meta-study 4 confirm + exp
kris evans
11/5/2020
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──## ✓ ggplot2 3.3.2 ✓ purrr 0.3.4
## ✓ tibble 3.0.4 ✓ dplyr 1.0.2
## ✓ tidyr 1.1.2 ✓ stringr 1.4.0
## ✓ readr 1.4.0 ✓ forcats 0.5.0## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()##
## Attaching package: 'kableExtra'## The following object is masked from 'package:dplyr':
##
## group_rows## Loading required package: Matrix##
## Attaching package: 'Matrix'## The following objects are masked from 'package:tidyr':
##
## expand, pack, unpack## Registered S3 methods overwritten by 'car':
## method from
## influence.merMod lme4
## cooks.distance.influence.merMod lme4
## dfbeta.influence.merMod lme4
## dfbetas.influence.merMod lme4## ************
## Welcome to afex. For support visit: http://afex.singmann.science/## - Functions for ANOVAs: aov_car(), aov_ez(), and aov_4()
## - Methods for calculating p-values with mixed(): 'KR', 'S', 'LRT', and 'PB'
## - 'afex_aov' and 'mixed' objects can be passed to emmeans() for follow-up tests
## - NEWS: library('emmeans') now needs to be called explicitly!
## - Get and set global package options with: afex_options()
## - Set orthogonal sum-to-zero contrasts globally: set_sum_contrasts()
## - For example analyses see: browseVignettes("afex")
## ************##
## Attaching package: 'afex'## The following object is masked from 'package:lme4':
##
## lmer#Data Preparation
##Load Data
##
## ── Column specification ────────────────────────────────────────────────────────
## cols(
## .default = col_double(),
## t1_gender_4_TEXT = col_logical(),
## t1_ethnicity_8_TEXT = col_character(),
## t1_religion_11_TEXT = col_character(),
## t1_job_and_industry_1 = col_character(),
## t1_job_and_industry_2 = col_character(),
## t1_debrief_purpose = col_character(),
## t1_debrief_glitch = col_character(),
## t1_debrief_else = col_character(),
## t2_full_vid1_q1 = col_character(),
## t2_full_vid2_q1 = col_character(),
## t2_full_vid2_q2 = col_character(),
## t2_full_vid3_q1 = col_character(),
## t2_full_vid3_q2 = col_character(),
## t2_full_vid4_q1 = col_character(),
## t2_full_vid4_q2 = col_character(),
## t2_full_vid5_q2 = col_character(),
## t2_abr_introvid_q1 = col_character(),
## t2_abr_exvid_q1 = col_character(),
## t2_abr_exvid_q2 = col_character(),
## t2_abr_strvid_q1 = col_character()
## # ... with 15 more columns
## )
## ℹ Use `spec()` for the full column specifications.How many people did we have?
d.study %>%
group_by(condition)%>%
summarise(n=n()) %>%
kable(digits = 2, caption = "Participants Per Task")## `summarise()` ungrouping output (override with `.groups` argument)| condition | n |
|---|---|
| abr_intervention | 112 |
| active_control | 107 |
| full_intervention | 105 |
======
#Confirmatory Analyses
##H1 - SFMM
Let’s tidy the data
d_sfmm <- d.study %>%
select(subid_final, condition, sfmm_all9_t1_score, sfmm_all9_t2_score)%>%
gather(item, score, contains("sfmm"))%>%
separate(item, sep = "_", into = c("construct_name", "type", "time", "score_name"))%>%
select(-construct_name, -score_name, -type)Let’s change data to be numeric & factors (and appropriate contrasts)
#Make Rating Numeric
d_sfmm$score <- as.numeric(d_sfmm$score)
#Factor Condition
d_sfmm$condition <- as.factor(d_sfmm$condition)
contrasts(d_sfmm$condition)## active_control full_intervention
## abr_intervention 0 0
## active_control 1 0
## full_intervention 0 1contrasts(d_sfmm$condition) = cbind(dummy_full_vs_control = c(0,0,1), dummy_abridged_vs_control = c(1,0,0))
contrasts(d_sfmm$condition)## dummy_full_vs_control dummy_abridged_vs_control
## abr_intervention 0 1
## active_control 0 0
## full_intervention 1 0#Factor Time
d_sfmm$time <- as.factor(d_sfmm$time)
contrasts(d_sfmm$time)## t2
## t1 0
## t2 1contrasts(d_sfmm$time) = cbind(dummy_t2_vs_t1 = c(0,1))
contrasts(d_sfmm$time)## dummy_t2_vs_t1
## t1 0
## t2 1#Factor subject id
d_sfmm$subid_final <- as.factor(d_sfmm$subid_final)Interaction
summary(lmer(score ~ time*condition + (1 | subid_final), data = d_sfmm))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: score ~ time * condition + (1 | subid_final)
## Data: d_sfmm
##
## REML criterion at convergence: 1163.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.88861 -0.47875 0.06395 0.50270 2.50306
##
## Random effects:
## Groups Name Variance Std.Dev.
## subid_final (Intercept) 0.2523 0.5023
## Residual 0.1736 0.4167
## Number of obs: 648, groups: subid_final, 324
##
## Fixed effects:
## Estimate Std. Error
## (Intercept) 4.717e+00 6.309e-02
## timedummy_t2_vs_t1 -1.807e-14 5.697e-02
## conditiondummy_full_vs_control -1.684e-01 8.965e-02
## conditiondummy_abridged_vs_control -1.014e-01 8.822e-02
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 1.979e-01 8.095e-02
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 2.391e-01 7.966e-02
## df t value
## (Intercept) 4.753e+02 74.760
## timedummy_t2_vs_t1 3.210e+02 0.000
## conditiondummy_full_vs_control 4.753e+02 -1.878
## conditiondummy_abridged_vs_control 4.753e+02 -1.150
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 3.210e+02 2.445
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 3.210e+02 3.001
## Pr(>|t|)
## (Intercept) <2e-16 ***
## timedummy_t2_vs_t1 1.0000
## conditiondummy_full_vs_control 0.0610 .
## conditiondummy_abridged_vs_control 0.2508
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 0.0150 *
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 0.0029 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) tm_2__1 cndtndmmy_f__ cndtndmmy_b__
## tmdmmy_2__1 -0.451
## cndtndmmy_f__ -0.704 0.318
## cndtndmmy_b__ -0.715 0.323 0.503
## tmdmmy_t2_vs_t1:cndtndmmy_f__ 0.318 -0.704 -0.451 -0.227
## tmdmmy_t2_vs_t1:cndtndmmy_b__ 0.323 -0.715 -0.227 -0.451
## tmdmmy_t2_vs_t1:cndtndmmy_f__
## tmdmmy_2__1
## cndtndmmy_f__
## cndtndmmy_b__
## tmdmmy_t2_vs_t1:cndtndmmy_f__
## tmdmmy_t2_vs_t1:cndtndmmy_b__ 0.503##Descriptives
d_sfmm %>%
ungroup()%>%
group_by(subid_final, condition, time) %>%
summarise(mean_score = mean(score))%>%
group_by(condition, time)%>%
summarise(mean = mean(mean_score),
sd = sd(mean_score)) %>%
kable(digits = 2)## `summarise()` regrouping output by 'subid_final', 'condition' (override with `.groups` argument)## `summarise()` regrouping output by 'condition' (override with `.groups` argument)| condition | time | mean | sd |
|---|---|---|---|
| abr_intervention | t1 | 4.62 | 0.59 |
| abr_intervention | t2 | 4.85 | 0.62 |
| active_control | t1 | 4.72 | 0.61 |
| active_control | t2 | 4.72 | 0.67 |
| full_intervention | t1 | 4.55 | 0.69 |
| full_intervention | t2 | 4.75 | 0.73 |
–
##Intelligence Mindset
Let’s tidy the data
d_mindset_intelligence <- d.study %>%
select(subid_final, condition, mndst_intelligence_t1_score, mndst_intelligence_t2_score)%>%
gather(item, score, contains("intelligence"))%>%
separate(item, sep = "_", into = c("construct_name", "type", "time", "score_name"))%>%
select(-construct_name, -score_name, -type)Let’s change data to be numeric & factors (and appropriate contrasts)
#Make Rating Numeric
d_mindset_intelligence$score <- as.numeric(d_mindset_intelligence$score)
#Factor Condition
d_mindset_intelligence$condition <- as.factor(d_mindset_intelligence$condition)
contrasts(d_mindset_intelligence$condition)## active_control full_intervention
## abr_intervention 0 0
## active_control 1 0
## full_intervention 0 1contrasts(d_mindset_intelligence$condition) = cbind(dummy_full_vs_control = c(0,0,1), dummy_abridged_vs_control = c(1,0,0))
contrasts(d_mindset_intelligence$condition)## dummy_full_vs_control dummy_abridged_vs_control
## abr_intervention 0 1
## active_control 0 0
## full_intervention 1 0#Factor Time
d_mindset_intelligence$time <- as.factor(d_mindset_intelligence$time)
contrasts(d_mindset_intelligence$time)## t2
## t1 0
## t2 1contrasts(d_mindset_intelligence$time) = cbind(dummy_t2_vs_t1 = c(0,1))
contrasts(d_mindset_intelligence$time)## dummy_t2_vs_t1
## t1 0
## t2 1#Factor subject id
d_mindset_intelligence$subid_final <- as.factor(d_mindset_intelligence$subid_final)Analysis
#Analysis
summary(lmer(score ~ time*condition + (1 | subid_final), data = d_mindset_intelligence))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: score ~ time * condition + (1 | subid_final)
## Data: d_mindset_intelligence
##
## REML criterion at convergence: 1436.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.3736 -0.3948 -0.0251 0.3622 4.2113
##
## Random effects:
## Groups Name Variance Std.Dev.
## subid_final (Intercept) 0.4666 0.6831
## Residual 0.2361 0.4859
## Number of obs: 648, groups: subid_final, 324
##
## Fixed effects:
## Estimate Std. Error
## (Intercept) 3.62617 0.08104
## timedummy_t2_vs_t1 0.06542 0.06643
## conditiondummy_full_vs_control -0.09522 0.11515
## conditiondummy_abridged_vs_control -0.02126 0.11332
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 0.13815 0.09440
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 0.00266 0.09289
## df t value
## (Intercept) 445.54554 44.745
## timedummy_t2_vs_t1 321.00001 0.985
## conditiondummy_full_vs_control 445.54554 -0.827
## conditiondummy_abridged_vs_control 445.54554 -0.188
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 321.00001 1.464
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 321.00001 0.029
## Pr(>|t|)
## (Intercept) <2e-16 ***
## timedummy_t2_vs_t1 0.325
## conditiondummy_full_vs_control 0.409
## conditiondummy_abridged_vs_control 0.851
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 0.144
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 0.977
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) tm_2__1 cndtndmmy_f__ cndtndmmy_b__
## tmdmmy_2__1 -0.410
## cndtndmmy_f__ -0.704 0.288
## cndtndmmy_b__ -0.715 0.293 0.503
## tmdmmy_t2_vs_t1:cndtndmmy_f__ 0.288 -0.704 -0.410 -0.206
## tmdmmy_t2_vs_t1:cndtndmmy_b__ 0.293 -0.715 -0.206 -0.410
## tmdmmy_t2_vs_t1:cndtndmmy_f__
## tmdmmy_2__1
## cndtndmmy_f__
## cndtndmmy_b__
## tmdmmy_t2_vs_t1:cndtndmmy_f__
## tmdmmy_t2_vs_t1:cndtndmmy_b__ 0.503Let’s plot!
#Summarize
d_mindset_intelligence_summ <- d_mindset_intelligence %>%
group_by(condition, time) %>%
summarise(mean_rating = mean(score),
ci_rating = ci(score))## `summarise()` regrouping output by 'condition' (override with `.groups` argument)#Change levels
d_mindset_intelligence_summ$time <- factor(d_mindset_intelligence_summ$time, levels = c("t1", "t2"))
#Plot
ggplot(d_mindset_intelligence_summ,
aes(x=time,
y=mean_rating,
fill = condition))+
geom_bar(stat="identity", position = "dodge")+
geom_errorbar(aes(ymin = (mean_rating - ci_rating), ymax = (mean_rating + ci_rating)),width = 0.2, position = position_dodge(width = 0.9))+
labs(x = "",
y = "Agreement (adj) \n 1 = Strongly disagree to 7 = Strongly agree",
title = "Mindset -- Intelligence",
caption = "95% confidence intervals") +
ggthemes::theme_few()+
coord_cartesian(ylim=c(1,7))+
theme(plot.caption =element_text(size=10),
axis.text=element_text(size=14),
axis.title = element_text(size=14),
#axis.text.x=element_blank(),
title = element_text(size=15))
##Descriptives
d_mindset_intelligence %>%
ungroup()%>%
group_by(subid_final, condition, time) %>%
summarise(mean_score = mean(score))%>%
group_by(condition, time)%>%
summarise(mean = mean(mean_score),
sd = sd(mean_score)) %>%
kable(digits = 2)## `summarise()` regrouping output by 'subid_final', 'condition' (override with `.groups` argument)## `summarise()` regrouping output by 'condition' (override with `.groups` argument)| condition | time | mean | sd |
|---|---|---|---|
| abr_intervention | t1 | 3.60 | 0.87 |
| abr_intervention | t2 | 3.67 | 0.88 |
| active_control | t1 | 3.63 | 0.77 |
| active_control | t2 | 3.69 | 0.85 |
| full_intervention | t1 | 3.53 | 0.82 |
| full_intervention | t2 | 3.73 | 0.84 |
Personality
d_mindset_personality <- d.study %>%
select(subid_final, condition, mndst_pers_t1_score, mndst_pers_t2_score)%>%
gather(item, score, contains("pers"))%>%
separate(item, sep = "_", into = c("construct_name", "type", "time", "score_name"))%>%
select(-construct_name, -score_name, -type)Let’s change data to be numeric & factors (and appropriate contrasts)
#Make Rating Numeric
d_mindset_personality$score <- as.numeric(d_mindset_personality$score)
#Factor Condition
d_mindset_personality$condition <- as.factor(d_mindset_personality$condition)
contrasts(d_mindset_personality$condition)## active_control full_intervention
## abr_intervention 0 0
## active_control 1 0
## full_intervention 0 1contrasts(d_mindset_personality$condition) = cbind(dummy_full_vs_control = c(0,0,1), dummy_abridged_vs_control = c(1,0,0))
contrasts(d_mindset_personality$condition)## dummy_full_vs_control dummy_abridged_vs_control
## abr_intervention 0 1
## active_control 0 0
## full_intervention 1 0#Factor Time
d_mindset_personality$time <- as.factor(d_mindset_personality$time)
contrasts(d_mindset_personality$time)## t2
## t1 0
## t2 1contrasts(d_mindset_personality$time) = cbind(dummy_t2_vs_t1 = c(0,1))
contrasts(d_mindset_personality$time)## dummy_t2_vs_t1
## t1 0
## t2 1#Factor subject id
d_mindset_personality$subid_final <- as.factor(d_mindset_personality$subid_final)Analysis
#Analysis
summary(lmer(score ~ time*condition + (1 | subid_final), data = d_mindset_personality))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: score ~ time * condition + (1 | subid_final)
## Data: d_mindset_personality
##
## REML criterion at convergence: 1670.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -5.0158 -0.3224 -0.0108 0.3458 4.9215
##
## Random effects:
## Groups Name Variance Std.Dev.
## subid_final (Intercept) 0.6872 0.8290
## Residual 0.3348 0.5786
## Number of obs: 648, groups: subid_final, 324
##
## Fixed effects:
## Estimate Std. Error
## (Intercept) 4.10514 0.09773
## timedummy_t2_vs_t1 0.02921 0.07911
## conditiondummy_full_vs_control -0.09085 0.13887
## conditiondummy_abridged_vs_control 0.10133 0.13666
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 0.22079 0.11241
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 0.15048 0.11062
## df t value
## (Intercept) 442.10832 42.004
## timedummy_t2_vs_t1 321.00000 0.369
## conditiondummy_full_vs_control 442.10832 -0.654
## conditiondummy_abridged_vs_control 442.10832 0.741
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 321.00000 1.964
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 321.00000 1.360
## Pr(>|t|)
## (Intercept) <2e-16 ***
## timedummy_t2_vs_t1 0.7122
## conditiondummy_full_vs_control 0.5133
## conditiondummy_abridged_vs_control 0.4588
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 0.0504 .
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 0.1747
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) tm_2__1 cndtndmmy_f__ cndtndmmy_b__
## tmdmmy_2__1 -0.405
## cndtndmmy_f__ -0.704 0.285
## cndtndmmy_b__ -0.715 0.289 0.503
## tmdmmy_t2_vs_t1:cndtndmmy_f__ 0.285 -0.704 -0.405 -0.204
## tmdmmy_t2_vs_t1:cndtndmmy_b__ 0.289 -0.715 -0.204 -0.405
## tmdmmy_t2_vs_t1:cndtndmmy_f__
## tmdmmy_2__1
## cndtndmmy_f__
## cndtndmmy_b__
## tmdmmy_t2_vs_t1:cndtndmmy_f__
## tmdmmy_t2_vs_t1:cndtndmmy_b__ 0.503d_mindset_personality %>%
ungroup()%>%
group_by(subid_final, condition, time) %>%
summarise(mean_score = mean(score))%>%
group_by(condition, time)%>%
summarise(mean = mean(mean_score),
sd = sd(mean_score)) %>%
kable(digits = 2)## `summarise()` regrouping output by 'subid_final', 'condition' (override with `.groups` argument)## `summarise()` regrouping output by 'condition' (override with `.groups` argument)| condition | time | mean | sd |
|---|---|---|---|
| abr_intervention | t1 | 4.21 | 1.04 |
| abr_intervention | t2 | 4.39 | 1.06 |
| active_control | t1 | 4.11 | 1.02 |
| active_control | t2 | 4.13 | 1.03 |
| full_intervention | t1 | 4.01 | 0.98 |
| full_intervention | t2 | 4.26 | 0.92 |
Failure
d_mindset_failure <- d.study %>%
select(subid_final, condition, mndst_fail_t1_score, mndst_fail_t2_score)%>%
gather(item, score, contains("fail"))%>%
separate(item, sep = "_", into = c("construct_name", "type", "time", "score_name"))%>%
select(-construct_name, -score_name, -type)Let’s change data to be numeric & factors (and appropriate contrasts)
#Make Rating Numeric
d_mindset_failure$score <- as.numeric(d_mindset_failure$score)
#Factor Condition
d_mindset_failure$condition <- as.factor(d_mindset_failure$condition)
contrasts(d_mindset_failure$condition)## active_control full_intervention
## abr_intervention 0 0
## active_control 1 0
## full_intervention 0 1contrasts(d_mindset_failure$condition) = cbind(dummy_full_vs_control = c(0,0,1), dummy_abridged_vs_control = c(1,0,0))
contrasts(d_mindset_failure$condition)## dummy_full_vs_control dummy_abridged_vs_control
## abr_intervention 0 1
## active_control 0 0
## full_intervention 1 0#Factor Time
d_mindset_failure$time <- as.factor(d_mindset_failure$time)
contrasts(d_mindset_failure$time)## t2
## t1 0
## t2 1contrasts(d_mindset_failure$time) = cbind(dummy_t2_vs_t1 = c(0,1))
contrasts(d_mindset_failure$time)## dummy_t2_vs_t1
## t1 0
## t2 1#Factor subject id
d_mindset_failure$subid_final <- as.factor(d_mindset_failure$subid_final)Analysis
#Analysis
summary(lmer(score ~ time*condition + (1 | subid_final), data = d_mindset_failure))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: score ~ time * condition + (1 | subid_final)
## Data: d_mindset_failure
##
## REML criterion at convergence: 1370.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.3046 -0.3711 -0.0822 0.2697 4.0540
