1. Loading, setting up

2. Null models (ready)

m0i <- lmer(challenge ~ 1 + learning +
                (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
            data = df)

sjPlot::sjt.lmer(m0i, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	challenge
	B	std. Error	p
Fixed Parts
(Intercept)	1.76	0.10	<.001
learning	0.19	0.02	<.001
Random Parts
N_{beep_ID_new}	248
N_{participant_ID}	203
N_{program_ID}	9
ICC_{beep_ID_new}	0.060
ICC_{participant_ID}	0.345
ICC_{program_ID}	0.032
Observations	2969
R² / Ω₀²	.536 / .529

m0ii <- lmer(relevance ~ 1 + 
                 (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
             data = df)

sjPlot::sjt.lmer(m0i, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	challenge
	B	std. Error	p
Fixed Parts
(Intercept)	1.76	0.10	<.001
learning	0.19	0.02	<.001
Random Parts
N_{beep_ID_new}	248
N_{participant_ID}	203
N_{program_ID}	9
ICC_{beep_ID_new}	0.060
ICC_{participant_ID}	0.345
ICC_{program_ID}	0.032
Observations	2969
R² / Ω₀²	.536 / .529

m0iii <- lmer(learning ~ 1 + 
                  (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
              data = df)

sjPlot::sjt.lmer(m0i, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	challenge
	B	std. Error	p
Fixed Parts
(Intercept)	1.76	0.10	<.001
learning	0.19	0.02	<.001
Random Parts
N_{beep_ID_new}	248
N_{participant_ID}	203
N_{program_ID}	9
ICC_{beep_ID_new}	0.060
ICC_{participant_ID}	0.345
ICC_{program_ID}	0.032
Observations	2969
R² / Ω₀²	.536 / .529

df$positive_affect <- jmRtools::composite_mean_maker(df,
                                                     happy, excited)

m0iv <- lmer(positive_affect ~ 1 + 
                 (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
             data = df)

sjPlot::sjt.lmer(m0i, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	challenge
	B	std. Error	p
Fixed Parts
(Intercept)	1.76	0.10	<.001
learning	0.19	0.02	<.001
Random Parts
N_{beep_ID_new}	248
N_{participant_ID}	203
N_{program_ID}	9
ICC_{beep_ID_new}	0.060
ICC_{participant_ID}	0.345
ICC_{program_ID}	0.032
Observations	2969
R² / Ω₀²	.536 / .529

3. Models for youth activity (ready)

video %>% 
    left_join(pm) %>% 
    count(program_name, youth_activity_rc) %>% 
    filter(!is.na(youth_activity_rc)) %>% 
    spread(youth_activity_rc, n, fill = 0) %>% 
    gather(youth_activity_rc, frequency, -program_name) %>% 
    group_by(program_name) %>% 
    mutate(frequency_prop = frequency / sum(frequency)) %>% 
    ggplot(aes(x = reorder(youth_activity_rc, frequency_prop), y = frequency_prop)) +
    facet_wrap( ~ program_name) +
    geom_col() +
    theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
    ylab("Frequency Proportion") +
    xlab(NULL) +
    ggtitle("Frequency of Youth Activity (Recoded) Codes by Program")

df$youth_activity_rc_fac <- as.factor(df$youth_activity_rc)
dc <- as.tibble(psych::dummy.code(df$youth_activity_rc_fac))
df_ss <- bind_cols(df, dc)

df_ss %>% 
    select(challenge, relevance, learning, positive_affect, 
           `Not Focused`, `Basic Skills Activity`, `Creating Product`, 
           `Field Trip Speaker`, `Lab Activity`, `Program Staff Led`) %>% 
    correlate() %>% 
    shave() %>% 
    fashion()

