library(readxl)
library(mediation) #Mediation package
## Warning: package 'mediation' was built under R version 4.0.4
## Loading required package: MASS
## Warning: package 'MASS' was built under R version 4.0.5
## Loading required package: Matrix
## Warning: package 'Matrix' was built under R version 4.0.5
## Loading required package: mvtnorm
## Loading required package: sandwich
## Registered S3 methods overwritten by 'tibble':
## method from
## format.tbl pillar
## print.tbl pillar
## mediation: Causal Mediation Analysis
## Version: 4.5.0
library(rockchalk) #Graphing simple slopes; moderation
## Warning: package 'rockchalk' was built under R version 4.0.4
##
## Attaching package: 'rockchalk'
## The following object is masked from 'package:MASS':
##
## mvrnorm
library(multilevel) #Sobel Test
## Warning: package 'multilevel' was built under R version 4.0.4
## Loading required package: nlme
library(bda) #Another Sobel Test option
## Warning: package 'bda' was built under R version 4.0.5
## Loading required package: boot
## bda v15 (Bin Wang, 2021)
library(MeMoBootR)
## Loading required package: diagram
## Loading required package: shape
## Loading required package: ggplot2
## Warning: package 'ggplot2' was built under R version 4.0.5
library(gvlma) #Testing Model Assumptions
library(stargazer) #Handy regression tables
##
## Please cite as:
## Hlavac, Marek (2018). stargazer: Well-Formatted Regression and Summary Statistics Tables.
## R package version 5.2.2. https://CRAN.R-project.org/package=stargazer
library(dplyr)
##
## Attaching package: 'dplyr'
## The following object is masked from 'package:nlme':
##
## collapse
## The following object is masked from 'package:rockchalk':
##
## summarize
## The following object is masked from 'package:MASS':
##
## select
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(car)
## Loading required package: carData
## Registered S3 methods overwritten by 'car':
## method from
## influence.merMod lme4
## cooks.distance.influence.merMod lme4
## dfbeta.influence.merMod lme4
## dfbetas.influence.merMod lme4
##
## Attaching package: 'car'
## The following object is masked from 'package:dplyr':
##
## recode
## The following object is masked from 'package:boot':
##
## logit
LEEP_covid <- read.csv("C:/Users/u6032404/OneDrive/backup 9.9.19/MJ/LEEP/QOL/LEEP_covidbig.csv")
LEEP_covid$Fear_seizure<-Recode(LEEP_covid$Fear_seizure, recodes="'Increased'=1;else=0",as.numeric=T)
LEEP_covid$health_conditions<-Recode(LEEP_covid$health_conditions, recodes="'Increased'=1;else=0",as.numeric=T)
#LEEP_covid[LEEP_covid=="No change"]<-0
LEEP_covid[LEEP_covid=="Not applicable"]<-"No change"
#LEEP_covid[LEEP_covid=="Decreased"]<- -1
#LEEP_covid[LEEP_covid=="Increased"]<- 1
#LEEP_covid[]<-lapply(LEEP_covid, function(x) as.numeric(as.character(x)))
LEEP_covid<-LEEP_covid %>%
filter(!Financial%in%c("Decline to answer", "Don’t know"))
LEEP_covid$f_3<-Recode(LEEP_covid$Financial
,recodes="'You have money to pay the bills, but only because you have to cut back on things.'=2;'You have enough money to pay the bills, but little spare money to buy extra or special things.'= 3;'You are having difficulty paying the bills, no matter what you do.'=1;'After paying the bills, you still have enough money for special things that you want.'= 3 ",as.numeric=T)
LEEP_covid$f_2<-Recode(LEEP_covid$Financial
,recodes="'You are having difficulty paying the bills, no matter what you do.'=0; else = 1 ",as.numeric=T)
Access PHC
LEEP_covid$Access_physicalhealthcare = as.factor(LEEP_covid$Access_physicalhealthcare)
LEEP_covid$Access_physicalhealthcare<-relevel(LEEP_covid$Access_physicalhealthcare, ref = "No change")
saved = mediation1(y = "Fear_seizure", #DV
x = "Access_physicalhealthcare", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept)
## (Intercept) 1.0000000
## Access_physicalhealthcareDecreased -0.3790685
## Access_physicalhealthcareIncreased -0.1405875
## f_3 -0.9169822
## Access_physicalhealthcareDecreased
## (Intercept) -0.3790685
## Access_physicalhealthcareDecreased 1.0000000
## Access_physicalhealthcareIncreased 0.2407239
## f_3 0.1566061
## Access_physicalhealthcareIncreased
## (Intercept) -0.14058753
## Access_physicalhealthcareDecreased 0.24072387
## Access_physicalhealthcareIncreased 1.00000000
## f_3 -0.02725982
## f_3
## (Intercept) -0.91698224
## Access_physicalhealthcareDecreased 0.15660609
## Access_physicalhealthcareIncreased -0.02725982
## f_3 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5875 -0.2361 -0.2361 0.4125 0.7639
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.23611 0.03813 6.192 2.41e-09 ***
## Access_physicalhealthcareDecreased 0.35139 0.06381 5.507 9.03e-08 ***
## Access_physicalhealthcareIncreased 0.16389 0.09184 1.785 0.0755 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4576 on 251 degrees of freedom
## Multiple R-squared: 0.1084, Adjusted R-squared: 0.1013
## F-statistic: 15.26 on 2 and 251 DF, p-value: 5.589e-07
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.5000 -0.4306 0.5000 0.5694 0.8500
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.43056 0.06674 36.417 <2e-16 ***
## Access_physicalhealthcareDecreased -0.28056 0.11168 -2.512 0.0126 *
## Access_physicalhealthcareIncreased 0.06944 0.16074 0.432 0.6661
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8009 on 251 degrees of freedom
## Multiple R-squared: 0.029, Adjusted R-squared: 0.02127
## F-statistic: 3.749 on 2 and 251 DF, p-value: 0.02487
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6781 -0.3488 -0.1912 0.4795 0.8088
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.42766 0.09487 4.508 1.01e-05 ***
## Access_physicalhealthcareDecreased 0.32928 0.06412 5.136 5.66e-07 ***
## Access_physicalhealthcareIncreased 0.16936 0.09118 1.858 0.0644 .
## f_3 -0.07881 0.03579 -2.202 0.0286 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4541 on 250 degrees of freedom
## Multiple R-squared: 0.1253, Adjusted R-squared: 0.1149
## F-statistic: 11.94 on 3 and 250 DF, p-value: 2.467e-07
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.3513889 0.1638889
## [1] 0.3292782 0.1693618
## [1] 0.022110655 -0.005472934
#Sobel test
saved$z.score; saved$p.value
## [1] 1.5863461 -0.3872429
## [1] 0.1126608 0.6985764
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.022110655 -2.931684e-05 0.01438052
## t2* -0.005472934 -2.270169e-05 0.01392926
#bootstrapped CI
saved$boot.ci
## $Access_physicalhealthcareDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0060, 0.0503 )
## Calculations and Intervals on Original Scale
##
## $Access_physicalhealthcareIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0328, 0.0219 )
## Calculations and Intervals on Original Scale
LEEP_covid$Access_physicalhealthcare = as.factor(LEEP_covid$Access_physicalhealthcare)
LEEP_covid$Access_physicalhealthcare<-relevel(LEEP_covid$Access_physicalhealthcare, ref = "No change")
saved = mediation1(y = "health_conditions", #DV
x = "Access_physicalhealthcare", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept)
## (Intercept) 1.0000000
## Access_physicalhealthcareDecreased -0.3790685
## Access_physicalhealthcareIncreased -0.1405875
## f_3 -0.9169822
## Access_physicalhealthcareDecreased
## (Intercept) -0.3790685
## Access_physicalhealthcareDecreased 1.0000000
## Access_physicalhealthcareIncreased 0.2407239
## f_3 0.1566061
## Access_physicalhealthcareIncreased
## (Intercept) -0.14058753
## Access_physicalhealthcareDecreased 0.24072387
## Access_physicalhealthcareIncreased 1.00000000
## f_3 -0.02725982
## f_3
## (Intercept) -0.91698224
## Access_physicalhealthcareDecreased 0.15660609
## Access_physicalhealthcareIncreased -0.02725982
## f_3 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5250 -0.1667 -0.1667 0.4750 0.8333
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.16667 0.03618 4.606 6.52e-06 ***
## Access_physicalhealthcareDecreased 0.35833 0.06054 5.919 1.06e-08 ***
## Access_physicalhealthcareIncreased 0.26667 0.08714 3.060 0.00245 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4342 on 251 degrees of freedom
## Multiple R-squared: 0.1307, Adjusted R-squared: 0.1237
## F-statistic: 18.86 on 2 and 251 DF, p-value: 2.33e-08
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.5000 -0.4306 0.5000 0.5694 0.8500
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.43056 0.06674 36.417 <2e-16 ***
## Access_physicalhealthcareDecreased -0.28056 0.11168 -2.512 0.0126 *
## Access_physicalhealthcareIncreased 0.06944 0.16074 0.432 0.6661
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8009 on 251 degrees of freedom
## Multiple R-squared: 0.029, Adjusted R-squared: 0.02127
## F-statistic: 3.749 on 2 and 251 DF, p-value: 0.02487
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6545 -0.3278 -0.1025 0.3847 0.8975
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.44041 0.08890 4.954 1.34e-06 ***
## Access_physicalhealthcareDecreased 0.32674 0.06008 5.438 1.28e-07 ***
## Access_physicalhealthcareIncreased 0.27449 0.08544 3.213 0.001487 **
## f_3 -0.11263 0.03354 -3.358 0.000907 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4256 on 250 degrees of freedom
## Multiple R-squared: 0.1682, Adjusted R-squared: 0.1582
## F-statistic: 16.85 on 3 and 250 DF, p-value: 5.322e-10
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.3583333 0.2666667
## [1] 0.3267356 0.2744879
## [1] 0.031597713 -0.007821216
#Sobel test
saved$z.score; saved$p.value
## [1] 1.9566968 -0.4109563
## [1] 0.05038313 0.68110458
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.031597713 6.550328e-04 0.01701040
## t2* -0.007821216 -9.775035e-05 0.02041062
#bootstrapped CI
saved$boot.ci
## $Access_physicalhealthcareDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0024, 0.0643 )
## Calculations and Intervals on Original Scale
##
## $Access_physicalhealthcareIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0477, 0.0323 )
## Calculations and Intervals on Original Scale
Access MCH
LEEP_covid$Access_mentalhealthcare = as.factor(LEEP_covid$Access_mentalhealthcare)
LEEP_covid$Access_mentalhealthcare<-relevel(LEEP_covid$Access_mentalhealthcare, ref = "No change")
saved = mediation1(y = "Fear_seizure", #DV
x = "Access_mentalhealthcare", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Access_mentalhealthcareDecreased
## (Intercept) 1.0000000 -0.3590530
## Access_mentalhealthcareDecreased -0.3590530 1.0000000
## Access_mentalhealthcareIncreased -0.2134940 0.2614006
## f_3 -0.9116476 0.1101616
## Access_mentalhealthcareIncreased f_3
## (Intercept) -0.21349397 -0.91164757
## Access_mentalhealthcareDecreased 0.26140061 0.11016156
## Access_mentalhealthcareIncreased 1.00000000 0.05094917
## f_3 0.05094917 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.4835 -0.2647 -0.2647 0.5165 0.7353
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.26471 0.04048 6.539 3.44e-10 ***
## Access_mentalhealthcareDecreased 0.21881 0.06393 3.422 0.000725 ***
## Access_mentalhealthcareIncreased 0.21678 0.09946 2.179 0.030225 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4721 on 251 degrees of freedom
## Multiple R-squared: 0.0511, Adjusted R-squared: 0.04354
## F-statistic: 6.758 on 2 and 251 DF, p-value: 0.001384
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4338 -0.4338 0.5662 0.5662 0.7582
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.43382 0.06925 35.144 <2e-16 ***