##
## Random effects:
## Groups Name Variance Std.Dev.
## subid_final (Intercept) 0.3525 0.5937
## Residual 0.2378 0.4877
## Number of obs: 648, groups: subid_final, 324
##
## Fixed effects:
## Estimate Std. Error
## (Intercept) 3.780374 0.074275
## timedummy_t2_vs_t1 0.090343 0.066674
## conditiondummy_full_vs_control -0.027993 0.105540
## conditiondummy_abridged_vs_control 0.041055 0.103862
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 0.049340 0.094740
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control -0.007009 0.093234
## df t value
## (Intercept) 473.269933 50.897
## timedummy_t2_vs_t1 321.000005 1.355
## conditiondummy_full_vs_control 473.269933 -0.265
## conditiondummy_abridged_vs_control 473.269933 0.395
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 321.000005 0.521
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 321.000005 -0.075
## Pr(>|t|)
## (Intercept) <2e-16 ***
## timedummy_t2_vs_t1 0.176
## conditiondummy_full_vs_control 0.791
## conditiondummy_abridged_vs_control 0.693
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 0.603
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 0.940
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) tm_2__1 cndtndmmy_f__ cndtndmmy_b__
## tmdmmy_2__1 -0.449
## cndtndmmy_f__ -0.704 0.316
## cndtndmmy_b__ -0.715 0.321 0.503
## tmdmmy_t2_vs_t1:cndtndmmy_f__ 0.316 -0.704 -0.449 -0.226
## tmdmmy_t2_vs_t1:cndtndmmy_b__ 0.321 -0.715 -0.226 -0.449
## tmdmmy_t2_vs_t1:cndtndmmy_f__
## tmdmmy_2__1
## cndtndmmy_f__
## cndtndmmy_b__
## tmdmmy_t2_vs_t1:cndtndmmy_f__
## tmdmmy_t2_vs_t1:cndtndmmy_b__ 0.503d_mindset_failure %>%
ungroup()%>%
group_by(subid_final, condition, time) %>%
summarise(mean_score = mean(score))%>%
group_by(condition, time)%>%
summarise(mean = mean(mean_score),
sd = sd(mean_score)) %>%
kable(digits = 2)## `summarise()` regrouping output by 'subid_final', 'condition' (override with `.groups` argument)## `summarise()` regrouping output by 'condition' (override with `.groups` argument)| condition | time | mean | sd |
|---|---|---|---|
| abr_intervention | t1 | 3.82 | 0.76 |
| abr_intervention | t2 | 3.90 | 0.85 |
| active_control | t1 | 3.78 | 0.72 |
| active_control | t2 | 3.87 | 0.75 |
| full_intervention | t1 | 3.75 | 0.72 |
| full_intervention | t2 | 3.89 | 0.79 |
Process
d_mindset_process <- d.study %>%
select(subid_final, condition, mndst_process_t1_score, mndst_process_t2_score)%>%
gather(item, score, contains("process"))%>%
separate(item, sep = "_", into = c("construct_name", "type", "time", "score_name"))%>%
select(-construct_name, -score_name, -type)Let’s change data to be numeric & factors (and appropriate contrasts)
#Make Rating Numeric
d_mindset_process$score <- as.numeric(d_mindset_process$score)
#Factor Condition
d_mindset_process$condition <- as.factor(d_mindset_process$condition)
contrasts(d_mindset_process$condition)## active_control full_intervention
## abr_intervention 0 0
## active_control 1 0
## full_intervention 0 1contrasts(d_mindset_process$condition) = cbind(dummy_full_vs_control = c(0,0,1), dummy_abridged_vs_control = c(1,0,0))
contrasts(d_mindset_process$condition)## dummy_full_vs_control dummy_abridged_vs_control
## abr_intervention 0 1
## active_control 0 0
## full_intervention 1 0#Factor Time
d_mindset_process$time <- as.factor(d_mindset_process$time)
contrasts(d_mindset_process$time)## t2
## t1 0
## t2 1contrasts(d_mindset_process$time) = cbind(dummy_t2_vs_t1 = c(0,1))
contrasts(d_mindset_process$time)## dummy_t2_vs_t1
## t1 0
## t2 1#Factor subject id
d_mindset_failure$subid_final <- as.factor(d_mindset_failure$subid_final)Analysis
#Analysis
summary(lmer(score ~ time*condition + (1 | subid_final), data = d_mindset_process))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: score ~ time * condition + (1 | subid_final)
## Data: d_mindset_process
##
## REML criterion at convergence: 935.4
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.50450 -0.47464 -0.01444 0.51168 2.50823
##
## Random effects:
## Groups Name Variance Std.Dev.
## subid_final (Intercept) 0.2096 0.4578
## Residual 0.1095 0.3309
## Number of obs: 648, groups: subid_final, 324
##
## Fixed effects:
## Estimate Std. Error
## (Intercept) 2.86248 0.05461
## timedummy_t2_vs_t1 0.06275 0.04524
## conditiondummy_full_vs_control -0.02439 0.07760
## conditiondummy_abridged_vs_control 0.07502 0.07636
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 0.08691 0.06428
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control -0.04362 0.06326
## df t value
## (Intercept) 448.47592 52.417
## timedummy_t2_vs_t1 321.00001 1.387
## conditiondummy_full_vs_control 448.47592 -0.314
## conditiondummy_abridged_vs_control 448.47592 0.982
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 321.00001 1.352
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 321.00001 -0.690
## Pr(>|t|)
## (Intercept) <2e-16 ***
## timedummy_t2_vs_t1 0.166
## conditiondummy_full_vs_control 0.753
## conditiondummy_abridged_vs_control 0.326
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 0.177
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 0.491
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) tm_2__1 cndtndmmy_f__ cndtndmmy_b__
## tmdmmy_2__1 -0.414
## cndtndmmy_f__ -0.704 0.291
## cndtndmmy_b__ -0.715 0.296 0.503
## tmdmmy_t2_vs_t1:cndtndmmy_f__ 0.291 -0.704 -0.414 -0.208
## tmdmmy_t2_vs_t1:cndtndmmy_b__ 0.296 -0.715 -0.208 -0.414
## tmdmmy_t2_vs_t1:cndtndmmy_f__
## tmdmmy_2__1
## cndtndmmy_f__
## cndtndmmy_b__
## tmdmmy_t2_vs_t1:cndtndmmy_f__
## tmdmmy_t2_vs_t1:cndtndmmy_b__ 0.503d_mindset_process %>%
ungroup()%>%
group_by(subid_final, condition, time) %>%
summarise(mean_score = mean(score))%>%
group_by(condition, time)%>%
summarise(mean = mean(mean_score),
sd = sd(mean_score)) %>%
kable(digits = 2)## `summarise()` regrouping output by 'subid_final', 'condition' (override with `.groups` argument)## `summarise()` regrouping output by 'condition' (override with `.groups` argument)| condition | time | mean | sd |
|---|---|---|---|
| abr_intervention | t1 | 2.94 | 0.53 |
| abr_intervention | t2 | 2.96 | 0.56 |
| active_control | t1 | 2.86 | 0.56 |
| active_control | t2 | 2.93 | 0.60 |
| full_intervention | t1 | 2.84 | 0.57 |
| full_intervention | t2 | 2.99 | 0.58 |
####Exercise Mindset
Let’s tidy the data
d_mindset_exercise <- d.study %>%
select(subid_final, condition, mndst_exercise_t1_score, mndst_exercise_t2_score)%>%
gather(item, score, contains("exercise"))%>%
separate(item, sep = "_", into = c("construct_name", "type", "time", "score_name"))%>%
select(-construct_name, -score_name, -type)Let’s change data to be numeric & factors (and appropriate contrasts)
#Make Rating Numeric
d_mindset_exercise$score <- as.numeric(d_mindset_exercise$score)
#Factor Condition
d_mindset_exercise$condition <- as.factor(d_mindset_exercise$condition)
contrasts(d_mindset_exercise$condition)## active_control full_intervention
## abr_intervention 0 0
## active_control 1 0
## full_intervention 0 1contrasts(d_mindset_exercise$condition)= cbind(dummy_full_vs_control = c(0,0,1), dummy_abridged_vs_control = c(1,0,0))
contrasts(d_mindset_exercise$condition)## dummy_full_vs_control dummy_abridged_vs_control
## abr_intervention 0 1
## active_control 0 0
## full_intervention 1 0#Factor Time
d_mindset_exercise$time <- as.factor(d_mindset_exercise$time)
contrasts(d_mindset_exercise$time)## t2
## t1 0
## t2 1contrasts(d_mindset_exercise$time) = cbind(dummy_t2_vs_t1 = c(0,1))
contrasts(d_mindset_exercise$time)## dummy_t2_vs_t1
## t1 0
## t2 1#Factor subject id
d_mindset_exercise$subid_final <- as.factor(d_mindset_exercise$subid_final)Analysis
#Analysis
summary(lmer(score ~ time*condition + (1 | subid_final), data = d_mindset_exercise))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: score ~ time * condition + (1 | subid_final)
## Data: d_mindset_exercise
##
## REML criterion at convergence: 1795.6
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.7155 -0.4781 -0.0023 0.4637 2.8513
##
## Random effects:
## Groups Name Variance Std.Dev.
## subid_final (Intercept) 0.9279 0.9633
## Residual 0.3779 0.6147
## Number of obs: 648, groups: subid_final, 324
##
## Fixed effects:
## Estimate Std. Error
## (Intercept) 4.666542 0.110470
## timedummy_t2_vs_t1 -0.097196 0.084047
## conditiondummy_full_vs_control 0.002029 0.156970
## conditiondummy_abridged_vs_control -0.055828 0.154475
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 0.220244 0.119425
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 0.245768 0.117526
## df t value
## (Intercept) 426.597671 42.243
## timedummy_t2_vs_t1 321.000011 -1.156
## conditiondummy_full_vs_control 426.597672 0.013
## conditiondummy_abridged_vs_control 426.597672 -0.361
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 321.000011 1.844
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 321.000011 2.091
## Pr(>|t|)
## (Intercept) <2e-16 ***
## timedummy_t2_vs_t1 0.2484
## conditiondummy_full_vs_control 0.9897
## conditiondummy_abridged_vs_control 0.7180
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 0.0661 .
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 0.0373 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) tm_2__1 cndtndmmy_f__ cndtndmmy_b__
## tmdmmy_2__1 -0.380
## cndtndmmy_f__ -0.704 0.268
## cndtndmmy_b__ -0.715 0.272 0.503
## tmdmmy_t2_vs_t1:cndtndmmy_f__ 0.268 -0.704 -0.380 -0.191
## tmdmmy_t2_vs_t1:cndtndmmy_b__ 0.272 -0.715 -0.191 -0.380
## tmdmmy_t2_vs_t1:cndtndmmy_f__
## tmdmmy_2__1
## cndtndmmy_f__
## cndtndmmy_b__
## tmdmmy_t2_vs_t1:cndtndmmy_f__
## tmdmmy_t2_vs_t1:cndtndmmy_b__ 0.503Let’s plot!
#Summarize
d_mindset_exercise_summ <- d_mindset_exercise %>%
group_by(condition, time) %>%
summarise(mean_rating = mean(score),
ci_rating = ci(score))## `summarise()` regrouping output by 'condition' (override with `.groups` argument)#Change levels
d_mindset_exercise_summ$time <- factor(d_mindset_exercise_summ$time, levels = c("t1", "t2"))
#Plot
ggplot(d_mindset_exercise_summ,
aes(x=time,
y=mean_rating,
fill = condition))+
geom_bar(stat="identity", position = "dodge")+
geom_errorbar(aes(ymin = (mean_rating - ci_rating), ymax = (mean_rating + ci_rating)),width = 0.2, position = position_dodge(width = 0.9))+
labs(x = "",
y = "Agreement (adj) \n 1 = Strongly disagree to 7 = Strongly agree",
title = "Mindset -- Exercise",
caption = "95% confidence intervals") +
ggthemes::theme_few()+
coord_cartesian(ylim=c(1,7))+
theme(plot.caption =element_text(size=10),
axis.text=element_text(size=14),
axis.title = element_text(size=14),
#axis.text.x=element_blank(),
title = element_text(size=15))
##Descriptives
d_mindset_exercise %>%
ungroup()%>%
group_by(subid_final, condition, time) %>%
summarise(mean_score = mean(score))%>%
group_by(condition, time)%>%
summarise(mean = mean(mean_score),
sd = sd(mean_score)) %>%
kable(digits = 2)## `summarise()` regrouping output by 'subid_final', 'condition' (override with `.groups` argument)## `summarise()` regrouping output by 'condition' (override with `.groups` argument)| condition | time | mean | sd |
|---|---|---|---|
| abr_intervention | t1 | 4.61 | 1.15 |
| abr_intervention | t2 | 4.76 | 1.28 |
| active_control | t1 | 4.67 | 1.15 |
| active_control | t2 | 4.57 | 1.19 |
| full_intervention | t1 | 4.67 | 1.06 |
| full_intervention | t2 | 4.79 | 1.00 |
####Stress Mindset
Let’s tidy the data
d_mindset_stress <- d.study %>%
select(subid_final, condition, mndst_stress_t1_score, mndst_stress_t2_score)%>%
gather(item, score, contains("stress"))%>%
separate(item, sep = "_", into = c("construct_name", "type", "time", "score_name"))%>%
select(-construct_name, -score_name, -type)Let’s change data to be numeric & factors (and appropriate contrasts)
#Make Rating Numeric
d_mindset_stress$score <- as.numeric(d_mindset_stress$score)
#Factor Condition
d_mindset_stress$condition <- as.factor(d_mindset_stress$condition)
contrasts(d_mindset_stress$condition)## active_control full_intervention
## abr_intervention 0 0
## active_control 1 0
## full_intervention 0 1contrasts(d_mindset_stress$condition) =cbind(dummy_full_vs_control = c(0,0,1), dummy_abridged_vs_control = c(1,0,0))
contrasts(d_mindset_stress$condition)## dummy_full_vs_control dummy_abridged_vs_control
## abr_intervention 0 1
## active_control 0 0
## full_intervention 1 0#Factor Time
d_mindset_stress$time <- as.factor(d_mindset_stress$time)
contrasts(d_mindset_stress$time)## t2
## t1 0
## t2 1contrasts(d_mindset_stress$time) = cbind(dummy_t2_vs_t1 = c(0,1))
contrasts(d_mindset_stress$time)## dummy_t2_vs_t1
## t1 0
## t2 1#Factor subject id
d_mindset_stress$subid_final <- as.factor(d_mindset_stress$subid_final)Analysis
#Analysis
summary(lmer(score ~ time*condition + (1 | subid_final), data = d_mindset_stress))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: score ~ time * condition + (1 | subid_final)
## Data: d_mindset_stress
##
## REML criterion at convergence: 1216.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.3928 -0.4316 0.0589 0.5032 3.2245
##
## Random effects:
## Groups Name Variance Std.Dev.
## subid_final (Intercept) 0.08469 0.2910
## Residual 0.29774 0.5457
## Number of obs: 648, groups: subid_final, 324
##
## Fixed effects:
## Estimate Std. Error
## (Intercept) 1.831e+00 5.978e-02
## timedummy_t2_vs_t1 -4.673e-03 7.460e-02
## conditiondummy_full_vs_control 4.677e-02 8.495e-02
## conditiondummy_abridged_vs_control 8.657e-04 8.360e-02
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 3.940e-01 1.060e-01
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 3.529e-01 1.043e-01
## df t value
## (Intercept) 6.120e+02 30.621
## timedummy_t2_vs_t1 3.210e+02 -0.063
## conditiondummy_full_vs_control 6.120e+02 0.551
## conditiondummy_abridged_vs_control 6.120e+02 0.010
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 3.210e+02 3.717
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 3.210e+02 3.383
## Pr(>|t|)
## (Intercept) < 2e-16 ***
## timedummy_t2_vs_t1 0.950093
## conditiondummy_full_vs_control 0.582101
## conditiondummy_abridged_vs_control 0.991741
## timedummy_t2_vs_t1:conditiondummy_full_vs_control 0.000238 ***
## timedummy_t2_vs_t1:conditiondummy_abridged_vs_control 0.000806 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) tm_2__1 cndtndmmy_f__ cndtndmmy_b__
## tmdmmy_2__1 -0.624
## cndtndmmy_f__ -0.704 0.439
## cndtndmmy_b__ -0.715 0.446 0.503
## tmdmmy_t2_vs_t1:cndtndmmy_f__ 0.439 -0.704 -0.624 -0.314
## tmdmmy_t2_vs_t1:cndtndmmy_b__ 0.446 -0.715 -0.314 -0.624
## tmdmmy_t2_vs_t1:cndtndmmy_f__
## tmdmmy_2__1
## cndtndmmy_f__
## cndtndmmy_b__
## tmdmmy_t2_vs_t1:cndtndmmy_f__
## tmdmmy_t2_vs_t1:cndtndmmy_b__ 0.503Let’s plot!
#Summarize
d_mindset_stress_summ <- d_mindset_stress %>%
group_by(condition, time) %>%
summarise(mean_rating = mean(score),
ci_rating = ci(score))## `summarise()` regrouping output by 'condition' (override with `.groups` argument)#Change levels
d_mindset_stress_summ$time <- factor(d_mindset_stress_summ$time, levels = c("t1", "t2"))
#Plot
ggplot(d_mindset_stress_summ,
aes(x=time,
y=mean_rating,
fill = condition))+
geom_bar(stat="identity", position = "dodge")+
geom_errorbar(aes(ymin = (mean_rating - ci_rating), ymax = (mean_rating + ci_rating)),width = 0.2, position = position_dodge(width = 0.9))+
labs(x = "",
y = "Agreement (adj) \n 0 = Strongly disagree to 4 = Strongly agree",
title = "Mindset -- Stress",
caption = "95% confidence intervals") +
ggthemes::theme_few()+
coord_cartesian(ylim=c(0,4))+
theme(plot.caption =element_text(size=10),
axis.text=element_text(size=14),
axis.title = element_text(size=14),
#axis.text.x=element_blank(),
title = element_text(size=15))
##Descriptives
d_mindset_intelligence %>%
ungroup()%>%
group_by(subid_final, condition, time) %>%
summarise(mean_score = mean(score))%>%
group_by(condition, time)%>%
summarise(mean = mean(mean_score),
sd = sd(mean_score)) %>%
kable(digits = 2)## `summarise()` regrouping output by 'subid_final', 'condition' (override with `.groups` argument)## `summarise()` regrouping output by 'condition' (override with `.groups` argument)| condition | time | mean | sd |
|---|---|---|---|
| abr_intervention | t1 | 3.60 | 0.87 |
| abr_intervention | t2 | 3.67 | 0.88 |
| active_control | t1 | 3.63 | 0.77 |
| active_control | t2 | 3.69 | 0.85 |
| full_intervention | t1 | 3.53 | 0.82 |
| full_intervention | t2 | 3.73 | 0.84 |
###All mindsets
##Plot
#Create tidy
d_mindset_all <- d.study %>%
select(subid_final, condition,
mndst_pers_t1_score, mndst_pers_t2_score,
mndst_process_t1_score, mndst_process_t2_score,
mndst_fail_t1_score, mndst_fail_t2_score,
mndst_exercise_t1_score, mndst_exercise_t2_score,
mndst_intelligence_t1_score, mndst_intelligence_t2_score,
mndst_stress_t1_score, mndst_stress_t2_score)%>%
gather(item, score, contains("score"))%>%
separate(item, sep = "_", into = c("mndst_name", "mndst_domain", "time", "score_name"))%>%
select(-mndst_name, -score_name) %>%
mutate(condition = ifelse(condition == "active_control", "Active Control",
ifelse(condition == "full_intervention", "Full Intervention",
ifelse(condition == "abr_intervention", "Abridged Intervention", "Error"))))
#mutate(time = ifelse(time == "t1", "Baseline",
# ifelse(time == "t2", "Post-Intervention", "error")))
#Summarize
d_meta_summ <- d_mindset_all %>%
group_by(condition, mndst_domain, time) %>%
summarise(mean_rating = mean(score),
ci_rating = ci(score))## `summarise()` regrouping output by 'condition', 'mndst_domain' (override with `.groups` argument)#Create list of lines
d_hline <- d_meta_summ %>%
filter((time == "Baseline") & (condition == "Active Control")) %>%
ungroup() %>%
select(mndst_domain) %>%
mutate(hline = ifelse(mndst_domain == "Exercise Mindset", 4,
ifelse(mndst_domain == "Intelligence Mindset", 3.5,
ifelse(mndst_domain == "Stress Mindset", 2, "error"))))
d_hline$hline <- as.numeric(d_hline$hline)
#Change levels
#d_meta_summ$time <- factor(d_meta_summ$time, levels = c("Baseline", "Post-Intervention"))
d_meta_summ$condition <- factor(d_meta_summ$condition, levels = c( "Full Intervention", "Abridged Intervention", "Active Control"))
#Colors
group.colors <- c("Active Control" = "#D3D3D3", "Abridged Intervention" = "#999999", "Full Intervention" = "#E69F00")
#Caption
caption <- "Note. Meta-mindset intervention, compared to the active control and the non-active control, lead to an increase in intelligence and stress mindset scores post-intervention compared to baseline. Horizontal grey line is midpoint of each scale (exercise mindset: 1 to 7; intelligence mindset: 1 to 6; stress mindset: 0 to 4). Participants received intervention or controls one week after baseline. Error bars represent 95% confidence intervals."
#Prep
wrap_strings <- function(vector_of_strings,width){as.character(sapply(vector_of_strings,FUN=function(x){paste(strwrap(x,width=width), collapse="\n")}))}
#function from here: https://stackoverflow.com/questions/7367138/text-wrap-for-plot-titles
#Plot
ggplot(d_meta_summ,
aes(x=time,
y=mean_rating,
col = condition))+
geom_point(size=3) +
geom_errorbar(data=d_meta_summ, aes(ymin = (mean_rating - ci_rating), ymax = (mean_rating + ci_rating)),width = 0.2, size = 1)+
geom_line(aes(group = condition, color=condition), size = 1) +
#geom_jitter(data=d_mindset_all, aes(x = time, y = score, col=condition),width=.1, height=.1,size=.6, alpha = 0.25) +
#geom_hline(data= d_hline, aes(yintercept=hline), linetype = "dotted") +
facet_grid(~mndst_domain, scales = "free_y") +
scale_color_manual(values=group.colors)+
scale_y_discrete(limits=c(1,2,3,4,5,6)) +
coord_cartesian(ylim=c(1,6.2)) +
scale_y_continuous(expand = c(0,0)) +
theme_few() +
labs(x = "Time",
y = "Mindset Score",
title = "Figure 2\nStudy 4: Effect of Condition on Mindset Scores"
#colour = "Condition",
#linetype = "Significance"
) +
theme(text = element_text(family = "Times New Roman"),
plot.caption =element_text(size=10, hjust = 0),
axis.text=element_text(size=12),
axis.title = element_text(size=12),
#axis.text.x=element_blank(),
title = element_text(size=12)) ## Warning: Continuous limits supplied to discrete scale.
## Did you mean `limits = factor(...)` or `scale_*_continuous()`?## Scale for 'y' is already present. Adding another scale for 'y', which will
## replace the existing scale.
=======
#Summarize new variables (CMM and mindfulness) #In this questionnaire you will be shown a number of statements regarding mindsets. Please indicate your agreement with each statement by selecting the number that best represents your answer on the scale presented below the statement.