##                  rowname challenge relevance learning positive_affect
## 1              challenge                                             
## 2              relevance       .39                                   
## 3               learning       .30       .65                         
## 4        positive_affect       .27       .52      .48                
## 5            Not Focused      -.02      -.06     -.05             .04
## 6  Basic Skills Activity      -.01      -.01      .04            -.06
## 7       Creating Product       .12       .08      .04             .05
## 8     Field Trip Speaker      -.04       .01     -.02             .02
## 9           Lab Activity       .00      -.03      .01             .02
## 10     Program Staff Led      -.06       .01     -.00            -.07
##    Not.Focused Basic.Skills.Activity Creating.Product Field.Trip.Speaker
## 1                                                                       
## 2                                                                       
## 3                                                                       
## 4                                                                       
## 5                                                                       
## 6         -.35                                                          
## 7         -.33                  -.25                                    
## 8         -.15                  -.11             -.11                   
## 9         -.14                  -.11             -.10               -.05
## 10        -.27                  -.21             -.20               -.09
##    Lab.Activity Program.Staff.Led
## 1                                
## 2                                
## 3                                
## 4                                
## 5                                
## 6                                
## 7                                
## 8                                
## 9                                
## 10         -.09

m1i <- lmer(challenge ~ 1 + 
                youth_activity_rc +
                (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
            data = df)

sjPlot::sjt.lmer(m1i, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	challenge
	B	std. Error	p
Fixed Parts
(Intercept)	2.19	0.09	<.001
youth_activity_rc (Basic Skills Activity)	0.10	0.06	.117
youth_activity_rc (Creating Product)	0.37	0.06	<.001
youth_activity_rc (Field Trip Speaker)	-0.08	0.13	.550
youth_activity_rc (Lab Activity)	0.20	0.12	.102
youth_activity_rc (Program Staff Led)	-0.10	0.07	.173
Random Parts
N_{beep_ID_new}	235
N_{participant_ID}	203
N_{program_ID}	9
ICC_{beep_ID_new}	0.045
ICC_{participant_ID}	0.385
ICC_{program_ID}	0.034
Observations	2818
R² / Ω₀²	.529 / .522

m1ii <- lmer(relevance ~ 1 + 
                 youth_activity_rc +
                 (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
             data = df)

sjPlot::sjt.lmer(m1ii, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	relevance
	B	std. Error	p
Fixed Parts
(Intercept)	2.46	0.07	<.001
youth_activity_rc (Basic Skills Activity)	0.15	0.04	<.001
youth_activity_rc (Creating Product)	0.23	0.04	<.001
youth_activity_rc (Field Trip Speaker)	0.29	0.07	<.001
youth_activity_rc (Lab Activity)	0.11	0.07	.144
youth_activity_rc (Program Staff Led)	0.15	0.04	<.001
Random Parts
N_{beep_ID_new}	235
N_{participant_ID}	203
N_{program_ID}	9
ICC_{beep_ID_new}	0.007
ICC_{participant_ID}	0.523
ICC_{program_ID}	0.016
Observations	2818
R² / Ω₀²	.586 / .583

m1iii <- lmer(learning ~ 1 + 
                  youth_activity_rc +
                  (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
              data = df)

sjPlot::sjt.lmer(m1iii, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	learning
	B	std. Error	p
Fixed Parts
(Intercept)	2.68	0.06	<.001
youth_activity_rc (Basic Skills Activity)	0.22	0.05	<.001
youth_activity_rc (Creating Product)	0.14	0.05	.009
youth_activity_rc (Field Trip Speaker)	0.10	0.10	.312
youth_activity_rc (Lab Activity)	0.15	0.10	.111
youth_activity_rc (Program Staff Led)	0.07	0.06	.218
Random Parts
N_{beep_ID_new}	235
N_{participant_ID}	203
N_{program_ID}	9
ICC_{beep_ID_new}	0.011
ICC_{participant_ID}	0.357
ICC_{program_ID}	0.002
Observations	2817
R² / Ω₀²	.428 / .421

df$positive_affect <- jmRtools::composite_mean_maker(df,
                                                     happy, excited)

m1iv <- lmer(positive_affect ~ 1 + 
                 youth_activity_rc +
                 (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
             data = df)

sjPlot::sjt.lmer(m1iv, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	positive_affect
	B	std. Error	p
Fixed Parts
(Intercept)	2.70	0.12	<.001
youth_activity_rc (Basic Skills Activity)	0.03	0.05	.532
youth_activity_rc (Creating Product)	0.01	0.05	.802
youth_activity_rc (Field Trip Speaker)	0.01	0.10	.926
youth_activity_rc (Lab Activity)	0.07	0.10	.510
youth_activity_rc (Program Staff Led)	-0.05	0.06	.380
Random Parts
N_{beep_ID_new}	235
N_{participant_ID}	203
N_{program_ID}	9
ICC_{beep_ID_new}	0.023
ICC_{participant_ID}	0.421
ICC_{program_ID}	0.091
Observations	2818
R² / Ω₀²	.580 / .576

