.322 2.77e-10 ***
## Leadership_Status1 -0.22778 0.03057 -7.450 1.07e-13 ***
## Disability_severity:Leadership_Status1 0.04252 0.03242 1.311 0.19
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8343 on 5653 degrees of freedom
## (373 observations deleted due to missingness)
## Multiple R-squared: 0.04329, Adjusted R-squared: 0.04278
## F-statistic: 85.26 on 3 and 5653 DF, p-value: < 2.2e-16
##
##
## Response LeadershipCommitment :
##
## Call:
## lm(formula = LeadershipCommitment ~ Disability_severity * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.67727 -0.44751 -0.01962 0.55249 2.26405
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.67727 0.02519 145.964 < 2e-16 ***
## Disability_severity -0.26290 0.02788 -9.430 < 2e-16 ***
## Leadership_Status1 -0.22976 0.02843 -8.080 7.84e-16 ***
## Disability_severity:Leadership_Status1 0.08501 0.03015 2.819 0.00483 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7759 on 5653 degrees of freedom
## (373 observations deleted due to missingness)
## Multiple R-squared: 0.06736, Adjusted R-squared: 0.06686
## F-statistic: 136.1 on 3 and 5653 DF, p-value: < 2.2e-16
##
##
## Response CareerExperience :
##
## Call:
## lm(formula = CareerExperience ~ Disability_severity * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.15370 -0.48704 0.08837 0.56175 1.64858
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.15370 0.02681 154.955 < 2e-16 ***
## Disability_severity -0.14504 0.02967 -4.889 1.04e-06 ***
## Leadership_Status1 -0.24207 0.03026 -8.001 1.49e-15 ***
## Disability_severity:Leadership_Status1 0.00499 0.03208 0.156 0.876
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8256 on 5653 degrees of freedom
## (373 observations deleted due to missingness)
## Multiple R-squared: 0.04224, Adjusted R-squared: 0.04173
## F-statistic: 83.11 on 3 and 5653 DF, p-value: < 2.2e-16# Plot significant interactions showing that leaders (vs individual contributors) with disabilities viewed the org and leadership more negatively
# Plot 1: OrgCommitment
model_org <- lm(OrgCommitment ~ Disability_severity * Leadership_Status, data = df)
interact_plot(model_org, pred = Disability_severity, modx = Leadership_Status,
main.title = "Interaction: Disability Level × Leadership Status on Org Commitment")
# Plot 2: LeadershipCommitment
model_lead <- lm(LeadershipCommitment ~ Disability_severity * Leadership_Status, data = df)
interact_plot(model_lead, pred = Disability_severity, modx = Leadership_Status,
main.title = "Interaction: Disability Level × Leadership Status on Leadership Commitment")
Mental Disability Status (yes-no) x Leadership Status –> All Outcomes
# Leadership Status modeled as moderator: Mental Disability Status (yes-no) --> All Outcomes
model_LeadershipStatus <- lm(cbind(Engagement,Accessibility,Accommodation,PsychSafety,PeoplePractices,OrgCommitment,ManagerEffectiveness,LeadershipCommitment,CareerExperience) ~ MentalHealth_status_binary * Leadership_Status, data = df)
summary(model_LeadershipStatus) # no significant interactions, except when predicting OrgCommitment, ManagerEffectiveness, and LeadershipCommitment## Response Engagement :
##
## Call:
## lm(formula = Engagement ~ MentalHealth_status_binary * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1648 -0.3743 -0.0409 0.6257 1.0339
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.37428 0.02271 192.657
## MentalHealth_status_binary1 -0.20949 0.05804 -3.610
## Leadership_Status1 -0.21337 0.02559 -8.339
## MentalHealth_status_binary1:Leadership_Status1 0.01463 0.06365 0.230
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_binary1 0.000309 ***
## Leadership_Status1 < 2e-16 ***
## MentalHealth_status_binary1:Leadership_Status1 0.818187
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7126 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.02674, Adjusted R-squared: 0.02624
## F-statistic: 52.6 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response Accessibility :
##
## Call:
## lm(formula = Accessibility ~ MentalHealth_status_binary * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.11193 -0.46664 0.03336 0.53336 1.21463
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.1119289 0.0224906 182.829
## MentalHealth_status_binary1 -0.1807492 0.0574886 -3.144
## Leadership_Status1 -0.1452851 0.0253443 -5.732
## MentalHealth_status_binary1:Leadership_Status1 -0.0005249 0.0630513 -0.008
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_binary1 0.00167 **
## Leadership_Status1 1.04e-08 ***
## MentalHealth_status_binary1:Leadership_Status1 0.99336
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7059 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.01768, Adjusted R-squared: 0.01717
## F-statistic: 34.45 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response Accommodation :
##
## Call:
## lm(formula = Accommodation ~ MentalHealth_status_binary * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4345 -0.6440 -0.1440 0.5655 2.1843
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 3.43452 0.02913 117.896
## MentalHealth_status_binary1 -0.44575 0.07446 -5.986
## Leadership_Status1 -0.29055 0.03283 -8.851
## MentalHealth_status_binary1:Leadership_Status1 0.11743 0.08167 1.438
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_binary1 2.28e-09 ***
## Leadership_Status1 < 2e-16 ***
## MentalHealth_status_binary1:Leadership_Status1 0.151
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9143 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.03762, Adjusted R-squared: 0.03711
## F-statistic: 74.81 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response PsychSafety :
##
## Call:
## lm(formula = PsychSafety ~ MentalHealth_status_binary * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1320 -0.5138 0.1277 0.5347 1.4863
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.13198 0.02725 151.659
## MentalHealth_status_binary1 -0.45033 0.06964 -6.466
## Leadership_Status1 -0.25965 0.03070 -8.457
## MentalHealth_status_binary1:Leadership_Status1 0.09176 0.07638 1.201
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_binary1 1.09e-10 ***
## Leadership_Status1 < 2e-16 ***
## MentalHealth_status_binary1:Leadership_Status1 0.23
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8551 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.04343, Adjusted R-squared: 0.04293
## F-statistic: 86.91 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response PeoplePractices :
##
## Call:
## lm(formula = PeoplePractices ~ MentalHealth_status_binary * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.65506 -0.41978 0.02558 0.58022 1.69753
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 3.974416 0.024908 159.562
## MentalHealth_status_binary1 -0.319360 0.063668 -5.016
## Leadership_Status1 -0.354635 0.028069 -12.635
## MentalHealth_status_binary1:Leadership_Status1 0.002044 0.069829 0.029
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_binary1 5.43e-07 ***
## Leadership_Status1 < 2e-16 ***
## MentalHealth_status_binary1:Leadership_Status1 0.977
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7817 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.05835, Adjusted R-squared: 0.05785
## F-statistic: 118.6 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response OrgCommitment :
##
## Call:
## lm(formula = OrgCommitment ~ MentalHealth_status_binary * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.8107 -0.5611 -0.0611 0.4389 1.7154
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 3.81066 0.02442 156.028
## MentalHealth_status_binary1 -0.40195 0.06243 -6.439
## Leadership_Status1 -0.24956 0.02752 -9.068
## MentalHealth_status_binary1:Leadership_Status1 0.12542 0.06847 1.832
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_binary1 1.3e-10 ***
## Leadership_Status1 < 2e-16 ***
## MentalHealth_status_binary1:Leadership_Status1 0.067 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7665 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.0389, Adjusted R-squared: 0.0384
## F-statistic: 77.48 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response ManagerEffectiveness :
##
## Call:
## lm(formula = ManagerEffectiveness ~ MentalHealth_status_binary *
## Leadership_Status, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.3622 -0.3668 0.1332 0.6378 1.1584
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.36218 0.02678 162.875
## MentalHealth_status_binary1 -0.40291 0.06846 -5.885
## Leadership_Status1 -0.24533 0.03018 -8.129
## MentalHealth_status_binary1:Leadership_Status1 0.12770 0.07508 1.701
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_binary1 4.19e-09 ***
## Leadership_Status1 5.26e-16 ***
## MentalHealth_status_binary1:Leadership_Status1 0.089 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8406 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.03198, Adjusted R-squared: 0.03148
## F-statistic: 63.24 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response LeadershipCommitment :
##
## Call:
## lm(formula = LeadershipCommitment ~ MentalHealth_status_binary *
## Leadership_Status, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.66117 -0.41781 -0.07422 0.58219 1.92578
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 3.66117 0.02494 146.777
## MentalHealth_status_binary1 -0.53898 0.06376 -8.453
## Leadership_Status1 -0.24336 0.02811 -8.658
## MentalHealth_status_binary1:Leadership_Status1 0.19539 0.06993 2.794
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_binary1 < 2e-16 ***
## Leadership_Status1 < 2e-16 ***
## MentalHealth_status_binary1:Leadership_Status1 0.00522 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7829 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.0489, Adjusted R-squared: 0.0484
## F-statistic: 98.41 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response CareerExperience :
##
## Call:
## lm(formula = CareerExperience ~ MentalHealth_status_binary *
## Leadership_Status, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1421 -0.5478 0.1189 0.5245 1.3612
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.14213 0.02649 156.345
## MentalHealth_status_binary1 -0.28071 0.06772 -4.145
## Leadership_Status1 -0.26104 0.02986 -8.743
## MentalHealth_status_binary1:Leadership_Status1 0.03841 0.07427 0.517
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_binary1 3.45e-05 ***
## Leadership_Status1 < 2e-16 ***
## MentalHealth_status_binary1:Leadership_Status1 0.605
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8315 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.02977, Adjusted R-squared: 0.02927
## F-statistic: 58.74 on 3 and 5742 DF, p-value: < 2.2e-16# Plot significant interactions showing that leaders (vs individual contributors) with mental disability viewed the org, management, and leadership more negatively
model_org <- lm(OrgCommitment ~ MentalHealth_status_binary * Leadership_Status, data = df)
model_mgr <- lm(ManagerEffectiveness ~ MentalHealth_status_binary * Leadership_Status, data = df)
model_lead <- lm(LeadershipCommitment ~ MentalHealth_status_binary * Leadership_Status, data = df)
# Plot 1: OrgCommitment
interact_plot(model_org, pred = MentalHealth_status_binary, modx = Leadership_Status,
main.title = "Interaction: Mental Health × Leadership Status on Org Commitment")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
# Plot 2: ManagerEffectiveness
interact_plot(model_mgr, pred = MentalHealth_status_binary, modx = Leadership_Status,
main.title = "Interaction: Mental Health × Leadership Status on Manager Effectiveness")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
# Plot 3: LeadershipCommitment
interact_plot(model_lead, pred = MentalHealth_status_binary, modx = Leadership_Status,
main.title = "Interaction: Mental Health × Leadership Status on Leadership Commitment")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
Mental Disability Status (range: 0 to 2) x Leadership Status –> All Outcomes
# Leadership Status modeled as moderator: Mental Disability Status (range: 0 to 2) --> All Outcomes
model_LeadershipStatus <- lm(cbind(Engagement,Accessibility,Accommodation,PsychSafety,PeoplePractices,OrgCommitment,ManagerEffectiveness,LeadershipCommitment,CareerExperience) ~ MentalHealth_status_cont * Leadership_Status, data = df)
summary(model_LeadershipStatus) # no significant interactions, except when predicting OrgCommitment, ManagerEffectiveness, LeadershipCommitment, and PsychSafety. Pattern same as above## Response Engagement :