1. No matter what kind of mindset I have, I can always change it.
2. To be honest, you can’t really change your mindsets. (R)
3. I can develop my ability to control my mindsets.
4. I could learn to have more control over my mindsets.
5. When it is necessary to, I have a considerable amount of control over my mindset.
6. You can learn about new mindsets, but you can’t really change your basic ability to control your mindset. (R)
7. As much as I hate to admit it, you can’t teach an old dog new tricks. You can’t really change your mindsets about things in the world. (R)
8. You have certain mindsets about the world, and there is not much that can be done to really change that.(R)
9. Even in moments when it really matters, I can’t do much to change my mindset. (R)
10. How much I can control my mindset is something about me that I can’t change very much. (R)
Scale: Strongly disagree (1), Disagree (2), Somewhat disagree (3), Somewhat agree (4), Agree (5), Strongly Agree (6)
Scoring: Reverse score items 2, 6, 7, 8, 9 and 10. Then, compute the mean score of all the items. A higher score will indicate greater agreement that one’s mindset is controllable and changeable.
CMM
Scoring: Reverse score items 2, 6, 7, 8, 9 and 10. Then, compute the mean score of all the items. A higher score will indicate greater agreement that one’s mindset is controllable and changeable.
d.study <- d.study %>%
mutate(t2_cmm_2_reversed = 7 - t2_cmm_2_toreverse,
t2_cmm_6_reversed = 7 - t2_cmm_6_toreverse,
t2_cmm_7_reversed = 7 - t2_cmm_7_toreverse,
t2_cmm_8_reversed = 7 - t2_cmm_8_toreverse,
t2_cmm_9_reversed = 7 - t2_cmm_9_toreverse,
t2_cmm_10_reversed = 7 - t2_cmm_10_toreverse) %>%
mutate(cmm_t2_score = (t2_cmm_1 +
t2_cmm_2_reversed +
t2_cmm_3 +
t2_cmm_4 +
t2_cmm_5 +
t2_cmm_6_reversed +
t2_cmm_7_reversed +
t2_cmm_8_reversed +
t2_cmm_9_reversed +
t2_cmm_10_reversed)/10)d.study <- d.study %>%
mutate(cmm_t2_score_6 = (t2_cmm_2_reversed + t2_cmm_6_reversed +
t2_cmm_7_reversed +
t2_cmm_8_reversed +
t2_cmm_9_reversed +
t2_cmm_10_reversed)/6)d.study <- d.study %>% mutate(cmm_t2_score_4 = (t2_cmm_2_reversed + t2_cmm_7_reversed +
t2_cmm_9_reversed +
t2_cmm_10_reversed)/4)#PANAS
d.study <- d.study %>%
mutate(posaff_sum = (t2_fil_panas_1 +
t2_fil_panas_3 +
t2_fil_panas_5 +
t2_fil_panas_9 +
t2_fil_panas_10 +
t2_fil_panas_12 +
t2_fil_panas_14 +
t2_fil_panas_17 +
t2_fil_panas_19),
negaff_sum = (t2_fil_panas_2 +
t2_fil_panas_4 +
t2_fil_panas_6 +
t2_fil_panas_7 +
t2_fil_panas_8 +
t2_fil_panas_11 +
t2_fil_panas_13 +
t2_fil_panas_15 +
t2_fil_panas_18 +
t2_fil_panas_20))
#missing item16 from the pos aff so max is 45 while max for neg is 50####Self-efficacy (post)
Scoring: Compute the sum of the items. Higher scores indicate more self-efficacy.
d.study <- d.study %>%
mutate(selfefficacy_score = (t2_fil_selfeff_1 +
t2_fil_selfeff_2 +
t2_fil_selfeff_3 +
t2_fil_selfeff_4 +
t2_fil_selfeff_5 +
t2_fil_selfeff_6 +
t2_fil_selfeff_7 +
t2_fil_selfeff_8 +
t2_fil_selfeff_9 +
t2_fil_selfeff_10))#mindfulness by factor than whole ffmq-15
#Observe 1, 6, 11
d.study <- d.study %>%
mutate(ffmq_obs = t2_ffmq15_1 + t2_ffmq15_6 + t2_ffmq15_11/3)
#describe 2, 7R, 12
d.study <- d.study %>%
mutate(t2_ffmq15_7_reversed = 6 - t2_ffmq15_7) %>%
mutate(ffmq_des = t2_ffmq15_2 + t2_ffmq15_7_reversed + t2_ffmq15_12/3)
#acting with awareness 3R, 8R, 13R
d.study <- d.study %>%
mutate(t2_ffmq15_3_reversed = 6 - t2_ffmq15_3,
t2_ffmq15_8_reversed = 6 - t2_ffmq15_8,
t2_ffmq15_13_reversed = 6 - t2_ffmq15_13) %>%
mutate(ffmq_awa = t2_ffmq15_3_reversed + t2_ffmq15_8_reversed + t2_ffmq15_13_reversed/3)
#nonjudging 4R, 9R, 14R
d.study <- d.study %>%
mutate(t2_ffmq15_4_reversed = 6 - t2_ffmq15_4,
t2_ffmq15_9_reversed = 6 - t2_ffmq15_9,
t2_ffmq15_14_reversed = 6 - t2_ffmq15_14) %>%
mutate(ffmq_nj = t2_ffmq15_4_reversed + t2_ffmq15_9_reversed + t2_ffmq15_14_reversed/3)
#nonreactivity 5,10, 15
d.study <- d.study %>%
mutate(ffmq_nr = t2_ffmq15_5 + t2_ffmq15_10 + t2_ffmq15_15/3)
#ffmq15-entire scale
d.study <- d.study %>%
mutate(ffmq15_5f = ffmq_obs + ffmq_des + ffmq_awa + ffmq_nj + ffmq_nr)#meta-awareness-observe factor only ffmq-39
d.study <- d.study %>%
mutate(MetAwa = t2_ffmq_1 + t2_ffmq_2 + t2_ffmq_3 + t2_ffmq_4 + t2_ffmq_5/5)#create table with the expl variables (CMM and other mindsets)
library(tidyverse)
df <- d.study %>%
select(ffmq15_5f, ffmq_obs, ffmq_des, ffmq_awa, ffmq_nj, ffmq_nr, MetAwa, cmm_t2_score, mndst_intelligence_t2_score, mndst_process_t2_score, mndst_exercise_t2_score, mndst_fail_t2_score, mndst_pers_t2_score, mndst_stress_t2_score, subid_final, condition, sfmm_all9_t2_score, cmm_t2_score_6, selfefficacy_score, posaff_sum, negaff_sum, cmm_t2_score_4)
names(df)## [1] "ffmq15_5f" "ffmq_obs"
## [3] "ffmq_des" "ffmq_awa"
## [5] "ffmq_nj" "ffmq_nr"
## [7] "MetAwa" "cmm_t2_score"
## [9] "mndst_intelligence_t2_score" "mndst_process_t2_score"
## [11] "mndst_exercise_t2_score" "mndst_fail_t2_score"
## [13] "mndst_pers_t2_score" "mndst_stress_t2_score"
## [15] "subid_final" "condition"
## [17] "sfmm_all9_t2_score" "cmm_t2_score_6"
## [19] "selfefficacy_score" "posaff_sum"
## [21] "negaff_sum" "cmm_t2_score_4"names(df)## [1] "ffmq15_5f" "ffmq_obs"
## [3] "ffmq_des" "ffmq_awa"
## [5] "ffmq_nj" "ffmq_nr"
## [7] "MetAwa" "cmm_t2_score"
## [9] "mndst_intelligence_t2_score" "mndst_process_t2_score"
## [11] "mndst_exercise_t2_score" "mndst_fail_t2_score"
## [13] "mndst_pers_t2_score" "mndst_stress_t2_score"
## [15] "subid_final" "condition"
## [17] "sfmm_all9_t2_score" "cmm_t2_score_6"
## [19] "selfefficacy_score" "posaff_sum"
## [21] "negaff_sum" "cmm_t2_score_4"str(df)## tibble [324 × 22] (S3: tbl_df/tbl/data.frame)
## $ ffmq15_5f : num [1:324] 37.7 35 37 32.7 38.3 ...
## $ ffmq_obs : num [1:324] 10.67 8.33 8.33 9.67 9.33 ...
## $ ffmq_des : num [1:324] 6.33 8 8 7.33 6.33 ...
## $ ffmq_awa : num [1:324] 4.33 6.67 4.67 3.33 8.67 ...
## $ ffmq_nj : num [1:324] 5.67 5 7 3.67 7.67 ...
## $ ffmq_nr : num [1:324] 10.67 7 9 8.67 6.33 ...
## $ MetAwa : num [1:324] 16.8 14.8 15.6 16.8 18 12.6 16.8 19 18 7.2 ...
## $ cmm_t2_score : num [1:324] 3.4 3.2 3.2 3.2 3.3 3.4 3.1 3.3 3 3.2 ...
## $ mndst_intelligence_t2_score: num [1:324] 3.25 3.5 3.25 3.75 3.62 ...
## $ mndst_process_t2_score : num [1:324] 2.86 2.43 2.29 3.43 3.86 ...
## $ mndst_exercise_t2_score : num [1:324] 3.6 4.24 4.24 4.32 7 3.64 4.92 5.2 5 4.8 ...
## $ mndst_fail_t2_score : num [1:324] 3.67 3.5 3.5 3.83 3.5 ...
## $ mndst_pers_t2_score : num [1:324] 4 3.75 3.75 4 4 ...
## $ mndst_stress_t2_score : num [1:324] 2.25 2.5 2.12 2.5 3.12 ...
## $ subid_final : num [1:324] 12 14 286 96 118 4 36 227 7 1 ...
## $ condition : chr [1:324] "full_intervention" "abr_intervention" "active_control" "active_control" ...
## $ sfmm_all9_t2_score : num [1:324] 5.11 4.22 5 5.22 6 ...
## $ cmm_t2_score_6 : num [1:324] 2.17 2.5 2.17 1.83 1.5 ...
## $ selfefficacy_score : num [1:324] 35 25 29 35 40 26 30 37 34 31 ...
## $ posaff_sum : num [1:324] 37 26 33 39 42 16 37 39 40 43 ...
## $ negaff_sum : num [1:324] 40 28 38 46 10 18 33 44 42 14 ...
## $ cmm_t2_score_4 : num [1:324] 2.25 2.25 2 1.75 1.25 2.75 2 1.75 1.5 1.75 ...head(df)## # A tibble: 6 x 22
## ffmq15_5f ffmq_obs ffmq_des ffmq_awa ffmq_nj ffmq_nr MetAwa cmm_t2_score
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 37.7 10.7 6.33 4.33 5.67 10.7 16.8 3.4
## 2 35 8.33 8 6.67 5 7 14.8 3.2
## 3 37 8.33 8 4.67 7 9 15.6 3.2
## 4 32.7 9.67 7.33 3.33 3.67 8.67 16.8 3.2
## 5 38.3 9.33 6.33 8.67 7.67 6.33 18 3.3
## 6 33.3 6.67 6 6.67 7 7 12.6 3.4
## # … with 14 more variables: mndst_intelligence_t2_score <dbl>,
## # mndst_process_t2_score <dbl>, mndst_exercise_t2_score <dbl>,
## # mndst_fail_t2_score <dbl>, mndst_pers_t2_score <dbl>,
## # mndst_stress_t2_score <dbl>, subid_final <dbl>, condition <chr>,
## # sfmm_all9_t2_score <dbl>, cmm_t2_score_6 <dbl>, selfefficacy_score <dbl>,
## # posaff_sum <dbl>, negaff_sum <dbl>, cmm_t2_score_4 <dbl>#add health?#scatter plots
# FFMQ15 and CMM
ggplot(df, aes(x=ffmq15_5f,
y=cmm_t2_score_4)) +
geom_point() +
facet_wrap(~condition)
# MetAwa and CMM
ggplot(df, aes(x=MetAwa,
y=cmm_t2_score)) +
geom_point() +
facet_wrap(~condition)
#Sfmm
ggplot(df, aes(x=sfmm_all9_t2_score,
y=cmm_t2_score)) +
geom_point() +
facet_wrap(~condition)
#intelligence mindset
ggplot(df, aes(x=mndst_intelligence_t2_score,
y=cmm_t2_score)) +
geom_point() +
facet_wrap(~condition)
#process mindset
ggplot(df, aes(x=mndst_process_t2_score,
y=cmm_t2_score)) +
geom_point() +
facet_wrap(~condition)
#exercise mindset
ggplot(df, aes(x=mndst_exercise_t2_score,
y=cmm_t2_score)) +
geom_point() +
facet_wrap(~condition)
#fail mindset
ggplot(df, aes(x=mndst_fail_t2_score,
y=cmm_t2_score)) +
geom_point() +
facet_wrap(~condition)
#personality mindset
ggplot(df, aes(x=mndst_pers_t2_score,
y=cmm_t2_score)) +
geom_point() +
facet_wrap(~condition)
#stress mindset
ggplot(df, aes(x=mndst_stress_t2_score,
y=cmm_t2_score)) +
geom_point() +
facet_wrap(~condition)
#scatter plots with CMM 4 item
# FFMQ15 and CMM
ggplot(df, aes(x=ffmq15_5f,
y=cmm_t2_score_4)) +
geom_point() +
facet_wrap(~condition)
# MetAwa and CMM
ggplot(df, aes(x=MetAwa,
y=cmm_t2_score_4)) +
geom_point() +
facet_wrap(~condition)
#Sfmm
ggplot(df, aes(x=sfmm_all9_t2_score,
y=cmm_t2_score_4)) +
geom_point() +
facet_wrap(~condition)
#intelligence mindset
ggplot(df, aes(x=mndst_intelligence_t2_score,
y=cmm_t2_score_4)) +
geom_point() +
facet_wrap(~condition)
#process mindset
ggplot(df, aes(x=mndst_process_t2_score,
y=cmm_t2_score_4)) +
geom_point() +
facet_wrap(~condition)
#exercise mindset
ggplot(df, aes(x=mndst_exercise_t2_score,
y=cmm_t2_score_4)) +
geom_point() +
facet_wrap(~condition)
#fail mindset
ggplot(df, aes(x=mndst_fail_t2_score,
y=cmm_t2_score_4)) +
geom_point() +
facet_wrap(~condition)
#personality mindset
ggplot(df, aes(x=mndst_pers_t2_score,
y=cmm_t2_score_4)) +
geom_point() +
facet_wrap(~condition)
#stress mindset
ggplot(df, aes(x=mndst_stress_t2_score,
y=cmm_t2_score_4)) +
geom_point() +
facet_wrap(~condition)
boxplot(df$cmm_t2_score) #few outliers with 10 item
boxplot(df$cmm_t2_score_6) # 6item more normal range
boxplot(df$cmm_t2_score_4) #4 item
controllability have normal distributions?
library("psych")##
## Attaching package: 'psych'## The following objects are masked from 'package:ggplot2':
##
## %+%, alpha#histograms
hist(df$cmm_t2_score_4)#**
hist(df$cmm_t2_score_6) #**
hist(df$ffmq15_5f)
hist(df$MetAwa)
hist(df$mndst_intelligence_t2_score)
hist(df$mndst_process_t2_score)
hist(df$sfmm_all9_t2_score)
hist(df$mndst_exercise_t2_score)
hist(df$mndst_fail_t2_score)
hist(df$mndst_pers_t2_score)
hist(df$mndst_stress_t2_score)
#descriptives of variables **
describe.by(df)## Warning: describe.by is deprecated. Please use the describeBy function## Warning in describeBy(x = x, group = group, mat = mat, type = type, ...): no
## grouping variable requested## vars n mean sd median trimmed mad min
## ffmq15_5f 1 324 38.34 5.33 37.33 37.74 4.45 27.33
## ffmq_obs 2 324 8.58 1.66 8.33 8.62 1.48 3.67
## ffmq_des 3 324 7.78 1.74 7.67 7.69 1.48 3.33
## ffmq_awa 4 324 7.21 2.39 7.00 7.16 2.97 2.33
## ffmq_nj 5 324 6.61 2.49 6.00 6.45 2.47 2.33
## ffmq_nr 6 324 8.16 1.93 8.17 8.20 1.73 2.33
## MetAwa 7 324 15.49 2.77 15.60 15.58 2.67 6.20
## cmm_t2_score 8 324 3.78 0.92 3.40 3.63 0.44 2.70
## mndst_intelligence_t2_score 9 324 3.70 0.85 3.62 3.63 0.56 1.00
## mndst_process_t2_score 10 324 2.96 0.58 3.00 2.96 0.64 1.43
## mndst_exercise_t2_score 11 324 4.71 1.17 4.52 4.70 1.01 1.48
## mndst_fail_t2_score 12 324 3.89 0.80 3.67 3.78 0.49 1.67
## mndst_pers_t2_score 13 324 4.26 1.01 4.12 4.18 0.56 1.00
## mndst_stress_t2_score 14 324 2.09 0.68 2.12 2.09 0.56 0.00
## subid_final 15 324 162.50 93.67 162.50 162.50 120.09 1.00
## condition* 16 324 1.98 0.82 2.00 1.97 1.48 1.00
## sfmm_all9_t2_score 17 324 4.77 0.67 4.78 4.79 0.66 2.33
## cmm_t2_score_6 18 324 3.05 1.41 2.50 2.89 0.99 1.00
## selfefficacy_score 19 324 31.48 4.41 31.00 31.50 4.45 20.00
## posaff_sum 20 324 33.69 7.52 34.00 34.22 7.41 9.00
## negaff_sum 21 324 25.89 11.69 27.00 25.53 15.57 10.00
## cmm_t2_score_4 22 324 3.05 1.44 2.50 2.91 1.11 1.00
## max range skew kurtosis se
## ffmq15_5f 58.33 31.00 1.18 1.86 0.30
## ffmq_obs 11.67 8.00 -0.16 -0.37 0.09
## ffmq_des 11.67 8.33 0.39 -0.03 0.10
## ffmq_awa 11.67 9.33 0.13 -0.78 0.13
## ffmq_nj 11.67 9.33 0.44 -0.59 0.14
## ffmq_nr 11.67 9.33 -0.30 0.01 0.11
## MetAwa 21.00 14.80 -0.34 0.00 0.15
## cmm_t2_score 6.00 3.30 1.25 0.30 0.05
## mndst_intelligence_t2_score 6.00 5.00 0.59 1.88 0.05
## mndst_process_t2_score 4.00 2.57 -0.04 -0.51 0.03
## mndst_exercise_t2_score 7.00 5.52 0.00 0.08 0.06
## mndst_fail_t2_score 6.00 4.33 1.12 0.99 0.04
## mndst_pers_t2_score 7.00 6.00 0.70 1.61 0.06
## mndst_stress_t2_score 4.00 4.00 0.04 1.81 0.04
## subid_final 324.00 323.00 0.00 -1.21 5.20
## condition* 3.00 2.00 0.04 -1.51 0.05
## sfmm_all9_t2_score 6.00 3.67 -0.35 0.11 0.04
## cmm_t2_score_6 6.00 5.00 0.85 -0.51 0.08
## selfefficacy_score 40.00 20.00 -0.07 -0.53 0.25
## posaff_sum 45.00 36.00 -0.64 0.02 0.42
## negaff_sum 50.00 40.00 0.08 -1.29 0.65
## cmm_t2_score_4 6.00 5.00 0.77 -0.61 0.08##kurtosis above 3 indicates tails may be heavier than normal - (.3)
### skewness between -.5 and .5 indicates fairly symmetrical - (1.25) - highly skewed - generally lower scores#alpha cmm (std.alpha 83)
df.CMM.10 <- d.study %>%