4. CLASS models (not ready)

df %>% 
    select(CLASS_EmotionalSupportEncouragement, CLASS_InstructionalSupport, CLASS_STEMConceptualDevelopment, CLASS_ActivityLeaderEnthusiasm, CLASS_Autonomy,
           challenge, relevance, learning, positive_affect) %>%  
    correlate() %>% 
    shave() %>% 
    fashion()

##                               rowname CLASS_EmotionalSupportEncouragement
## 1 CLASS_EmotionalSupportEncouragement                                    
## 2          CLASS_InstructionalSupport                                 .39
## 3     CLASS_STEMConceptualDevelopment                                 .28
## 4      CLASS_ActivityLeaderEnthusiasm                                 .63
## 5                      CLASS_Autonomy                                 .29
## 6                           challenge                                 .03
## 7                           relevance                                -.01
## 8                            learning                                 .00
## 9                     positive_affect                                 .01
##   CLASS_InstructionalSupport CLASS_STEMConceptualDevelopment
## 1                                                           
## 2                                                           
## 3                        .89                                
## 4                        .77                             .63
## 5                        .50                             .51
## 6                        .06                             .04
## 7                        .05                             .04
## 8                        .07                             .07
## 9                        .06                             .05
##   CLASS_ActivityLeaderEnthusiasm CLASS_Autonomy challenge relevance
## 1                                                                  
## 2                                                                  
## 3                                                                  
## 4                                                                  
## 5                            .52                                   
## 6                            .07            .06                    
## 7                            .04            .01       .39          
## 8                            .05            .02       .30       .65
## 9                            .09            .02       .27       .52
##   learning positive_affect
## 1                         
## 2                         
## 3                         
## 4                         
## 5                         
## 6                         
## 7                         
## 8                         
## 9      .48

m1v <- lmer(relevance ~ 1 + 
                # CLASS_EmotionalSupportEncouragement +
                # CLASS_InstructionalSupport +
                # CLASS_STEMConceptualDevelopment +
                # CLASS_ActivityLeaderEnthusiasm +
                CLASS_Autonomy +
                (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
            data = df)

sjPlot::sjt.lmer(m1v, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	relevance
	B	std. Error	p
Fixed Parts
(Intercept)	2.48	0.07	<.001
CLASS_Autonomy	0.03	0.01	.012
Random Parts
N_{beep_ID_new}	236
N_{participant_ID}	203
N_{program_ID}	9
ICC_{beep_ID_new}	0.013
ICC_{participant_ID}	0.518
ICC_{program_ID}	0.012
Observations	2800
R² / Ω₀²	.588 / .585

m1vi <- lmer(challenge ~ 1 +
                 # CLASS_EmotionalSupportEncouragement +
                 #CLASS_InstructionalSupport +
                 # CLASS_STEMConceptualDevelopment +
                 #CLASS_ActivityLeaderEnthusiasm +
                 CLASS_Autonomy +
                 (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
             data = df)

sjPlot::sjt.lmer(m1vi, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	challenge
	B	std. Error	p
Fixed Parts
(Intercept)	2.01	0.11	<.001
CLASS_Autonomy	0.08	0.02	<.001
Random Parts
N_{beep_ID_new}	236
N_{participant_ID}	203
N_{program_ID}	9
ICC_{beep_ID_new}	0.053
ICC_{participant_ID}	0.375
ICC_{program_ID}	0.043
Observations	2800
R² / Ω₀²	.531 / .523

m1viii <- lmer(learning ~ 1 +
                   # CLASS_EmotionalSupportEncouragement +
                   #CLASS_InstructionalSupport +
                   # CLASS_STEMConceptualDevelopment +
                   #CLASS_ActivityLeaderEnthusiasm +
                   CLASS_Autonomy +
                   (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
               data = df)

sjPlot::sjt.lmer(m1viii, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	learning
	B	std. Error	p
Fixed Parts
(Intercept)	2.68	0.07	<.001
CLASS_Autonomy	0.03	0.01	.045
Random Parts
N_{beep_ID_new}	236
N_{participant_ID}	203
N_{program_ID}	9
ICC_{beep_ID_new}	0.014
ICC_{participant_ID}	0.354
ICC_{program_ID}	0.000
Observations	2799
R² / Ω₀²	.428 / .421