## Access_mentalhealthcareDecreased -0.19207 0.10938 -1.756 0.0803 .
## Access_mentalhealthcareIncreased -0.13753 0.17016 -0.808 0.4197
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8076 on 251 degrees of freedom
## Multiple R-squared: 0.01266, Adjusted R-squared: 0.004795
## F-statistic: 1.609 on 2 and 251 DF, p-value: 0.202
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6011 -0.3970 -0.2125 0.5611 0.7875
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.48929 0.09746 5.021 9.8e-07 ***
## Access_mentalhealthcareDecreased 0.20109 0.06365 3.159 0.00178 **
## Access_mentalhealthcareIncreased 0.20409 0.09854 2.071 0.03937 *
## f_3 -0.09228 0.03651 -2.528 0.01210 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4671 on 250 degrees of freedom
## Multiple R-squared: 0.07475, Adjusted R-squared: 0.06364
## F-statistic: 6.732 on 3 and 250 DF, p-value: 0.0002196
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.2188106 0.2167756
## [1] 0.2010877 0.2040853
## [1] 0.01772286 0.01269035
#Sobel test
saved$z.score; saved$p.value
## [1] 1.3715653 0.7203926
## [1] 0.1701988 0.4712833
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.01772286 -0.0001085637 0.01301741
## t2* 0.01269035 -0.0013473399 0.01907658
#bootstrapped CI
saved$boot.ci
## $Access_mentalhealthcareDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0077, 0.0433 )
## Calculations and Intervals on Original Scale
##
## $Access_mentalhealthcareIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0234, 0.0514 )
## Calculations and Intervals on Original Scale
LEEP_covid$Access_mentalhealthcare = as.factor(LEEP_covid$Access_mentalhealthcare)
LEEP_covid$Access_mentalhealthcare<-relevel(LEEP_covid$Access_mentalhealthcare, ref = "No change")
saved = mediation1(y = "health_conditions", #DV
x = "Access_mentalhealthcare", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Access_mentalhealthcareDecreased
## (Intercept) 1.0000000 -0.3590530
## Access_mentalhealthcareDecreased -0.3590530 1.0000000
## Access_mentalhealthcareIncreased -0.2134940 0.2614006
## f_3 -0.9116476 0.1101616
## Access_mentalhealthcareIncreased f_3
## (Intercept) -0.21349397 -0.91164757
## Access_mentalhealthcareDecreased 0.26140061 0.11016156
## Access_mentalhealthcareIncreased 1.00000000 0.05094917
## f_3 0.05094917 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.4815 -0.1691 -0.1691 0.5275 0.8309
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.16912 0.03771 4.485 1.11e-05 ***
## Access_mentalhealthcareDecreased 0.30341 0.05955 5.095 6.87e-07 ***
## Access_mentalhealthcareIncreased 0.31236 0.09264 3.372 0.000865 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4397 on 251 degrees of freedom
## Multiple R-squared: 0.1083, Adjusted R-squared: 0.1012
## F-statistic: 15.25 on 2 and 251 DF, p-value: 5.625e-07
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4338 -0.4338 0.5662 0.5662 0.7582
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.43382 0.06925 35.144 <2e-16 ***
## Access_mentalhealthcareDecreased -0.19207 0.10938 -1.756 0.0803 .
## Access_mentalhealthcareIncreased -0.13753 0.17016 -0.808 0.4197
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8076 on 251 degrees of freedom
## Multiple R-squared: 0.01266, Adjusted R-squared: 0.004795
## F-statistic: 1.609 on 2 and 251 DF, p-value: 0.202
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6337 -0.3375 -0.1026 0.3816 0.8974
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.45493 0.08977 5.068 7.83e-07 ***
## Access_mentalhealthcareDecreased 0.28086 0.05862 4.791 2.85e-06 ***
## Access_mentalhealthcareIncreased 0.29621 0.09076 3.264 0.001254 **
## f_3 -0.11743 0.03362 -3.492 0.000566 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4302 on 250 degrees of freedom
## Multiple R-squared: 0.1498, Adjusted R-squared: 0.1396
## F-statistic: 14.68 on 3 and 250 DF, p-value: 7.735e-09
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.3034098 0.3123638
## [1] 0.2808552 0.2962138
## [1] 0.02255458 0.01615008
#Sobel test
saved$z.score; saved$p.value
## [1] 1.5198901 0.7584666
## [1] 0.1285386 0.4481717
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.02255458 -0.0002216568 0.01566331
## t2* 0.01615008 -0.0002443843 0.02310018
#bootstrapped CI
saved$boot.ci
## $Access_mentalhealthcareDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0079, 0.0535 )
## Calculations and Intervals on Original Scale
##
## $Access_mentalhealthcareIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0289, 0.0617 )
## Calculations and Intervals on Original Scale
Cancell MH
LEEP_covid$Q8.4 = as.factor(LEEP_covid$Q8.4)
LEEP_covid$Q8.4<-relevel(LEEP_covid$Q8.4, ref = "No")
saved = mediation1(y = "Fear_seizure", #DV
x = "Q8.4", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Q8.4Yes f_3
## (Intercept) 1.0000000 -0.29765406 -0.91985452
## Q8.4Yes -0.2976541 1.00000000 0.06331635
## f_3 -0.9198545 0.06331635 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5158 -0.2767 -0.2767 0.4842 0.7233
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.27673 0.03723 7.432 1.66e-12 ***
## Q8.4Yes 0.23906 0.06088 3.927 0.000111 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4695 on 252 degrees of freedom
## Multiple R-squared: 0.05765, Adjusted R-squared: 0.05391
## F-statistic: 15.42 on 1 and 252 DF, p-value: 0.0001113
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.3899 -0.3899 0.6101 0.6101 0.7158
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.3899 0.0642 37.226 <2e-16 ***
## Q8.4Yes -0.1057 0.1050 -1.007 0.315
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8095 on 252 degrees of freedom
## Multiple R-squared: 0.004009, Adjusted R-squared: 5.661e-05
## F-statistic: 1.014 on 1 and 252 DF, p-value: 0.3148
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6409 -0.4121 -0.2173 0.5539 0.7827
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.50948 0.09376 5.434 1.3e-07 ***
## Q8.4Yes 0.22876 0.06026 3.796 0.000184 ***
## f_3 -0.09739 0.03609 -2.699 0.007435 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4638 on 251 degrees of freedom
## Multiple R-squared: 0.08422, Adjusted R-squared: 0.07693
## F-statistic: 11.54 on 2 and 251 DF, p-value: 1.601e-05
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.2390599
## [1] 0.2287635
## [1] 0.01029644
#Sobel test
saved$z.score; saved$p.value
## [1] 0.8913799
## [1] 0.3727254
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.01029644 0.0005171643 0.01207756
#bootstrapped CI
saved$boot.ci
## $Q8.4Yes
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0139, 0.0335 )
## Calculations and Intervals on Original Scale
saved = mediation1(y = "health_conditions", #DV
x = "Q8.4", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Q8.4Yes f_3
## (Intercept) 1.0000000 -0.29765406 -0.91985452
## Q8.4Yes -0.2976541 1.00000000 0.06331635
## f_3 -0.9198545 0.06331635 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.4421 -0.2327 -0.2327 0.5579 0.7673
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.23270 0.03596 6.471 5.05e-10 ***
## Q8.4Yes 0.20940 0.05880 3.561 0.000442 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4535 on 252 degrees of freedom
## Multiple R-squared: 0.04791, Adjusted R-squared: 0.04413
## F-statistic: 12.68 on 1 and 252 DF, p-value: 0.0004416
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.3899 -0.3899 0.6101 0.6101 0.7158
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.3899 0.0642 37.226 <2e-16 ***
## Q8.4Yes -0.1057 0.1050 -1.007 0.315
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8095 on 252 degrees of freedom
## Multiple R-squared: 0.004009, Adjusted R-squared: 5.661e-05
## F-statistic: 1.014 on 1 and 252 DF, p-value: 0.3148
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6082 -0.3495 -0.1538 0.3918 0.8462
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.54188 0.08938 6.063 4.89e-09 ***
## Q8.4Yes 0.19572 0.05744 3.407 0.000764 ***
## f_3 -0.12936 0.03440 -3.760 0.000211 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4421 on 251 degrees of freedom
## Multiple R-squared: 0.09869, Adjusted R-squared: 0.0915
## F-statistic: 13.74 on 2 and 251 DF, p-value: 2.172e-06
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.2094009
## [1] 0.1957236
## [1] 0.01367723
#Sobel test
saved$z.score; saved$p.value
## [1] 0.9422588
## [1] 0.3460602
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.01367723 0.0006369633 0.01527829
#bootstrapped CI
saved$boot.ci
## $Q8.4Yes
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0169, 0.0430 )
## Calculations and Intervals on Original Scale
Fear Health Care
LEEP_covid$Fear_healthcare = as.factor(LEEP_covid$Fear_healthcare)
LEEP_covid$Fear_healthcare<-relevel(LEEP_covid$Fear_healthcare, ref = "No change")
saved = mediation1(y = "Fear_seizure", #DV
x = "Fear_healthcare", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Fear_healthcareDecreased
## (Intercept) 1.0000000 -0.11972559
## Fear_healthcareDecreased -0.1197256 1.00000000
## Fear_healthcareIncreased -0.3662152 0.21699247
## f_3 -0.9199859 -0.03568507
## Fear_healthcareIncreased f_3
## (Intercept) -0.3662152 -0.91998591
## Fear_healthcareDecreased 0.2169925 -0.03568507
## Fear_healthcareIncreased 1.0000000 0.15451053
## f_3 0.1545105 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6184 -0.2649 -0.2649 0.3816 0.7778
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.26490 0.03704 7.151 9.38e-12 ***
## Fear_healthcareDecreased -0.04268 0.09511 -0.449 0.654
## Fear_healthcareIncreased 0.35352 0.06402 5.522 8.35e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4552 on 251 degrees of freedom
## Multiple R-squared: 0.1178, Adjusted R-squared: 0.1108
## F-statistic: 16.76 on 2 and 251 DF, p-value: 1.475e-07
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.5185 -0.4238 0.4815 0.5762 0.8553
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.42384 0.06518 37.187 <2e-16 ***
## Fear_healthcareDecreased 0.09468 0.16736 0.566 0.5721
## Fear_healthcareIncreased -0.27910 0.11265 -2.478 0.0139 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.801 on 251 degrees of freedom
## Multiple R-squared: 0.0289, Adjusted R-squared: 0.02116
## F-statistic: 3.735 on 2 and 251 DF, p-value: 0.02521
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.7028 -0.2961 -0.2224 0.4446 0.8133
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.44354 0.09390 4.724 3.86e-06 ***