select(t2_cmm_1, t2_cmm_2_reversed, t2_cmm_3, t2_cmm_4, t2_cmm_5, t2_cmm_6_reversed, t2_cmm_7_reversed, t2_cmm_8_reversed, t2_cmm_9_reversed, t2_cmm_10_reversed)
#adjusting CMM items removing all items loading on second factor in cmm.10
df.CMM.6 <- df.CMM.10 %>% select(-t2_cmm_1, -t2_cmm_3, -t2_cmm_4, -t2_cmm_5)
#adjusting to create 4 item scale - removing items 1,3,4, 5, #6 and #8
df.CMM.4 <- df.CMM.10 %>% select(t2_cmm_2_reversed, t2_cmm_7_reversed, t2_cmm_9_reversed, t2_cmm_10_reversed)
library(corrr)
- #inter item correlation
cor(df.CMM.6)## t2_cmm_2_reversed t2_cmm_6_reversed t2_cmm_7_reversed
## t2_cmm_2_reversed -1.0000000 -0.7742452 -0.8000453
## t2_cmm_6_reversed -0.7742452 -1.0000000 -0.7408900
## t2_cmm_7_reversed -0.8000453 -0.7408900 -1.0000000
## t2_cmm_8_reversed -0.7327086 -0.8036319 -0.7412689
## t2_cmm_9_reversed -0.7239716 -0.7189249 -0.7015721
## t2_cmm_10_reversed -0.7498984 -0.7903516 -0.7412374
## t2_cmm_8_reversed t2_cmm_9_reversed t2_cmm_10_reversed
## t2_cmm_2_reversed -0.7327086 -0.7239716 -0.7498984
## t2_cmm_6_reversed -0.8036319 -0.7189249 -0.7903516
## t2_cmm_7_reversed -0.7412689 -0.7015721 -0.7412374
## t2_cmm_8_reversed -1.0000000 -0.7327862 -0.7664108
## t2_cmm_9_reversed -0.7327862 -1.0000000 -0.7598499
## t2_cmm_10_reversed -0.7664108 -0.7598499 -1.0000000alpha(df.CMM.10) #suggests dropping no items will add to reliability, however 2 dropping 2 items (#3, and #5) would not lower reliability, adding (#1, #4) would remove .02. - possibly remove items (#3, and #5) or (#5 and #1), r.drop <.3 indicate low correlation with overall (this would sugegst removing (1,3,4, and 5)) - looking at reliability analysis reveals that removing items, 1, 3, 4, 5 will not reduce reliability very much -- later on we see that it expands it - good reliability - low raw.r whih are item-total correlations still decent but lowest for nonreversed ##
## Reliability analysis
## Call: alpha(x = df.CMM.10)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.87 0.84 0.89 0.34 5.2 0.0093 3.8 0.92 0.14
##
## lower alpha upper 95% confidence boundaries
## 0.85 0.87 0.88
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r
## t2_cmm_1 0.87 0.84 0.89 0.38 5.4 0.0085 0.113
## t2_cmm_2_reversed 0.83 0.80 0.87 0.31 4.1 0.0122 0.092
## t2_cmm_3 0.88 0.85 0.89 0.38 5.5 0.0084 0.110
## t2_cmm_4 0.88 0.85 0.89 0.38 5.6 0.0082 0.108
## t2_cmm_5 0.88 0.85 0.90 0.39 5.7 0.0084 0.108
## t2_cmm_6_reversed 0.83 0.81 0.87 0.31 4.1 0.0120 0.089
## t2_cmm_7_reversed 0.83 0.80 0.87 0.31 4.1 0.0120 0.094
## t2_cmm_8_reversed 0.84 0.81 0.87 0.32 4.2 0.0119 0.090
## t2_cmm_9_reversed 0.84 0.81 0.87 0.32 4.2 0.0118 0.096
## t2_cmm_10_reversed 0.83 0.81 0.87 0.31 4.1 0.0120 0.090
## med.r
## t2_cmm_1 0.23
## t2_cmm_2_reversed 0.12
## t2_cmm_3 0.25
## t2_cmm_4 0.27
## t2_cmm_5 0.28
## t2_cmm_6_reversed 0.13
## t2_cmm_7_reversed 0.12
## t2_cmm_8_reversed 0.13
## t2_cmm_9_reversed 0.13
## t2_cmm_10_reversed 0.13
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## t2_cmm_1 324 0.34 0.45 0.36 0.24 4.8 0.94
## t2_cmm_2_reversed 324 0.86 0.80 0.80 0.80 3.1 1.64
## t2_cmm_3 324 0.30 0.42 0.33 0.21 5.0 0.93
## t2_cmm_4 324 0.29 0.41 0.32 0.19 4.9 1.00
## t2_cmm_5 324 0.27 0.38 0.27 0.17 4.9 0.91
## t2_cmm_6_reversed 324 0.85 0.79 0.80 0.80 3.0 1.54
## t2_cmm_7_reversed 324 0.85 0.79 0.79 0.79 3.1 1.60
## t2_cmm_8_reversed 324 0.84 0.77 0.77 0.77 3.1 1.56
## t2_cmm_9_reversed 324 0.83 0.78 0.77 0.77 3.0 1.59
## t2_cmm_10_reversed 324 0.85 0.79 0.80 0.80 3.0 1.56
##
## Non missing response frequency for each item
## 1 2 3 4 5 6 miss
## t2_cmm_1 0.01 0.02 0.04 0.28 0.44 0.22 0
## t2_cmm_2_reversed 0.18 0.27 0.19 0.10 0.15 0.12 0
## t2_cmm_3 0.00 0.02 0.04 0.20 0.42 0.32 0
## t2_cmm_4 0.01 0.01 0.07 0.21 0.40 0.30 0
## t2_cmm_5 0.00 0.01 0.05 0.25 0.41 0.28 0
## t2_cmm_6_reversed 0.15 0.32 0.22 0.10 0.11 0.10 0
## t2_cmm_7_reversed 0.16 0.27 0.23 0.09 0.13 0.12 0
## t2_cmm_8_reversed 0.15 0.29 0.23 0.09 0.13 0.10 0
## t2_cmm_9_reversed 0.17 0.33 0.18 0.11 0.09 0.11 0
## t2_cmm_10_reversed 0.17 0.30 0.23 0.09 0.12 0.10 0#r.drop which item-total, correlation without that item itself indicate low correlation owith rest of scale and <.3 suggest consider removal
alpha(df.CMM.6)#much higher reliability and internal consistency at .95 alpha afterremoving 1, 3, 4, 5##
## Reliability analysis
## Call: alpha(x = df.CMM.6)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.95 0.95 0.94 0.75 18 0.0045 3 1.4 0.74
##
## lower alpha upper 95% confidence boundaries
## 0.94 0.95 0.96
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r
## t2_cmm_2_reversed 0.94 0.94 0.92 0.75 15 0.0055 0.00097
## t2_cmm_6_reversed 0.94 0.94 0.92 0.74 15 0.0057 0.00071
## t2_cmm_7_reversed 0.94 0.94 0.93 0.76 15 0.0054 0.00082
## t2_cmm_8_reversed 0.94 0.94 0.93 0.75 15 0.0055 0.00100
## t2_cmm_9_reversed 0.94 0.94 0.93 0.76 16 0.0051 0.00071
## t2_cmm_10_reversed 0.94 0.94 0.93 0.75 15 0.0056 0.00118
## med.r
## t2_cmm_2_reversed 0.74
## t2_cmm_6_reversed 0.74
## t2_cmm_7_reversed 0.75
## t2_cmm_8_reversed 0.75
## t2_cmm_9_reversed 0.76
## t2_cmm_10_reversed 0.74
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## t2_cmm_2_reversed 324 0.90 0.89 0.87 0.85 3.1 1.6
## t2_cmm_6_reversed 324 0.90 0.90 0.88 0.86 3.0 1.5
## t2_cmm_7_reversed 324 0.89 0.88 0.86 0.83 3.1 1.6
## t2_cmm_8_reversed 324 0.89 0.89 0.87 0.84 3.1 1.6
## t2_cmm_9_reversed 324 0.87 0.87 0.83 0.81 3.0 1.6
## t2_cmm_10_reversed 324 0.90 0.90 0.88 0.85 3.0 1.6
##
## Non missing response frequency for each item
## 1 2 3 4 5 6 miss
## t2_cmm_2_reversed 0.18 0.27 0.19 0.10 0.15 0.12 0
## t2_cmm_6_reversed 0.15 0.32 0.22 0.10 0.11 0.10 0
## t2_cmm_7_reversed 0.16 0.27 0.23 0.09 0.13 0.12 0
## t2_cmm_8_reversed 0.15 0.29 0.23 0.09 0.13 0.10 0
## t2_cmm_9_reversed 0.17 0.33 0.18 0.11 0.09 0.11 0
## t2_cmm_10_reversed 0.17 0.30 0.23 0.09 0.12 0.10 0alpha(df.CMM.4) ### Reliability analysis##
## Reliability analysis
## Call: alpha(x = df.CMM.4)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.92 0.92 0.9 0.75 12 0.0071 3 1.4 0.75
##
## lower alpha upper 95% confidence boundaries
## 0.91 0.92 0.94
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r
## t2_cmm_2_reversed 0.89 0.89 0.85 0.73 8.3 0.0104 0.00089
## t2_cmm_7_reversed 0.90 0.90 0.85 0.74 8.7 0.0099 0.00034
## t2_cmm_9_reversed 0.91 0.91 0.87 0.76 9.7 0.0090 0.00101
## t2_cmm_10_reversed 0.90 0.90 0.86 0.74 8.6 0.0100 0.00266
## med.r
## t2_cmm_2_reversed 0.74
## t2_cmm_7_reversed 0.75
## t2_cmm_9_reversed 0.75
## t2_cmm_10_reversed 0.72
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## t2_cmm_2_reversed 324 0.91 0.91 0.87 0.84 3.1 1.6
## t2_cmm_7_reversed 324 0.90 0.90 0.86 0.82 3.1 1.6
## t2_cmm_9_reversed 324 0.88 0.89 0.83 0.79 3.0 1.6
## t2_cmm_10_reversed 324 0.90 0.90 0.86 0.82 3.0 1.6
##
## Non missing response frequency for each item
## 1 2 3 4 5 6 miss
## t2_cmm_2_reversed 0.18 0.27 0.19 0.10 0.15 0.12 0
## t2_cmm_7_reversed 0.16 0.27 0.23 0.09 0.13 0.12 0
## t2_cmm_9_reversed 0.17 0.33 0.18 0.11 0.09 0.11 0
## t2_cmm_10_reversed 0.17 0.30 0.23 0.09 0.12 0.10 0#variable correlations - CMM strong cor with intelligence, failure, personality, and ffmq, .2 for stress, strong 10 item and 6 item as expected, strong correlations with same 6 item but little les
cor.df <- df %>% select(cmm_t2_score, mndst_intelligence_t2_score, mndst_process_t2_score, mndst_exercise_t2_score, mndst_fail_t2_score, mndst_pers_t2_score, mndst_stress_t2_score, ffmq15_5f, MetAwa, cmm_t2_score_6, selfefficacy_score, posaff_sum, negaff_sum, cmm_t2_score_4)
cor.df <- cor(cor.df) ## CMM has med-strong correlations for intelligence, failure,pers, ffmq, (neg association with pos/neg affect)
print(cor.df)# correlations between variables **## cmm_t2_score mndst_intelligence_t2_score
## cmm_t2_score 1.000000000 0.4980558
## mndst_intelligence_t2_score 0.498055810 1.0000000
## mndst_process_t2_score -0.094740700 0.1810352
## mndst_exercise_t2_score 0.131160900 0.2499219
## mndst_fail_t2_score 0.667283008 0.4320036
## mndst_pers_t2_score 0.564614591 0.6684287
## mndst_stress_t2_score 0.206082087 0.2630046
## ffmq15_5f 0.618308306 0.3819139
## MetAwa -0.005256606 0.1258818
## cmm_t2_score_6 0.952440527 0.4322670
## selfefficacy_score 0.287431561 0.2737648
## posaff_sum -0.130889122 0.1151058
## negaff_sum -0.635583384 -0.2721320
## cmm_t2_score_4 0.944059574 0.4214614
## mndst_process_t2_score mndst_exercise_t2_score
## cmm_t2_score -0.0947407 0.13116090
## mndst_intelligence_t2_score 0.1810352 0.24992194
## mndst_process_t2_score 1.0000000 0.53762085
## mndst_exercise_t2_score 0.5376208 1.00000000
## mndst_fail_t2_score 0.1161936 0.19133976
## mndst_pers_t2_score 0.1364244 0.18528674
## mndst_stress_t2_score 0.2638673 0.19276511
## ffmq15_5f 0.2093272 0.35009636
## MetAwa 0.1807367 0.10518023
## cmm_t2_score_6 -0.2039079 0.04436655
## selfefficacy_score 0.3775149 0.35701330
## posaff_sum 0.5857798 0.49644524
## negaff_sum -0.1206436 -0.34669977
## cmm_t2_score_4 -0.1981307 0.04900776
## mndst_fail_t2_score mndst_pers_t2_score
## cmm_t2_score 0.66728301 0.56461459
## mndst_intelligence_t2_score 0.43200355 0.66842872
## mndst_process_t2_score 0.11619360 0.13642443
## mndst_exercise_t2_score 0.19133976 0.18528674
## mndst_fail_t2_score 1.00000000 0.38026763
## mndst_pers_t2_score 0.38026763 1.00000000
## mndst_stress_t2_score 0.39500577 0.20535604
## ffmq15_5f 0.53206639 0.38638805
## MetAwa 0.08867452 0.04213356
## cmm_t2_score_6 0.61276266 0.47969513
## selfefficacy_score 0.34144717 0.25067094
## posaff_sum 0.08139726 0.02478875
## negaff_sum -0.52414531 -0.26671057
## cmm_t2_score_4 0.61162301 0.46878145
## mndst_stress_t2_score ffmq15_5f MetAwa
## cmm_t2_score 0.20608209 0.6183083 -0.005256606
## mndst_intelligence_t2_score 0.26300457 0.3819139 0.125881813
## mndst_process_t2_score 0.26386728 0.2093272 0.180736671
## mndst_exercise_t2_score 0.19276511 0.3500964 0.105180233
## mndst_fail_t2_score 0.39500577 0.5320664 0.088674522
## mndst_pers_t2_score 0.20535604 0.3863880 0.042133559
## mndst_stress_t2_score 1.00000000 0.1628913 0.027343666
## ffmq15_5f 0.16289126 1.0000000 0.236757434
## MetAwa 0.02734367 0.2367574 1.000000000
## cmm_t2_score_6 0.15816946 0.5523426 -0.107135029
## selfefficacy_score 0.12576554 0.4773617 0.392697705
## posaff_sum 0.13865123 0.1784645 0.401485553
## negaff_sum -0.14315856 -0.5561133 0.166435584
## cmm_t2_score_4 0.14009778 0.5535466 -0.109644666
## cmm_t2_score_6 selfefficacy_score posaff_sum
## cmm_t2_score 0.95244053 0.2874316 -0.13088912
## mndst_intelligence_t2_score 0.43226703 0.2737648 0.11510584
## mndst_process_t2_score -0.20390785 0.3775149 0.58577976
## mndst_exercise_t2_score 0.04436655 0.3570133 0.49644524
## mndst_fail_t2_score 0.61276266 0.3414472 0.08139726
## mndst_pers_t2_score 0.47969513 0.2506709 0.02478875
## mndst_stress_t2_score 0.15816946 0.1257655 0.13865123
## ffmq15_5f 0.55234262 0.4773617 0.17846455
## MetAwa -0.10713503 0.3926977 0.40148555
## cmm_t2_score_6 1.00000000 0.1156522 -0.29773353
## selfefficacy_score 0.11565215 1.0000000 0.52252851
## posaff_sum -0.29773353 0.5225285 1.00000000
## negaff_sum -0.66160617 -0.1643181 0.07395620
## cmm_t2_score_4 0.98589374 0.1191795 -0.29273330
## negaff_sum cmm_t2_score_4
## cmm_t2_score -0.6355834 0.94405957
## mndst_intelligence_t2_score -0.2721320 0.42146141
## mndst_process_t2_score -0.1206436 -0.19813067
## mndst_exercise_t2_score -0.3466998 0.04900776
## mndst_fail_t2_score -0.5241453 0.61162301
## mndst_pers_t2_score -0.2667106 0.46878145
## mndst_stress_t2_score -0.1431586 0.14009778
## ffmq15_5f -0.5561133 0.55354656
## MetAwa 0.1664356 -0.10964467
## cmm_t2_score_6 -0.6616062 0.98589374
## selfefficacy_score -0.1643181 0.11917955
## posaff_sum 0.0739562 -0.29273330
## negaff_sum 1.0000000 -0.65322463
## cmm_t2_score_4 -0.6532246 1.00000000#cor matrix with sig levels
library(Hmisc)## Loading required package: lattice## Loading required package: survival## Loading required package: Formula##
## Attaching package: 'Hmisc'## The following object is masked from 'package:psych':
##
## describe## The following objects are masked from 'package:dplyr':
##
## src, summarize## The following objects are masked from 'package:base':
##
## format.pval, unitscor.df.2 <- rcorr(as.matrix(cor.df))
print(cor.df.2) # s approaching or significant when looking a pvalues-process, fail, ffmq, and perapproach --intelligence not signifcant - pvales - sig values **## cmm_t2_score mndst_intelligence_t2_score