m1viv <- lmer(positive_affect ~ 1 +
                  # CLASS_EmotionalSupportEncouragement +
                  #CLASS_InstructionalSupport +
                  # CLASS_STEMConceptualDevelopment +
                  #CLASS_ActivityLeaderEnthusiasm +
                  CLASS_Autonomy +
                  (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
              data = df)

sjPlot::sjt.lmer(m1viv, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	positive_affect
	B	std. Error	p
Fixed Parts
(Intercept)	2.59	0.13	<.001
CLASS_Autonomy	0.03	0.01	.021
Random Parts
N_{beep_ID_new}	236
N_{participant_ID}	203
N_{program_ID}	9
ICC_{beep_ID_new}	0.022
ICC_{participant_ID}	0.424
ICC_{program_ID}	0.093
Observations	2800
R² / Ω₀²	.583 / .580

5. Pre-survey measures (ready)

df %>% 
    select(overall_pre_competence_beliefs, overall_pre_interest, overall_pre_utility_value,
           challenge, relevance, learning, positive_affect) %>%  
    correlate() %>% 
    shave() %>% 
    fashion()

##                          rowname overall_pre_competence_beliefs
## 1 overall_pre_competence_beliefs                               
## 2           overall_pre_interest                            .73
## 3      overall_pre_utility_value                            .68
## 4                      challenge                           -.12
## 5                      relevance                            .03
## 6                       learning                            .09
## 7                positive_affect                            .08
##   overall_pre_interest overall_pre_utility_value challenge relevance
## 1                                                                   
## 2                                                                   
## 3                  .65                                              
## 4                 -.00                      -.04                    
## 5                  .09                       .08       .39          
## 6                  .08                       .07       .30       .65
## 7                  .20                       .07       .27       .52
##   learning positive_affect
## 1                         
## 2                         
## 3                         
## 4                         
## 5                         
## 6                         
## 7      .48

m2i <- lmer(challenge ~ 1 + 
                overall_pre_competence_beliefs +
                overall_pre_interest +
                #overall_pre_utility_value +
                classroom_versus_field_enrichment +
                #youth_activity_rc +
                (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
            data = df)

sjPlot::sjt.lmer(m2i, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	challenge
	B	std. Error	p
Fixed Parts
(Intercept)	2.42	0.25	<.001
overall_pre_competence_beliefs	-0.30	0.11	.005
overall_pre_interest	0.23	0.10	.024
classroom_versus_field_enrichment	0.15	0.06	.019
Random Parts
N_{beep_ID_new}	238
N_{participant_ID}	181
N_{program_ID}	9
ICC_{beep_ID_new}	0.064
ICC_{participant_ID}	0.376
ICC_{program_ID}	0.034
Observations	2622
R² / Ω₀²	.535 / .527

m2ib <- lmer(challenge ~ 1 +
                 overall_pre_competence_beliefs +
                 overall_pre_interest +
                 #overall_pre_utility_value +
                 classroom_versus_field_enrichment +
                 youth_activity_rc +
                 (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
             data = df)

sjPlot::sjt.lmer(m2ib, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	challenge
	B	std. Error	p
Fixed Parts
(Intercept)	2.43	0.24	<.001
overall_pre_competence_beliefs	-0.30	0.11	.005
overall_pre_interest	0.22	0.10	.033
classroom_versus_field_enrichment	0.05	0.06	.457
youth_activity_rc (Basic Skills Activity)	0.10	0.07	.142
youth_activity_rc (Creating Product)	0.34	0.07	<.001
youth_activity_rc (Field Trip Speaker)	-0.08	0.14	.571
youth_activity_rc (Lab Activity)	0.17	0.13	.201
youth_activity_rc (Program Staff Led)	-0.13	0.08	.099
Random Parts
N_{beep_ID_new}	235
N_{participant_ID}	181
N_{program_ID}	9
ICC_{beep_ID_new}	0.049
ICC_{participant_ID}	0.387
ICC_{program_ID}	0.027
Observations	2590
R² / Ω₀²	.531 / .524