##
## Call:
## lm(formula = Engagement ~ MentalHealth_status_cont * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.16202 -0.37601 -0.04267 0.62399 1.12045
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.37601 0.02245 194.908
## MentalHealth_status_cont -0.16039 0.03933 -4.078
## Leadership_Status1 -0.21399 0.02528 -8.465
## MentalHealth_status_cont:Leadership_Status1 0.01916 0.04291 0.446
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_cont 4.6e-05 ***
## Leadership_Status1 < 2e-16 ***
## MentalHealth_status_cont:Leadership_Status1 0.655
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7116 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.02939, Adjusted R-squared: 0.02888
## F-statistic: 57.96 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response Accessibility :
##
## Call:
## lm(formula = Accessibility ~ MentalHealth_status_cont * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.10865 -0.46845 0.03155 0.53155 1.29975
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.10865 0.02225 184.687
## MentalHealth_status_cont -0.11575 0.03897 -2.970
## Leadership_Status1 -0.14020 0.02505 -5.597
## MentalHealth_status_cont:Leadership_Status1 -0.01835 0.04252 -0.432
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_cont 0.00299 **
## Leadership_Status1 2.28e-08 ***
## MentalHealth_status_cont:Leadership_Status1 0.66604
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7051 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.01974, Adjusted R-squared: 0.01923
## F-statistic: 38.54 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response Accommodation :
##
## Call:
## lm(formula = Accommodation ~ MentalHealth_status_cont * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4353 -0.6411 -0.1411 0.5647 2.3018
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 3.43530 0.02882 119.209
## MentalHealth_status_cont -0.32757 0.05048 -6.489
## Leadership_Status1 -0.29425 0.03245 -9.068
## MentalHealth_status_cont:Leadership_Status1 0.10617 0.05507 1.928
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_cont 9.36e-11 ***
## Leadership_Status1 < 2e-16 ***
## MentalHealth_status_cont:Leadership_Status1 0.0539 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9134 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.03951, Adjusted R-squared: 0.03901
## F-statistic: 78.73 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response PsychSafety :
##
## Call:
## lm(formula = PsychSafety ~ MentalHealth_status_cont * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1341 -0.5361 0.1305 0.5406 1.6165
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.13412 0.02694 153.475
## MentalHealth_status_cont -0.33736 0.04719 -7.150
## Leadership_Status1 -0.26465 0.03033 -8.726
## MentalHealth_status_cont:Leadership_Status1 0.09439 0.05148 1.834
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_cont 9.79e-13 ***
## Leadership_Status1 < 2e-16 ***
## MentalHealth_status_cont:Leadership_Status1 0.0668 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8538 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.04634, Adjusted R-squared: 0.04584
## F-statistic: 93 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response PeoplePractices :
##
## Call:
## lm(formula = PeoplePractices ~ MentalHealth_status_cont * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.6191 -0.4191 0.0225 0.5809 1.8240
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 3.97750 0.02461 161.596
## MentalHealth_status_cont -0.24667 0.04312 -5.721
## Leadership_Status1 -0.35836 0.02771 -12.930
## MentalHealth_status_cont:Leadership_Status1 0.02512 0.04704 0.534
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_cont 1.11e-08 ***
## Leadership_Status1 < 2e-16 ***
## MentalHealth_status_cont:Leadership_Status1 0.593
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7802 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.06216, Adjusted R-squared: 0.06167
## F-statistic: 126.9 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response OrgCommitment :
##
## Call:
## lm(formula = OrgCommitment ~ MentalHealth_status_cont * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.8137 -0.5595 -0.0595 0.4405 1.8195
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 3.81367 0.02414 157.965
## MentalHealth_status_cont -0.30633 0.04229 -7.243
## Leadership_Status1 -0.25418 0.02718 -9.350
## MentalHealth_status_cont:Leadership_Status1 0.11686 0.04614 2.533
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_cont 4.95e-13 ***
## Leadership_Status1 < 2e-16 ***
## MentalHealth_status_cont:Leadership_Status1 0.0113 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7652 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.04213, Adjusted R-squared: 0.04163
## F-statistic: 84.19 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response ManagerEffectiveness :
##
## Call:
## lm(formula = ManagerEffectiveness ~ MentalHealth_status_cont *
## Leadership_Status, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.3601 -0.3649 0.0724 0.6399 1.2596
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.36012 0.02650 164.528
## MentalHealth_status_cont -0.28293 0.04642 -6.095
## Leadership_Status1 -0.24525 0.02984 -8.219
## MentalHealth_status_cont:Leadership_Status1 0.09571 0.05065 1.890
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_cont 1.17e-09 ***
## Leadership_Status1 2.51e-16 ***
## MentalHealth_status_cont:Leadership_Status1 0.0588 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.84 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.03336, Adjusted R-squared: 0.03286
## F-statistic: 66.06 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response LeadershipCommitment :
##
## Call:
## lm(formula = LeadershipCommitment ~ MentalHealth_status_cont *
## Leadership_Status, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.6623 -0.4185 -0.1623 0.5761 2.0707
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 3.66234 0.02462 148.768
## MentalHealth_status_cont -0.39716 0.04312 -9.210
## Leadership_Status1 -0.24387 0.02772 -8.798
## MentalHealth_status_cont:Leadership_Status1 0.15256 0.04705 3.243
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_cont < 2e-16 ***
## Leadership_Status1 < 2e-16 ***
## MentalHealth_status_cont:Leadership_Status1 0.00119 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7803 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.05514, Adjusted R-squared: 0.05465
## F-statistic: 111.7 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response CareerExperience :
##
## Call:
## lm(formula = CareerExperience ~ MentalHealth_status_cont * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1450 -0.5465 0.1202 0.5216 1.4530
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.14505 0.02621 158.159
## MentalHealth_status_cont -0.21777 0.04591 -4.743
## Leadership_Status1 -0.26523 0.02951 -8.988
## MentalHealth_status_cont:Leadership_Status1 0.05135 0.05009 1.025
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## MentalHealth_status_cont 2.15e-06 ***
## Leadership_Status1 < 2e-16 ***
## MentalHealth_status_cont:Leadership_Status1 0.305
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8307 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.03165, Adjusted R-squared: 0.03115
## F-statistic: 62.57 on 3 and 5742 DF, p-value: < 2.2e-16Physical Disability Status (yes-no) x Leadership Status –> All Outcomes
# Leadership Status modeled as moderator: Physical Disability Status (yes-no) --> All Outcomes
model_LeadershipStatus <- lm(cbind(Engagement,Accessibility,Accommodation,PsychSafety,PeoplePractices,OrgCommitment,ManagerEffectiveness,LeadershipCommitment,CareerExperience) ~ PhysicalHealth_status_binary * Leadership_Status, data = df)
summary(model_LeadershipStatus) # no significant interactions## Response Engagement :
##
## Call:
## lm(formula = Engagement ~ PhysicalHealth_status_binary * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.2299 -0.3563 -0.0197 0.6437 0.9803
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.356263 0.022896 190.265
## PhysicalHealth_status_binary1 -0.126316 0.057049 -2.214
## Leadership_Status1 -0.205682 0.025885 -7.946
## PhysicalHealth_status_binary1:Leadership_Status1 -0.004566 0.062224 -0.073
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 0.0269 *
## Leadership_Status1 2.3e-15 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.9415
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7146 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.02005, Adjusted R-squared: 0.01954
## F-statistic: 39.17 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response Accessibility :
##
## Call:
## lm(formula = Accessibility ~ PhysicalHealth_status_binary * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.98715 -0.48384 0.01285 0.51285 1.26616
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.10780 0.02252 182.428
## PhysicalHealth_status_binary1 -0.16663 0.05611 -2.970
## Leadership_Status1 -0.12065 0.02546 -4.740
## PhysicalHealth_status_binary1:Leadership_Status1 -0.08668 0.06120 -1.416
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 0.00299 **
## Leadership_Status1 2.19e-06 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.15669
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7027 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.02721, Adjusted R-squared: 0.0267
## F-statistic: 53.53 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response Accommodation :
##
## Call:
## lm(formula = Accommodation ~ PhysicalHealth_status_binary * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4112 -0.6579 -0.1579 0.5888 2.2008
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 3.41119 0.02926 116.572
## PhysicalHealth_status_binary1 -0.28820 0.07291 -3.953
## Leadership_Status1 -0.25328 0.03308 -7.656
## PhysicalHealth_status_binary1:Leadership_Status1 -0.07054 0.07953 -0.887
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 7.82e-05 ***
## Leadership_Status1 2.24e-14 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.375
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9133 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.03975, Adjusted R-squared: 0.03925
## F-statistic: 79.24 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response PsychSafety :
##
## Call:
## lm(formula = PsychSafety ~ PhysicalHealth_status_binary * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1157 -0.5094 0.1145 0.5510 1.4906
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.115674 0.027390 150.260
## PhysicalHealth_status_binary1 -0.368794 0.068249 -5.404
## Leadership_Status1 -0.230180 0.030966 -7.433
## PhysicalHealth_status_binary1:Leadership_Status1 -0.007313 0.074440 -0.098
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 6.79e-08 ***
## Leadership_Status1 1.21e-13 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.922
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8548 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.04567, Adjusted R-squared: 0.04517
## F-statistic: 91.59 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response PeoplePractices :
##
## Call:
## lm(formula = PeoplePractices ~ PhysicalHealth_status_binary *
## Leadership_Status, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.71551 -0.43152 0.03409 0.56848 1.70139
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 3.96591 0.02505 158.292
## PhysicalHealth_status_binary1 -0.25041 0.06243 -4.011
## Leadership_Status1 -0.33439 0.02833 -11.805
## PhysicalHealth_status_binary1:Leadership_Status1 -0.08250 0.06809 -1.212
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 6.12e-05 ***
## Leadership_Status1 < 2e-16 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.226
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7819 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.06153, Adjusted R-squared: 0.06104
## F-statistic: 125.5 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response OrgCommitment :
##
## Call:
## lm(formula = OrgCommitment ~ PhysicalHealth_status_binary * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.80287 -0.57888 -0.05287 0.42112 1.74792
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 3.80287 0.02446 155.462
## PhysicalHealth_status_binary1 -0.35635 0.06095 -5.846
## Leadership_Status1 -0.22399 0.02766 -8.099
## PhysicalHealth_status_binary1:Leadership_Status1 0.02954 0.06648 0.444
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 5.30e-09 ***