## cmm_t2_score 1.00 0.72
## mndst_intelligence_t2_score 0.72 1.00
## mndst_process_t2_score -0.49 -0.17
## mndst_exercise_t2_score -0.05 0.13
## mndst_fail_t2_score 0.90 0.68
## mndst_pers_t2_score 0.78 0.90
## mndst_stress_t2_score 0.19 0.26
## ffmq15_5f 0.82 0.61
## MetAwa -0.50 -0.35
## cmm_t2_score_6 0.99 0.69
## selfefficacy_score 0.04 0.11
## posaff_sum -0.66 -0.38
## negaff_sum -0.92 -0.68
## cmm_t2_score_4 0.99 0.69
## mndst_process_t2_score mndst_exercise_t2_score
## cmm_t2_score -0.49 -0.05
## mndst_intelligence_t2_score -0.17 0.13
## mndst_process_t2_score 1.00 0.75
## mndst_exercise_t2_score 0.75 1.00
## mndst_fail_t2_score -0.27 0.10
## mndst_pers_t2_score -0.28 0.02
## mndst_stress_t2_score 0.17 0.18
## ffmq15_5f -0.09 0.32
## MetAwa 0.31 0.07
## cmm_t2_score_6 -0.55 -0.11
## selfefficacy_score 0.50 0.54
## posaff_sum 0.84 0.61
## negaff_sum 0.14 -0.32
## cmm_t2_score_4 -0.55 -0.11
## mndst_fail_t2_score mndst_pers_t2_score
## cmm_t2_score 0.90 0.78
## mndst_intelligence_t2_score 0.68 0.90
## mndst_process_t2_score -0.27 -0.28
## mndst_exercise_t2_score 0.10 0.02
## mndst_fail_t2_score 1.00 0.67
## mndst_pers_t2_score 0.67 1.00
## mndst_stress_t2_score 0.41 0.18
## ffmq15_5f 0.82 0.62
## MetAwa -0.40 -0.45
## cmm_t2_score_6 0.87 0.76
## selfefficacy_score 0.19 0.04
## posaff_sum -0.45 -0.50
## negaff_sum -0.91 -0.70
## cmm_t2_score_4 0.87 0.76
## mndst_stress_t2_score ffmq15_5f MetAwa
## cmm_t2_score 0.19 0.82 -0.50
## mndst_intelligence_t2_score 0.26 0.61 -0.35
## mndst_process_t2_score 0.17 -0.09 0.31
## mndst_exercise_t2_score 0.18 0.32 0.07
## mndst_fail_t2_score 0.41 0.82 -0.40
## mndst_pers_t2_score 0.18 0.62 -0.45
## mndst_stress_t2_score 1.00 0.14 -0.31
## ffmq15_5f 0.14 1.00 -0.17
## MetAwa -0.31 -0.17 1.00
## cmm_t2_score_6 0.18 0.78 -0.54
## selfefficacy_score -0.05 0.44 0.44
## posaff_sum -0.06 -0.24 0.59
## negaff_sum -0.31 -0.90 0.45
## cmm_t2_score_4 0.17 0.78 -0.54
## cmm_t2_score_6 selfefficacy_score posaff_sum
## cmm_t2_score 0.99 0.04 -0.66
## mndst_intelligence_t2_score 0.69 0.11 -0.38
## mndst_process_t2_score -0.55 0.50 0.84
## mndst_exercise_t2_score -0.11 0.54 0.61
## mndst_fail_t2_score 0.87 0.19 -0.45
## mndst_pers_t2_score 0.76 0.04 -0.50
## mndst_stress_t2_score 0.18 -0.05 -0.06
## ffmq15_5f 0.78 0.44 -0.24
## MetAwa -0.54 0.44 0.59
## cmm_t2_score_6 1.00 -0.05 -0.73
## selfefficacy_score -0.05 1.00 0.59
## posaff_sum -0.73 0.59 1.00
## negaff_sum -0.89 -0.23 0.39
## cmm_t2_score_4 1.00 -0.05 -0.72
## negaff_sum cmm_t2_score_4
## cmm_t2_score -0.92 0.99
## mndst_intelligence_t2_score -0.68 0.69
## mndst_process_t2_score 0.14 -0.55
## mndst_exercise_t2_score -0.32 -0.11
## mndst_fail_t2_score -0.91 0.87
## mndst_pers_t2_score -0.70 0.76
## mndst_stress_t2_score -0.31 0.17
## ffmq15_5f -0.90 0.78
## MetAwa 0.45 -0.54
## cmm_t2_score_6 -0.89 1.00
## selfefficacy_score -0.23 -0.05
## posaff_sum 0.39 -0.72
## negaff_sum 1.00 -0.89
## cmm_t2_score_4 -0.89 1.00
##
## n= 14
##
##
## P
## cmm_t2_score mndst_intelligence_t2_score
## cmm_t2_score 0.0037
## mndst_intelligence_t2_score 0.0037
## mndst_process_t2_score 0.0739 0.5585
## mndst_exercise_t2_score 0.8638 0.6631
## mndst_fail_t2_score 0.0000 0.0077
## mndst_pers_t2_score 0.0009 0.0000
## mndst_stress_t2_score 0.5238 0.3789
## ffmq15_5f 0.0003 0.0201
## MetAwa 0.0682 0.2131
## cmm_t2_score_6 0.0000 0.0062
## selfefficacy_score 0.8853 0.7138
## posaff_sum 0.0102 0.1858
## negaff_sum 0.0000 0.0071
## cmm_t2_score_4 0.0000 0.0067
## mndst_process_t2_score mndst_exercise_t2_score
## cmm_t2_score 0.0739 0.8638
## mndst_intelligence_t2_score 0.5585 0.6631
## mndst_process_t2_score 0.0021
## mndst_exercise_t2_score 0.0021
## mndst_fail_t2_score 0.3575 0.7442
## mndst_pers_t2_score 0.3313 0.9348
## mndst_stress_t2_score 0.5518 0.5485
## ffmq15_5f 0.7659 0.2670
## MetAwa 0.2797 0.8109
## cmm_t2_score_6 0.0413 0.7049
## selfefficacy_score 0.0672 0.0474
## posaff_sum 0.0002 0.0210
## negaff_sum 0.6363 0.2629
## cmm_t2_score_4 0.0415 0.7097
## mndst_fail_t2_score mndst_pers_t2_score
## cmm_t2_score 0.0000 0.0009
## mndst_intelligence_t2_score 0.0077 0.0000
## mndst_process_t2_score 0.3575 0.3313
## mndst_exercise_t2_score 0.7442 0.9348
## mndst_fail_t2_score 0.0088
## mndst_pers_t2_score 0.0088
## mndst_stress_t2_score 0.1493 0.5312
## ffmq15_5f 0.0003 0.0182
## MetAwa 0.1571 0.1026
## cmm_t2_score_6 0.0000 0.0016
## selfefficacy_score 0.5118 0.8949
## posaff_sum 0.1077 0.0685
## negaff_sum 0.0000 0.0056
## cmm_t2_score_4 0.0000 0.0018
## mndst_stress_t2_score ffmq15_5f MetAwa
## cmm_t2_score 0.5238 0.0003 0.0682
## mndst_intelligence_t2_score 0.3789 0.0201 0.2131
## mndst_process_t2_score 0.5518 0.7659 0.2797
## mndst_exercise_t2_score 0.5485 0.2670 0.8109
## mndst_fail_t2_score 0.1493 0.0003 0.1571
## mndst_pers_t2_score 0.5312 0.0182 0.1026
## mndst_stress_t2_score 0.6257 0.2885
## ffmq15_5f 0.6257 0.5571
## MetAwa 0.2885 0.5571
## cmm_t2_score_6 0.5389 0.0011 0.0448
## selfefficacy_score 0.8585 0.1131 0.1148
## posaff_sum 0.8338 0.4145 0.0249
## negaff_sum 0.2866 0.0000 0.1082
## cmm_t2_score_4 0.5609 0.0010 0.0448
## cmm_t2_score_6 selfefficacy_score posaff_sum
## cmm_t2_score 0.0000 0.8853 0.0102
## mndst_intelligence_t2_score 0.0062 0.7138 0.1858
## mndst_process_t2_score 0.0413 0.0672 0.0002
## mndst_exercise_t2_score 0.7049 0.0474 0.0210
## mndst_fail_t2_score 0.0000 0.5118 0.1077
## mndst_pers_t2_score 0.0016 0.8949 0.0685
## mndst_stress_t2_score 0.5389 0.8585 0.8338
## ffmq15_5f 0.0011 0.1131 0.4145
## MetAwa 0.0448 0.1148 0.0249
## cmm_t2_score_6 0.8535 0.0033
## selfefficacy_score 0.8535 0.0276
## posaff_sum 0.0033 0.0276
## negaff_sum 0.0000 0.4353 0.1716
## cmm_t2_score_4 0.0000 0.8602 0.0034
## negaff_sum cmm_t2_score_4
## cmm_t2_score 0.0000 0.0000
## mndst_intelligence_t2_score 0.0071 0.0067
## mndst_process_t2_score 0.6363 0.0415
## mndst_exercise_t2_score 0.2629 0.7097
## mndst_fail_t2_score 0.0000 0.0000
## mndst_pers_t2_score 0.0056 0.0018
## mndst_stress_t2_score 0.2866 0.5609
## ffmq15_5f 0.0000 0.0010
## MetAwa 0.1082 0.0448
## cmm_t2_score_6 0.0000 0.0000
## selfefficacy_score 0.4353 0.8602
## posaff_sum 0.1716 0.0034
## negaff_sum 0.0000
## cmm_t2_score_4 0.0000symnum(cor.df)## cm_2_ mndst_n_2_ mndst_prc_2_ mndst_x_2_ mndst_f_2_
## cmm_t2_score 1
## mndst_intelligence_t2_score . 1
## mndst_process_t2_score 1
## mndst_exercise_t2_score . 1
## mndst_fail_t2_score , . 1
## mndst_pers_t2_score . , .
## mndst_stress_t2_score .
## ffmq15_5f , . . .
## MetAwa
## cmm_t2_score_6 B . ,
## selfefficacy_score . . .
## posaff_sum . .
## negaff_sum , . .
## cmm_t2_score_4 * . ,
## mndst_prs_2_ mndst_s_2_ f M c_2__6 s p n c_2__4
## cmm_t2_score
## mndst_intelligence_t2_score
## mndst_process_t2_score
## mndst_exercise_t2_score
## mndst_fail_t2_score
## mndst_pers_t2_score 1
## mndst_stress_t2_score 1
## ffmq15_5f . 1
## MetAwa 1
## cmm_t2_score_6 . . 1
## selfefficacy_score . . 1
## posaff_sum . . 1
## negaff_sum . , 1
## cmm_t2_score_4 . . B , 1
## attr(,"legend")
## [1] 0 ' ' 0.3 '.' 0.6 ',' 0.8 '+' 0.9 '*' 0.95 'B' 1#correlogram
library(corrplot)## corrplot 0.84 loadedcorrplot(cor.df) #visualize variable relations **
print(cor.df)## cmm_t2_score mndst_intelligence_t2_score
## cmm_t2_score 1.000000000 0.4980558
## mndst_intelligence_t2_score 0.498055810 1.0000000
## mndst_process_t2_score -0.094740700 0.1810352
## mndst_exercise_t2_score 0.131160900 0.2499219
## mndst_fail_t2_score 0.667283008 0.4320036
## mndst_pers_t2_score 0.564614591 0.6684287
## mndst_stress_t2_score 0.206082087 0.2630046
## ffmq15_5f 0.618308306 0.3819139
## MetAwa -0.005256606 0.1258818
## cmm_t2_score_6 0.952440527 0.4322670
## selfefficacy_score 0.287431561 0.2737648
## posaff_sum -0.130889122 0.1151058
## negaff_sum -0.635583384 -0.2721320
## cmm_t2_score_4 0.944059574 0.4214614
## mndst_process_t2_score mndst_exercise_t2_score
## cmm_t2_score -0.0947407 0.13116090
## mndst_intelligence_t2_score 0.1810352 0.24992194
## mndst_process_t2_score 1.0000000 0.53762085
## mndst_exercise_t2_score 0.5376208 1.00000000
## mndst_fail_t2_score 0.1161936 0.19133976
## mndst_pers_t2_score 0.1364244 0.18528674
## mndst_stress_t2_score 0.2638673 0.19276511
## ffmq15_5f 0.2093272 0.35009636
## MetAwa 0.1807367 0.10518023
## cmm_t2_score_6 -0.2039079 0.04436655
## selfefficacy_score 0.3775149 0.35701330
## posaff_sum 0.5857798 0.49644524
## negaff_sum -0.1206436 -0.34669977
## cmm_t2_score_4 -0.1981307 0.04900776
## mndst_fail_t2_score mndst_pers_t2_score
## cmm_t2_score 0.66728301 0.56461459
## mndst_intelligence_t2_score 0.43200355 0.66842872
## mndst_process_t2_score 0.11619360 0.13642443
## mndst_exercise_t2_score 0.19133976 0.18528674
## mndst_fail_t2_score 1.00000000 0.38026763
## mndst_pers_t2_score 0.38026763 1.00000000
## mndst_stress_t2_score 0.39500577 0.20535604
## ffmq15_5f 0.53206639 0.38638805
## MetAwa 0.08867452 0.04213356
## cmm_t2_score_6 0.61276266 0.47969513
## selfefficacy_score 0.34144717 0.25067094
## posaff_sum 0.08139726 0.02478875
## negaff_sum -0.52414531 -0.26671057
## cmm_t2_score_4 0.61162301 0.46878145
## mndst_stress_t2_score ffmq15_5f MetAwa
## cmm_t2_score 0.20608209 0.6183083 -0.005256606
## mndst_intelligence_t2_score 0.26300457 0.3819139 0.125881813
## mndst_process_t2_score 0.26386728 0.2093272 0.180736671
## mndst_exercise_t2_score 0.19276511 0.3500964 0.105180233
## mndst_fail_t2_score 0.39500577 0.5320664 0.088674522
## mndst_pers_t2_score 0.20535604 0.3863880 0.042133559
## mndst_stress_t2_score 1.00000000 0.1628913 0.027343666
## ffmq15_5f 0.16289126 1.0000000 0.236757434
## MetAwa 0.02734367 0.2367574 1.000000000
## cmm_t2_score_6 0.15816946 0.5523426 -0.107135029
## selfefficacy_score 0.12576554 0.4773617 0.392697705
## posaff_sum 0.13865123 0.1784645 0.401485553
## negaff_sum -0.14315856 -0.5561133 0.166435584
## cmm_t2_score_4 0.14009778 0.5535466 -0.109644666
## cmm_t2_score_6 selfefficacy_score posaff_sum
## cmm_t2_score 0.95244053 0.2874316 -0.13088912
## mndst_intelligence_t2_score 0.43226703 0.2737648 0.11510584
## mndst_process_t2_score -0.20390785 0.3775149 0.58577976
## mndst_exercise_t2_score 0.04436655 0.3570133 0.49644524
## mndst_fail_t2_score 0.61276266 0.3414472 0.08139726
## mndst_pers_t2_score 0.47969513 0.2506709 0.02478875
## mndst_stress_t2_score 0.15816946 0.1257655 0.13865123
## ffmq15_5f 0.55234262 0.4773617 0.17846455
## MetAwa -0.10713503 0.3926977 0.40148555
## cmm_t2_score_6 1.00000000 0.1156522 -0.29773353
## selfefficacy_score 0.11565215 1.0000000 0.52252851
## posaff_sum -0.29773353 0.5225285 1.00000000
## negaff_sum -0.66160617 -0.1643181 0.07395620
## cmm_t2_score_4 0.98589374 0.1191795 -0.29273330
## negaff_sum cmm_t2_score_4
## cmm_t2_score -0.6355834 0.94405957
## mndst_intelligence_t2_score -0.2721320 0.42146141
## mndst_process_t2_score -0.1206436 -0.19813067
## mndst_exercise_t2_score -0.3466998 0.04900776
## mndst_fail_t2_score -0.5241453 0.61162301
## mndst_pers_t2_score -0.2667106 0.46878145
## mndst_stress_t2_score -0.1431586 0.14009778
## ffmq15_5f -0.5561133 0.55354656
## MetAwa 0.1664356 -0.10964467
## cmm_t2_score_6 -0.6616062 0.98589374
## selfefficacy_score -0.1643181 0.11917955
## posaff_sum 0.0739562 -0.29273330
## negaff_sum 1.0000000 -0.65322463
## cmm_t2_score_4 -0.6532246 1.00000000#scatterplot with fitted line cmm x ffmq
ggplot(df, aes(x = cmm_t2_score_4, y = ffmq15_5f)) +
geom_point() +
stat_smooth()## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#scatterplot with fitted line cmm x mindset
ggplot(df, aes(x = cmm_t2_score_4, y = sfmm_all9_t2_score)) +
geom_point() +
stat_smooth()## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
df.lm.4.ffmq <- lm(ffmq15_5f ~ cmm_t2_score_4, data=df) # build linear regression model on full data
print(df.lm.4.ffmq)##
## Call:
## lm(formula = ffmq15_5f ~ cmm_t2_score_4, data = df)
##
## Coefficients:
## (Intercept) cmm_t2_score_4
## 32.084 2.052ggplot(df, aes(cmm_t2_score_4, ffmq15_5f)) +
geom_point() +
stat_smooth(method = lm)## `geom_smooth()` using formula 'y ~ x'
summary(df.lm.4.ffmq)##
## Call:
## lm(formula = ffmq15_5f ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -14.0634 -2.7395 0.1322 2.4069 13.9366
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 32.0838 0.5800 55.32 <2e-16 ***
## cmm_t2_score_4 2.0522 0.1721 11.93 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4.449 on 322 degrees of freedom
## Multiple R-squared: 0.3064, Adjusted R-squared: 0.3043
## F-statistic: 142.3 on 1 and 322 DF, p-value: < 2.2e-16df.lm.4.ex <- lm(cmm_t2_score_4 ~ mndst_exercise_t2_score, data=df) # build linear regression model on full data#EFA - looking for theoretically meaningful subdimensions of latent construct optimally - using principle components analysis
df.CMM.4.pca <- princomp(df.CMM.4)
summary(df.CMM.4.pca)## Importance of components:
## Comp.1 Comp.2 Comp.3 Comp.4
## Standard deviation 2.8737674 0.91540784 0.76143123 0.72041275
## Proportion of Variance 0.8100353 0.08219208 0.05686723 0.05090536
## Cumulative Proportion 0.8100353 0.89222741 0.94909464 1.00000000plot(df.CMM.4.pca) #scree plot
cor(df.CMM.4)## t2_cmm_2_reversed t2_cmm_7_reversed t2_cmm_9_reversed
## t2_cmm_2_reversed 1.0000000 0.8000453 0.7239716
## t2_cmm_7_reversed 0.8000453 1.0000000 0.7015721
## t2_cmm_9_reversed 0.7239716 0.7015721 1.0000000
## t2_cmm_10_reversed 0.7498984 0.7412374 0.7598499
## t2_cmm_10_reversed
## t2_cmm_2_reversed 0.7498984
## t2_cmm_7_reversed 0.7412374
## t2_cmm_9_reversed 0.7598499
## t2_cmm_10_reversed 1.0000000#summary suggest one factor lookin at variances PCA - adds little to variance continuing past maybe 2 - control and change (#check varimax - oblimique) - assumes factors are orthogonal - factanal uses max likelihood
CMM.4.fa1 <- factanal(df.CMM.4, factors = 1)
print(CMM.4.fa1) #test hypothesis that 1 factor is sufficient - factanal uses max likelihood, not recommended for efa - yes##
## Call:
## factanal(x = df.CMM.4, factors = 1)
##
## Uniquenesses:
## t2_cmm_2_reversed t2_cmm_7_reversed t2_cmm_9_reversed t2_cmm_10_reversed
## 0.212 0.238 0.310 0.255
##
## Loadings:
## Factor1
## t2_cmm_2_reversed 0.888
## t2_cmm_7_reversed 0.873
## t2_cmm_9_reversed 0.831
## t2_cmm_10_reversed 0.863
##
## Factor1
## SS loadings 2.986
## Proportion Var 0.746
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 16.15 on 2 degrees of freedom.
## The p-value is 0.000312#summary suggest one factor lookin at variances PCA - adds little to variance continuing past maybe 2 - control and change (#check oblique) - factors correlated? - asssumes factors are orthogonal - below using promax -
CMM.4.fa1.pro <- factanal(df.CMM.4, factors = 1, rotation = "promax")
print(CMM.4.fa1.pro) #test hypothesis that 1 factor is sufficient - factanal uses max likelihood, not recommended for efa##
## Call:
## factanal(x = df.CMM.4, factors = 1, rotation = "promax")
##
## Uniquenesses:
## t2_cmm_2_reversed t2_cmm_7_reversed t2_cmm_9_reversed t2_cmm_10_reversed
## 0.212 0.238 0.310 0.255
##
## Loadings:
## Factor1
## t2_cmm_2_reversed 0.888
## t2_cmm_7_reversed 0.873
## t2_cmm_9_reversed 0.831
## t2_cmm_10_reversed 0.863
##
## Factor1
## SS loadings 2.986
## Proportion Var 0.746
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 16.15 on 2 degrees of freedom.
## The p-value is 0.000312#summary suggest one factor lookin at variances PCA - adds little to variance continuing past maybe 2 - control and change (#check oblique) - factors correlated? - factors are orthogonal - below using promax - an oblique rotation, which allows for factors to be correlated. we suggest control and changing underlying factors are correlated. #critieria reached with 2 factors Using logic like that in the preceding quote, Thurstone (1947) first proposed and argued for five # criteria that needed to be met for simple structure to be achieved: # 1. Each variable should produce at least one zero loading on some factor. # 2. Each factor should have at least as many zero loadings as there are factors. # 3. Each pair of factors should have variables with significant loadings on one # and zero loadings on the other. # 4. Each pair of factors should have a large proportion of zero loadings on both factors # (if there are say four or more factors total). # 5. Each pair of factors should have only a few complex variables.
#Items suggested retaining with factor loading above .8, were all the reverse scored items -2 factor structure (hints at the theoretical and conceptual approach to phenomena, a metamindset getting at control and change of mindsets) #Factor 2 - lower but all above .52 # 1. No matter what kind of mindset I have, I can always change it. # 3. I can develop my ability to control my mindsets. # 4. I could learn to have more control over my mindsets. # 5. When it is necessary to, I have a considerable amount of control over my mindset.
#Factor 1- principical component - most variance explained al l load .8+ # 2.To be honest, you can’t really change your mindsets. (R) # 6. You can learn about new mindsets, but you can’t really change your basic ability to control your mindset. (R) # 7. As much as I hate to admit it, you can’t teach an old dog new tricks. You can’t really change your mindsets about things in the world. (R) # 8. You have certain mindsets about the world, and there is not much that can be done to really change that.(R) # 9. Even in moments when it really matters, I can’t do much to change my mindset. (R) # 10. How much I can control my mindset is something about me that I can’t change very much. (R)
#using Princial Axis Factor analysis w psych package continue exploring this should be doneusing CFA in new sample
#maximizes variance from factors
CMM.PAF.4 <- factor.pa(df.CMM.4, nfactors = 1, rotate = "promax")## Warning: factor.pa is deprecated. Please use the fa function with fm=paprint(CMM.PAF.4)## Factor Analysis using method = pa