m2ii <- lmer(relevance ~ 1 + 
                 overall_pre_competence_beliefs +
                 overall_pre_interest +
                 #overall_pre_utility_value +
                 # youth_activity_rc +
                 classroom_versus_field_enrichment +
                 (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
             data = df)

sjPlot::sjt.lmer(m2ii, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	relevance
	B	std. Error	p
Fixed Parts
(Intercept)	2.37	0.22	<.001
overall_pre_competence_beliefs	-0.08	0.10	.446
overall_pre_interest	0.16	0.10	.102
classroom_versus_field_enrichment	-0.04	0.04	.293
Random Parts
N_{beep_ID_new}	238
N_{participant_ID}	181
N_{program_ID}	9
ICC_{beep_ID_new}	0.017
ICC_{participant_ID}	0.526
ICC_{program_ID}	0.008
Observations	2622
R² / Ω₀²	.595 / .592

m2iib <- lmer(relevance ~ 1 +
                  #overall_pre_competence_beliefs +
                  overall_pre_interest +
                  #overall_pre_utility_value +
                  youth_activity_rc +
                  classroom_versus_field_enrichment +
                  (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
              data = df)

sjPlot::sjt.lmer(m2iib, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	relevance
	B	std. Error	p
Fixed Parts
(Intercept)	2.21	0.21	<.001
overall_pre_interest	0.11	0.06	.101
youth_activity_rc (Basic Skills Activity)	0.13	0.04	.001
youth_activity_rc (Creating Product)	0.23	0.04	<.001
youth_activity_rc (Field Trip Speaker)	0.23	0.08	.003
youth_activity_rc (Lab Activity)	0.09	0.08	.235
youth_activity_rc (Program Staff Led)	0.15	0.05	.001
classroom_versus_field_enrichment	-0.08	0.04	.051
Random Parts
N_{beep_ID_new}	235
N_{participant_ID}	181
N_{program_ID}	9
ICC_{beep_ID_new}	0.009
ICC_{participant_ID}	0.527
ICC_{program_ID}	0.017
Observations	2590
R² / Ω₀²	.593 / .590

m2iii <- lmer(learning ~ 1 + 
                  overall_pre_competence_beliefs +
                  overall_pre_interest +
                  #overall_pre_utility_value +
                  classroom_versus_field_enrichment +
                  #youth_activity_rc +
                  (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
              data = df)

sjPlot::sjt.lmer(m2iii, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	learning
	B	std. Error	p
Fixed Parts
(Intercept)	2.47	0.20	<.001
overall_pre_competence_beliefs	0.03	0.09	.724
overall_pre_interest	0.06	0.09	.466
classroom_versus_field_enrichment	0.01	0.05	.751
Random Parts
N_{beep_ID_new}	238
N_{participant_ID}	181
N_{program_ID}	9
ICC_{beep_ID_new}	0.014
ICC_{participant_ID}	0.352
ICC_{program_ID}	0.000
Observations	2621
R² / Ω₀²	.420 / .413

m2iiib <- lmer(learning ~ 1 + 
                   overall_pre_competence_beliefs +
                   overall_pre_interest +
                   #overall_pre_utility_value +
                   classroom_versus_field_enrichment +
                   youth_activity_rc +
                   (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
               data = df)

sjPlot::sjt.lmer(m2iiib, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	learning
	B	std. Error	p
Fixed Parts
(Intercept)	2.41	0.20	<.001
overall_pre_competence_beliefs	0.02	0.09	.836
overall_pre_interest	0.07	0.09	.448
classroom_versus_field_enrichment	0.01	0.05	.799
youth_activity_rc (Basic Skills Activity)	0.22	0.05	<.001
youth_activity_rc (Creating Product)	0.12	0.06	.036
youth_activity_rc (Field Trip Speaker)	0.08	0.10	.417
youth_activity_rc (Lab Activity)	0.19	0.10	.053
youth_activity_rc (Program Staff Led)	0.07	0.06	.245
Random Parts
N_{beep_ID_new}	235
N_{participant_ID}	181
N_{program_ID}	9
ICC_{beep_ID_new}	0.010
ICC_{participant_ID}	0.358
ICC_{program_ID}	0.000
Observations	2589
R² / Ω₀²	.420 / .414

df$positive_affect <- jmRtools::composite_mean_maker(df, happy, excited)