## Leadership_Status1 6.69e-16 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.657
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7634 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.04653, Adjusted R-squared: 0.04603
## F-statistic: 93.41 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response ManagerEffectiveness :
##
## Call:
## lm(formula = ManagerEffectiveness ~ PhysicalHealth_status_binary *
## Leadership_Status, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.3419 -0.3839 0.1161 0.6581 1.1854
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.34189 0.02695 161.086
## PhysicalHealth_status_binary1 -0.29643 0.06716 -4.414
## Leadership_Status1 -0.20804 0.03047 -6.827
## PhysicalHealth_status_binary1:Leadership_Status1 -0.02278 0.07325 -0.311
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 1.03e-05 ***
## Leadership_Status1 9.56e-12 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.756
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8412 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.0355, Adjusted R-squared: 0.03499
## F-statistic: 70.44 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response LeadershipCommitment :
##
## Call:
## lm(formula = LeadershipCommitment ~ PhysicalHealth_status_binary *
## Leadership_Status, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.64784 -0.42718 -0.07248 0.57282 1.92752
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 3.64784 0.02515 145.063
## PhysicalHealth_status_binary1 -0.45667 0.06266 -7.288
## Leadership_Status1 -0.22066 0.02843 -7.762
## PhysicalHealth_status_binary1:Leadership_Status1 0.10197 0.06834 1.492
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 3.56e-13 ***
## Leadership_Status1 9.86e-15 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.136
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7848 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.05001, Adjusted R-squared: 0.04951
## F-statistic: 100.8 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response CareerExperience :
##
## Call:
## lm(formula = CareerExperience ~ PhysicalHealth_status_binary *
## Leadership_Status, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1277 -0.5661 0.1006 0.5390 1.3890
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.12765 0.02656 155.428
## PhysicalHealth_status_binary1 -0.21321 0.06617 -3.222
## Leadership_Status1 -0.22826 0.03002 -7.603
## PhysicalHealth_status_binary1:Leadership_Status1 -0.07522 0.07217 -1.042
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 0.00128 **
## Leadership_Status1 3.37e-14 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.29736
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8288 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.03418, Adjusted R-squared: 0.03367
## F-statistic: 67.73 on 3 and 5742 DF, p-value: < 2.2e-16# Leadership Status modeled as moderator: Physical Disability Status (range: 0 to 2) --> All Outcomes
model_LeadershipStatus <- lm(cbind(Engagement,Accessibility,Accommodation,PsychSafety,PeoplePractices,OrgCommitment,ManagerEffectiveness,LeadershipCommitment,CareerExperience) ~ PhysicalHealth_status_binary * Leadership_Status, data = df)
summary(model_LeadershipStatus) # no significant interactions## Response Engagement :
##
## Call:
## lm(formula = Engagement ~ PhysicalHealth_status_binary * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.2299 -0.3563 -0.0197 0.6437 0.9803
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.356263 0.022896 190.265
## PhysicalHealth_status_binary1 -0.126316 0.057049 -2.214
## Leadership_Status1 -0.205682 0.025885 -7.946
## PhysicalHealth_status_binary1:Leadership_Status1 -0.004566 0.062224 -0.073
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 0.0269 *
## Leadership_Status1 2.3e-15 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.9415
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7146 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.02005, Adjusted R-squared: 0.01954
## F-statistic: 39.17 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response Accessibility :
##
## Call:
## lm(formula = Accessibility ~ PhysicalHealth_status_binary * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.98715 -0.48384 0.01285 0.51285 1.26616
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.10780 0.02252 182.428
## PhysicalHealth_status_binary1 -0.16663 0.05611 -2.970
## Leadership_Status1 -0.12065 0.02546 -4.740
## PhysicalHealth_status_binary1:Leadership_Status1 -0.08668 0.06120 -1.416
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 0.00299 **
## Leadership_Status1 2.19e-06 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.15669
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7027 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.02721, Adjusted R-squared: 0.0267
## F-statistic: 53.53 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response Accommodation :
##
## Call:
## lm(formula = Accommodation ~ PhysicalHealth_status_binary * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4112 -0.6579 -0.1579 0.5888 2.2008
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 3.41119 0.02926 116.572
## PhysicalHealth_status_binary1 -0.28820 0.07291 -3.953
## Leadership_Status1 -0.25328 0.03308 -7.656
## PhysicalHealth_status_binary1:Leadership_Status1 -0.07054 0.07953 -0.887
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 7.82e-05 ***
## Leadership_Status1 2.24e-14 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.375
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9133 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.03975, Adjusted R-squared: 0.03925
## F-statistic: 79.24 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response PsychSafety :
##
## Call:
## lm(formula = PsychSafety ~ PhysicalHealth_status_binary * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1157 -0.5094 0.1145 0.5510 1.4906
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.115674 0.027390 150.260
## PhysicalHealth_status_binary1 -0.368794 0.068249 -5.404
## Leadership_Status1 -0.230180 0.030966 -7.433
## PhysicalHealth_status_binary1:Leadership_Status1 -0.007313 0.074440 -0.098
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 6.79e-08 ***
## Leadership_Status1 1.21e-13 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.922
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8548 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.04567, Adjusted R-squared: 0.04517
## F-statistic: 91.59 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response PeoplePractices :
##
## Call:
## lm(formula = PeoplePractices ~ PhysicalHealth_status_binary *
## Leadership_Status, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.71551 -0.43152 0.03409 0.56848 1.70139
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 3.96591 0.02505 158.292
## PhysicalHealth_status_binary1 -0.25041 0.06243 -4.011
## Leadership_Status1 -0.33439 0.02833 -11.805
## PhysicalHealth_status_binary1:Leadership_Status1 -0.08250 0.06809 -1.212
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 6.12e-05 ***
## Leadership_Status1 < 2e-16 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.226
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7819 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.06153, Adjusted R-squared: 0.06104
## F-statistic: 125.5 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response OrgCommitment :
##
## Call:
## lm(formula = OrgCommitment ~ PhysicalHealth_status_binary * Leadership_Status,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.80287 -0.57888 -0.05287 0.42112 1.74792
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 3.80287 0.02446 155.462
## PhysicalHealth_status_binary1 -0.35635 0.06095 -5.846
## Leadership_Status1 -0.22399 0.02766 -8.099
## PhysicalHealth_status_binary1:Leadership_Status1 0.02954 0.06648 0.444
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 5.30e-09 ***
## Leadership_Status1 6.69e-16 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.657
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7634 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.04653, Adjusted R-squared: 0.04603
## F-statistic: 93.41 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response ManagerEffectiveness :
##
## Call:
## lm(formula = ManagerEffectiveness ~ PhysicalHealth_status_binary *
## Leadership_Status, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.3419 -0.3839 0.1161 0.6581 1.1854
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.34189 0.02695 161.086
## PhysicalHealth_status_binary1 -0.29643 0.06716 -4.414
## Leadership_Status1 -0.20804 0.03047 -6.827
## PhysicalHealth_status_binary1:Leadership_Status1 -0.02278 0.07325 -0.311
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 1.03e-05 ***
## Leadership_Status1 9.56e-12 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.756
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8412 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.0355, Adjusted R-squared: 0.03499
## F-statistic: 70.44 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response LeadershipCommitment :
##
## Call:
## lm(formula = LeadershipCommitment ~ PhysicalHealth_status_binary *
## Leadership_Status, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.64784 -0.42718 -0.07248 0.57282 1.92752
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 3.64784 0.02515 145.063
## PhysicalHealth_status_binary1 -0.45667 0.06266 -7.288
## Leadership_Status1 -0.22066 0.02843 -7.762
## PhysicalHealth_status_binary1:Leadership_Status1 0.10197 0.06834 1.492
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 3.56e-13 ***
## Leadership_Status1 9.86e-15 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.136
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7848 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.05001, Adjusted R-squared: 0.04951
## F-statistic: 100.8 on 3 and 5742 DF, p-value: < 2.2e-16
##
##
## Response CareerExperience :
##
## Call:
## lm(formula = CareerExperience ~ PhysicalHealth_status_binary *
## Leadership_Status, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1277 -0.5661 0.1006 0.5390 1.3890
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 4.12765 0.02656 155.428
## PhysicalHealth_status_binary1 -0.21321 0.06617 -3.222
## Leadership_Status1 -0.22826 0.03002 -7.603
## PhysicalHealth_status_binary1:Leadership_Status1 -0.07522 0.07217 -1.042
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## PhysicalHealth_status_binary1 0.00128 **
## Leadership_Status1 3.37e-14 ***
## PhysicalHealth_status_binary1:Leadership_Status1 0.29736
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8288 on 5742 degrees of freedom
## (284 observations deleted due to missingness)
## Multiple R-squared: 0.03418, Adjusted R-squared: 0.03367
## F-statistic: 67.73 on 3 and 5742 DF, p-value: < 2.2e-16Multilevel Models: Cross-Level Main Effects
Disability Status & Org Level Predictors –> Outcome
# Disability Inclusion (Level 2)
model_accessibility <- lmer(Accessibility ~ DisabilityStatus + disInclusion2_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_accommodation <- lmer(Accommodation ~ DisabilityStatus + disInclusion2_2024 + (DisabilityStatus | company_mapped), data = df)
model_psychsafety <- lmer(PsychSafety ~ DisabilityStatus + disInclusion2_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ DisabilityStatus + disInclusion2_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_orgcommit <- lmer(OrgCommitment ~ DisabilityStatus + disInclusion2_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_mgr_effect <- lmer(ManagerEffectiveness ~ DisabilityStatus + disInclusion2_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_leadership <- lmer(LeadershipCommitment ~ DisabilityStatus + disInclusion2_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_career <- lmer(CareerExperience ~ DisabilityStatus + disInclusion2_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')summary(model_accessibility)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## Accessibility ~ DisabilityStatus + disInclusion2_2024 + (DisabilityStatus |
## company_mapped)
## Data: df
##
## REML criterion at convergence: 12291.4
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.2312 -0.6857 0.0234 0.7325 1.7208