## Call: factor.pa(r = df.CMM.4, nfactors = 1, rotate = "promax")
## Unstandardized loadings (pattern matrix) based upon covariance matrix
## PA1 h2 u2 H2 U2
## t2_cmm_2_reversed 0.88 0.78 0.22 0.78 0.22
## t2_cmm_7_reversed 0.87 0.75 0.25 0.75 0.25
## t2_cmm_9_reversed 0.83 0.69 0.31 0.69 0.31
## t2_cmm_10_reversed 0.87 0.76 0.24 0.76 0.24
##
## PA1
## SS loadings 2.99
## Proportion Var 0.75
##
## Standardized loadings (pattern matrix)
## V PA1 h2 u2
## t2_cmm_2_reversed 1 0.88 0.78 0.22
## t2_cmm_7_reversed 2 0.87 0.75 0.25
## t2_cmm_9_reversed 3 0.83 0.69 0.31
## t2_cmm_10_reversed 4 0.87 0.76 0.24
##
## PA1
## SS loadings 2.98
## Proportion Var 0.75
##
## Mean item complexity = 1
## Test of the hypothesis that 1 factor is sufficient.
##
## The degrees of freedom for the null model are 6 and the objective function was 3.01 with Chi Square of 964.56
## The degrees of freedom for the model are 2 and the objective function was 0.05
##
## The root mean square of the residuals (RMSR) is 0.02
## The df corrected root mean square of the residuals is 0.04
##
## The harmonic number of observations is 324 with the empirical chi square 2.26 with prob < 0.32
## The total number of observations was 324 with Likelihood Chi Square = 16.44 with prob < 0.00027
##
## Tucker Lewis Index of factoring reliability = 0.955
## RMSEA index = 0.149 and the 90 % confidence intervals are 0.088 0.22
## BIC = 4.87
## Fit based upon off diagonal values = 1
## Measures of factor score adequacy
## PA1
## Correlation of (regression) scores with factors 0.96
## Multiple R square of scores with factors 0.92
## Minimum correlation of possible factor scores 0.85#other EFA using minsres
EFA.model.CMM.4 <- fa(df.CMM.4)
EFA.model.CMM.4$loadings##
## Loadings:
## MR1
## t2_cmm_2_reversed 0.885
## t2_cmm_7_reversed 0.867
## t2_cmm_9_reversed 0.833
## t2_cmm_10_reversed 0.870
##
## MR1
## SS loadings 2.986
## Proportion Var 0.747#factor loadings
fa.diagram(EFA.model.CMM.4)
head(df.CMM.4)## # A tibble: 6 x 4
## t2_cmm_2_reversed t2_cmm_7_reversed t2_cmm_9_reversed t2_cmm_10_reversed
## <dbl> <dbl> <dbl> <dbl>
## 1 3 3 1 2
## 2 2 2 2 3
## 3 1 2 2 3
## 4 1 2 2 2
## 5 1 1 2 1
## 6 3 3 2 3#this function shows individuals scores on factor
EFA.model.CMM.4$scores## MR1
## [1,] -0.480961809
## [2,] -0.520250325
## [3,] -0.710337968
## [4,] -0.892304416
## [5,] -1.236821254
## [6,] -0.167612291
## [7,] -0.733384093
## [8,] -0.833599842
## [9,] -1.054854806
## [10,] -0.825478647
## [11,] -0.249362989
## [12,] 0.629758330
## [13,] 0.713731689
## [14,] -0.520250325
## [15,] 0.366992191
## [16,] -0.733384093
## [17,] -0.996150232
## [18,] -0.861137096
## [19,] 0.780557458
## [20,] 0.230166985
## [21,] -0.861137096
## [22,] 1.961733433
## [23,] 0.343946066
## [24,] -0.729754026
## [25,] 1.961733433
## [26,] 1.295745882
## [27,] -0.864767163
## [28,] 0.629758330
## [29,] -0.520250325
## [30,] -0.005061901
## [31,] 1.304818084
## [32,] -1.015566290
## [33,] -1.074270864
## [34,] -0.884183221
## [35,] -0.570833703
## [36,] -1.186237876
## [37,] -0.453424555
## [38,] 1.961733433
## [39,] -0.368994797
## [40,] 1.295745882
## [41,] -0.520250325
## [42,] 0.710558022
## [43,] -0.520250325
## [44,] 0.943107848
## [45,] 1.164362812
## [46,] 1.295745882
## [47,] 1.961733433
## [48,] 1.164362812
## [49,] -0.884183221
## [50,] -0.307116556
## [51,] -0.036229221
## [52,] -0.520250325
## [53,] -0.662928257
## [54,] -0.643512199
## [55,] -0.520250325
## [56,] 1.961733433
## [57,] 0.126321169
## [58,] -0.167612291
## [59,] -0.349578739
## [60,] -0.380746059
## [61,] 1.771645789
## [62,] 0.041891411
## [63,] 1.830350363
## [64,] 1.485833525
## [65,] 0.176904547
## [66,] 0.203490794
## [67,] -1.186237876
## [68,] -0.833599842
## [69,] -0.218195669
## [70,] 0.375113386
## [71,] 1.295745882
## [72,] -1.236821254
## [73,] 0.428375824
## [74,] -0.547787578
## [75,] -0.833599842
## [76,] 1.648383915
## [77,] -1.186237876
## [78,] -0.539666383
## [79,] -1.015566290
## [80,] -0.570833703
## [81,] 1.961733433
## [82,] 0.265825434
## [83,] -1.186237876
## [84,] -0.864767163
## [85,] 1.961733433
## [86,] -0.884183221
## [87,] -0.721632831
## [88,] 1.477712330
## [89,] 0.176904547
## [90,] -1.046733611
## [91,] -0.884183221
## [92,] -0.814183784
## [93,] -1.205653934
## [94,] 0.819845974
## [95,] -0.450250888
## [96,] -0.662928257
## [97,] -1.236821254
## [98,] -0.702216773
## [99,] 1.648383915
## [100,] -0.702216773
## [101,] 1.961733433
## [102,] 0.529542581
## [103,] -0.059275346
## [104,] -0.408283313
## [105,] 1.133195492
## [106,] -0.988029037
## [107,] -0.884183221
## [108,] -0.032599155
## [109,] 1.295745882
## [110,] -0.694095577
## [111,] -0.218195669
## [112,] 0.652804455
## [113,] -0.512129129
## [114,] -0.694095577
## [115,] -0.996150232
## [116,] 1.961733433
## [117,] 0.257704239
## [118,] -0.036229221
## [119,] -0.055645279
## [120,] 1.617216595
## [121,] -0.167612291
## [122,] -1.186237876
## [123,] -0.388867255
## [124,] 1.102484571
## [125,] 0.629758330
## [126,] -0.702216773
## [127,] -0.598370956
## [128,] -0.290874165
## [129,] -0.911720474
## [130,] -0.911720474
## [131,] -1.023687486
## [132,] -1.368204324
## [133,] -0.923471736
## [134,] -0.911720474
## [135,] -0.167612291
## [136,] -1.186237876
## [137,] -0.547787578
## [138,] 0.792308720
## [139,] -0.167612291
## [140,] 0.204441801
## [141,] -1.015566290
## [142,] -0.702216773
## [143,] -0.721632831
## [144,] -0.718002764
## [145,] -0.671049452
## [146,] -0.140075037
## [147,] 1.295745882
## [148,] 1.295745882
## [149,] -0.915350541
## [150,] 1.961733433
## [151,] -0.094933795
## [152,] -0.539666383
## [153,] 1.295745882
## [154,] -1.236821254
## [155,] -0.570833703
## [156,] -0.780337405
## [157,] -1.236821254
## [158,] -0.257484185
## [159,] 0.467207940
## [160,] -0.752800151
## [161,] -0.330162681
## [162,] -0.229946931
## [163,] -0.195149545
## [164,] -0.036229221
## [165,] 1.295745882
## [166,] -1.186237876
## [167,] -0.760921346
## [168,] -0.702216773
## [169,] -0.512129129
## [170,] -0.590249761
## [171,] 1.164362812
## [172,] -0.388867255
## [173,] 0.394985844
## [174,] -0.892304416
## [175,] -0.547787578
## [176,] 1.609095399
## [177,] -0.598370956
## [178,] -1.023687486
## [179,] -1.368204324
## [180,] -1.046733611
## [181,] 1.164362812
## [182,] -0.036229221
## [183,] -1.074270864
## [184,] -1.368204324
## [185,] -0.694095577
## [186,] 1.961733433
## [187,] -0.856645967
## [188,] -0.570833703
## [189,] -0.872888358
## [190,] -0.884183221
## [191,] -0.131953842
## [192,] -0.028108026
## [193,] -1.368204324
## [194,] -0.330162681
## [195,] 0.819845974
## [196,] -0.036229221
## [197,] 0.285241492
## [198,] -1.004271428
## [199,] 1.295745882
## [200,] -1.046733611
## [201,] 1.961733433
## [202,] 1.295745882
## [203,] 1.164362812
## [204,] -0.298995361
## [205,] -0.198779611
## [206,] 0.223857859
## [207,] -0.357699935
## [208,] -0.598370956
## [209,] -1.023687486
## [210,] -0.643512199
## [211,] -0.067396541
## [212,] 1.295745882
## [213,] 1.071317251
## [214,] -0.570833703
## [215,] -0.539666383
## [216,] 0.153858422
## [217,] 1.133195492
## [218,] 0.475329136
## [219,] 1.648383915
## [220,] -0.733384093
## [221,] 0.394529444
## [222,] -0.520250325
## [223,] -0.702216773
## [224,] -0.117028913
## [225,] 0.145737227
## [226,] 1.771645789
## [227,] -0.187028349
## [228,] 0.629758330
## [229,] -0.996150232
## [230,] -0.702216773
## [231,] -0.067396541
## [232,] 1.961733433
## [233,] -0.298995361
## [234,] 1.961733433
## [235,] 1.295745882
## [236,] 1.961733433
## [237,] -0.218195669
## [238,] 1.961733433
## [239,] -0.179363553
## [240,] 0.629758330
## [241,] 1.961733433
## [242,] -0.570833703
## [243,] -0.167612291
## [244,] -0.923471736
## [245,] -0.198779611
## [246,] 0.224314258
## [247,] -0.710337968
## [248,] -0.570833703
## [249,] 1.295745882
## [250,] 1.779766985
## [251,] 1.961733433
## [252,] 1.458296271
## [253,] -0.005061901
## [254,] 0.185025743
## [255,] 0.304657550
## [256,] 1.427128951
## [257,] 1.295745882
## [258,] 1.961733433
## [259,] 1.961733433
## [260,] 0.181395676
## [261,] 1.295745882
## [262,] -0.047524084
## [263,] 0.095153849
## [264,] 0.288871559
## [265,] -0.539666383
## [266,] -0.044350417
## [267,] 0.249583043
## [268,] 0.355697328
## [269,] -0.380746059
## [270,] -0.067396541
## [271,] -0.679170648
## [272,] -0.570833703
## [273,] 1.961733433
## [274,] -0.294504232
## [275,] -0.520250325
## [276,] -0.349578739
## [277,] 1.779766985
## [278,] -0.702216773
## [279,] 0.394985844
## [280,] -0.923471736
## [281,] 1.961733433
## [282,] -0.923471736
## [283,] -1.186237876
## [284,] 1.961733433
## [285,] 0.819845974
## [286,] 0.022475353
## [287,] -0.682800714
## [288,] -0.539666383
## [289,] -0.131953842
## [290,] -0.578954898
## [291,] -0.520250325
## [292,] -0.276900243
## [293,] -0.408283313
## [294,] 1.427128951
## [295,] -0.721632831
## [296,] -1.074270864
## [297,] 1.001812422
## [298,] -0.547787578
## [299,] 1.295745882
## [300,] 0.475329136
## [301,] -0.492713071
## [302,] -0.861137096
## [303,] 1.961733433
## [304,] -0.884183221
## [305,] -0.036229221
## [306,] -0.915350541
## [307,] -0.988029037
## [308,] -1.074270864
## [309,] -1.074270864
## [310,] -0.198779611
## [311,] 0.347576132
## [312,] 0.982396364
## [313,] 0.041891411
## [314,] -0.671049452
## [315,] -0.520250325
## [316,] -0.660705597
## [317,] -0.996150232
## [318,] -0.671049452
## [319,] -0.733384093
## [320,] -0.543296449
## [321,] 0.145737227
## [322,] 1.961733433
## [323,] -0.721632831
## [324,] 0.629758330summary(EFA.model.CMM.4$scores)## MR1
## Min. :-1.3682
## 1st Qu.:-0.7216
## Median :-0.2927
## Mean : 0.0000
## 3rd Qu.: 0.6298
## Max. : 1.9617#feel for distribution of factor scores
summary(df.CMM.4)## t2_cmm_2_reversed t2_cmm_7_reversed t2_cmm_9_reversed t2_cmm_10_reversed
## Min. :1.00 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:2.00 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:2.000
## Median :3.00 Median :3.000 Median :2.500 Median :3.000
## Mean :3.12 Mean :3.108 Mean :2.972 Mean :2.997
## 3rd Qu.:5.00 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :6.00 Max. :6.000 Max. :6.000 Max. :6.000plot(density(EFA.model.CMM.4$scores))
describe(df.CMM.4)## df.CMM.4
##
## 4 Variables 324 Observations
## --------------------------------------------------------------------------------
## t2_cmm_2_reversed
## n missing distinct Info Mean Gmd
## 324 0 6 0.962 3.12 1.845
##
## lowest : 1 2 3 4 5, highest: 2 3 4 5 6
##
## Value 1 2 3 4 5 6
## Frequency 57 87 63 32 47 38
## Proportion 0.176 0.269 0.194 0.099 0.145 0.117
## --------------------------------------------------------------------------------
## t2_cmm_7_reversed
## n missing distinct Info Mean Gmd
## 324 0 6 0.959 3.108 1.784
##
## lowest : 1 2 3 4 5, highest: 2 3 4 5 6
##
## Value 1 2 3 4 5 6
## Frequency 51 89 75 30 41 38
## Proportion 0.157 0.275 0.231 0.093 0.127 0.117
## --------------------------------------------------------------------------------
## t2_cmm_9_reversed
## n missing distinct Info Mean Gmd
## 324 0 6 0.95 2.972 1.754
##
## lowest : 1 2 3 4 5, highest: 2 3 4 5 6
##
## Value 1 2 3 4 5 6
## Frequency 55 107 58 37 30 37
## Proportion 0.170 0.330 0.179 0.114 0.093 0.114
## --------------------------------------------------------------------------------
## t2_cmm_10_reversed
## n missing distinct Info Mean Gmd
## 324 0 6 0.954 2.997 1.731
##
## lowest : 1 2 3 4 5, highest: 2 3 4 5 6
##
## Value 1 2 3 4 5 6
## Frequency 54 97 73 28 40 32
## Proportion 0.167 0.299 0.225 0.086 0.123 0.099
## --------------------------------------------------------------------------------describe(df$cmm_t2_score_4)## df$cmm_t2_score_4
## n missing distinct Info Mean Gmd .05 .10
## 324 0 21 0.994 3.049 1.587 1.25 1.50
## .25 .50 .75 .90 .95
## 2.00 2.50 4.00 5.50 6.00
##
## lowest : 1.00 1.25 1.50 1.75 2.00, highest: 5.00 5.25 5.50 5.75 6.00#does CMM differ by condition? CMM data does not seem normally distributed so will use Kruskal-Wallis test suggested for comparison of means using continuous and categorical data - non par
str(df)## tibble [324 × 22] (S3: tbl_df/tbl/data.frame)
## $ ffmq15_5f : num [1:324] 37.7 35 37 32.7 38.3 ...
## $ ffmq_obs : num [1:324] 10.67 8.33 8.33 9.67 9.33 ...
## $ ffmq_des : num [1:324] 6.33 8 8 7.33 6.33 ...
## $ ffmq_awa : num [1:324] 4.33 6.67 4.67 3.33 8.67 ...
## $ ffmq_nj : num [1:324] 5.67 5 7 3.67 7.67 ...
## $ ffmq_nr : num [1:324] 10.67 7 9 8.67 6.33 ...
## $ MetAwa : num [1:324] 16.8 14.8 15.6 16.8 18 12.6 16.8 19 18 7.2 ...
## $ cmm_t2_score : num [1:324] 3.4 3.2 3.2 3.2 3.3 3.4 3.1 3.3 3 3.2 ...
## $ mndst_intelligence_t2_score: num [1:324] 3.25 3.5 3.25 3.75 3.62 ...
## $ mndst_process_t2_score : num [1:324] 2.86 2.43 2.29 3.43 3.86 ...
## $ mndst_exercise_t2_score : num [1:324] 3.6 4.24 4.24 4.32 7 3.64 4.92 5.2 5 4.8 ...
## $ mndst_fail_t2_score : num [1:324] 3.67 3.5 3.5 3.83 3.5 ...
## $ mndst_pers_t2_score : num [1:324] 4 3.75 3.75 4 4 ...
## $ mndst_stress_t2_score : num [1:324] 2.25 2.5 2.12 2.5 3.12 ...
## $ subid_final : num [1:324] 12 14 286 96 118 4 36 227 7 1 ...
## $ condition : chr [1:324] "full_intervention" "abr_intervention" "active_control" "active_control" ...
## $ sfmm_all9_t2_score : num [1:324] 5.11 4.22 5 5.22 6 ...
## $ cmm_t2_score_6 : num [1:324] 2.17 2.5 2.17 1.83 1.5 ...
## $ selfefficacy_score : num [1:324] 35 25 29 35 40 26 30 37 34 31 ...
## $ posaff_sum : num [1:324] 37 26 33 39 42 16 37 39 40 43 ...
## $ negaff_sum : num [1:324] 40 28 38 46 10 18 33 44 42 14 ...
## $ cmm_t2_score_4 : num [1:324] 2.25 2.25 2 1.75 1.25 2.75 2 1.75 1.5 1.75 ...#changing data to factors and proper contrasts for conditions in CMM
Let’s tidy the data
d.cmm.4 <- df %>%
select(subid_final, condition, cmm_t2_score_4)%>%
gather(item, score, contains("cmm"))%>%
separate(item, sep = "_", into = c("construct_name", "type", "time", "score_name"))%>%
select(-construct_name, -score_name, -type)Let’s change data to be numeric & factors (and appropriate contrasts)
#Make Rating Numeric
d.cmm.4$score <- as.numeric(df$cmm_t2_score_4)
#Factor Condition
d.cmm.4$condition <- as.factor(d.cmm.4$condition)
contrasts(d.cmm.4$condition)## active_control full_intervention
## abr_intervention 0 0
## active_control 1 0
## full_intervention 0 1contrasts(d.cmm.4$condition) = cbind(dummy_full_vs_control = c(0,0,1), dummy_abridged_vs_control = c(1,0,0))
contrasts(d.cmm.4$condition)## dummy_full_vs_control dummy_abridged_vs_control
## abr_intervention 0 1
## active_control 0 0
## full_intervention 1 0#Factor subject id
d.cmm.4$subid_final <- as.factor(d.cmm.4$subid_final)levels(d.cmm.4$condition)## [1] "abr_intervention" "active_control" "full_intervention"library(dplyr)
#summary by condition - for CMM.4
group_by(d.cmm.4, condition) %>%
summarise( count = n(), mean = mean(score),
sd = sd(score),
median = median(score),
IQR = IQR(score))## `summarise()` ungrouping output (override with `.groups` argument)## # A tibble: 3 x 6
## condition count mean sd median IQR
## <fct> <int> <dbl> <dbl> <dbl> <dbl>
## 1 abr_intervention 112 3.16 1.50 2.75 2.25
## 2 active_control 107 3.00 1.42 2.5 2.25
## 3 full_intervention 105 2.98 1.40 2.5 1.5##mean for full intervention is lowest##use lm to determine if there is a difference in cmm by condition - evidence suggests - no?