m2iv <- lmer(positive_affect ~ 
                 overall_pre_competence_beliefs +
                 overall_pre_interest +
                 #overall_pre_utility_value +
                 classroom_versus_field_enrichment +
                 # youth_activity_rc +
                 (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
             data = df)

sjPlot::sjt.lmer(m2iv, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	positive_affect
	B	std. Error	p
Fixed Parts
(Intercept)	2.17	0.26	<.001
overall_pre_competence_beliefs	-0.05	0.11	.683
overall_pre_interest	0.23	0.11	.031
classroom_versus_field_enrichment	-0.05	0.05	.273
Random Parts
N_{beep_ID_new}	238
N_{participant_ID}	181
N_{program_ID}	9
ICC_{beep_ID_new}	0.029
ICC_{participant_ID}	0.443
ICC_{program_ID}	0.061
Observations	2622
R² / Ω₀²	.586 / .582

m2ivb <- lmer(positive_affect ~ 
                  overall_pre_competence_beliefs +
                  overall_pre_interest +
                  classroom_versus_field_enrichment +
                  youth_activity_rc +
                  (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
              data = df)

sjPlot::sjt.lmer(m2ivb, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	positive_affect
	B	std. Error	p
Fixed Parts
(Intercept)	2.20	0.26	<.001
overall_pre_competence_beliefs	-0.05	0.11	.657
overall_pre_interest	0.23	0.11	.031
classroom_versus_field_enrichment	-0.06	0.05	.253
youth_activity_rc (Basic Skills Activity)	0.00	0.06	.977
youth_activity_rc (Creating Product)	0.01	0.06	.824
youth_activity_rc (Field Trip Speaker)	-0.03	0.11	.768
youth_activity_rc (Lab Activity)	0.07	0.11	.530
youth_activity_rc (Program Staff Led)	-0.07	0.07	.266
Random Parts
N_{beep_ID_new}	235
N_{participant_ID}	181
N_{program_ID}	9
ICC_{beep_ID_new}	0.030
ICC_{participant_ID}	0.441
ICC_{program_ID}	0.058
Observations	2590
R² / Ω₀²	.585 / .581

6. Situational experiences (ready)

df$overall_engagement <- jmRtools::composite_mean_maker(df, hard_working, concentrating, enjoy)

df %>% 
    select(overall_engagement, interest, challenge, relevance, learning, positive_affect) %>%  
    correlate() %>% 
    shave() %>% 
    fashion()

##              rowname overall_engagement interest challenge relevance
## 1 overall_engagement                                                
## 2           interest                .69                             
## 3          challenge                .31      .28                    
## 4          relevance                .65      .61       .39          
## 5           learning                .68      .56       .30       .65
## 6    positive_affect                .65      .56       .27       .52
##   learning positive_affect
## 1                         
## 2                         
## 3                         
## 4                         
## 5                         
## 6      .48

m3i <- lmer(interest ~ 1 +
                challenge + relevance + learning + positive_affect +
                (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
            data = df)

sjPlot::sjt.lmer(m3i, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	interest
	B	std. Error	p
Fixed Parts
(Intercept)	0.65	0.07	<.001
challenge	0.02	0.01	.141
relevance	0.36	0.02	<.001
learning	0.17	0.02	<.001
positive_affect	0.28	0.02	<.001
Random Parts
N_{beep_ID_new}	248
N_{participant_ID}	203
N_{program_ID}	9
ICC_{beep_ID_new}	0.033
ICC_{participant_ID}	0.098
ICC_{program_ID}	0.016
Observations	2969
R² / Ω₀²	.583 / .582

m3v <- lmer(overall_engagement ~ 1 + 
                challenge + relevance + learning + positive_affect +
                (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
            data = df)

sjPlot::sjt.lmer(m3v, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	overall_engagement
	B	std. Error	p
Fixed Parts
(Intercept)	0.70	0.05	<.001
challenge	0.03	0.01	<.001
relevance	0.23	0.02	<.001
learning	0.27	0.01	<.001
positive_affect	0.28	0.01	<.001
Random Parts
N_{beep_ID_new}	248
N_{participant_ID}	203
N_{program_ID}	9
ICC_{beep_ID_new}	0.028
ICC_{participant_ID}	0.203
ICC_{program_ID}	0.000
Observations	2969
R² / Ω₀²	.734 / .733