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.003776 0.06145
## DisabilityStatus1 0.009788 0.09893 -1.00
## Residual 0.497199 0.70512
## Number of obs: 5737, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.66999 0.13912 1.97309 26.380 0.00154 **
## DisabilityStatus1 -0.15250 0.06117 2.64650 -2.493 0.09951 .
## disInclusion2_2024 0.09532 0.03775 2.88290 2.525 0.08918 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) DsblS1
## DsbltyStts1 -0.589
## dsInc2_2024 -0.972 0.409
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')summary(model_people)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## PeoplePractices ~ DisabilityStatus + disInclusion2_2024 + (DisabilityStatus |
## company_mapped)
## Data: df
##
## REML criterion at convergence: 13586.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.3253 -0.5375 -0.0306 0.7297 2.0883
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.022899 0.15132
## DisabilityStatus1 0.006075 0.07794 -1.00
## Residual 0.622759 0.78915
## Number of obs: 5737, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.04714 0.41251 1.56155 4.963 0.0615 .
## DisabilityStatus1 -0.21639 0.05818 2.24156 -3.719 0.0546 .
## disInclusion2_2024 0.48958 0.10524 1.51098 4.652 0.0716 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) DsblS1
## DsbltyStts1 -0.730
## dsInc2_2024 -0.988 0.645
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')# Disability Support (Level 2)
model_engagement <- lmer(Engagement ~ DisabilityStatus + disSupport1_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_accessibility <- lmer(Accessibility ~ DisabilityStatus + disSupport1_2024 + (DisabilityStatus | company_mapped), data = df)
model_accommodation <- lmer(Accommodation ~ DisabilityStatus + disSupport1_2024 + (DisabilityStatus | company_mapped), data = df)
model_psychsafety <- lmer(PsychSafety ~ DisabilityStatus + disSupport1_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ DisabilityStatus + disSupport1_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_orgcommit <- lmer(OrgCommitment ~ DisabilityStatus + disSupport1_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_mgr_effect <- lmer(ManagerEffectiveness ~ DisabilityStatus + disSupport1_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_leadership <- lmer(LeadershipCommitment ~ DisabilityStatus + disSupport1_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_career <- lmer(CareerExperience ~ DisabilityStatus + disSupport1_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')summary(model_engagement)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## Engagement ~ DisabilityStatus + disSupport1_2024 + (DisabilityStatus |
## company_mapped)
## Data: df
##
## REML criterion at convergence: 12508.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.4295 -0.5481 -0.0831 0.8382 1.4892
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 3.204e-04 0.017899
## DisabilityStatus1 3.799e-05 0.006164 1.00
## Residual 5.167e-01 0.718801
## Number of obs: 5737, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.41771 0.05125 2.39329 86.200 3.09e-05 ***
## DisabilityStatus1 -0.12223 0.02705 9.04876 -4.518 0.00143 **
## disSupport1_2024 -0.12045 0.02431 5.48692 -4.954 0.00330 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) DsblS1
## DsbltyStts1 -0.045
## dsSpp1_2024 -0.944 0.003
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')# Disability Training (Level 2)
model_engagement <- lmer(Engagement ~ DisabilityStatus + training3_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_accessibility <- lmer(Accessibility ~ DisabilityStatus + training3_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')## Warning: Model failed to converge with 1 negative eigenvalue: -1.3e+03model_accommodation <- lmer(Accommodation ~ DisabilityStatus + training3_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_psychsafety <- lmer(PsychSafety ~ DisabilityStatus + training3_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ DisabilityStatus + training3_2024 + (DisabilityStatus | company_mapped), data = df)
model_orgcommit <- lmer(OrgCommitment ~ DisabilityStatus + training3_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_mgr_effect <- lmer(ManagerEffectiveness ~ DisabilityStatus + training3_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_leadership <- lmer(LeadershipCommitment ~ DisabilityStatus + training3_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_career <- lmer(CareerExperience ~ DisabilityStatus + training3_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')summary(model_accessibility)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## Accessibility ~ DisabilityStatus + training3_2024 + (DisabilityStatus |
## company_mapped)
## Data: df
##
## REML criterion at convergence: 12291.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.2305 -0.6851 0.0239 0.7330 1.7214
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.001773 0.04210
## DisabilityStatus1 0.006758 0.08221 -1.00
## Residual 0.497232 0.70515
## Number of obs: 5737, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.86179 0.05553 1.18251 69.542 0.00442 **
## DisabilityStatus1 -0.15692 0.05535 1.71873 -2.835 0.12441
## training3_2024 0.05040 0.01752 3.50425 2.878 0.05285 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) DsblS1
## DsbltyStts1 -0.662
## trnng3_2024 -0.884 0.310
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')summary(model_people)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## PeoplePractices ~ DisabilityStatus + training3_2024 + (DisabilityStatus |
## company_mapped)
## Data: df
##
## REML criterion at convergence: 13585.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.3241 -0.5365 -0.0296 0.7306 2.0844
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.007328 0.08560
## DisabilityStatus1 0.001979 0.04449 -0.42
## Residual 0.622842 0.78920
## Number of obs: 5737, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.14567 0.16613 1.89559 18.936 0.00353 **
## DisabilityStatus1 -0.24092 0.04434 0.66161 -5.433 0.20248
## training3_2024 0.22241 0.04681 1.85353 4.751 0.04808 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) DsblS1
## DsbltyStts1 -0.209
## trnng3_2024 -0.968 0.126# Overall Accessibility (Level 2)
model_engagement <- lmer(Engagement ~ DisabilityStatus + overallAccessibility2_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')## Warning: Model failed to converge with 1 negative eigenvalue: -2.7e+02model_accessibility <- lmer(Accessibility ~ DisabilityStatus + overallAccessibility2_2024 + (DisabilityStatus | company_mapped), data = df)
model_accommodation <- lmer(Accommodation ~ DisabilityStatus + overallAccessibility2_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_psychsafety <- lmer(PsychSafety ~ DisabilityStatus + overallAccessibility2_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ DisabilityStatus + overallAccessibility2_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_orgcommit <- lmer(OrgCommitment ~ DisabilityStatus + overallAccessibility2_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_mgr_effect <- lmer(ManagerEffectiveness ~ DisabilityStatus + overallAccessibility2_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_leadership <- lmer(LeadershipCommitment ~ DisabilityStatus + overallAccessibility2_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_career <- lmer(CareerExperience ~ DisabilityStatus + overallAccessibility2_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')# Note: Overall Accessibility (Level 2) has no significant direct effect on outcomes# Accommodations (Level 2)
model_engagement <- lmer(Engagement ~ DisabilityStatus + Accommodations1_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_accessibility <- lmer(Accessibility ~ DisabilityStatus + Accommodations1_2024 + (DisabilityStatus | company_mapped), data = df)
model_accommodation <- lmer(Accommodation ~ DisabilityStatus + Accommodations1_2024 + (DisabilityStatus | company_mapped), data = df)
model_psychsafety <- lmer(PsychSafety ~ DisabilityStatus + Accommodations1_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ DisabilityStatus + Accommodations1_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_orgcommit <- lmer(OrgCommitment ~ DisabilityStatus + Accommodations1_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_mgr_effect <- lmer(ManagerEffectiveness ~ DisabilityStatus + Accommodations1_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_leadership <- lmer(LeadershipCommitment ~ DisabilityStatus + Accommodations1_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_career <- lmer(CareerExperience ~ DisabilityStatus + Accommodations1_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')# Note: Accommodations (Level 2) have no significant direct effect on outcomes# Disability Promotion (Level 2)
model_engagement <- lmer(Engagement ~ DisabilityStatus + overallDisPromotion_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_accessibility <- lmer(Accessibility ~ DisabilityStatus + overallDisPromotion_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_accommodation <- lmer(Accommodation ~ DisabilityStatus + overallDisPromotion_2024 + (DisabilityStatus | company_mapped), data = df)
model_psychsafety <- lmer(PsychSafety ~ DisabilityStatus + overallDisPromotion_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ DisabilityStatus + overallDisPromotion_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_orgcommit <- lmer(OrgCommitment ~ DisabilityStatus + overallDisPromotion_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_mgr_effect <- lmer(ManagerEffectiveness ~ DisabilityStatus + overallDisPromotion_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_leadership <- lmer(LeadershipCommitment ~ DisabilityStatus + overallDisPromotion_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_career <- lmer(CareerExperience ~ DisabilityStatus + overallDisPromotion_2024 + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')summary(model_accessibility)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Accessibility ~ DisabilityStatus + overallDisPromotion_2024 +
## (DisabilityStatus | company_mapped)
## Data: df
##
## REML criterion at convergence: 12291.4
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.2312 -0.6857 0.0234 0.7325 1.7208