## Fear_healthcareDecreased -0.03570 0.09456 -0.378 0.7061
## Fear_healthcareIncreased 0.33295 0.06438 5.172 4.75e-07 ***
## f_3 -0.07370 0.03564 -2.068 0.0397 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4522 on 250 degrees of freedom
## Multiple R-squared: 0.1326, Adjusted R-squared: 0.1222
## F-statistic: 12.74 on 3 and 250 DF, p-value: 8.907e-08
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] -0.04267844 0.35352039
## [1] -0.03570071 0.33295040
## [1] -0.006977731 0.020569988
#Sobel test
saved$z.score; saved$p.value
## [1] -0.4945204 1.5164961
## [1] 0.6209387 0.1293940
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* -0.006977731 1.405698e-04 0.01342352
## t2* 0.020569988 -2.381353e-05 0.01450935
#bootstrapped CI
saved$boot.ci
## $Fear_healthcareDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0334, 0.0192 )
## Calculations and Intervals on Original Scale
##
## $Fear_healthcareIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0078, 0.0490 )
## Calculations and Intervals on Original Scale
# partial med
saved = mediation1(y = "health_conditions", #DV
x = "Fear_healthcare", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Fear_healthcareDecreased
## (Intercept) 1.0000000 -0.11972559
## Fear_healthcareDecreased -0.1197256 1.00000000
## Fear_healthcareIncreased -0.3662152 0.21699247
## f_3 -0.9199859 -0.03568507
## Fear_healthcareIncreased f_3
## (Intercept) -0.3662152 -0.91998591
## Fear_healthcareDecreased 0.2169925 -0.03568507
## Fear_healthcareIncreased 1.0000000 0.15451053
## f_3 0.1545105 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5395 -0.1920 -0.1920 0.4605 0.8079
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.19205 0.03570 5.379 1.71e-07 ***
## Fear_healthcareDecreased 0.14128 0.09167 1.541 0.125
## Fear_healthcareIncreased 0.34742 0.06170 5.631 4.80e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4387 on 251 degrees of freedom
## Multiple R-squared: 0.1124, Adjusted R-squared: 0.1053
## F-statistic: 15.89 on 2 and 251 DF, p-value: 3.178e-07
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.5185 -0.4238 0.4815 0.5762 0.8553
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.42384 0.06518 37.187 <2e-16 ***
## Fear_healthcareDecreased 0.09468 0.16736 0.566 0.5721
## Fear_healthcareIncreased -0.27910 0.11265 -2.478 0.0139 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.801 on 251 degrees of freedom
## Multiple R-squared: 0.0289, Adjusted R-squared: 0.02116
## F-statistic: 3.735 on 2 and 251 DF, p-value: 0.02521
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6667 -0.2798 -0.1280 0.3333 0.8720
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.46138 0.08937 5.162 4.98e-07 ***
## Fear_healthcareDecreased 0.15180 0.09000 1.687 0.0929 .
## Fear_healthcareIncreased 0.31641 0.06128 5.164 4.95e-07 ***
## f_3 -0.11112 0.03392 -3.276 0.0012 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4305 on 250 degrees of freedom
## Multiple R-squared: 0.1489, Adjusted R-squared: 0.1387
## F-statistic: 14.58 on 3 and 250 DF, p-value: 8.809e-09
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.1412804 0.3474207
## [1] 0.1518006 0.3164077
## [1] -0.01052021 0.03101304
#Sobel test
saved$z.score; saved$p.value
## [1] -0.533832 1.919949
## [1] 0.59345778 0.05486434
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* -0.01052021 -0.0003103916 0.01701795
## t2* 0.03101304 0.0003561664 0.01708586
#bootstrapped CI
saved$boot.ci
## $Fear_healthcareDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0436, 0.0231 )
## Calculations and Intervals on Original Scale
##
## $Fear_healthcareIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0028, 0.0641 )
## Calculations and Intervals on Original Scale
# partial med
use PHC
LEEP_covid$Use_health_care = as.factor(LEEP_covid$Use_health_care)
LEEP_covid$Use_health_care<-relevel(LEEP_covid$Use_health_care
, ref = "No change")
saved = mediation1(y = "Fear_seizure", #DV
x = "Use_health_care", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Use_health_careDecreased
## (Intercept) 1.0000000 -0.3639382
## Use_health_careDecreased -0.3639382 1.0000000
## Use_health_careIncreased -0.2989987 0.2792444
## f_3 -0.9192819 0.1486415
## Use_health_careIncreased f_3
## (Intercept) -0.2989987 -0.9192819
## Use_health_careDecreased 0.2792444 0.1486415
## Use_health_careIncreased 1.0000000 0.1328529
## f_3 0.1328529 1.0000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5135 -0.2587 -0.2587 0.4865 0.7413
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.25874 0.03920 6.600 2.42e-10 ***
## Use_health_careDecreased 0.25477 0.06713 3.795 0.000185 ***
## Use_health_careIncreased 0.22775 0.08646 2.634 0.008962 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4688 on 251 degrees of freedom
## Multiple R-squared: 0.06434, Adjusted R-squared: 0.05688
## F-statistic: 8.629 on 2 and 251 DF, p-value: 0.0002374
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4755 -0.4755 0.5245 0.5245 0.8378
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.4755 0.0669 37.002 <2e-16 ***
## Use_health_careDecreased -0.2728 0.1146 -2.381 0.0180 *
## Use_health_careIncreased -0.3134 0.1476 -2.124 0.0347 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8 on 251 degrees of freedom
## Multiple R-squared: 0.03114, Adjusted R-squared: 0.02342
## F-statistic: 4.034 on 2 and 251 DF, p-value: 0.01886
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6125 -0.3801 -0.2156 0.5002 0.7844
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.46239 0.09881 4.680 4.71e-06 ***
## Use_health_careDecreased 0.23233 0.06734 3.450 0.000658 ***
## Use_health_careIncreased 0.20197 0.08654 2.334 0.020406 *
## f_3 -0.08227 0.03669 -2.242 0.025832 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4651 on 250 degrees of freedom
## Multiple R-squared: 0.08278, Adjusted R-squared: 0.07177
## F-statistic: 7.521 on 3 and 250 DF, p-value: 7.734e-05
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.2547723 0.2277452
## [1] 0.2323284 0.2019663
## [1] 0.02244383 0.02577892
#Sobel test
saved$z.score; saved$p.value
## [1] 1.56109 1.46682
## [1] 0.1185024 0.1424251
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.02244383 -0.0004272486 0.01494527
## t2* 0.02577892 -0.0007923517 0.01796777
#bootstrapped CI
saved$boot.ci
## $Use_health_careDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0064, 0.0522 )
## Calculations and Intervals on Original Scale
##
## $Use_health_careIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0086, 0.0618 )
## Calculations and Intervals on Original Scale
# partial med
saved = mediation1(y = "health_conditions", #DV
x = "Use_health_care", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Use_health_careDecreased
## (Intercept) 1.0000000 -0.3639382
## Use_health_careDecreased -0.3639382 1.0000000
## Use_health_careIncreased -0.2989987 0.2792444
## f_3 -0.9192819 0.1486415
## Use_health_careIncreased f_3
## (Intercept) -0.2989987 -0.9192819
## Use_health_careDecreased 0.2792444 0.1486415
## Use_health_careIncreased 1.0000000 0.1328529
## f_3 0.1328529 1.0000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5405 -0.1678 -0.1678 0.4595 0.8322
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.16783 0.03642 4.608 6.46e-06 ***
## Use_health_careDecreased 0.30514 0.06237 4.893 1.78e-06 ***
## Use_health_careIncreased 0.37271 0.08033 4.640 5.62e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4355 on 251 degrees of freedom
## Multiple R-squared: 0.1253, Adjusted R-squared: 0.1184
## F-statistic: 17.98 on 2 and 251 DF, p-value: 5.024e-08
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4755 -0.4755 0.5245 0.5245 0.8378
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.4755 0.0669 37.002 <2e-16 ***
## Use_health_careDecreased -0.2728 0.1146 -2.381 0.0180 *
## Use_health_careIncreased -0.3134 0.1476 -2.124 0.0347 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8 on 251 degrees of freedom
## Multiple R-squared: 0.03114, Adjusted R-squared: 0.02342
## F-statistic: 4.034 on 2 and 251 DF, p-value: 0.01886
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6617 -0.3217 -0.1132 0.4016 0.8869
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.42595 0.09100 4.681 4.69e-06 ***
## Use_health_careDecreased 0.27669 0.06202 4.461 1.23e-05 ***
## Use_health_careIncreased 0.34004 0.07970 4.266 2.82e-05 ***
## f_3 -0.10427 0.03379 -3.086 0.00226 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4283 on 250 degrees of freedom
## Multiple R-squared: 0.1574, Adjusted R-squared: 0.1473
## F-statistic: 15.57 on 3 and 250 DF, p-value: 2.575e-09
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.3051408 0.3727084
## [1] 0.2766948 0.3400353
## [1] 0.02844605 0.03267305
#Sobel test
saved$z.score; saved$p.value
## [1] 1.826068 1.690143
## [1] 0.06783997 0.09100051
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.02844605 0.0009175431 0.01682361
## t2* 0.03267305 -0.0005004971 0.02132520
#bootstrapped CI
saved$boot.ci
## $Use_health_careDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0054, 0.0605 )
## Calculations and Intervals on Original Scale
##
## $Use_health_careIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0086, 0.0750 )
## Calculations and Intervals on Original Scale
# partial med
use MHC
LEEP_covid$Use_mental_health_care = as.factor(LEEP_covid$Use_mental_health_care)
LEEP_covid$Use_mental_health_care<-relevel(LEEP_covid$Use_mental_health_care
, ref = "No change")
saved = mediation1(y = "Fear_seizure", #DV
x = "Use_mental_health_care", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Use_mental_health_careDecreased
## (Intercept) 1.0000000 -0.3225374
## Use_mental_health_careDecreased -0.3225374 1.0000000
## Use_mental_health_careIncreased -0.2353129 0.2088484
## f_3 -0.9239681 0.1196383
## Use_mental_health_careIncreased f_3
## (Intercept) -0.2353129 -0.9239681
## Use_mental_health_careDecreased 0.2088484 0.1196383
## Use_mental_health_careIncreased 1.0000000 0.1083908
## f_3 0.1083908 1.0000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6087 -0.2830 -0.2830 0.5278 0.7170
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.28302 0.03735 7.577 6.82e-13 ***
## Use_mental_health_careDecreased 0.18920 0.06691 2.828 0.00507 **
## Use_mental_health_careIncreased 0.32568 0.10508 3.099 0.00216 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.471 on 251 degrees of freedom
## Multiple R-squared: 0.05534, Adjusted R-squared: 0.04781
## F-statistic: 7.351 on 2 and 251 DF, p-value: 0.0007895
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4403 -0.4402 0.5597 0.5597 0.8696
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.44025 0.06376 38.273 <2e-16 ***