m3i_update <- lmer(interest ~ 1 +
                       challenge + relevance + learning + positive_affect +
                       overall_pre_competence_beliefs +
                       overall_pre_interest +
                       classroom_versus_field_enrichment +
                       (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
                   data = df)

sjPlot::sjt.lmer(m3i_update, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	interest
	B	std. Error	p
Fixed Parts
(Intercept)	0.54	0.12	<.001
challenge	0.03	0.02	.111
relevance	0.35	0.02	<.001
learning	0.17	0.02	<.001
positive_affect	0.28	0.02	<.001
overall_pre_competence_beliefs	0.02	0.05	.708
overall_pre_interest	0.01	0.04	.752
classroom_versus_field_enrichment	0.07	0.04	.093
Random Parts
N_{beep_ID_new}	238
N_{participant_ID}	181
N_{program_ID}	9
ICC_{beep_ID_new}	0.037
ICC_{participant_ID}	0.100
ICC_{program_ID}	0.014
Observations	2621
R² / Ω₀²	.580 / .578

m3v_update <- lmer(overall_engagement ~ 1 + 
                       challenge + relevance + learning + positive_affect + 
                       overall_pre_competence_beliefs +
                       overall_pre_interest +
                       classroom_versus_field_enrichment +
                       (1|program_ID) + (1|participant_ID) + (1|beep_ID_new),
                   data = df)

sjPlot::sjt.lmer(m3v_update, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

	overall_engagement
	B	std. Error	p
Fixed Parts
(Intercept)	0.57	0.10	<.001
challenge	0.03	0.01	.006
relevance	0.24	0.02	<.001
learning	0.25	0.01	<.001
positive_affect	0.28	0.01	<.001
overall_pre_competence_beliefs	0.01	0.04	.835
overall_pre_interest	0.02	0.04	.686
classroom_versus_field_enrichment	0.09	0.03	<.001
Random Parts
N_{beep_ID_new}	238
N_{participant_ID}	181
N_{program_ID}	9
ICC_{beep_ID_new}	0.028
ICC_{participant_ID}	0.213
ICC_{program_ID}	0.002
Observations	2621
R² / Ω₀²	.738 / .737

7. Outcomes (not ready)

participant_df <-df %>% 
    select(participant_ID, challenge, relevance, learning, positive_affect, good_at) %>% 
    group_by(participant_ID) %>% 
    mutate_at(vars(challenge, relevance, learning, positive_affect, good_at), funs(mean, sd)) %>%
    select(participant_ID, contains("mean"), contains("sd")) %>% 
    distinct()

df_ss <- left_join(df, participant_df)

## Joining, by = "participant_ID"

df_ss <- select(df_ss, 
                participant_ID, program_ID,
                challenge_mean, relevance_mean, learning_mean, positive_affect_mean, good_at_mean,
                challenge_sd, relevance_sd, learning_sd, positive_affect_sd, good_at_sd,
                overall_post_interest, overall_pre_interest,
                future_goals)

df_ss <- distinct(df_ss)

df_ss$program_ID <- as.integer(df_ss$program_ID)

df_ss <- left_join(df_ss, pm)

## Joining, by = "program_ID"

# df_ss <- left_join(df_ss, m)

m4ia <- lmer(overall_post_interest ~ 1 + 
                 #challenge_mean + challenge_sd +
                 #learning_mean + 
                 relevance_mean + 
                 #positive_affect_mean + 
                 overall_pre_interest +
                 
                 (1|program_ID),
             data = df_ss)

sjPlot::sjt.lmer(m4ia, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

## Computing p-values via Wald-statistics approximation (treating t as Wald z).

## Warning: This function will be removed in future versions of sjmisc and
## has been moved to package 'sjlabelled'. Please use sjlabelled::get_label()
## instead.

## Warning: This function will be removed in future versions of sjmisc and
## has been moved to package 'sjlabelled'. Please use sjlabelled::get_label()
## instead.

	overall_post_interest
	B	std. Error	p
Fixed Parts
(Intercept)	0.94	0.22	<.001
relevance_mean	0.22	0.05	<.001
overall_pre_interest	0.51	0.05	<.001
Random Parts
N_{program_ID}	9
ICC_{program_ID}	0.111
Observations	427
R² / Ω₀²	.427 / .427

m4ib <- lmer(overall_post_interest ~ 1 + 
                 challenge_mean + challenge_sd +
                 learning_mean + learning_sd +
                 relevance_mean + relevance_sd +
                 positive_affect_mean + positive_affect_sd +
                 overall_pre_interest +
                 (1|program_ID),
             data = df_ss)

sjPlot::sjt.lmer(m4ib, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

## Computing p-values via Wald-statistics approximation (treating t as Wald z).

## Warning: This function will be removed in future versions of sjmisc and
## has been moved to package 'sjlabelled'. Please use sjlabelled::get_label()
## instead.