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.003776 0.06145
## DisabilityStatus1 0.009788 0.09893 -1.00
## Residual 0.497199 0.70512
## Number of obs: 5737, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.38403 0.25061 2.28925 13.503 0.00313 **
## DisabilityStatus1 -0.15250 0.06117 2.64650 -2.493 0.09951 .
## overallDisPromotion_2024 0.09532 0.03775 2.88290 2.525 0.08918 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) DsblS1
## DsbltyStts1 -0.512
## ovrlDP_2024 -0.991 0.409
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')summary(model_people)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: PeoplePractices ~ DisabilityStatus + overallDisPromotion_2024 +
## (DisabilityStatus | company_mapped)
## Data: df
##
## REML criterion at convergence: 13586.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.3253 -0.5375 -0.0306 0.7297 2.0883
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.022899 0.15132
## DisabilityStatus1 0.006075 0.07794 -1.00
## Residual 0.622759 0.78915
## Number of obs: 5737, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 0.57840 0.72605 1.52415 0.797 0.5308
## DisabilityStatus1 -0.21639 0.05818 2.24156 -3.719 0.0546 .
## overallDisPromotion_2024 0.48958 0.10524 1.51098 4.652 0.0716 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) DsblS1
## DsbltyStts1 -0.696
## ovrlDP_2024 -0.996 0.645
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')Multilevel Models: Cross-Level Interaction Effects
Note: Disability Status x Org-Level Predictors –> Outcome No sig cross-level interactions
Below Analyses: Mental Health Status x Org-Level Predictors –> Outcomes
# Disability Inclusion (Level 2)
model_accessibility <- lmer(Accessibility ~ MentalHealth_status_binary * disInclusion2_2024 + (1 | company_mapped), data = df)
model_accommodation <- lmer(Accommodation ~ MentalHealth_status_binary * disInclusion2_2024 + (1 | company_mapped), data = df)
model_psychsafety <- lmer(PsychSafety ~ MentalHealth_status_binary * disInclusion2_2024 + (1 | company_mapped), data = df)
model_people <- lmer(PeoplePractices ~ MentalHealth_status_binary * disInclusion2_2024 + (1 | company_mapped), data = df)
model_orgcommit <- lmer(OrgCommitment ~ MentalHealth_status_binary * disInclusion2_2024 + (1 | company_mapped), data = df)
model_mgr_effect <- lmer(ManagerEffectiveness ~ MentalHealth_status_binary * disInclusion2_2024 + (1 | company_mapped), data = df)
model_leadership <- lmer(LeadershipCommitment ~ MentalHealth_status_binary * disInclusion2_2024 + (1 | company_mapped), data = df)
model_career <- lmer(CareerExperience ~ MentalHealth_status_binary * disInclusion2_2024 + (1 | company_mapped), data = df)
summary(model_people)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: PeoplePractices ~ MentalHealth_status_binary * disInclusion2_2024 +
## (1 | company_mapped)
## Data: df
##
## REML criterion at convergence: 13513.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.3909 -0.5798 0.0188 0.6980 2.2000
##
## Random effects:
## Groups Name Variance Std.Dev.
## company_mapped (Intercept) 0.01734 0.1317
## Residual 0.61246 0.7826
## Number of obs: 5746, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 2.60543 0.56269 3.33930
## MentalHealth_status_binary1 -0.78911 0.23650 5433.54218
## disInclusion2_2024 0.34943 0.14689 3.48461
## MentalHealth_status_binary1:disInclusion2_2024 0.13788 0.07477 5357.02921
## t value Pr(>|t|)
## (Intercept) 4.630 0.014930 *
## MentalHealth_status_binary1 -3.337 0.000854 ***
## disInclusion2_2024 2.379 0.085676 .
## MentalHealth_status_binary1:disInclusion2_2024 1.844 0.065216 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) MnH__1 dI2_20
## MntlHlth__1 -0.097
## dsInc2_2024 -0.995 0.118
## MH__1:I2_20 0.098 -0.994 -0.120interact_plot(model_people, pred = MentalHealth_status_binary, modx = disInclusion2_2024,
main.title = "Interaction: Mental Health Status × Disability Inclusion on People Practices")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
# Disability Support (Level 2)
model_engagement <- lmer(Engagement ~ MentalHealth_status_binary * disSupport1_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_accessibility <- lmer(Accessibility ~ MentalHealth_status_binary * disSupport1_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_accommodation <- lmer(Accommodation ~ MentalHealth_status_binary * disSupport1_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_psychsafety <- lmer(PsychSafety ~ MentalHealth_status_binary * disSupport1_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ MentalHealth_status_binary * disSupport1_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_orgcommit <- lmer(OrgCommitment ~ MentalHealth_status_binary * disSupport1_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_mgr_effect <- lmer(ManagerEffectiveness ~ MentalHealth_status_binary * disSupport1_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_leadership <- lmer(LeadershipCommitment ~ MentalHealth_status_binary * disSupport1_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_career <- lmer(CareerExperience ~ MentalHealth_status_binary * disSupport1_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')summary(model_orgcommit)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: OrgCommitment ~ MentalHealth_status_binary * disSupport1_2024 +
## (MentalHealth_status_binary | company_mapped)
## Data: df
##
## REML criterion at convergence: 13269
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.5328 -0.7651 -0.1121 0.5408 2.2795
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.028152 0.16779
## MentalHealth_status_binary1 0.001765 0.04201 1.00
## Residual 0.586382 0.76576
## Number of obs: 5746, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 3.804389 0.163375 5.403511
## MentalHealth_status_binary1 -0.496666 0.125940 51.686150
## disSupport1_2024 -0.005446 0.070524 5.805722
## MentalHealth_status_binary1:disSupport1_2024 0.108634 0.061231 89.500829
## t value Pr(>|t|)
## (Intercept) 23.286 1.25e-06 ***
## MentalHealth_status_binary1 -3.944 0.000243 ***
## disSupport1_2024 -0.077 0.941037
## MentalHealth_status_binary1:disSupport1_2024 1.774 0.079434 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) MnH__1 dS1_20
## MntlHlth__1 0.110
## dsSpp1_2024 -0.909 -0.057
## MH__1:S1_20 -0.050 -0.970 0.042
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')interact_plot(model_orgcommit, pred = MentalHealth_status_binary, modx = disSupport1_2024,
main.title = "Interaction: Mental Health Status × Disability Support on Org Commitment")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
# Disability Training (Level 2)
model_engagement <- lmer(Engagement ~ MentalHealth_status_binary * training3_2024 + (MentalHealth_status_binary | company_mapped), data = df)
model_accessibility <- lmer(Accessibility ~ MentalHealth_status_binary * training3_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_accommodation <- lmer(Accommodation ~ MentalHealth_status_binary * training3_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_psychsafety <- lmer(PsychSafety ~ MentalHealth_status_binary * training3_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ MentalHealth_status_binary * training3_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_orgcommit <- lmer(OrgCommitment ~ MentalHealth_status_binary * training3_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_mgr_effect <- lmer(ManagerEffectiveness ~ MentalHealth_status_binary * training3_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_leadership <- lmer(LeadershipCommitment ~ MentalHealth_status_binary * training3_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_career <- lmer(CareerExperience ~ MentalHealth_status_binary * training3_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')## Warning: Model failed to converge with 1 negative eigenvalue: -2.7e+01# Note: No significant interactions# Overall Accessibility (Level 2)
model_engagement <- lmer(Engagement ~ MentalHealth_status_binary * overallAccessibility2_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_accessibility <- lmer(Accessibility ~ MentalHealth_status_binary * overallAccessibility2_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_accommodation <- lmer(Accommodation ~ MentalHealth_status_binary * overallAccessibility2_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')## Warning: Model failed to converge with 1 negative eigenvalue: -8.6e+03model_psychsafety <- lmer(PsychSafety ~ MentalHealth_status_binary * overallAccessibility2_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ MentalHealth_status_binary * overallAccessibility2_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_orgcommit <- lmer(OrgCommitment ~ MentalHealth_status_binary * overallAccessibility2_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_mgr_effect <- lmer(ManagerEffectiveness ~ MentalHealth_status_binary * overallAccessibility2_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_leadership <- lmer(LeadershipCommitment ~ MentalHealth_status_binary * overallAccessibility2_2024 + (MentalHealth_status_binary | company_mapped), data = df)## Warning in checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, :
## Model failed to converge with max|grad| = 0.00204505 (tol = 0.002, component 1)model_career <- lmer(CareerExperience ~ MentalHealth_status_binary * overallAccessibility2_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')# Note: No significant interactions# Accommodations (Level 2)
model_engagement <- lmer(Engagement ~ MentalHealth_status_binary * Accommodations1_2024 + (MentalHealth_status_binary | company_mapped), data = df)
model_accessibility <- lmer(Accessibility ~ MentalHealth_status_binary * Accommodations1_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_accommodation <- lmer(Accommodation ~ MentalHealth_status_binary * Accommodations1_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_psychsafety <- lmer(PsychSafety ~ MentalHealth_status_binary * Accommodations1_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ MentalHealth_status_binary * Accommodations1_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_orgcommit <- lmer(OrgCommitment ~ MentalHealth_status_binary * Accommodations1_2024 + (MentalHealth_status_binary | company_mapped), data = df)
model_mgr_effect <- lmer(ManagerEffectiveness ~ MentalHealth_status_binary * Accommodations1_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_leadership <- lmer(LeadershipCommitment ~ MentalHealth_status_binary * Accommodations1_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_career <- lmer(CareerExperience ~ MentalHealth_status_binary * Accommodations1_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')# Note: No significant interactions# Disability Promotion (Level 2)