## Use_mental_health_careDecreased -0.21803 0.11420 -1.909 0.0574 .
## Use_mental_health_careIncreased -0.30982 0.17935 -1.727 0.0853 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.804 on 251 degrees of freedom
## Multiple R-squared: 0.02159, Adjusted R-squared: 0.01379
## F-statistic: 2.769 on 2 and 251 DF, p-value: 0.06465
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.7076 -0.3215 -0.2341 0.5083 0.7660
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.49650 0.09676 5.131 5.79e-07 ***
## Use_mental_health_careDecreased 0.17013 0.06677 2.548 0.01143 *
## Use_mental_health_careIncreased 0.29857 0.10472 2.851 0.00472 **
## f_3 -0.08748 0.03664 -2.388 0.01769 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4667 on 250 degrees of freedom
## Multiple R-squared: 0.0764, Adjusted R-squared: 0.06532
## F-statistic: 6.893 on 3 and 250 DF, p-value: 0.0001773
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.1892034 0.3256768
## [1] 0.1701293 0.2985729
## [1] 0.01907401 0.02710392
#Sobel test
saved$z.score; saved$p.value
## [1] 1.417221 1.325344
## [1] 0.1564184 0.1850571
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.01907401 -0.0001448414 0.01365651
## t2* 0.02710392 -0.0003375116 0.02154129
#bootstrapped CI
saved$boot.ci
## $Use_mental_health_careDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0075, 0.0460 )
## Calculations and Intervals on Original Scale
##
## $Use_mental_health_careIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0148, 0.0697 )
## Calculations and Intervals on Original Scale
# partial med
saved = mediation1(y = "health_conditions", #DV
x = "Use_health_care", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Use_health_careDecreased
## (Intercept) 1.0000000 -0.3639382
## Use_health_careDecreased -0.3639382 1.0000000
## Use_health_careIncreased -0.2989987 0.2792444
## f_3 -0.9192819 0.1486415
## Use_health_careIncreased f_3
## (Intercept) -0.2989987 -0.9192819
## Use_health_careDecreased 0.2792444 0.1486415
## Use_health_careIncreased 1.0000000 0.1328529
## f_3 0.1328529 1.0000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5405 -0.1678 -0.1678 0.4595 0.8322
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.16783 0.03642 4.608 6.46e-06 ***
## Use_health_careDecreased 0.30514 0.06237 4.893 1.78e-06 ***
## Use_health_careIncreased 0.37271 0.08033 4.640 5.62e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4355 on 251 degrees of freedom
## Multiple R-squared: 0.1253, Adjusted R-squared: 0.1184
## F-statistic: 17.98 on 2 and 251 DF, p-value: 5.024e-08
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4755 -0.4755 0.5245 0.5245 0.8378
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.4755 0.0669 37.002 <2e-16 ***
## Use_health_careDecreased -0.2728 0.1146 -2.381 0.0180 *
## Use_health_careIncreased -0.3134 0.1476 -2.124 0.0347 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8 on 251 degrees of freedom
## Multiple R-squared: 0.03114, Adjusted R-squared: 0.02342
## F-statistic: 4.034 on 2 and 251 DF, p-value: 0.01886
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6617 -0.3217 -0.1132 0.4016 0.8869
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.42595 0.09100 4.681 4.69e-06 ***
## Use_health_careDecreased 0.27669 0.06202 4.461 1.23e-05 ***
## Use_health_careIncreased 0.34004 0.07970 4.266 2.82e-05 ***
## f_3 -0.10427 0.03379 -3.086 0.00226 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4283 on 250 degrees of freedom
## Multiple R-squared: 0.1574, Adjusted R-squared: 0.1473
## F-statistic: 15.57 on 3 and 250 DF, p-value: 2.575e-09
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.3051408 0.3727084
## [1] 0.2766948 0.3400353
## [1] 0.02844605 0.03267305
#Sobel test
saved$z.score; saved$p.value
## [1] 1.826068 1.690143
## [1] 0.06783997 0.09100051
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.02844605 -0.0004792670 0.01608376
## t2* 0.03267305 -0.0003574007 0.01981415
#bootstrapped CI
saved$boot.ci
## $Use_health_careDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0026, 0.0604 )
## Calculations and Intervals on Original Scale
##
## $Use_health_careIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0058, 0.0719 )
## Calculations and Intervals on Original Scale
# partial med
Social_isolation
LEEP_covid$Social_isolation = as.factor(LEEP_covid$Social_isolation)
LEEP_covid$Social_isolation<-relevel(LEEP_covid$Social_isolation
, ref = "No change")
saved = mediation1(y = "Fear_seizure", #DV
x = "Social_isolation", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Social_isolationDecreased
## (Intercept) 1.0000000 -0.25911444
## Social_isolationDecreased -0.2591144 1.00000000
## Social_isolationIncreased -0.4184725 0.38080791
## f_3 -0.8789790 0.02045341
## Social_isolationIncreased f_3
## (Intercept) -0.41847255 -0.87897897
## Social_isolationDecreased 0.38080791 0.02045341
## Social_isolationIncreased 1.00000000 0.06905238
## f_3 0.06905238 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.4800 -0.4800 -0.2708 0.5200 0.7879
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.27083 0.04807 5.634 4.7e-08 ***
## Social_isolationDecreased -0.05871 0.09504 -0.618 0.53728
## Social_isolationIncreased 0.20917 0.06391 3.273 0.00122 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.471 on 251 degrees of freedom
## Multiple R-squared: 0.05556, Adjusted R-squared: 0.04804
## F-statistic: 7.383 on 2 and 251 DF, p-value: 0.000766
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4167 -0.4167 0.5833 0.7040 0.7040
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.41667 0.08275 29.203 <2e-16 ***
## Social_isolationDecreased -0.05303 0.16362 -0.324 0.746
## Social_isolationIncreased -0.12067 0.11004 -1.097 0.274
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8108 on 251 degrees of freedom
## Multiple R-squared: 0.004808, Adjusted R-squared: -0.003122
## F-statistic: 0.6063 on 2 and 251 DF, p-value: 0.5461
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6068 -0.4112 -0.2138 0.4910 0.8501
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.50718 0.09956 5.094 6.9e-07 ***
## Social_isolationDecreased -0.06390 0.09389 -0.681 0.49676
## Social_isolationIncreased 0.19737 0.06328 3.119 0.00203 **
## f_3 -0.09780 0.03621 -2.701 0.00739 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4652 on 250 degrees of freedom
## Multiple R-squared: 0.08234, Adjusted R-squared: 0.07133
## F-statistic: 7.477 on 3 and 250 DF, p-value: 8.193e-05
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] -0.05871212 0.20916667
## [1] -0.0638985 0.1973654
## [1] 0.005186382 0.011801242
#Sobel test
saved$z.score; saved$p.value
## [1] 0.3020391 0.9610729
## [1] 0.7626223 0.3365155
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.005186382 2.140873e-04 0.01678141
## t2* 0.011801242 5.100572e-05 0.01194803
#bootstrapped CI
saved$boot.ci
## $Social_isolationDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0279, 0.0379 )
## Calculations and Intervals on Original Scale
##
## $Social_isolationIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0117, 0.0352 )
## Calculations and Intervals on Original Scale
# partial med
saved = mediation1(y = "health_conditions", #DV
x = "Social_isolation", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Social_isolationDecreased
## (Intercept) 1.0000000 -0.25911444
## Social_isolationDecreased -0.2591144 1.00000000
## Social_isolationIncreased -0.4184725 0.38080791
## f_3 -0.8789790 0.02045341
## Social_isolationIncreased f_3
## (Intercept) -0.41847255 -0.87897897
## Social_isolationDecreased 0.38080791 0.02045341
## Social_isolationIncreased 1.00000000 0.06905238
## f_3 0.06905238 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.4640 -0.4640 -0.1146 0.5360 0.8854
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.11458 0.04454 2.573 0.0107 *
## Social_isolationDecreased 0.18845 0.08806 2.140 0.0333 *
## Social_isolationIncreased 0.34942 0.05922 5.900 1.17e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4364 on 251 degrees of freedom
## Multiple R-squared: 0.1218, Adjusted R-squared: 0.1148
## F-statistic: 17.41 on 2 and 251 DF, p-value: 8.284e-08
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4167 -0.4167 0.5833 0.7040 0.7040
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.41667 0.08275 29.203 <2e-16 ***
## Social_isolationDecreased -0.05303 0.16362 -0.324 0.746
## Social_isolationIncreased -0.12067 0.11004 -1.097 0.274
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8108 on 251 degrees of freedom
## Multiple R-squared: 0.004808, Adjusted R-squared: -0.003122
## F-statistic: 0.6063 on 2 and 251 DF, p-value: 0.5461
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.62412 -0.37702 -0.04251 0.37588 0.95749
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.41316 0.09109 4.536 8.91e-06 ***
## Social_isolationDecreased 0.18190 0.08590 2.118 0.035193 *
## Social_isolationIncreased 0.33451 0.05789 5.778 2.24e-08 ***
## f_3 -0.12355 0.03313 -3.729 0.000238 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4256 on 250 degrees of freedom
## Multiple R-squared: 0.1681, Adjusted R-squared: 0.1581
## F-statistic: 16.84 on 3 and 250 DF, p-value: 5.38e-10
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.1884470 0.3494167
## [1] 0.1818952 0.3345085
## [1] 0.006551817 0.014908192
#Sobel test
saved$z.score; saved$p.value
## [1] 0.3119543 1.0188957
## [1] 0.7550753 0.3082525
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.006551817 0.0017829679 0.02024823
## t2* 0.014908192 0.0008849292 0.01530608
#bootstrapped CI
saved$boot.ci