## Warning: This function will be removed in future versions of sjmisc and
## has been moved to package 'sjlabelled'. Please use sjlabelled::get_label()
## instead.

	overall_post_interest
	B	std. Error	p
Fixed Parts
(Intercept)	0.69	0.27	.011
challenge_mean	-0.07	0.06	.275
challenge_sd	-0.50	0.13	<.001
learning_mean	0.51	0.11	<.001
learning_sd	0.05	0.13	.701
relevance_mean	-0.25	0.12	.037
relevance_sd	0.31	0.18	.087
positive_affect_mean	0.16	0.07	.022
positive_affect_sd	0.07	0.13	.570
overall_pre_interest	0.47	0.05	<.001
Random Parts
N_{program_ID}	9
ICC_{program_ID}	0.110
Observations	425
R² / Ω₀²	.492 / .492

m4iia <- lmer(future_goals ~ 1 + 
                  challenge_mean + 
                  learning_mean + 
                  relevance_mean +
                  positive_affect_mean + 
                  overall_pre_interest +
                  (1|program_ID),
              data = df_ss)

sjPlot::sjt.lmer(m4iia, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

## Computing p-values via Wald-statistics approximation (treating t as Wald z).

## Warning: This function will be removed in future versions of sjmisc and
## has been moved to package 'sjlabelled'. Please use sjlabelled::get_label()
## instead.

## Warning: This function will be removed in future versions of sjmisc and
## has been moved to package 'sjlabelled'. Please use sjlabelled::get_label()
## instead.

	future_goals
	B	std. Error	p
Fixed Parts
(Intercept)	1.27	0.27	<.001
challenge_mean	0.07	0.08	.351
learning_mean	-0.15	0.15	.302
relevance_mean	0.62	0.15	<.001
positive_affect_mean	-0.05	0.08	.556
overall_pre_interest	-0.00	0.05	.941
Random Parts
N_{program_ID}	9
ICC_{program_ID}	0.000
Observations	529
R² / Ω₀²	.092 / .092

m4iib <- lmer(future_goals ~ 1 + 
                  challenge_mean + challenge_sd +
                  learning_mean + learning_sd +
                  relevance_mean + relevance_sd +
                  positive_affect_mean + positive_affect_sd +
                  overall_pre_interest +
                  (1|program_ID),
              data = df_ss)

sjPlot::sjt.lmer(m4iib, p.kr = F, show.re.var = F, show.ci = F, show.se = T)

## Computing p-values via Wald-statistics approximation (treating t as Wald z).

## Warning: This function will be removed in future versions of sjmisc and
## has been moved to package 'sjlabelled'. Please use sjlabelled::get_label()
## instead.

## Warning: This function will be removed in future versions of sjmisc and
## has been moved to package 'sjlabelled'. Please use sjlabelled::get_label()
## instead.

	future_goals
	B	std. Error	p
Fixed Parts
(Intercept)	1.29	0.33	<.001
challenge_mean	0.06	0.08	.443
challenge_sd	-0.09	0.16	.582
learning_mean	-0.13	0.15	.408
learning_sd	0.06	0.18	.753
relevance_mean	0.61	0.15	<.001
relevance_sd	-0.15	0.25	.559
positive_affect_mean	-0.04	0.08	.624
positive_affect_sd	0.08	0.17	.632
overall_pre_interest	-0.01	0.05	.818
Random Parts
N_{program_ID}	9
ICC_{program_ID}	0.000
Observations	528
R² / Ω₀²	.091 / .091

STEM-IE Models

Joshua Rosenberg

6/11/2017

1. Loading, setting up

2. Null models (ready)

3. Models for youth activity (ready)

4. CLASS models (not ready)

5. Pre-survey measures (ready)

6. Situational experiences (ready)

7. Outcomes (not ready)