model_engagement <- lmer(Engagement ~ MentalHealth_status_binary * overallDisPromotion_2024 + (MentalHealth_status_binary | company_mapped), data = df)
model_accessibility <- lmer(Accessibility ~ MentalHealth_status_binary * overallDisPromotion_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_accommodation <- lmer(Accommodation ~ MentalHealth_status_binary * overallDisPromotion_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_psychsafety <- lmer(PsychSafety ~ MentalHealth_status_binary * overallDisPromotion_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ MentalHealth_status_binary * overallDisPromotion_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_orgcommit <- lmer(OrgCommitment ~ MentalHealth_status_binary * overallDisPromotion_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_mgr_effect <- lmer(ManagerEffectiveness ~ MentalHealth_status_binary * overallDisPromotion_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_leadership <- lmer(LeadershipCommitment ~ MentalHealth_status_binary * overallDisPromotion_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_career <- lmer(CareerExperience ~ MentalHealth_status_binary * overallDisPromotion_2024 + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')# Note: No significant interactionsBelow Analyses: Physical Status x Org-Level Predictors –> Outcomes
# Disability Inclusion (Level 2)
model_engagement <- lmer(Engagement ~ PhysicalHealth_status_binary * disInclusion2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_accessibility <- lmer(Accessibility ~ PhysicalHealth_status_binary * disInclusion2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_accommodation <- lmer(Accommodation ~ PhysicalHealth_status_binary * disInclusion2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_psychsafety <- lmer(PsychSafety ~ PhysicalHealth_status_binary * disInclusion2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ PhysicalHealth_status_binary * disInclusion2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_orgcommit <- lmer(OrgCommitment ~ PhysicalHealth_status_binary * disInclusion2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_mgr_effect <- lmer(ManagerEffectiveness ~ PhysicalHealth_status_binary * disInclusion2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_leadership <- lmer(LeadershipCommitment ~ PhysicalHealth_status_binary * disInclusion2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_career <- lmer(CareerExperience ~ PhysicalHealth_status_binary * disInclusion2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
summary(model_accessibility)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Accessibility ~ PhysicalHealth_status_binary * disInclusion2_2024 +
## (PhysicalHealth_status_binary | company_mapped)
## Data: df
##
## REML criterion at convergence: 12291.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.2738 -0.6997 -0.0106 0.7000 1.7872
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.005276 0.07264
## PhysicalHealth_status_binary1 0.038344 0.19582 -1.00
## Residual 0.495179 0.70369
## Number of obs: 5746, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 3.87904 0.32010 1.72037
## PhysicalHealth_status_binary1 -0.67644 0.84731 2.45056
## disInclusion2_2024 0.04280 0.08475 1.89425
## PhysicalHealth_status_binary1:disInclusion2_2024 0.13712 0.22249 2.61798
## t value Pr(>|t|)
## (Intercept) 12.118 0.0115 *
## PhysicalHealth_status_binary1 -0.798 0.4947
## disInclusion2_2024 0.505 0.6661
## PhysicalHealth_status_binary1:disInclusion2_2024 0.616 0.5871
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PhH__1 dI2_20
## PhysclHl__1 -0.955
## dsInc2_2024 -0.993 0.936
## PH__1:I2_20 0.944 -0.994 -0.935
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')interact_plot(model_accessibility, pred = PhysicalHealth_status_binary, modx = disInclusion2_2024,
main.title = "Interaction: Physical Disability Status × Disability Inclusion on Accessibility")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
summary(model_accommodation)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: Accommodation ~ PhysicalHealth_status_binary * disInclusion2_2024 +
## (PhysicalHealth_status_binary | company_mapped)
## Data: df
##
## REML criterion at convergence: 15345.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.5840 -0.7800 -0.2352 0.7693 2.3666
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.022416 0.14972
## PhysicalHealth_status_binary1 0.003323 0.05765 -0.33
## Residual 0.842565 0.91791
## Number of obs: 5746, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 3.27336 0.64057 2.80455
## PhysicalHealth_status_binary1 -0.95052 0.37138 0.15370
## disInclusion2_2024 -0.01914 0.16730 2.92844
## PhysicalHealth_status_binary1:disInclusion2_2024 0.18741 0.10947 0.25831
## t value Pr(>|t|)
## (Intercept) 5.110 0.0171 *
## PhysicalHealth_status_binary1 -2.559 0.6790
## disInclusion2_2024 -0.114 0.9163
## PhysicalHealth_status_binary1:disInclusion2_2024 1.712 0.6214
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PhH__1 dI2_20
## PhysclHl__1 -0.283
## dsInc2_2024 -0.995 0.296
## PH__1:I2_20 0.262 -0.990 -0.280interact_plot(model_accommodation, pred = PhysicalHealth_status_binary, modx = disInclusion2_2024,
main.title = "Interaction: Physical Disability Status × Disability Inclusion on Accommodations")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
summary(model_people)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: PeoplePractices ~ PhysicalHealth_status_binary * disInclusion2_2024 +
## (PhysicalHealth_status_binary | company_mapped)
## Data: df
##
## REML criterion at convergence: 13528.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.3957 -0.5883 0.1013 0.6878 2.1698
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.015716 0.12536
## PhysicalHealth_status_binary1 0.005892 0.07676 -1.00
## Residual 0.614114 0.78365
## Number of obs: 5746, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 2.6727 0.5370 2.7439
## PhysicalHealth_status_binary1 -0.8465 0.4009 0.9881
## disInclusion2_2024 0.3294 0.1403 2.8707
## PhysicalHealth_status_binary1:disInclusion2_2024 0.1617 0.1128 1.3915
## t value Pr(>|t|)
## (Intercept) 4.977 0.0192 *
## PhysicalHealth_status_binary1 -2.111 0.2839
## disInclusion2_2024 2.348 0.1044
## PhysicalHealth_status_binary1:disInclusion2_2024 1.433 0.3356
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PhH__1 dI2_20
## PhysclHl__1 -0.844
## dsInc2_2024 -0.995 0.845
## PH__1:I2_20 0.785 -0.990 -0.795
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')interact_plot(model_people, pred = PhysicalHealth_status_binary, modx = disInclusion2_2024,
main.title = "Interaction: Physical Disability Status × Disability Inclusion on People Practices")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
# Disability Support (Level 2)
model_engagement <- lmer(Engagement ~ PhysicalHealth_status_binary * disSupport1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_accessibility <- lmer(Accessibility ~ PhysicalHealth_status_binary * disSupport1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_accommodation <- lmer(Accommodation ~ PhysicalHealth_status_binary * disSupport1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_psychsafety <- lmer(PsychSafety ~ PhysicalHealth_status_binary * disSupport1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ PhysicalHealth_status_binary * disSupport1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_orgcommit <- lmer(OrgCommitment ~ PhysicalHealth_status_binary * disSupport1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_mgr_effect <- lmer(ManagerEffectiveness ~ PhysicalHealth_status_binary * disSupport1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_leadership <- lmer(LeadershipCommitment ~ PhysicalHealth_status_binary * disSupport1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_career <- lmer(CareerExperience ~ PhysicalHealth_status_binary * disSupport1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')summary(model_leadership) # Suggests that support increase the negative effect of physical health status on perceived leadership commitment## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## LeadershipCommitment ~ PhysicalHealth_status_binary * disSupport1_2024 +
## (PhysicalHealth_status_binary | company_mapped)
## Data: df
##
## REML criterion at convergence: 13568.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.4446 -0.5807 -0.0765 0.6913 2.4674
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.012327 0.11103
## PhysicalHealth_status_binary1 0.003643 0.06035 1.00
## Residual 0.618091 0.78619
## Number of obs: 5746, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 3.48469 0.11667 5.05341
## PhysicalHealth_status_binary1 -0.06378 0.14801 32.49064
## disSupport1_2024 0.05406 0.05122 5.79101
## PhysicalHealth_status_binary1:disSupport1_2024 -0.12925 0.07129 57.03211
## t value Pr(>|t|)
## (Intercept) 29.868 7.02e-07 ***
## PhysicalHealth_status_binary1 -0.431 0.6694
## disSupport1_2024 1.055 0.3332
## PhysicalHealth_status_binary1:disSupport1_2024 -1.813 0.0751 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PhH__1 dS1_20
## PhysclHl__1 0.130
## dsSpp1_2024 -0.911 -0.054
## PH__1:S1_20 -0.057 -0.970 0.039
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')interact_plot(model_leadership, pred = PhysicalHealth_status_binary, modx = disSupport1_2024,
main.title = "Interaction: Physical Disability Status × Disability Support on Leadership Commitment")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
# Disability Training (Level 2)
model_engagement <- lmer(Engagement ~ PhysicalHealth_status_binary * training3_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_accessibility <- lmer(Accessibility ~ PhysicalHealth_status_binary * training3_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_accommodation <- lmer(Accommodation ~ PhysicalHealth_status_binary * training3_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_psychsafety <- lmer(PsychSafety ~ PhysicalHealth_status_binary * training3_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_people <- lmer(PeoplePractices ~ PhysicalHealth_status_binary * training3_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_orgcommit <- lmer(OrgCommitment ~ PhysicalHealth_status_binary * training3_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_mgr_effect <- lmer(ManagerEffectiveness ~ PhysicalHealth_status_binary * training3_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_leadership <- lmer(LeadershipCommitment ~ PhysicalHealth_status_binary * training3_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_career <- lmer(CareerExperience ~ PhysicalHealth_status_binary * training3_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')## Warning: Model failed to converge with 1 negative eigenvalue: -2.1e+01# Note: No significant interactions# Overall Accessibility (Level 2)