## $Social_isolationDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0349, 0.0445 )
## Calculations and Intervals on Original Scale
##
## $Social_isolationIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.016, 0.044 )
## Calculations and Intervals on Original Scale
# partial med
Control_over_life
LEEP_covid$Control_over_life = as.factor(LEEP_covid$Control_over_life)
LEEP_covid$Control_over_life<-relevel(LEEP_covid$Control_over_life
, ref = "No change")
saved = mediation1(y = "Fear_seizure", #DV
x = "Control_over_life", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Control_over_lifeDecreased
## (Intercept) 1.0000000 -0.4097094
## Control_over_lifeDecreased -0.4097094 1.0000000
## Control_over_lifeIncreased -0.3226105 0.3110107
## f_3 -0.9081582 0.1400393
## Control_over_lifeIncreased f_3
## (Intercept) -0.3226105 -0.9081582
## Control_over_lifeDecreased 0.3110107 0.1400393
## Control_over_lifeIncreased 1.0000000 0.1579175
## f_3 0.1579175 1.0000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5000 -0.4762 -0.2397 0.5238 0.7603
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.23967 0.04265 5.620 5.07e-08 ***
## Control_over_lifeDecreased 0.23652 0.06257 3.780 0.000196 ***
## Control_over_lifeIncreased 0.26033 0.09838 2.646 0.008656 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4691 on 251 degrees of freedom
## Multiple R-squared: 0.06291, Adjusted R-squared: 0.05545
## F-statistic: 8.426 on 2 and 251 DF, p-value: 0.0002873
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4959 -0.4959 0.5041 0.5041 0.9286
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.49587 0.07262 34.369 <2e-16 ***
## Control_over_lifeDecreased -0.23872 0.10654 -2.241 0.0259 *
## Control_over_lifeIncreased -0.42444 0.16752 -2.534 0.0119 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7988 on 251 degrees of freedom
## Multiple R-squared: 0.03409, Adjusted R-squared: 0.02639
## F-statistic: 4.429 on 2 and 251 DF, p-value: 0.01287
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5886 -0.4148 -0.1980 0.5026 0.8020
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.44595 0.10106 4.413 1.52e-05 ***
## Control_over_lifeDecreased 0.21679 0.06269 3.458 0.000639 ***
## Control_over_lifeIncreased 0.22525 0.09884 2.279 0.023509 *
## f_3 -0.08265 0.03677 -2.248 0.025478 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4654 on 250 degrees of freedom
## Multiple R-squared: 0.08147, Adjusted R-squared: 0.07045
## F-statistic: 7.392 on 3 and 250 DF, p-value: 9.171e-05
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.2365211 0.2603306
## [1] 0.2167906 0.2252509
## [1] 0.01973047 0.03507964
#Sobel test
saved$z.score; saved$p.value
## [1] 1.513479 1.612531
## [1] 0.1301581 0.1068465
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.01973047 -0.0001077263 0.01310425
## t2* 0.03507964 -0.0006944995 0.02141036
#bootstrapped CI
saved$boot.ci
## $Control_over_lifeDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0058, 0.0455 )
## Calculations and Intervals on Original Scale
##
## $Control_over_lifeIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0062, 0.0777 )
## Calculations and Intervals on Original Scale
# partial med
saved = mediation1(y = "health_conditions", #DV
x = "Control_over_life", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Control_over_lifeDecreased
## (Intercept) 1.0000000 -0.4097094
## Control_over_lifeDecreased -0.4097094 1.0000000
## Control_over_lifeIncreased -0.3226105 0.3110107
## f_3 -0.9081582 0.1400393
## Control_over_lifeIncreased f_3
## (Intercept) -0.3226105 -0.9081582
## Control_over_lifeDecreased 0.3110107 0.1400393
## Control_over_lifeIncreased 1.0000000 0.1579175
## f_3 0.1579175 1.0000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5000 -0.4571 -0.1405 0.5429 0.8595
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.14050 0.03962 3.546 0.000466 ***
## Control_over_lifeDecreased 0.31665 0.05812 5.448 1.22e-07 ***
## Control_over_lifeIncreased 0.35950 0.09139 3.934 0.000108 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4358 on 251 degrees of freedom
## Multiple R-squared: 0.1242, Adjusted R-squared: 0.1172
## F-statistic: 17.8 on 2 and 251 DF, p-value: 5.908e-08
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4959 -0.4959 0.5041 0.5041 0.9286
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.49587 0.07262 34.369 <2e-16 ***
## Control_over_lifeDecreased -0.23872 0.10654 -2.241 0.0259 *
## Control_over_lifeIncreased -0.42444 0.16752 -2.534 0.0119 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7988 on 251 degrees of freedom
## Multiple R-squared: 0.03409, Adjusted R-squared: 0.02639
## F-statistic: 4.429 on 2 and 251 DF, p-value: 0.01287
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6122 -0.3794 -0.0877 0.4112 0.9123
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.40187 0.09306 4.318 2.27e-05 ***
## Control_over_lifeDecreased 0.29165 0.05772 5.052 8.43e-07 ***
## Control_over_lifeIncreased 0.31506 0.09101 3.462 0.000631 ***
## f_3 -0.10472 0.03386 -3.093 0.002209 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4285 on 250 degrees of freedom
## Multiple R-squared: 0.1565, Adjusted R-squared: 0.1464
## F-statistic: 15.46 on 3 and 250 DF, p-value: 2.955e-09
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.3166470 0.3595041
## [1] 0.2916471 0.3150557
## [1] 0.02499990 0.04444839
#Sobel test
saved$z.score; saved$p.value
## [1] 1.755331 1.901340
## [1] 0.07920273 0.05725747
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.02499990 0.0006859288 0.01517873
## t2* 0.04444839 0.0005592214 0.02510059
#bootstrapped CI
saved$boot.ci
## $Control_over_lifeDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0054, 0.0541 )
## Calculations and Intervals on Original Scale
##
## $Control_over_lifeIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0053, 0.0931 )
## Calculations and Intervals on Original Scale
# partial med
Alcohol_consumption
LEEP_covid$Alcohol_consumption = as.factor(LEEP_covid$Alcohol_consumption)
LEEP_covid$Alcohol_consumption<-relevel(LEEP_covid$Alcohol_consumption
, ref = "No change")
saved = mediation1(y = "Fear_seizure", #DV
x = "Control_over_life", #IV
m = "f_3", #Alcohol_consumption
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Control_over_lifeDecreased
## (Intercept) 1.0000000 -0.4097094
## Control_over_lifeDecreased -0.4097094 1.0000000
## Control_over_lifeIncreased -0.3226105 0.3110107
## f_3 -0.9081582 0.1400393
## Control_over_lifeIncreased f_3
## (Intercept) -0.3226105 -0.9081582
## Control_over_lifeDecreased 0.3110107 0.1400393
## Control_over_lifeIncreased 1.0000000 0.1579175
## f_3 0.1579175 1.0000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5000 -0.4762 -0.2397 0.5238 0.7603
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.23967 0.04265 5.620 5.07e-08 ***
## Control_over_lifeDecreased 0.23652 0.06257 3.780 0.000196 ***
## Control_over_lifeIncreased 0.26033 0.09838 2.646 0.008656 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4691 on 251 degrees of freedom
## Multiple R-squared: 0.06291, Adjusted R-squared: 0.05545
## F-statistic: 8.426 on 2 and 251 DF, p-value: 0.0002873
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4959 -0.4959 0.5041 0.5041 0.9286
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.49587 0.07262 34.369 <2e-16 ***
## Control_over_lifeDecreased -0.23872 0.10654 -2.241 0.0259 *
## Control_over_lifeIncreased -0.42444 0.16752 -2.534 0.0119 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7988 on 251 degrees of freedom
## Multiple R-squared: 0.03409, Adjusted R-squared: 0.02639
## F-statistic: 4.429 on 2 and 251 DF, p-value: 0.01287
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5886 -0.4148 -0.1980 0.5026 0.8020
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.44595 0.10106 4.413 1.52e-05 ***
## Control_over_lifeDecreased 0.21679 0.06269 3.458 0.000639 ***
## Control_over_lifeIncreased 0.22525 0.09884 2.279 0.023509 *
## f_3 -0.08265 0.03677 -2.248 0.025478 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4654 on 250 degrees of freedom
## Multiple R-squared: 0.08147, Adjusted R-squared: 0.07045
## F-statistic: 7.392 on 3 and 250 DF, p-value: 9.171e-05
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.2365211 0.2603306
## [1] 0.2167906 0.2252509
## [1] 0.01973047 0.03507964
#Sobel test
saved$z.score; saved$p.value
## [1] 1.513479 1.612531
## [1] 0.1301581 0.1068465
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.01973047 0.0001760663 0.01289569
## t2* 0.03507964 0.0001375395 0.02185977
#bootstrapped CI
saved$boot.ci
## $Control_over_lifeDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0057, 0.0448 )
## Calculations and Intervals on Original Scale
##
## $Control_over_lifeIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0079, 0.0778 )
## Calculations and Intervals on Original Scale
# partial med
saved = mediation1(y = "health_conditions", #DV
x = "Alcohol_consumption", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Alcohol_consumptionDecreased
## (Intercept) 1.0000000 -0.19297893
## Alcohol_consumptionDecreased -0.1929789 1.00000000
## Alcohol_consumptionIncreased -0.3189562 0.19966599
## f_3 -0.9269606 0.05085172
## Alcohol_consumptionIncreased f_3
## (Intercept) -0.3189562 -0.92696060
## Alcohol_consumptionDecreased 0.1996660 0.05085172
## Alcohol_consumptionIncreased 1.0000000 0.14383279
## f_3 0.1438328 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.4333 -0.2560 -0.2560 0.5893 0.7440
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.25595 0.03542 7.225 5.98e-12 ***