cmm.lm <- lm(d.cmm.4$score ~ d.cmm.4$condition)
summary(cmm.lm)##
## Call:
## lm(formula = d.cmm.4$score ~ d.cmm.4$condition)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.0023 -1.1607 -0.4786 0.8789 3.0214
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.00234 0.13928 21.556 <2e-16
## d.cmm.4$conditiondummy_full_vs_control -0.02377 0.19791 -0.120 0.904
## d.cmm.4$conditiondummy_abridged_vs_control 0.15838 0.19476 0.813 0.417
##
## (Intercept) ***
## d.cmm.4$conditiondummy_full_vs_control
## d.cmm.4$conditiondummy_abridged_vs_control
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.441 on 321 degrees of freedom
## Multiple R-squared: 0.003219, Adjusted R-squared: -0.002992
## F-statistic: 0.5183 on 2 and 321 DF, p-value: 0.5961#non parametric model diff between condition on cmm? - NO
kruskal.test(cmm_t2_score_4 ~ condition, data = df)##
## Kruskal-Wallis rank sum test
##
## data: cmm_t2_score_4 by condition
## Kruskal-Wallis chi-squared = 0.89637, df = 2, p-value = 0.6388kruskal.test(score ~ condition, data = d.cmm.4)##
## Kruskal-Wallis rank sum test
##
## data: score by condition
## Kruskal-Wallis chi-squared = 0.89637, df = 2, p-value = 0.6388#variable correlations - CMM strong cor with intelligence, failure, personality, and ffmq, .2 for stress, strong 10 item and 6 item as expected, strong correlations with same 6 item but little les
library(corrplot)
library(corrr)
cor.df <- df %>% select(cmm_t2_score, mndst_intelligence_t2_score, mndst_process_t2_score, mndst_exercise_t2_score, mndst_fail_t2_score, mndst_pers_t2_score, mndst_stress_t2_score, ffmq15_5f, MetAwa, cmm_t2_score_6, cmm_t2_score_4, selfefficacy_score, posaff_sum, negaff_sum)
cor.df <- cor(cor.df, method = "pearson")
print(cor.df)# correlations between variables ** #strong cor with int, pers, mindfulness, pos and neg aff## cmm_t2_score mndst_intelligence_t2_score
## cmm_t2_score 1.000000000 0.4980558
## mndst_intelligence_t2_score 0.498055810 1.0000000
## mndst_process_t2_score -0.094740700 0.1810352
## mndst_exercise_t2_score 0.131160900 0.2499219
## mndst_fail_t2_score 0.667283008 0.4320036
## mndst_pers_t2_score 0.564614591 0.6684287
## mndst_stress_t2_score 0.206082087 0.2630046
## ffmq15_5f 0.618308306 0.3819139
## MetAwa -0.005256606 0.1258818
## cmm_t2_score_6 0.952440527 0.4322670
## cmm_t2_score_4 0.944059574 0.4214614
## selfefficacy_score 0.287431561 0.2737648
## posaff_sum -0.130889122 0.1151058
## negaff_sum -0.635583384 -0.2721320
## mndst_process_t2_score mndst_exercise_t2_score
## cmm_t2_score -0.0947407 0.13116090
## mndst_intelligence_t2_score 0.1810352 0.24992194
## mndst_process_t2_score 1.0000000 0.53762085
## mndst_exercise_t2_score 0.5376208 1.00000000
## mndst_fail_t2_score 0.1161936 0.19133976
## mndst_pers_t2_score 0.1364244 0.18528674
## mndst_stress_t2_score 0.2638673 0.19276511
## ffmq15_5f 0.2093272 0.35009636
## MetAwa 0.1807367 0.10518023
## cmm_t2_score_6 -0.2039079 0.04436655
## cmm_t2_score_4 -0.1981307 0.04900776
## selfefficacy_score 0.3775149 0.35701330
## posaff_sum 0.5857798 0.49644524
## negaff_sum -0.1206436 -0.34669977
## mndst_fail_t2_score mndst_pers_t2_score
## cmm_t2_score 0.66728301 0.56461459
## mndst_intelligence_t2_score 0.43200355 0.66842872
## mndst_process_t2_score 0.11619360 0.13642443
## mndst_exercise_t2_score 0.19133976 0.18528674
## mndst_fail_t2_score 1.00000000 0.38026763
## mndst_pers_t2_score 0.38026763 1.00000000
## mndst_stress_t2_score 0.39500577 0.20535604
## ffmq15_5f 0.53206639 0.38638805
## MetAwa 0.08867452 0.04213356
## cmm_t2_score_6 0.61276266 0.47969513
## cmm_t2_score_4 0.61162301 0.46878145
## selfefficacy_score 0.34144717 0.25067094
## posaff_sum 0.08139726 0.02478875
## negaff_sum -0.52414531 -0.26671057
## mndst_stress_t2_score ffmq15_5f MetAwa
## cmm_t2_score 0.20608209 0.6183083 -0.005256606
## mndst_intelligence_t2_score 0.26300457 0.3819139 0.125881813
## mndst_process_t2_score 0.26386728 0.2093272 0.180736671
## mndst_exercise_t2_score 0.19276511 0.3500964 0.105180233
## mndst_fail_t2_score 0.39500577 0.5320664 0.088674522
## mndst_pers_t2_score 0.20535604 0.3863880 0.042133559
## mndst_stress_t2_score 1.00000000 0.1628913 0.027343666
## ffmq15_5f 0.16289126 1.0000000 0.236757434
## MetAwa 0.02734367 0.2367574 1.000000000
## cmm_t2_score_6 0.15816946 0.5523426 -0.107135029
## cmm_t2_score_4 0.14009778 0.5535466 -0.109644666
## selfefficacy_score 0.12576554 0.4773617 0.392697705
## posaff_sum 0.13865123 0.1784645 0.401485553
## negaff_sum -0.14315856 -0.5561133 0.166435584
## cmm_t2_score_6 cmm_t2_score_4 selfefficacy_score
## cmm_t2_score 0.95244053 0.94405957 0.2874316
## mndst_intelligence_t2_score 0.43226703 0.42146141 0.2737648
## mndst_process_t2_score -0.20390785 -0.19813067 0.3775149
## mndst_exercise_t2_score 0.04436655 0.04900776 0.3570133
## mndst_fail_t2_score 0.61276266 0.61162301 0.3414472
## mndst_pers_t2_score 0.47969513 0.46878145 0.2506709
## mndst_stress_t2_score 0.15816946 0.14009778 0.1257655
## ffmq15_5f 0.55234262 0.55354656 0.4773617
## MetAwa -0.10713503 -0.10964467 0.3926977
## cmm_t2_score_6 1.00000000 0.98589374 0.1156522
## cmm_t2_score_4 0.98589374 1.00000000 0.1191795
## selfefficacy_score 0.11565215 0.11917955 1.0000000
## posaff_sum -0.29773353 -0.29273330 0.5225285
## negaff_sum -0.66160617 -0.65322463 -0.1643181
## posaff_sum negaff_sum
## cmm_t2_score -0.13088912 -0.6355834
## mndst_intelligence_t2_score 0.11510584 -0.2721320
## mndst_process_t2_score 0.58577976 -0.1206436
## mndst_exercise_t2_score 0.49644524 -0.3466998
## mndst_fail_t2_score 0.08139726 -0.5241453
## mndst_pers_t2_score 0.02478875 -0.2667106
## mndst_stress_t2_score 0.13865123 -0.1431586
## ffmq15_5f 0.17846455 -0.5561133
## MetAwa 0.40148555 0.1664356
## cmm_t2_score_6 -0.29773353 -0.6616062
## cmm_t2_score_4 -0.29273330 -0.6532246
## selfefficacy_score 0.52252851 -0.1643181
## posaff_sum 1.00000000 0.0739562
## negaff_sum 0.07395620 1.0000000corrplot(cor.df) #visualize variable relations **
corrplot(cor.df, method="number", type="lower")
corrplot.mixed(cor.df)
#diff cor method, rounded
cor.r.df <-round(cor(cor.df),2)
cor.r.df ## pay attention to cmm4## cmm_t2_score mndst_intelligence_t2_score
## cmm_t2_score 1.00 0.72
## mndst_intelligence_t2_score 0.72 1.00
## mndst_process_t2_score -0.49 -0.17
## mndst_exercise_t2_score -0.05 0.13
## mndst_fail_t2_score 0.90 0.68
## mndst_pers_t2_score 0.78 0.90
## mndst_stress_t2_score 0.19 0.26
## ffmq15_5f 0.82 0.61
## MetAwa -0.50 -0.35
## cmm_t2_score_6 0.99 0.69
## cmm_t2_score_4 0.99 0.69
## selfefficacy_score 0.04 0.11
## posaff_sum -0.66 -0.38
## negaff_sum -0.92 -0.68
## mndst_process_t2_score mndst_exercise_t2_score
## cmm_t2_score -0.49 -0.05
## mndst_intelligence_t2_score -0.17 0.13
## mndst_process_t2_score 1.00 0.75
## mndst_exercise_t2_score 0.75 1.00
## mndst_fail_t2_score -0.27 0.10
## mndst_pers_t2_score -0.28 0.02
## mndst_stress_t2_score 0.17 0.18
## ffmq15_5f -0.09 0.32
## MetAwa 0.31 0.07
## cmm_t2_score_6 -0.55 -0.11
## cmm_t2_score_4 -0.55 -0.11
## selfefficacy_score 0.50 0.54
## posaff_sum 0.84 0.61
## negaff_sum 0.14 -0.32
## mndst_fail_t2_score mndst_pers_t2_score
## cmm_t2_score 0.90 0.78
## mndst_intelligence_t2_score 0.68 0.90
## mndst_process_t2_score -0.27 -0.28
## mndst_exercise_t2_score 0.10 0.02
## mndst_fail_t2_score 1.00 0.67
## mndst_pers_t2_score 0.67 1.00
## mndst_stress_t2_score 0.41 0.18
## ffmq15_5f 0.82 0.62
## MetAwa -0.40 -0.45
## cmm_t2_score_6 0.87 0.76
## cmm_t2_score_4 0.87 0.76
## selfefficacy_score 0.19 0.04
## posaff_sum -0.45 -0.50
## negaff_sum -0.91 -0.70
## mndst_stress_t2_score ffmq15_5f MetAwa
## cmm_t2_score 0.19 0.82 -0.50
## mndst_intelligence_t2_score 0.26 0.61 -0.35
## mndst_process_t2_score 0.17 -0.09 0.31
## mndst_exercise_t2_score 0.18 0.32 0.07
## mndst_fail_t2_score 0.41 0.82 -0.40
## mndst_pers_t2_score 0.18 0.62 -0.45
## mndst_stress_t2_score 1.00 0.14 -0.31
## ffmq15_5f 0.14 1.00 -0.17
## MetAwa -0.31 -0.17 1.00
## cmm_t2_score_6 0.18 0.78 -0.54
## cmm_t2_score_4 0.17 0.78 -0.54
## selfefficacy_score -0.05 0.44 0.44
## posaff_sum -0.06 -0.24 0.59
## negaff_sum -0.31 -0.90 0.45
## cmm_t2_score_6 cmm_t2_score_4 selfefficacy_score
## cmm_t2_score 0.99 0.99 0.04
## mndst_intelligence_t2_score 0.69 0.69 0.11
## mndst_process_t2_score -0.55 -0.55 0.50
## mndst_exercise_t2_score -0.11 -0.11 0.54
## mndst_fail_t2_score 0.87 0.87 0.19
## mndst_pers_t2_score 0.76 0.76 0.04
## mndst_stress_t2_score 0.18 0.17 -0.05
## ffmq15_5f 0.78 0.78 0.44
## MetAwa -0.54 -0.54 0.44
## cmm_t2_score_6 1.00 1.00 -0.05
## cmm_t2_score_4 1.00 1.00 -0.05
## selfefficacy_score -0.05 -0.05 1.00
## posaff_sum -0.73 -0.72 0.59
## negaff_sum -0.89 -0.89 -0.23
## posaff_sum negaff_sum
## cmm_t2_score -0.66 -0.92
## mndst_intelligence_t2_score -0.38 -0.68
## mndst_process_t2_score 0.84 0.14
## mndst_exercise_t2_score 0.61 -0.32
## mndst_fail_t2_score -0.45 -0.91
## mndst_pers_t2_score -0.50 -0.70
## mndst_stress_t2_score -0.06 -0.31
## ffmq15_5f -0.24 -0.90
## MetAwa 0.59 0.45
## cmm_t2_score_6 -0.73 -0.89
## cmm_t2_score_4 -0.72 -0.89
## selfefficacy_score 0.59 -0.23
## posaff_sum 1.00 0.39
## negaff_sum 0.39 1.00#pmatrix
library(ggcorrplot)
p.mat.df <- cor_pmat(cor.df)
ggcorrplot(cor.df)
ggcorrplot(cor.df, p.mat = p.mat.df) ##pmatrix of correllogram - X = nonsig at <.05 - 
#CMM4 sig relationship with intel, process, fail, pers, mindfulness, metaAwa,pos, neg aff#use corrplot for p-matrix, last coeff seemd high using ggplot
corp3 <- cor.mtest(cor.df, conf.level = .95)
corrplot(cor.df, p.mat = corp3$p, sig.level = .05)
#scatter plots with fitted lines - simple linear models with mindfulness and mindsets (Y ~ X=CMM)
#scatterplot with fitted line cmm x ffmq
ggplot(df, aes(x = cmm_t2_score_4, y = ffmq15_5f)) +
geom_point() +
stat_smooth()## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#scatterplot with fitted line cmm x sfmm mindset
ggplot(df, aes(x = cmm_t2_score_4, y = sfmm_all9_t2_score)) +
geom_point() +
stat_smooth()## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#intelligence
ggplot(df, aes(x = cmm_t2_score_4, y = mndst_intelligence_t2_score)) +
geom_point() +
stat_smooth()## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#exercise
ggplot(df, aes(x = cmm_t2_score_4, y = mndst_exercise_t2_score)) +
geom_point() +
stat_smooth()## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#fail
ggplot(df, aes(x = cmm_t2_score_4, y = mndst_fail_t2_score)) +
geom_point() +
stat_smooth()## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#pers
ggplot(df, aes(x = cmm_t2_score_4, y = mndst_pers_t2_score)) +
geom_point() +
stat_smooth()## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#stress
ggplot(df, aes(x = cmm_t2_score_4, y = mndst_stress_t2_score)) +
geom_point() +
stat_smooth()## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#process
ggplot(df, aes(x = cmm_t2_score_4, y = mndst_process_t2_score)) +
geom_point() +
stat_smooth()## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#Metawareness
ggplot(df, aes(x = cmm_t2_score_4, y = MetAwa)) +
geom_point() +
stat_smooth()## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#self-eff
ggplot(df, aes(x = cmm_t2_score_4, y = selfefficacy_score)) +
geom_point() +
stat_smooth()## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#pos aff
ggplot(df, aes(x = cmm_t2_score_4, y = posaff_sum)) +
geom_point() +
stat_smooth()## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#neg aff
ggplot(df, aes(x = cmm_t2_score_4, y = negaff_sum)) +
geom_point() +
stat_smooth()## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#simple linear models with mindfulness and mindsets and other variables
##build linear regression variables for summary statistics -
#mindfulness
df.lm.4.ffmq <- lm(ffmq15_5f ~ cmm_t2_score_4, data=df)
#failure
df.lm.4.fail<- lm(mndst_fail_t2_score ~ cmm_t2_score_4, data=df)
#intelligence
df.lm.4.int<- lm(mndst_intelligence_t2_score ~ cmm_t2_score_4, data=df)
#persistence
df.lm.4.pers<- lm(mndst_pers_t2_score ~ cmm_t2_score_4, data=df)
#process
df.lm.4.proc<- lm(mndst_process_t2_score ~ cmm_t2_score_4, data=df)
#exercise
df.lm.4.exer<- lm(mndst_exercise_t2_score ~ cmm_t2_score_4, data=df)
#stress
df.lm.4.str<- lm(mndst_stress_t2_score ~ cmm_t2_score_4, data=df)
#sfmm
df.lm.4.sfmm <- lm(sfmm_all9_t2_score ~ cmm_t2_score_4, data=df)
#metaawa
df.lm.4.met <- lm(MetAwa ~ cmm_t2_score_4, data=df)
#self-eff
df.lm.4.eff <- lm(selfefficacy_score ~ cmm_t2_score_4, data=df)
#posaff
df.lm.4.pos <- lm(posaff_sum ~ cmm_t2_score_4, data=df)
#negaff
df.lm.4.neg <- lm(negaff_sum ~ cmm_t2_score_4, data=df)#summary of models - sig predictor linear models CMM predicts ffmq, fail, int, pers, proc, str, metAwa, self-eff
#sig
summary(df.lm.4.ffmq)##
## Call:
## lm(formula = ffmq15_5f ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -14.0634 -2.7395 0.1322 2.4069 13.9366
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 32.0838 0.5800 55.32 <2e-16 ***
## cmm_t2_score_4 2.0522 0.1721 11.93 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4.449 on 322 degrees of freedom
## Multiple R-squared: 0.3064, Adjusted R-squared: 0.3043
## F-statistic: 142.3 on 1 and 322 DF, p-value: < 2.2e-16summary(df.lm.4.fail)##
## Call:
## lm(formula = mndst_fail_t2_score ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.88909 -0.36720 -0.03387 0.29947 2.21750
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.85626 0.08232 34.70 <2e-16 ***
## cmm_t2_score_4 0.33881 0.02442 13.87 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6314 on 322 degrees of freedom
## Multiple R-squared: 0.3741, Adjusted R-squared: 0.3721
## F-statistic: 192.4 on 1 and 322 DF, p-value: < 2.2e-16summary(df.lm.4.int)##
## Call:
## lm(formula = mndst_intelligence_t2_score ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.3739 -0.2493 0.0010 0.3756 2.1883
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.93710 0.10100 29.08 < 2e-16 ***
## cmm_t2_score_4 0.24988 0.02996 8.34 2.2e-15 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7747 on 322 degrees of freedom
## Multiple R-squared: 0.1776, Adjusted R-squared: 0.1751
## F-statistic: 69.55 on 1 and 322 DF, p-value: 2.202e-15summary(df.lm.4.pers)##
## Call:
## lm(formula = mndst_pers_t2_score ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.1527 -0.3021 0.0805 0.4143 2.5881
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.25947 0.11654 27.968 <2e-16 ***
## cmm_t2_score_4 0.32926 0.03457 9.523 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8939 on 322 degrees of freedom
## Multiple R-squared: 0.2198, Adjusted R-squared: 0.2173
## F-statistic: 90.69 on 1 and 322 DF, p-value: < 2.2e-16summary(df.lm.4.proc)##
## Call:
## lm(formula = mndst_process_t2_score ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.31301 -0.38885 -0.04165 0.34901 1.27830
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.19885 0.07390 43.286 < 2e-16 ***
## cmm_t2_score_4 -0.07952 0.02192 -3.627 0.000333 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.5668 on 322 degrees of freedom
## Multiple R-squared: 0.03926, Adjusted R-squared: 0.03627
## F-statistic: 13.16 on 1 and 322 DF, p-value: 0.000333summary(df.lm.4.str)##
## Call:
## lm(formula = mndst_stress_t2_score ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.28656 -0.27528 0.02818 0.31885 1.83692
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.88899 0.08797 21.474 <2e-16 ***
## cmm_t2_score_4 0.06626 0.02610 2.539 0.0116 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6747 on 322 degrees of freedom
## Multiple R-squared: 0.01963, Adjusted R-squared: 0.01658
## F-statistic: 6.447 on 1 and 322 DF, p-value: 0.01159summary(df.lm.4.met)##
## Call:
## lm(formula = MetAwa ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -9.1900 -1.8541 0.0931 1.7553 6.1384
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 16.1296 0.3599 44.822 <2e-16 ***
## cmm_t2_score_4 -0.2113 0.1068 -1.979 0.0486 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.76 on 322 degrees of freedom
## Multiple R-squared: 0.01202, Adjusted R-squared: 0.008954
## F-statistic: 3.918 on 1 and 322 DF, p-value: 0.04862summary(df.lm.4.eff)##
## Call:
## lm(formula = selfefficacy_score ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -12.097 -3.092 -0.183 3.183 9.183
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 30.3604 0.5721 53.064 <2e-16 ***
## cmm_t2_score_4 0.3656 0.1697 2.154 0.032 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4.389 on 322 degrees of freedom
## Multiple R-squared: 0.0142, Adjusted R-squared: 0.01114
## F-statistic: 4.64 on 1 and 322 DF, p-value: 0.03199summary(df.lm.4.pos)##
## Call:
## lm(formula = posaff_sum ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -20.180 -4.300 0.334 4.466 15.820
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 38.3605 0.9389 40.858 < 2e-16 ***
## cmm_t2_score_4 -1.5302 0.2785 -5.494 8.01e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 7.202 on 322 degrees of freedom
## Multiple R-squared: 0.08569, Adjusted R-squared: 0.08285
## F-statistic: 30.18 on 1 and 322 DF, p-value: 8.012e-08summary(df.lm.4.neg)##
## Call:
## lm(formula = negaff_sum ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -25.4406 -5.5408 0.5393 6.5960 16.7659
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 42.0739 1.1554 36.41 <2e-16 ***
## cmm_t2_score_4 -5.3066 0.3428 -15.48 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 8.863 on 322 degrees of freedom
## Multiple R-squared: 0.4267, Adjusted R-squared: 0.4249
## F-statistic: 239.7 on 1 and 322 DF, p-value: < 2.2e-16#nonsig - interesting that only variables cmm did not significantly predict was exercise and sfmm
summary(df.lm.4.exer)##
## Call:
## lm(formula = mndst_exercise_t2_score ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.2946 -0.6702 -0.1503 0.7572 2.3744
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.58593 0.15204 30.16 <2e-16 ***
## cmm_t2_score_4 0.03971 0.04511 0.88 0.379
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.166 on 322 degrees of freedom
## Multiple R-squared: 0.002402, Adjusted R-squared: -0.0006964
## F-statistic: 0.7752 on 1 and 322 DF, p-value: 0.3793summary(df.lm.4.sfmm)##
## Call:
## lm(formula = sfmm_all9_t2_score ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.42687 -0.50363 0.03594 0.48038 1.27041
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.69898 0.08782 53.51 <2e-16 ***
## cmm_t2_score_4 0.02449 0.02605 0.94 0.348
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6736 on 322 degrees of freedom
## Multiple R-squared: 0.002737, Adjusted R-squared: -0.0003604
## F-statistic: 0.8836 on 1 and 322 DF, p-value: 0.3479##looking at data descriptives again by cond
describe.by(df, df$condition) #outcome variables by condition # abr > active control > full intervention## Warning: describe.by is deprecated. Please use the describeBy function##