model_engagement <- lmer(Engagement ~ PhysicalHealth_status_binary * overallAccessibility2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_accessibility <- lmer(Accessibility ~ PhysicalHealth_status_binary * overallAccessibility2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')## Warning: Model failed to converge with 1 negative eigenvalue: -1.7e+02model_accommodation <- lmer(Accommodation ~ PhysicalHealth_status_binary * overallAccessibility2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_psychsafety <- lmer(PsychSafety ~ PhysicalHealth_status_binary * overallAccessibility2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ PhysicalHealth_status_binary * overallAccessibility2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_orgcommit <- lmer(OrgCommitment ~ PhysicalHealth_status_binary * overallAccessibility2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_mgr_effect <- lmer(ManagerEffectiveness ~ PhysicalHealth_status_binary * overallAccessibility2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_leadership <- lmer(LeadershipCommitment ~ PhysicalHealth_status_binary * overallAccessibility2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_career <- lmer(CareerExperience ~ PhysicalHealth_status_binary * overallAccessibility2_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')summary(model_mgr_effect) # Suggests that accessibility increase the negative effect of physical health status on perceived manager effectiveness## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## ManagerEffectiveness ~ PhysicalHealth_status_binary * overallAccessibility2_2024 +
## (PhysicalHealth_status_binary | company_mapped)
## Data: df
##
## REML criterion at convergence: 14367
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.8805 -0.4891 0.1042 0.9073 1.4025
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.0127095 0.11274
## PhysicalHealth_status_binary1 0.0002878 0.01696 -1.00
## Residual 0.7103342 0.84281
## Number of obs: 5746, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error
## (Intercept) 3.62742 0.50235
## PhysicalHealth_status_binary1 1.27749 0.56335
## overallAccessibility2_2024 0.05193 0.04109
## PhysicalHealth_status_binary1:overallAccessibility2_2024 -0.12637 0.04383
## df t value
## (Intercept) 10.96981 7.221
## PhysicalHealth_status_binary1 256.58584 2.268
## overallAccessibility2_2024 10.03726 1.264
## PhysicalHealth_status_binary1:overallAccessibility2_2024 190.54555 -2.883
## Pr(>|t|)
## (Intercept) 1.73e-05 ***
## PhysicalHealth_status_binary1 0.02418 *
## overallAccessibility2_2024 0.23486
## PhysicalHealth_status_binary1:overallAccessibility2_2024 0.00439 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PhH__1 oA2_20
## PhysclHl__1 -0.482
## ovrlA2_2024 -0.995 0.466
## PH__1:A2_20 0.486 -0.999 -0.472
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')interact_plot(model_mgr_effect, pred = PhysicalHealth_status_binary, modx = overallAccessibility2_2024,
main.title = "Interaction: Physical Disability Status × Overall Accessibility on Manager Effectiveness")## Warning: 13.4340220570054 is outside the observed range of
## overallAccessibility2_2024## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
# Accommodations (Level 2)
model_engagement <- lmer(Engagement ~ PhysicalHealth_status_binary * Accommodations1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_accessibility <- lmer(Accessibility ~ PhysicalHealth_status_binary * Accommodations1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_accommodation <- lmer(Accommodation ~ PhysicalHealth_status_binary * Accommodations1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_psychsafety <- lmer(PsychSafety ~ PhysicalHealth_status_binary * Accommodations1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ PhysicalHealth_status_binary * Accommodations1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')## Warning: Model failed to converge with 1 negative eigenvalue: -1.1e+03model_orgcommit <- lmer(OrgCommitment ~ PhysicalHealth_status_binary * Accommodations1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_mgr_effect <- lmer(ManagerEffectiveness ~ PhysicalHealth_status_binary * Accommodations1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_leadership <- lmer(LeadershipCommitment ~ PhysicalHealth_status_binary * Accommodations1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_career <- lmer(CareerExperience ~ PhysicalHealth_status_binary * Accommodations1_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')# Note: No significant interactions# Disability Promotion (Level 2)
model_engagement <- lmer(Engagement ~ PhysicalHealth_status_binary * overallDisPromotion_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_accessibility <- lmer(Accessibility ~ PhysicalHealth_status_binary * overallDisPromotion_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_accommodation <- lmer(Accommodation ~ PhysicalHealth_status_binary * overallDisPromotion_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_psychsafety <- lmer(PsychSafety ~ PhysicalHealth_status_binary * overallDisPromotion_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ PhysicalHealth_status_binary * overallDisPromotion_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_orgcommit <- lmer(OrgCommitment ~ PhysicalHealth_status_binary * overallDisPromotion_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_mgr_effect <- lmer(ManagerEffectiveness ~ PhysicalHealth_status_binary * overallDisPromotion_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_leadership <- lmer(LeadershipCommitment ~ PhysicalHealth_status_binary * overallDisPromotion_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
model_career <- lmer(CareerExperience ~ PhysicalHealth_status_binary * overallDisPromotion_2024 + (PhysicalHealth_status_binary | company_mapped), data = df)
# Note: No significant interactionsDisability Status x Accommodations (Employee Survey) –> Outcomes
Moderating Role of Accomodations at Level 1
# Accommodations (Level 1)
model_engagement <- lmer(Engagement ~ DisabilityStatus * Accommodation + (DisabilityStatus | company_mapped), data = df)
model_accessibility <- lmer(Accessibility ~ DisabilityStatus * Accommodation + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_psychsafety <- lmer(PsychSafety ~ DisabilityStatus * Accommodation + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ DisabilityStatus * Accommodation + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_orgcommit <- lmer(OrgCommitment ~ DisabilityStatus * Accommodation + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')## Warning: Model failed to converge with 1 negative eigenvalue: -2.2e+01model_mgr_effect <- lmer(ManagerEffectiveness ~ DisabilityStatus * Accommodation + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_leadership <- lmer(LeadershipCommitment ~ DisabilityStatus * Accommodation + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_career <- lmer(CareerExperience ~ DisabilityStatus * Accommodation + (DisabilityStatus | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')summary(model_psychsafety)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: PsychSafety ~ DisabilityStatus * Accommodation + (DisabilityStatus |
## company_mapped)
## Data: df
##
## REML criterion at convergence: 12320.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.3251 -0.4878 0.0920 0.5913 3.5793
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.005964 0.07723
## DisabilityStatus1 0.002681 0.05178 -1.00
## Residual 0.498968 0.70638
## Number of obs: 5737, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 2.29302 0.05206 20.94228 44.044
## DisabilityStatus1 -0.38423 0.08569 97.31742 -4.484
## Accommodation 0.52717 0.01115 5729.45704 47.269
## DisabilityStatus1:Accommodation 0.06307 0.02636 5730.27318 2.393
## Pr(>|t|)
## (Intercept) <2e-16 ***
## DisabilityStatus1 2e-05 ***
## Accommodation <2e-16 ***
## DisabilityStatus1:Accommodation 0.0168 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) DsblS1 Accmmd
## DsbltyStts1 -0.508
## Accommodatn -0.680 0.413
## DsbltySt1:A 0.284 -0.904 -0.423
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')interact_plot(model_psychsafety, pred = DisabilityStatus, modx = Accommodation,
main.title = "Interaction: Disability Status × Accommodations on Psych Safety")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
summary(model_mgr_effect)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## ManagerEffectiveness ~ DisabilityStatus * Accommodation + (DisabilityStatus |
## company_mapped)
## Data: df
##
## REML criterion at convergence: 13123.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.8225 -0.5198 0.1069 0.7248 2.5874
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.016326 0.12778
## DisabilityStatus1 0.009905 0.09953 -1.00
## Residual 0.573723 0.75745
## Number of obs: 5737, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 2.99067 0.06768 13.85594 44.190
## DisabilityStatus1 -0.37809 0.09786 50.95240 -3.863
## Accommodation 0.40364 0.01196 5732.74925 33.737
## DisabilityStatus1:Accommodation 0.05805 0.02827 5729.79323 2.054
## Pr(>|t|)
## (Intercept) 2.6e-16 ***
## DisabilityStatus1 0.000317 ***
## Accommodation < 2e-16 ***
## DisabilityStatus1:Accommodation 0.040033 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) DsblS1 Accmmd
## DsbltyStts1 -0.591
## Accommodatn -0.561 0.388
## DsbltySt1:A 0.235 -0.849 -0.423
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')interact_plot(model_mgr_effect, pred = DisabilityStatus, modx = Accommodation,
main.title = "Interaction: Disability Status × Accommodations on Manager Effectiveness")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
summary(model_leadership) ## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## LeadershipCommitment ~ DisabilityStatus * Accommodation + (DisabilityStatus |
## company_mapped)
## Data: df
##
## REML criterion at convergence: 10824.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.5885 -0.5448 -0.1102 0.6653 4.3474
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.0094001 0.09695