## Alcohol_consumptionDecreased 0.17738 0.09101 1.949 0.0524 .
## Alcohol_consumptionIncreased 0.15476 0.07085 2.184 0.0299 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4591 on 251 degrees of freedom
## Multiple R-squared: 0.02783, Adjusted R-squared: 0.02009
## F-statistic: 3.593 on 2 and 251 DF, p-value: 0.02894
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4286 -0.4286 0.5714 0.5714 0.8571
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.42857 0.06204 39.146 <2e-16 ***
## Alcohol_consumptionDecreased -0.12857 0.15938 -0.807 0.4206
## Alcohol_consumptionIncreased -0.28571 0.12408 -2.303 0.0221 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8041 on 251 degrees of freedom
## Multiple R-squared: 0.0212, Adjusted R-squared: 0.0134
## F-statistic: 2.718 on 2 and 251 DF, p-value: 0.06795
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5985 -0.3104 -0.1834 0.5286 0.8166
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.56441 0.09224 6.119 3.62e-09 ***
## Alcohol_consumptionDecreased 0.16105 0.08902 1.809 0.071621 .
## Alcohol_consumptionIncreased 0.11847 0.06994 1.694 0.091517 .
## f_3 -0.12701 0.03521 -3.608 0.000373 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4485 on 250 degrees of freedom
## Multiple R-squared: 0.07594, Adjusted R-squared: 0.06485
## F-statistic: 6.848 on 3 and 250 DF, p-value: 0.0001883
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.1773810 0.1547619
## [1] 0.1610506 0.1184723
## [1] 0.01633030 0.03628956
#Sobel test
saved$z.score; saved$p.value
## [1] 0.7599302 1.8900763
## [1] 0.44729632 0.05874776
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.01633030 0.001525506 0.02070314
## t2* 0.03628956 0.001046134 0.02036596
#bootstrapped CI
saved$boot.ci
## $Alcohol_consumptionDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0258, 0.0554 )
## Calculations and Intervals on Original Scale
##
## $Alcohol_consumptionIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0047, 0.0752 )
## Calculations and Intervals on Original Scale
# partial med
Anger
LEEP_covid$Anger = as.factor(LEEP_covid$Anger)
LEEP_covid$Anger<-relevel(LEEP_covid$Anger
, ref = "No change")
saved = mediation1(y = "Fear_seizure", #DV
x = "Anger", #IV
m = "f_3", #Alcohol_consumption
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) AngerDecreased AngerIncreased f_3
## (Intercept) 1.0000000 -0.1272399 -0.3789119 -0.9192986
## AngerDecreased -0.1272399 1.0000000 0.2083025 -0.0124896
## AngerIncreased -0.3789119 0.2083025 1.0000000 0.1567983
## f_3 -0.9192986 -0.0124896 0.1567983 1.0000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.4706 -0.3108 -0.3108 0.5294 0.6892
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.31081 0.03936 7.897 8.93e-14 ***
## AngerDecreased 0.02252 0.11165 0.202 0.8403
## AngerIncreased 0.15978 0.06516 2.452 0.0149 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4788 on 251 degrees of freedom
## Multiple R-squared: 0.0238, Adjusted R-squared: 0.01602
## F-statistic: 3.06 on 2 and 251 DF, p-value: 0.04865
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4762 -0.4392 0.5608 0.5608 0.8353
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.43919 0.06591 37.007 <2e-16 ***
## AngerDecreased 0.03700 0.18698 0.198 0.8433
## AngerIncreased -0.27448 0.10913 -2.515 0.0125 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8019 on 251 degrees of freedom
## Multiple R-squared: 0.02672, Adjusted R-squared: 0.01896
## F-statistic: 3.445 on 2 and 251 DF, p-value: 0.03342
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5797 -0.3715 -0.2582 0.5543 0.7418
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.53940 0.09896 5.450 1.2e-07 ***
## AngerDecreased 0.02599 0.11050 0.235 0.8142
## AngerIncreased 0.13405 0.06529 2.053 0.0411 *
## f_3 -0.09372 0.03730 -2.513 0.0126 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4738 on 250 degrees of freedom
## Multiple R-squared: 0.04784, Adjusted R-squared: 0.03642
## F-statistic: 4.187 on 3 and 250 DF, p-value: 0.00648
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.02252252 0.15977742
## [1] 0.02599012 0.13405408
## [1] -0.003467595 0.025723346
#Sobel test
saved$z.score; saved$p.value
## [1] -0.1833709 1.7112102
## [1] 0.85450704 0.08704232
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* -0.003467595 0.0005726274 0.01835025
## t2* 0.025723346 -0.0005162771 0.01518155
#bootstrapped CI
saved$boot.ci
## $AngerDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0400, 0.0319 )
## Calculations and Intervals on Original Scale
##
## $AngerIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0035, 0.0560 )
## Calculations and Intervals on Original Scale
# partial med
saved = mediation1(y = "health_conditions", #DV
x = "Anger", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) AngerDecreased AngerIncreased f_3
## (Intercept) 1.0000000 -0.1272399 -0.3789119 -0.9192986
## AngerDecreased -0.1272399 1.0000000 0.2083025 -0.0124896
## AngerIncreased -0.3789119 0.2083025 1.0000000 0.1567983
## f_3 -0.9192986 -0.0124896 0.1567983 1.0000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.4941 -0.2297 -0.2297 0.5059 0.8571
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.22973 0.03669 6.261 1.64e-09 ***
## AngerDecreased -0.08687 0.10408 -0.835 0.405
## AngerIncreased 0.26439 0.06075 4.352 1.96e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4464 on 251 degrees of freedom
## Multiple R-squared: 0.08123, Adjusted R-squared: 0.07391
## F-statistic: 11.1 on 2 and 251 DF, p-value: 2.411e-05
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4762 -0.4392 0.5608 0.5608 0.8353
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.43919 0.06591 37.007 <2e-16 ***
## AngerDecreased 0.03700 0.18698 0.198 0.8433
## AngerIncreased -0.27448 0.10913 -2.515 0.0125 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8019 on 251 degrees of freedom
## Multiple R-squared: 0.02672, Adjusted R-squared: 0.01896
## F-statistic: 3.445 on 2 and 251 DF, p-value: 0.03342
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6260 -0.2795 -0.1662 0.3740 0.9165
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.50600 0.09146 5.533 7.95e-08 ***
## AngerDecreased -0.08268 0.10212 -0.810 0.418902
## AngerIncreased 0.23330 0.06034 3.866 0.000141 ***
## f_3 -0.11326 0.03447 -3.286 0.001163 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4379 on 250 degrees of freedom
## Multiple R-squared: 0.1193, Adjusted R-squared: 0.1087
## F-statistic: 11.29 on 3 and 250 DF, p-value: 5.729e-07
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] -0.08687259 0.26438792
## [1] -0.08268178 0.23329961
## [1] -0.004190811 0.031088312
#Sobel test
saved$z.score; saved$p.value
## [1] -0.1890014 1.9413821
## [1] 0.85009174 0.05221194
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* -0.004190811 0.0008750419 0.01974461
## t2* 0.031088312 0.0002494828 0.01678639
#bootstrapped CI
saved$boot.ci
## $AngerDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0438, 0.0336 )
## Calculations and Intervals on Original Scale
##
## $AngerIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0021, 0.0637 )
## Calculations and Intervals on Original Scale
# partial med
Anger
LEEP_covid$Anxiety = as.factor(LEEP_covid$Anxiety)
LEEP_covid$Anxiety<-relevel(LEEP_covid$Anxiety
, ref = "No change")
saved = mediation1(y = "Fear_seizure", #DV
x = "Anxiety", #IV
m = "f_3", #Alcohol_consumption
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) AnxietyDecreased AnxietyIncreased f_3
## (Intercept) 1.0000000 -0.20786434 -0.4949983 -0.87283021
## AnxietyDecreased -0.2078643 1.00000000 0.3664018 -0.02413748
## AnxietyIncreased -0.4949983 0.36640176 1.0000000 0.12675203
## f_3 -0.8728302 -0.02413748 0.1267520 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.4897 -0.4897 -0.2235 0.5103 0.8750
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.22353 0.05013 4.459 1.24e-05 ***
## AnxietyDecreased -0.09853 0.10683 -0.922 0.357
## AnxietyIncreased 0.26613 0.06313 4.215 3.48e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4622 on 251 degrees of freedom
## Multiple R-squared: 0.09053, Adjusted R-squared: 0.08328
## F-statistic: 12.49 on 2 and 251 DF, p-value: 6.733e-06
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.5417 -0.4706 0.5294 0.7517 0.7517
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.47059 0.08719 28.335 <2e-16 ***
## AnxietyDecreased 0.07108 0.18582 0.383 0.702
## AnxietyIncreased -0.22231 0.10981 -2.024 0.044 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8039 on 251 degrees of freedom
## Multiple R-squared: 0.02182, Adjusted R-squared: 0.01403
## F-statistic: 2.799 on 2 and 251 DF, p-value: 0.06274
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5912 -0.4285 -0.1805 0.4901 0.9123
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.42450 0.10189 4.166 4.27e-05 ***
## AnxietyDecreased -0.09275 0.10600 -0.875 0.38242
## AnxietyIncreased 0.24804 0.06313 3.929 0.00011 ***
## f_3 -0.08134 0.03600 -2.260 0.02469 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4584 on 250 degrees of freedom
## Multiple R-squared: 0.1087, Adjusted R-squared: 0.09804
## F-statistic: 10.17 on 3 and 250 DF, p-value: 2.426e-06
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] -0.09852941 0.26612576
## [1] -0.0927476 0.2480420
## [1] -0.005781813 0.018083805
#Sobel test
saved$z.score; saved$p.value
## [1] -0.3456858 1.4320971
## [1] 0.7295789 0.1521160
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* -0.005781813 -0.0002973666 0.01468639
## t2* 0.018083805 -0.0004429578 0.01231334
#bootstrapped CI
saved$boot.ci
## $AnxietyDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0343, 0.0233 )
## Calculations and Intervals on Original Scale
##
## $AnxietyIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0056, 0.0427 )
## Calculations and Intervals on Original Scale
# partial med
saved = mediation1(y = "health_conditions", #DV
x = "Anxiety", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) AnxietyDecreased AnxietyIncreased f_3
## (Intercept) 1.0000000 -0.20786434 -0.4949983 -0.87283021
## AnxietyDecreased -0.2078643 1.00000000 0.3664018 -0.02413748
## AnxietyIncreased -0.4949983 0.36640176 1.0000000 0.12675203
## f_3 -0.8728302 -0.02413748 0.1267520 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.45517 -0.45517 -0.08235 0.54483 0.91765
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.08235 0.04688 1.757 0.0802 .