## Descriptive statistics by group
## group: abr_intervention
## vars n mean sd median trimmed mad min
## ffmq15_5f 1 112 38.58 4.94 37.67 38.05 3.95 30.67
## ffmq_obs 2 112 8.49 1.78 8.33 8.49 1.98 3.67
## ffmq_des 3 112 8.01 1.64 7.67 7.90 1.48 4.33
## ffmq_awa 4 112 7.29 2.40 7.00 7.29 2.47 2.33
## ffmq_nj 5 112 6.60 2.22 6.33 6.46 2.47 2.33
## ffmq_nr 6 112 8.18 1.81 8.33 8.22 1.98 2.33
## MetAwa 7 112 15.41 2.76 15.00 15.48 2.67 7.20
## cmm_t2_score 8 112 3.86 0.99 3.40 3.72 0.59 2.80
## mndst_intelligence_t2_score 9 112 3.67 0.88 3.50 3.65 0.56 1.00
## mndst_process_t2_score 10 112 2.96 0.56 3.00 2.96 0.64 1.71
## mndst_exercise_t2_score 11 112 4.76 1.28 4.62 4.78 1.16 1.48
## mndst_fail_t2_score 12 112 3.90 0.85 3.67 3.80 0.49 1.67
## mndst_pers_t2_score 13 112 4.39 1.06 4.12 4.31 0.56 1.38
## mndst_stress_t2_score 14 112 2.18 0.68 2.12 2.16 0.46 0.00
## subid_final 15 112 157.51 95.02 159.50 156.89 123.80 1.00
## condition* 16 112 1.00 0.00 1.00 1.00 0.00 1.00
## sfmm_all9_t2_score 17 112 4.85 0.62 4.89 4.85 0.66 3.33
## cmm_t2_score_6 18 112 3.15 1.48 2.67 3.00 1.24 1.17
## selfefficacy_score 19 112 31.68 4.49 30.50 31.74 3.71 20.00
## posaff_sum 20 112 33.31 7.56 34.50 33.87 6.67 11.00
## negaff_sum 21 112 24.68 11.58 25.00 24.09 16.31 10.00
## cmm_t2_score_4 22 112 3.16 1.50 2.75 3.03 1.11 1.25
## max range skew kurtosis se
## ffmq15_5f 58.33 27.67 1.18 1.81 0.47
## ffmq_obs 11.67 8.00 -0.06 -0.53 0.17
## ffmq_des 11.67 7.33 0.53 -0.23 0.16
## ffmq_awa 11.67 9.33 0.02 -0.70 0.23
## ffmq_nj 11.67 9.33 0.47 -0.39 0.21
## ffmq_nr 11.67 9.33 -0.41 0.73 0.17
## MetAwa 21.00 13.80 -0.36 0.40 0.26
## cmm_t2_score 6.00 3.20 1.09 -0.23 0.09
## mndst_intelligence_t2_score 6.00 5.00 0.21 1.17 0.08
## mndst_process_t2_score 4.00 2.29 -0.03 -0.58 0.05
## mndst_exercise_t2_score 7.00 5.52 -0.13 -0.20 0.12
## mndst_fail_t2_score 6.00 4.33 0.85 0.73 0.08
## mndst_pers_t2_score 7.00 5.62 0.65 0.58 0.10
## mndst_stress_t2_score 4.00 4.00 0.07 1.98 0.06
## subid_final 320.00 319.00 0.04 -1.21 8.98
## condition* 1.00 0.00 NaN NaN 0.00
## sfmm_all9_t2_score 6.00 2.67 -0.07 -0.57 0.06
## cmm_t2_score_6 6.00 4.83 0.80 -0.74 0.14
## selfefficacy_score 40.00 20.00 -0.07 -0.39 0.42
## posaff_sum 45.00 34.00 -0.68 0.07 0.71
## negaff_sum 48.00 38.00 0.24 -1.25 1.09
## cmm_t2_score_4 6.00 4.75 0.74 -0.80 0.14
## ------------------------------------------------------------
## group: active_control
## vars n mean sd median trimmed mad min
## ffmq15_5f 1 107 38.40 5.47 37.33 37.87 4.45 27.33
## ffmq_obs 2 107 8.63 1.69 8.67 8.70 1.48 4.33
## ffmq_des 3 107 7.71 1.81 7.67 7.65 1.98 3.33
## ffmq_awa 4 107 7.25 2.53 7.00 7.20 2.97 2.33
## ffmq_nj 5 107 6.59 2.77 6.00 6.48 2.97 2.33
## ffmq_nr 6 107 8.22 2.09 8.00 8.27 2.47 2.33
## MetAwa 7 107 15.61 2.71 15.60 15.67 2.97 8.00
## cmm_t2_score 8 107 3.73 0.84 3.30 3.60 0.44 2.80
## mndst_intelligence_t2_score 9 107 3.69 0.85 3.62 3.62 0.56 1.00
## mndst_process_t2_score 10 107 2.93 0.60 2.86 2.93 0.64 1.43
## mndst_exercise_t2_score 11 107 4.57 1.19 4.52 4.58 0.89 1.68
## mndst_fail_t2_score 12 107 3.87 0.75 3.67 3.78 0.49 2.17
## mndst_pers_t2_score 13 107 4.13 1.03 4.00 4.09 0.37 1.00
## mndst_stress_t2_score 14 107 1.83 0.67 1.88 1.88 0.56 0.00
## subid_final 15 107 168.17 95.72 165.00 169.05 127.50 3.00
## condition* 16 107 1.00 0.00 1.00 1.00 0.00 1.00
## sfmm_all9_t2_score 17 107 4.72 0.67 4.78 4.75 0.82 2.33
## cmm_t2_score_6 18 107 2.98 1.39 2.50 2.83 1.24 1.17
## selfefficacy_score 19 107 31.86 4.25 32.00 31.97 4.45 21.00
## posaff_sum 20 107 34.09 7.98 35.00 34.83 7.41 9.00
## negaff_sum 21 107 26.38 12.14 27.00 26.11 14.83 10.00
## cmm_t2_score_4 22 107 3.00 1.42 2.50 2.86 1.11 1.00
## max range skew kurtosis se
## ffmq15_5f 56.67 29.33 1.05 1.23 0.53
## ffmq_obs 11.67 7.33 -0.35 -0.45 0.16
## ffmq_des 11.67 8.33 0.31 -0.13 0.18
## ffmq_awa 11.67 9.33 0.18 -0.96 0.24
## ffmq_nj 11.67 9.33 0.43 -0.90 0.27
## ffmq_nr 11.67 9.33 -0.29 -0.33 0.20
## MetAwa 21.00 13.00 -0.17 -0.60 0.26
## cmm_t2_score 6.00 3.20 1.28 0.50 0.08
## mndst_intelligence_t2_score 6.00 5.00 0.60 2.08 0.08
## mndst_process_t2_score 4.00 2.57 -0.16 -0.43 0.06
## mndst_exercise_t2_score 7.00 5.32 -0.05 -0.08 0.12
## mndst_fail_t2_score 6.00 3.83 1.14 0.98 0.07
## mndst_pers_t2_score 7.00 6.00 0.36 2.28 0.10
## mndst_stress_t2_score 4.00 4.00 -0.51 1.04 0.07
## subid_final 323.00 320.00 -0.06 -1.38 9.25
## condition* 1.00 0.00 NaN NaN 0.00
## sfmm_all9_t2_score 6.00 3.67 -0.52 0.28 0.06
## cmm_t2_score_6 6.00 4.83 0.82 -0.59 0.13
## selfefficacy_score 40.00 19.00 -0.27 -0.37 0.41
## posaff_sum 45.00 36.00 -0.81 0.20 0.77
## negaff_sum 50.00 40.00 0.01 -1.39 1.17
## cmm_t2_score_4 6.00 5.00 0.72 -0.72 0.14
## ------------------------------------------------------------
## group: full_intervention
## vars n mean sd median trimmed mad min
## ffmq15_5f 1 105 38.03 5.62 37.00 37.38 4.45 27.67
## ffmq_obs 2 105 8.63 1.48 8.33 8.64 1.48 4.67
## ffmq_des 3 105 7.60 1.75 7.67 7.51 1.98 3.67
## ffmq_awa 4 105 7.08 2.26 6.67 7.04 2.97 2.33
## ffmq_nj 5 105 6.64 2.47 6.00 6.51 2.47 2.33
## ffmq_nr 6 105 8.08 1.89 8.00 8.11 1.98 2.33
## MetAwa 7 105 15.43 2.87 15.80 15.56 2.97 6.20
## cmm_t2_score 8 105 3.74 0.92 3.40 3.60 0.44 2.70
## mndst_intelligence_t2_score 9 105 3.73 0.84 3.62 3.63 0.56 1.00
## mndst_process_t2_score 10 105 2.99 0.58 3.00 2.98 0.64 1.71
## mndst_exercise_t2_score 11 105 4.79 1.00 4.52 4.72 0.89 1.88
## mndst_fail_t2_score 12 105 3.89 0.79 3.67 3.77 0.25 2.83
## mndst_pers_t2_score 13 105 4.26 0.92 4.12 4.15 0.56 2.25
## mndst_stress_t2_score 14 105 2.27 0.61 2.12 2.20 0.37 1.00
## subid_final 15 105 162.05 90.66 167.00 161.49 111.19 4.00
## condition* 16 105 1.00 0.00 1.00 1.00 0.00 1.00
## sfmm_all9_t2_score 17 105 4.75 0.73 4.78 4.76 0.66 2.56
## cmm_t2_score_6 18 105 3.01 1.36 2.50 2.87 0.99 1.00
## selfefficacy_score 19 105 30.87 4.47 30.00 30.78 5.93 22.00
## posaff_sum 20 105 33.70 7.03 34.00 33.91 7.41 16.00
## negaff_sum 21 105 26.69 11.33 28.00 26.48 13.34 10.00
## cmm_t2_score_4 22 105 2.98 1.40 2.50 2.84 1.11 1.00
## max range skew kurtosis se
## ffmq15_5f 58.33 30.67 1.31 2.29 0.55
## ffmq_obs 11.67 7.00 0.00 -0.27 0.14
## ffmq_des 11.67 8.00 0.41 0.06 0.17
## ffmq_awa 11.67 9.33 0.17 -0.76 0.22
## ffmq_nj 11.67 9.33 0.39 -0.59 0.24
## ffmq_nr 11.67 9.33 -0.21 -0.36 0.18
## MetAwa 21.00 14.80 -0.45 -0.02 0.28
## cmm_t2_score 6.00 3.30 1.33 0.52 0.09
## mndst_intelligence_t2_score 6.00 5.00 1.04 2.25 0.08
## mndst_process_t2_score 4.00 2.29 0.11 -0.72 0.06
## mndst_exercise_t2_score 7.00 5.12 0.48 0.16 0.10
## mndst_fail_t2_score 6.00 3.17 1.39 1.07 0.08
## mndst_pers_t2_score 7.00 4.75 1.26 1.77 0.09
## mndst_stress_t2_score 4.00 3.00 1.03 1.17 0.06
## subid_final 324.00 320.00 0.02 -1.09 8.85
## condition* 1.00 0.00 NaN NaN 0.00
## sfmm_all9_t2_score 6.00 3.44 -0.33 0.00 0.07
## cmm_t2_score_6 6.00 5.00 0.89 -0.30 0.13
## selfefficacy_score 40.00 18.00 0.12 -0.78 0.44
## posaff_sum 45.00 29.00 -0.34 -0.55 0.69
## negaff_sum 47.00 37.00 -0.02 -1.23 1.11
## cmm_t2_score_4 6.00 5.00 0.82 -0.41 0.14describe.by(d.cmm.4, d.cmm.4$condition) ##cmm score by condition## Warning: describe.by is deprecated. Please use the describeBy function##
## Descriptive statistics by group
## group: abr_intervention
## vars n mean sd median trimmed mad min max range skew
## subid_final* 1 112 157.51 95.02 159.50 156.89 123.80 1.00 320 319.00 0.04
## condition* 2 112 1.00 0.00 1.00 1.00 0.00 1.00 1 0.00 NaN
## time* 3 112 1.00 0.00 1.00 1.00 0.00 1.00 1 0.00 NaN
## score 4 112 3.16 1.50 2.75 3.03 1.11 1.25 6 4.75 0.74
## kurtosis se
## subid_final* -1.21 8.98
## condition* NaN 0.00
## time* NaN 0.00
## score -0.80 0.14
## ------------------------------------------------------------
## group: active_control
## vars n mean sd median trimmed mad min max range skew
## subid_final* 1 107 168.17 95.72 165.0 169.05 127.50 3 323 320 -0.06
## condition* 2 107 2.00 0.00 2.0 2.00 0.00 2 2 0 NaN
## time* 3 107 1.00 0.00 1.0 1.00 0.00 1 1 0 NaN
## score 4 107 3.00 1.42 2.5 2.86 1.11 1 6 5 0.72
## kurtosis se
## subid_final* -1.38 9.25
## condition* NaN 0.00
## time* NaN 0.00
## score -0.72 0.14
## ------------------------------------------------------------
## group: full_intervention
## vars n mean sd median trimmed mad min max range skew
## subid_final* 1 105 162.05 90.66 167.0 161.49 111.19 4 324 320 0.02
## condition* 2 105 3.00 0.00 3.0 3.00 0.00 3 3 0 NaN
## time* 3 105 1.00 0.00 1.0 1.00 0.00 1 1 0 NaN
## score 4 105 2.98 1.40 2.5 2.84 1.11 1 6 5 0.82
## kurtosis se
## subid_final* -1.09 8.85
## condition* NaN 0.00
## time* NaN 0.00
## score -0.41 0.14##boxplots by condition for CMM
boxplot( score ~ condition, data = d.cmm.4)
boxplot(cmm_t2_score_4 ~ condition, data = df)
boxplot(df$cmm_t2_score_4 ~ df$condition, main = "Boxplot", xlab = "Group condition", ylab = "CMM")
#looking at different mediation models --really this is just controlling for next variable?
model_sfmx <- lm(sfmm_all9_t2_score ~ cmm_t2_score_4, data = df)
model_mx <- lm(MetAwa ~ cmm_t2_score_4, data = df)
model_mxmm <- lm(ffmq15_5f ~ cmm_t2_score_4, data = df)
model_sfxm <- lm(sfmm_all9_t2_score ~ cmm_t2_score_4 + MetAwa, data = df) ##or high MA moderates the predictino of cmm to sfmm?
model_sfxmm <- lm(sfmm_all9_t2_score ~ cmm_t2_score_4 + ffmq15_5f, data = df) ## the impact of cmm on sfmm is mediated by mindfulness
summary(model_sfmx)##
## Call:
## lm(formula = sfmm_all9_t2_score ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.42687 -0.50363 0.03594 0.48038 1.27041
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.69898 0.08782 53.51 <2e-16 ***
## cmm_t2_score_4 0.02449 0.02605 0.94 0.348
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6736 on 322 degrees of freedom
## Multiple R-squared: 0.002737, Adjusted R-squared: -0.0003604
## F-statistic: 0.8836 on 1 and 322 DF, p-value: 0.3479summary(model_mx)##
## Call:
## lm(formula = MetAwa ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -9.1900 -1.8541 0.0931 1.7553 6.1384
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 16.1296 0.3599 44.822 <2e-16 ***
## cmm_t2_score_4 -0.2113 0.1068 -1.979 0.0486 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.76 on 322 degrees of freedom
## Multiple R-squared: 0.01202, Adjusted R-squared: 0.008954
## F-statistic: 3.918 on 1 and 322 DF, p-value: 0.04862summary(model_mxmm)##
## Call:
## lm(formula = ffmq15_5f ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -14.0634 -2.7395 0.1322 2.4069 13.9366
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 32.0838 0.5800 55.32 <2e-16 ***
## cmm_t2_score_4 2.0522 0.1721 11.93 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4.449 on 322 degrees of freedom
## Multiple R-squared: 0.3064, Adjusted R-squared: 0.3043
## F-statistic: 142.3 on 1 and 322 DF, p-value: < 2.2e-16summary(model_sfxm)##
## Call:
## lm(formula = sfmm_all9_t2_score ~ cmm_t2_score_4 + MetAwa, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.15737 -0.38741 0.02108 0.38119 1.65434
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.02789 0.21427 14.131 < 2e-16 ***
## cmm_t2_score_4 0.04639 0.02377 1.951 0.0519 .
## MetAwa 0.10360 0.01233 8.401 1.45e-15 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6109 on 321 degrees of freedom
## Multiple R-squared: 0.1825, Adjusted R-squared: 0.1774
## F-statistic: 35.82 on 2 and 321 DF, p-value: 9.053e-15summary(model_sfxmm) ##
## Call:
## lm(formula = sfmm_all9_t2_score ~ cmm_t2_score_4 + ffmq15_5f,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.43103 -0.44074 0.05335 0.46897 1.49210
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.579505 0.277401 12.904 < 2e-16 ***
## cmm_t2_score_4 -0.047113 0.030490 -1.545 0.123
## ffmq15_5f 0.034892 0.008224 4.243 2.89e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6565 on 321 degrees of freedom
## Multiple R-squared: 0.05569, Adjusted R-squared: 0.0498
## F-statistic: 9.465 on 2 and 321 DF, p-value: 0.0001014#looking at different mediation models
model_yxi <- lm(mndst_intelligence_t2_score ~ cmm_t2_score_4, data = df)
model_mxi <- lm(MetAwa ~ cmm_t2_score_4, data = df)
model_yxmi <- lm(mndst_intelligence_t2_score ~ cmm_t2_score_4 + MetAwa, data = df)
model_yxmmi <- lm(mndst_intelligence_t2_score~ cmm_t2_score_4 + ffmq15_5f, data = df)
summary(model_yxi)##
## Call:
## lm(formula = mndst_intelligence_t2_score ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.3739 -0.2493 0.0010 0.3756 2.1883
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.93710 0.10100 29.08 < 2e-16 ***
## cmm_t2_score_4 0.24988 0.02996 8.34 2.2e-15 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7747 on 322 degrees of freedom
## Multiple R-squared: 0.1776, Adjusted R-squared: 0.1751
## F-statistic: 69.55 on 1 and 322 DF, p-value: 2.202e-15summary(model_mxi)##
## Call:
## lm(formula = MetAwa ~ cmm_t2_score_4, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -9.1900 -1.8541 0.0931 1.7553 6.1384
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 16.1296 0.3599 44.822 <2e-16 ***
## cmm_t2_score_4 -0.2113 0.1068 -1.979 0.0486 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.76 on 322 degrees of freedom
## Multiple R-squared: 0.01202, Adjusted R-squared: 0.008954
## F-statistic: 3.918 on 1 and 322 DF, p-value: 0.04862summary(model_yxmi)##
## Call:
## lm(formula = mndst_intelligence_t2_score ~ cmm_t2_score_4 + MetAwa,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.4749 -0.2793 0.0459 0.3426 2.1235
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.07284 0.26715 7.759 1.15e-13 ***
## cmm_t2_score_4 0.26120 0.02964 8.814 < 2e-16 ***
## MetAwa 0.05358 0.01538 3.485 0.000561 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7616 on 321 degrees of freedom
## Multiple R-squared: 0.2076, Adjusted R-squared: 0.2027
## F-statistic: 42.05 on 2 and 321 DF, p-value: < 2.2e-16summary(model_yxmmi) ##
## Call:
## lm(formula = mndst_intelligence_t2_score ~ cmm_t2_score_4 + ffmq15_5f,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.7777 -0.2644 0.0137 0.3360 2.4602
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.837682 0.321424 5.717 2.48e-08 ***
## cmm_t2_score_4 0.179557 0.035329 5.082 6.34e-07 ***
## ffmq15_5f 0.034267 0.009529 3.596 0.000374 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7607 on 321 degrees of freedom
## Multiple R-squared: 0.2095, Adjusted R-squared: 0.2045
## F-statistic: 42.53 on 2 and 321 DF, p-value: < 2.2e-16#looking at different moderation models
model_sfxc <- lm(sfmm_all9_t2_score ~ condition, data = df)
model_sfmxc <- lm(cmm_t2_score_4 ~ condition, data = df)
model_sfmcxc <- lm(sfmm_all9_t2_score ~ condition + cmm_t2_score_4, data = df)
summary(model_sfxc)##
## Call:
## lm(formula = sfmm_all9_t2_score ~ condition, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.38318 -0.49429 0.03472 0.47619 1.28349
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.85417 0.06359 76.341 <2e-16 ***
## conditionactive_control -0.13766 0.09097 -1.513 0.131
## conditionfull_intervention -0.10813 0.09141 -1.183 0.238
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6729 on 321 degrees of freedom
## Multiple R-squared: 0.007887, Adjusted R-squared: 0.001705
## F-statistic: 1.276 on 2 and 321 DF, p-value: 0.2806summary(model_sfmxc)##
## Call:
## lm(formula = cmm_t2_score_4 ~ condition, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.0023 -1.1607 -0.4786 0.8789 3.0214
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.1607 0.1361 23.217 <2e-16 ***
## conditionactive_control -0.1584 0.1948 -0.813 0.417
## conditionfull_intervention -0.1821 0.1957 -0.931 0.353
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.441 on 321 degrees of freedom
## Multiple R-squared: 0.003219, Adjusted R-squared: -0.002992
## F-statistic: 0.5183 on 2 and 321 DF, p-value: 0.5961summary(model_sfmcxc)##
## Call:
## lm(formula = sfmm_all9_t2_score ~ condition + cmm_t2_score_4,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.37196 -0.49005 0.04423 0.49385 1.27238
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.78361 0.10412 45.942 <2e-16 ***
## conditionactive_control -0.13412 0.09110 -1.472 0.142
## conditionfull_intervention -0.10407 0.09157 -1.136 0.257
## cmm_t2_score_4 0.02232 0.02608 0.856 0.393
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6732 on 320 degrees of freedom
## Multiple R-squared: 0.01015, Adjusted R-squared: 0.0008734
## F-statistic: 1.094 on 3 and 320 DF, p-value: 0.3517does CMM moderate the effect of condition on mindsets (sfmm main +)?
Compute the interaction term XZ=X*Z. Fit a multiple regression model with X, Z, and XZ as predictors. Test whether the regression coefficient for XZ is significant or not. Interpret the moderation effect. Display the moderation effect graphically.
#computer interaction term XZ=X*Z
xz<- df$sfmm_all9_t2_score * df$cmm_t2_score_4 #interaction term using x = sfmm z (moderator) = cmm
summary(lm(df$mndst_intelligence_t2_score ~ df$sfmm_all9_t2_score + df$cmm_t2_score_4 + xz)) #using x, z, and xz as predictors##
## Call:
## lm(formula = df$mndst_intelligence_t2_score ~ df$sfmm_all9_t2_score +
## df$cmm_t2_score_4 + xz)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.4284 -0.2498 0.0367 0.3420 2.5953
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.99000 0.81262 4.910 1.45e-06 ***
## df$sfmm_all9_t2_score -0.18745 0.16072 -1.166 0.24436
## df$cmm_t2_score_4 -0.47105 0.23232 -2.028 0.04343 *
## xz 0.13968 0.04508 3.098 0.00212 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7439 on 320 degrees of freedom
## Multiple R-squared: 0.2464, Adjusted R-squared: 0.2394
## F-statistic: 34.88 on 3 and 320 DF, p-value: < 2.2e-16# p <.01 suggests there is a sig moderation effect - in other words there is a significant relationship such that sf is moderated by cmm to predict intelligence mindset - the relation between sfmm and int mindset significantly depends on different levels of CMM#plug in some other mindsets for same model does CMM moderate relationship of SFMM and mindsets?
#computer interaction term XZ=X*Z
xzmi <- df$sfmm_all9_t2_score * df$cmm_t2_score_4 #interaction term using x = sfmm z (moderator) = cmm
summary(lm(df$mndst_stress_t2_score~ df$sfmm_all9_t2_score + df$cmm_t2_score_4 + xzmi)) #using x, z, and xz as predictors##
## Call:
## lm(formula = df$mndst_stress_t2_score ~ df$sfmm_all9_t2_score +
## df$cmm_t2_score_4 + xzmi)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.6149 -0.3212 0.0230 0.3241 1.7569
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.48866 0.67644 6.636 1.38e-10 ***
## df$sfmm_all9_t2_score -0.49342 0.13379 -3.688 0.000265 ***
## df$cmm_t2_score_4 -1.10680 0.19339 -5.723 2.40e-08 ***
## xzmi 0.22816 0.03753 6.080 3.42e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6192 on 320 degrees of freedom
## Multiple R-squared: 0.1795, Adjusted R-squared: 0.1718
## F-statistic: 23.33 on 3 and 320 DF, p-value: 1.103e-13# the relationship between sfmm and mindsets (process, exercise, fail, pers, stress) significantly depends on different levels of CMM#computer interaction term XZ=X*Z
xzm<- df$cmm_t2_score * df$ffmq15_5f #interaction term using x = sfmm z (moderator) = cmm
summary(lm(df$sfmm_all9_t2_score ~ df$cmm_t2_score_4 + df$ffmq15_5f + xzm)) #using x, z, and xz as predictors##
## Call:
## lm(formula = df$sfmm_all9_t2_score ~ df$cmm_t2_score_4 + df$ffmq15_5f +
## xzm)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.52471 -0.35698 0.06422 0.36317 1.93081
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.50386 0.40254 16.157 < 2e-16 ***
## df$cmm_t2_score_4 -0.54987 0.06101 -9.012 < 2e-16 ***
## df$ffmq15_5f -0.08843 0.01527 -5.790 1.68e-08 ***
## xzm 0.02254 0.00245 9.202 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.5847 on 320 degrees of freedom
## Multiple R-squared: 0.2533, Adjusted R-squared: 0.2463
## F-statistic: 36.18 on 3 and 320 DF, p-value: < 2.2e-16# p <.0001 suggests there is a sig moderation effect - in other words there is a significant relationship such that the relationship between CMM and mindset (intelligence, process, exercise, fail, pers, stress, sfmm ) significantly depends on different levels of mindfulness #plug in some other mindsets for same model does mindfulness moderate relationship of CMM and mindsets?