## DisabilityStatus1 0.0005187 0.02277 -1.00
## Residual 0.3841891 0.61983
## Number of obs: 5737, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df t value
## (Intercept) 1.950e+00 5.261e-02 1.311e+01 37.066
## DisabilityStatus1 -4.851e-01 7.267e-02 7.046e+02 -6.675
## Accommodation 5.129e-01 9.789e-03 5.732e+03 52.397
## DisabilityStatus1:Accommodation 9.327e-02 2.314e-02 5.727e+03 4.031
## Pr(>|t|)
## (Intercept) 1.16e-14 ***
## DisabilityStatus1 5.01e-11 ***
## Accommodation < 2e-16 ***
## DisabilityStatus1:Accommodation 5.62e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) DsblS1 Accmmd
## DsbltyStts1 -0.380
## Accommodatn -0.591 0.428
## DsbltySt1:A 0.242 -0.936 -0.422
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')interact_plot(model_leadership, pred = DisabilityStatus, modx = Accommodation,
main.title = "Interaction: Disability Status × Accommodations on Leadership Commitment")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
Mental Health Status x Accommodations (Employee Survey) –> Outcomes
# Accommodations (Level 1)
model_engagement <- lmer(Engagement ~ MentalHealth_status_binary * Accommodation + (MentalHealth_status_binary | company_mapped), data = df)
model_accessibility <- lmer(Accessibility ~ MentalHealth_status_binary * Accommodation + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_psychsafety <- lmer(PsychSafety ~ MentalHealth_status_binary * Accommodation + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ MentalHealth_status_binary * Accommodation + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_orgcommit <- lmer(OrgCommitment ~ MentalHealth_status_binary * Accommodation + (MentalHealth_status_binary | company_mapped), data = df)
model_mgr_effect <- lmer(ManagerEffectiveness ~ MentalHealth_status_binary * Accommodation + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_leadership <- lmer(LeadershipCommitment ~ MentalHealth_status_binary * Accommodation + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_career <- lmer(CareerExperience ~ MentalHealth_status_binary * Accommodation + (MentalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')summary(model_psychsafety)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## PsychSafety ~ MentalHealth_status_binary * Accommodation + (MentalHealth_status_binary |
## company_mapped)
## Data: df
##
## REML criterion at convergence: 12345.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.3405 -0.4769 0.0718 0.6327 3.6171
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 5.313e-03 0.072892
## MentalHealth_status_binary1 6.852e-05 0.008278 1.00
## Residual 4.994e-01 0.706714
## Number of obs: 5746, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 2.33774 0.05119 22.98080
## MentalHealth_status_binary1 -0.39892 0.07493 1748.64887
## Accommodation 0.51505 0.01152 5738.28953
## MentalHealth_status_binary1:Accommodation 0.07104 0.02424 5733.82876
## t value Pr(>|t|)
## (Intercept) 45.668 < 2e-16 ***
## MentalHealth_status_binary1 -5.324 1.15e-07 ***
## Accommodation 44.727 < 2e-16 ***
## MentalHealth_status_binary1:Accommodation 2.930 0.0034 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) MnH__1 Accmmd
## MntlHlth__1 -0.349
## Accommodatn -0.723 0.492
## MntlHl__1:A 0.336 -0.947 -0.474
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')interact_plot(model_psychsafety, pred = MentalHealth_status_binary, modx = Accommodation,
main.title = "Interaction: Mental Health Status × Accommodations on Psych Safety")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
summary(model_mgr_effect)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: ManagerEffectiveness ~ MentalHealth_status_binary * Accommodation +
## (MentalHealth_status_binary | company_mapped)
## Data: df
##
## REML criterion at convergence: 13113.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.8425 -0.4893 0.1211 0.7138 2.6271
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.0152713 0.12358
## MentalHealth_status_binary1 0.0005445 0.02333 -1.00
## Residual 0.5705852 0.75537
## Number of obs: 5746, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 3.01780 0.06658 14.44439
## MentalHealth_status_binary1 -0.34047 0.08060 536.49821
## Accommodation 0.39412 0.01231 5739.94248
## MentalHealth_status_binary1:Accommodation 0.05237 0.02591 5736.19962
## t value Pr(>|t|)
## (Intercept) 45.328 < 2e-16 ***
## MentalHealth_status_binary1 -4.224 2.82e-05 ***
## Accommodation 32.008 < 2e-16 ***
## MentalHealth_status_binary1:Accommodation 2.021 0.0433 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) MnH__1 Accmmd
## MntlHlth__1 -0.410
## Accommodatn -0.595 0.489
## MntlHl__1:A 0.277 -0.939 -0.474
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')interact_plot(model_mgr_effect, pred = MentalHealth_status_binary, modx = Accommodation,
main.title = "Interaction: Mental Health Status × Accommodations on Manager Effectiveness")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
summary(model_leadership) ## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: LeadershipCommitment ~ MentalHealth_status_binary * Accommodation +
## (MentalHealth_status_binary | company_mapped)
## Data: df
##
## REML criterion at convergence: 10831.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.6079 -0.5650 -0.0975 0.6512 4.8744
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.0060784 0.07796
## MentalHealth_status_binary1 0.0006621 0.02573 1.00
## Residual 0.3835192 0.61929
## Number of obs: 5746, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 1.96440 0.04777 22.48732
## MentalHealth_status_binary1 -0.37811 0.06653 449.63980
## Accommodation 0.50689 0.01009 5739.76419
## MentalHealth_status_binary1:Accommodation 0.07217 0.02125 5734.82043
## t value Pr(>|t|)
## (Intercept) 41.119 < 2e-16 ***
## MentalHealth_status_binary1 -5.684 2.37e-08 ***
## Accommodation 50.228 < 2e-16 ***
## MentalHealth_status_binary1:Accommodation 3.397 0.000687 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) MnH__1 Accmmd
## MntlHlth__1 -0.235
## Accommodatn -0.679 0.485
## MntlHl__1:A 0.314 -0.935 -0.473
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')interact_plot(model_leadership, pred = MentalHealth_status_binary, modx = Accommodation,
main.title = "Interaction: Mental Health Status × Accommodations on Leadership Commitment")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
Physical Health Status x Accommodations (Employee Survey) –> Outcomes
# Accommodations (Level 1)
model_engagement <- lmer(Engagement ~ PhysicalHealth_status_binary * Accommodation + (PhysicalHealth_status_binary | company_mapped), data = df)
model_accessibility <- lmer(Accessibility ~ PhysicalHealth_status_binary * Accommodation + (PhysicalHealth_status_binary | company_mapped), data = df)
model_psychsafety <- lmer(PsychSafety ~ PhysicalHealth_status_binary * Accommodation + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_people <- lmer(PeoplePractices ~ PhysicalHealth_status_binary * Accommodation + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_orgcommit <- lmer(OrgCommitment ~ PhysicalHealth_status_binary * Accommodation + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_mgr_effect <- lmer(ManagerEffectiveness ~ PhysicalHealth_status_binary * Accommodation + (PhysicalHealth_status_binary | company_mapped), data = df)
model_leadership <- lmer(LeadershipCommitment ~ PhysicalHealth_status_binary * Accommodation + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')model_career <- lmer(CareerExperience ~ PhysicalHealth_status_binary * Accommodation + (PhysicalHealth_status_binary | company_mapped), data = df)## boundary (singular) fit: see help('isSingular')summary(model_psychsafety)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: PsychSafety ~ PhysicalHealth_status_binary * Accommodation +
## (PhysicalHealth_status_binary | company_mapped)
## Data: df
##
## REML criterion at convergence: 12342.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.3516 -0.4743 0.1021 0.6312 3.5586
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.0055196 0.07429
## PhysicalHealth_status_binary1 0.0001624 0.01274 1.00
## Residual 0.4991100 0.70648
## Number of obs: 5746, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 2.31684 0.05162 19.16708
## PhysicalHealth_status_binary1 -0.32291 0.07335 539.50392
## Accommodation 0.52023 0.01167 5736.92988
## PhysicalHealth_status_binary1:Accommodation 0.04603 0.02364 5732.25092
## t value Pr(>|t|)
## (Intercept) 44.880 < 2e-16 ***
## PhysicalHealth_status_binary1 -4.402 1.29e-05 ***
## Accommodation 44.582 < 2e-16 ***
## PhysicalHealth_status_binary1:Accommodation 1.947 0.0516 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PhH__1 Accmmd
## PhysclHl__1 -0.339
## Accommodatn -0.724 0.511
## PhyscH__1:A 0.348 -0.947 -0.493
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')interact_plot(model_psychsafety, pred = PhysicalHealth_status_binary, modx = Accommodation,
main.title = "Interaction: Physical Health Status × Accommodations on Psych Safety")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.
summary(model_mgr_effect)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: ManagerEffectiveness ~ PhysicalHealth_status_binary * Accommodation +
## (PhysicalHealth_status_binary | company_mapped)
## Data: df
##
## REML criterion at convergence: 13125.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.8523 -0.4835 0.1397 0.7002 2.6325
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## company_mapped (Intercept) 0.01236 0.1112
## PhysicalHealth_status_binary1 0.01434 0.1197 0.19
## Residual 0.57142 0.7559
## Number of obs: 5746, groups: company_mapped, 7
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) 3.00254 0.06376 15.82504
## PhysicalHealth_status_binary1 -0.30427 0.10300 4.66710
## Accommodation 0.39447 0.01249 5729.31422
## PhysicalHealth_status_binary1:Accommodation 0.04770 0.02532 5684.54795
## t value Pr(>|t|)
## (Intercept) 47.094 <2e-16 ***
## PhysicalHealth_status_binary1 -2.954 0.0345 *
## Accommodation 31.584 <2e-16 ***
## PhysicalHealth_status_binary1:Accommodation 1.884 0.0597 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) PhH__1 Accmmd
## PhysclHl__1 -0.270
## Accommodatn -0.627 0.387
## PhyscH__1:A 0.306 -0.737 -0.493interact_plot(model_mgr_effect, pred = PhysicalHealth_status_binary, modx = Accommodation,
main.title = "Interaction: Physical Health Status × Accommodations on Manager Effectiveness")## ✖ Detected factor predictor.
## ℹ Plotting with cat_plot() instead.
## ℹ See `?interactions::cat_plot()` for full details on how to specify models
## with categorical predictors.
## ℹ If you experience errors or unexpected results, try using cat_plot()
## directly.