## AnxietyDecreased 0.16765 0.09990 1.678 0.0946 .
## AnxietyIncreased 0.37282 0.05904 6.315 1.22e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4322 on 251 degrees of freedom
## Multiple R-squared: 0.1387, Adjusted R-squared: 0.1318
## F-statistic: 20.2 on 2 and 251 DF, p-value: 7.322e-09
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.5417 -0.4706 0.5294 0.7517 0.7517
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.47059 0.08719 28.335 <2e-16 ***
## AnxietyDecreased 0.07108 0.18582 0.383 0.702
## AnxietyIncreased -0.22231 0.10981 -2.024 0.044 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8039 on 251 degrees of freedom
## Multiple R-squared: 0.02182, Adjusted R-squared: 0.01403
## F-statistic: 2.799 on 2 and 251 DF, p-value: 0.06274
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.59317 -0.37207 -0.02383 0.40683 0.97617
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.35547 0.09419 3.774 0.000201 ***
## AnxietyDecreased 0.17550 0.09799 1.791 0.074493 .
## AnxietyIncreased 0.34824 0.05836 5.967 8.23e-09 ***
## f_3 -0.11055 0.03328 -3.322 0.001027 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4238 on 250 degrees of freedom
## Multiple R-squared: 0.1751, Adjusted R-squared: 0.1652
## F-statistic: 17.69 on 3 and 250 DF, p-value: 1.921e-10
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.1676471 0.3728195
## [1] 0.1755045 0.3482436
## [1] -0.007857484 0.024575893
#Sobel test
saved$z.score; saved$p.value
## [1] -0.364080 1.674327
## [1] 0.71579826 0.09406633
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* -0.007857484 -0.0002871044 0.01899441
## t2* 0.024575893 0.0001067671 0.01516643
#bootstrapped CI
saved$boot.ci
## $AnxietyDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0448, 0.0297 )
## Calculations and Intervals on Original Scale
##
## $AnxietyIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0053, 0.0542 )
## Calculations and Intervals on Original Scale
# partial med
Time_spent_outside
LEEP_covid$Time_spent_outside = as.factor(LEEP_covid$Time_spent_outside)
LEEP_covid$Time_spent_outside<-relevel(LEEP_covid$Time_spent_outside
, ref = "No change")
saved = mediation1(y = "Fear_seizure", #DV
x = "Time_spent_outside", #IV
m = "f_3", #Alcohol_consumption
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Time_spent_outsideDecreased
## (Intercept) 1.0000000 -0.4120435
## Time_spent_outsideDecreased -0.4120435 1.0000000
## Time_spent_outsideIncreased -0.2758743 0.4302437
## f_3 -0.8821143 0.1016056
## Time_spent_outsideIncreased f_3
## (Intercept) -0.27587431 -0.88211432
## Time_spent_outsideDecreased 0.43024368 0.10160563
## Time_spent_outsideIncreased 1.00000000 -0.02487482
## f_3 -0.02487482 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5169 -0.3636 -0.2323 0.4832 0.7677
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.23232 0.04711 4.931 1.49e-06 ***
## Time_spent_outsideDecreased 0.28453 0.06847 4.155 4.46e-05 ***
## Time_spent_outsideIncreased 0.13131 0.07449 1.763 0.0792 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4688 on 251 degrees of freedom
## Multiple R-squared: 0.06437, Adjusted R-squared: 0.05692
## F-statistic: 8.635 on 2 and 251 DF, p-value: 0.0002362
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4546 -0.4546 0.5454 0.5960 0.7865
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.40404 0.08103 29.669 <2e-16 ***
## Time_spent_outsideDecreased -0.19056 0.11777 -1.618 0.107
## Time_spent_outsideIncreased 0.05051 0.12812 0.394 0.694
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8062 on 251 degrees of freedom
## Multiple R-squared: 0.0161, Adjusted R-squared: 0.008257
## F-statistic: 2.053 on 2 and 251 DF, p-value: 0.1305
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6286 -0.3616 -0.1774 0.5024 0.8226
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.45368 0.09895 4.585 7.19e-06 ***
## Time_spent_outsideDecreased 0.26698 0.06810 3.921 0.000114 ***
## Time_spent_outsideIncreased 0.13596 0.07372 1.844 0.066322 .
## f_3 -0.09208 0.03631 -2.536 0.011824 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4638 on 250 degrees of freedom
## Multiple R-squared: 0.08784, Adjusted R-squared: 0.07689
## F-statistic: 8.025 on 3 and 250 DF, p-value: 3.98e-05
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.2845307 0.1313131
## [1] 0.2669844 0.1359636
## [1] 0.017546251 -0.004650436
#Sobel test
saved$z.score; saved$p.value
## [1] 1.2944384 -0.3629553
## [1] 0.1955140 0.7166382
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.017546251 -0.0003245128 0.01385420
## t2* -0.004650436 -0.0006542688 0.01271356
#bootstrapped CI
saved$boot.ci
## $Time_spent_outsideDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0093, 0.0450 )
## Calculations and Intervals on Original Scale
##
## $Time_spent_outsideIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0289, 0.0209 )
## Calculations and Intervals on Original Scale
# partial med
saved = mediation1(y = "health_conditions", #DV
x = "Time_spent_outside", #IV
m = "f_2", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) Time_spent_outsideDecreased
## (Intercept) 1.0000000 -0.50239125
## Time_spent_outsideDecreased -0.5023912 1.00000000
## Time_spent_outsideIncreased -0.3654503 0.42921992
## f_2 -0.7792455 0.09378542
## Time_spent_outsideIncreased f_2
## (Intercept) -0.36545028 -0.77924551
## Time_spent_outsideDecreased 0.42921992 0.09378542
## Time_spent_outsideIncreased 1.00000000 -0.03928856
## f_2 -0.03928856 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.3820 -0.3333 -0.2323 0.6180 0.7677
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.23232 0.04633 5.015 1.01e-06 ***
## Time_spent_outsideDecreased 0.14970 0.06733 2.223 0.0271 *
## Time_spent_outsideIncreased 0.10101 0.07325 1.379 0.1691
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.461 on 251 degrees of freedom
## Multiple R-squared: 0.02011, Adjusted R-squared: 0.0123
## F-statistic: 2.576 on 2 and 251 DF, p-value: 0.0781
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.8485 0.1515 0.1919 0.2586 0.2809
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.80808 0.04102 19.699 <2e-16 ***
## Time_spent_outsideDecreased -0.08898 0.05962 -1.492 0.137
## Time_spent_outsideIncreased 0.04040 0.06486 0.623 0.534
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4082 on 251 degrees of freedom
## Multiple R-squared: 0.01655, Adjusted R-squared: 0.008715
## F-statistic: 2.112 on 2 and 251 DF, p-value: 0.1231
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5489 -0.3169 -0.1878 0.4698 0.8122
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.41981 0.07249 5.791 2.09e-08 ***
## Time_spent_outsideDecreased 0.12905 0.06632 1.946 0.05279 .
## Time_spent_outsideIncreased 0.11038 0.07189 1.536 0.12593
## f_2 -0.23202 0.06990 -3.319 0.00104 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.452 on 250 degrees of freedom
## Multiple R-squared: 0.06147, Adjusted R-squared: 0.05021
## F-statistic: 5.458 on 3 and 250 DF, p-value: 0.001194
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.1496992 0.1010101
## [1] 0.1290545 0.1103845
## [1] 0.020644717 -0.009374387
#Sobel test
saved$z.score; saved$p.value
## [1] 1.3124978 -0.5870426
## [1] 0.1893522 0.5571751
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.020644717 -0.0005421994 0.01593103
## t2* -0.009374387 0.0011115771 0.01487974
#bootstrapped CI
saved$boot.ci
## $Time_spent_outsideDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0100, 0.0524 )
## Calculations and Intervals on Original Scale
##
## $Time_spent_outsideIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0396, 0.0187 )
## Calculations and Intervals on Original Scale
# partial med
Smoking
LEEP_covid$Smoking = as.factor(LEEP_covid$Smoking)
LEEP_covid$Smoking<-relevel(LEEP_covid$Smoking
, ref = "No change")
saved = mediation1(y = "Fear_seizure", #DV
x = "Smoking", #IV
m = "f_2", #Alcohol_consumption
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) SmokingDecreased SmokingIncreased f_2
## (Intercept) 1.0000000 -0.1457478 -0.35039269 -0.84242410
## SmokingDecreased -0.1457478 1.0000000 0.19446056 -0.06435430
## SmokingIncreased -0.3503927 0.1944606 1.00000000 0.07272218
## f_2 -0.8424241 -0.0643543 0.07272218 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5000 -0.3148 -0.3148 0.5000 0.6852
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.31481 0.03755 8.384 3.7e-15 ***
## SmokingDecreased 0.03134 0.10097 0.310 0.75653
## SmokingIncreased 0.18519 0.06979 2.653 0.00847 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4779 on 251 degrees of freedom
## Multiple R-squared: 0.02748, Adjusted R-squared: 0.01973
## F-statistic: 3.546 on 2 and 251 DF, p-value: 0.0303
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.8846 0.1154 0.2037 0.2037 0.2727
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.79630 0.03215 24.770 <2e-16 ***
## SmokingDecreased 0.08832 0.08644 1.022 0.308
## SmokingIncreased -0.06902 0.05975 -1.155 0.249
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4092 on 251 degrees of freedom
## Multiple R-squared: 0.01169, Adjusted R-squared: 0.003817
## F-statistic: 1.485 on 2 and 251 DF, p-value: 0.2285
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6138 -0.3281 -0.2829 0.5427 0.7170
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.43936 0.06920 6.349 1.01e-09 ***
## SmokingDecreased 0.04515 0.10047 0.449 0.6535
## SmokingIncreased 0.17439 0.06948 2.510 0.0127 *
## f_2 -0.15641 0.07321 -2.137 0.0336 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4746 on 250 degrees of freedom
## Multiple R-squared: 0.04492, Adjusted R-squared: 0.03346
## F-statistic: 3.919 on 3 and 250 DF, p-value: 0.009256
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.03133903 0.18518519
## [1] 0.04515282 0.17438936
## [1] -0.01381379 0.01079582
#Sobel test
saved$z.score; saved$p.value
## [1] -0.8491232 0.9396464
## [1] 0.3958127 0.3473990
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* -0.01381379 -0.0006443372 0.01463090
## t2* 0.01079582 -0.0004925975 0.01173633
#bootstrapped CI
saved$boot.ci
## $SmokingDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0418, 0.0155 )
## Calculations and Intervals on Original Scale
##
## $SmokingIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0117, 0.0343 )
## Calculations and Intervals on Original Scale
# partial med
saved = mediation1(y = "health_conditions", #DV
x = "Smoking", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) SmokingDecreased SmokingIncreased f_3
## (Intercept) 1.00000000 -0.09718209 -0.3374368 -0.9237714
## SmokingDecreased -0.09718209 1.00000000 0.1906931 -0.0487776
## SmokingIncreased -0.33743681 0.19069307 1.0000000 0.1445891
## f_3 -0.92377141 -0.04877760 0.1445891 1.0000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.4849 -0.2716 -0.2716 0.5151 0.8846
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.27160 0.03548 7.655 4.17e-13 ***
## SmokingDecreased -0.15622 0.09541 -1.637 0.10280
## SmokingIncreased 0.21324 0.06595 3.234 0.00139 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4516 on 251 degrees of freedom
## Multiple R-squared: 0.05955, Adjusted R-squared: 0.05205
## F-statistic: 7.946 on 2 and 251 DF, p-value: 0.0004507
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.5385 -0.4074 0.4615 0.5926 0.8636
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.40741 0.06299 38.218 <2e-16 ***
## SmokingDecreased 0.13105 0.16939 0.774 0.4398
## SmokingIncreased -0.27104 0.11708 -2.315 0.0214 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8018 on 251 degrees of freedom
## Multiple R-squared: 0.02696, Adjusted R-squared: 0.0192
## F-statistic: 3.477 on 2 and 251 DF, p-value: 0.03241
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6180 -0.3193 -0.2022 0.4992 0.9387
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.55368 0.09081 6.097 4.07e-09 ***
## SmokingDecreased -0.14086 0.09362 -1.505 0.133671
## SmokingIncreased 0.18149 0.06532 2.778 0.005876 **
## f_3 -0.11717 0.03484 -3.363 0.000893 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4426 on 250 degrees of freedom
## Multiple R-squared: 0.1002, Adjusted R-squared: 0.08945
## F-statistic: 9.284 on 3 and 250 DF, p-value: 7.64e-06
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] -0.1562203 0.2132435
## [1] -0.1408646 0.1814852
## [1] -0.01535570 0.03175838
#Sobel test
saved$z.score; saved$p.value
## [1] -0.7242038 1.8521009
## [1] 0.46894066 0.06401134
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* -0.01535570 0.0008544169 0.01931083
## t2* 0.03175838 0.0006172557 0.01762197
#bootstrapped CI
saved$boot.ci
## $SmokingDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0541, 0.0216 )
## Calculations and Intervals on Original Scale
##
## $SmokingIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0034, 0.0657 )
## Calculations and Intervals on Original Scale
# partial med
Hobbies
LEEP_covid$Hobbies = as.factor(LEEP_covid$Hobbies)
LEEP_covid$Hobbies<-relevel(LEEP_covid$Hobbies
, ref = "No change")
saved = mediation1(y = "Fear_seizure", #DV
x = "Hobbies", #IV
m = "f_2", #Alcohol_consumption
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) HobbiesDecreased HobbiesIncreased f_2
## (Intercept) 1.0000000 -0.3841555 -0.33168047 -0.83017603
## HobbiesDecreased -0.3841555 1.0000000 0.29394179 0.08710680
## HobbiesIncreased -0.3316805 0.2939418 1.00000000 0.05207872
## f_2 -0.8301760 0.0871068 0.05207872 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.4375 -0.3529 -0.3381 0.6471 0.6619
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.33813 0.04095 8.257 8.57e-15 ***
## HobbiesDecreased 0.09937 0.07293 1.363 0.174
## HobbiesIncreased 0.01481 0.07904 0.187 0.852
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4828 on 251 degrees of freedom
## Multiple R-squared: 0.007529, Adjusted R-squared: -0.0003788
## F-statistic: 0.9521 on 2 and 251 DF, p-value: 0.3873
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.8201 0.1799 0.1799 0.2353 0.2656
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.82014 0.03476 23.592 <2e-16 ***
## HobbiesDecreased -0.08577 0.06191 -1.385 0.167
## HobbiesIncreased -0.05544 0.06710 -0.826 0.409
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4099 on 251 degrees of freedom
## Multiple R-squared: 0.008355, Adjusted R-squared: 0.0004532
## F-statistic: 1.057 on 2 and 251 DF, p-value: 0.3489
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5572 -0.3146 -0.3088 0.6058 0.6912
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.471836 0.072891 6.473 5.04e-10 ***
## HobbiesDecreased 0.085388 0.072649 1.175 0.241
## HobbiesIncreased 0.005774 0.078542 0.074 0.941
## f_2 -0.163028 0.073783 -2.210 0.028 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4791 on 250 degrees of freedom
## Multiple R-squared: 0.02654, Adjusted R-squared: 0.01486
## F-statistic: 2.272 on 3 and 250 DF, p-value: 0.08073
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.09937050 0.01481168
## [1] 0.085387807 0.005773755
## [1] 0.013982697 0.009037925
#Sobel test
saved$z.score; saved$p.value
## [1] 1.0958940 0.7124979
## [1] 0.2731252 0.4761565
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.013982697 -7.037632e-05 0.01413970
## t2* 0.009037925 -1.143448e-04 0.01308951
#bootstrapped CI
saved$boot.ci
## $HobbiesDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0137, 0.0418 )
## Calculations and Intervals on Original Scale
##
## $HobbiesIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0165, 0.0348 )
## Calculations and Intervals on Original Scale
# partial med
saved = mediation1(y = "health_conditions", #DV
x = "Hobbies", #IV
m = "f_3", #Mediator
cvs = NULL, #Any covariates
df = LEEP_covid
)
####view data screening####
#outlier information is in the DF
#View(saved$datascreening$fulldata)
#additivity
saved$datascreening$correl
## (Intercept) HobbiesDecreased HobbiesIncreased f_3
## (Intercept) 1.0000000 -0.3230484 -0.28966744 -0.91377080
## HobbiesDecreased -0.3230484 1.0000000 0.29739629 0.10530253
## HobbiesIncreased -0.2896674 0.2973963 1.00000000 0.08756083
## f_3 -0.9137708 0.1053025 0.08756083 1.00000000
#linearity
saved$datascreening$linearity
#normality
saved$datascreening$normality
#homogs
saved$datascreening$homogen
####view the analysis####
summary(saved$model1) #c path
##
## Call:
## lm(formula = allformulas$eq1, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.4531 -0.3922 -0.2158 0.5469 0.7842
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.21583 0.03844 5.615 5.19e-08 ***
## HobbiesDecreased 0.23730 0.06845 3.467 0.00062 ***
## HobbiesIncreased 0.17633 0.07419 2.377 0.01821 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4531 on 251 degrees of freedom
## Multiple R-squared: 0.05305, Adjusted R-squared: 0.04551
## F-statistic: 7.031 on 2 and 251 DF, p-value: 0.001069
summary(saved$model2) #a path
##
## Call:
## lm(formula = allformulas$eq2, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4388 -0.4389 0.5612 0.5612 0.7656
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.43885 0.06844 35.637 <2e-16 ***
## HobbiesDecreased -0.20447 0.12188 -1.678 0.0947 .
## HobbiesIncreased -0.18395 0.13209 -1.393 0.1650
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8068 on 251 degrees of freedom
## Multiple R-squared: 0.01456, Adjusted R-squared: 0.006707
## F-statistic: 1.854 on 2 and 251 DF, p-value: 0.1587
summary(saved$model3) #b and c' path
##
## Call:
## lm(formula = allformulas$eq3, data = finaldata)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6047 -0.3007 -0.1469 0.4538 0.8531
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.51524 0.09251 5.569 6.59e-08 ***
## HobbiesDecreased 0.21219 0.06731 3.153 0.001815 **
## HobbiesIncreased 0.15375 0.07282 2.111 0.035729 *
## f_3 -0.12277 0.03466 -3.542 0.000474 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4431 on 250 degrees of freedom
## Multiple R-squared: 0.0983, Adjusted R-squared: 0.08748
## F-statistic: 9.085 on 3 and 250 DF, p-value: 9.912e-06
saved$total.effect; saved$direct.effect; saved$indirect.effect
## [1] 0.2372977 0.1763295
## [1] 0.2121948 0.1537467
## [1] 0.02510283 0.02258278
#Sobel test
saved$z.score; saved$p.value
## [1] 1.469089 1.253453
## [1] 0.1418087 0.2100408
#bootstrapped indirect
saved$boot.results
##
## ORDINARY NONPARAMETRIC BOOTSTRAP
##
##
## Call:
## boot(data = finaldata, statistic = indirectmed, R = nboot, formula2 = allformulas$eq2,
## formula3 = allformulas$eq3, x = x, med.var = m)
##
##
## Bootstrap Statistics :
## original bias std. error
## t1* 0.02510283 0.0011196984 0.01844536
## t2* 0.02258278 0.0003513311 0.01789637
#bootstrapped CI
saved$boot.ci
## $HobbiesDecreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0122, 0.0601 )
## Calculations and Intervals on Original Scale
##
## $HobbiesIncreased
## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = bootresults, conf = conf_level, type = "norm",
## index = i)
##
## Intervals :
## Level Normal
## 95% (-0.0128, 0.0573 )
## Calculations and Intervals on Original Scale
# partial med
Social_isolation