Quick summary of findings:
1. Graphs: Does anger change from pre, during, to post-election?
2. Graphs: Does anger change depending on vote confidence?
3. Graphs: Does anger change depending on vote influence?
4. Graphs: Does hope change from pre, during, to post-election?
5. Graphs: Does hope change depending on vote confidence?
6. Graphs: Does hope change depending on vote influence?
7. Graphs: Does exposure to Fox News change over timing of election?
8. Graphs: Does expected election win change over timing of election?
9. Graphs: Does trust in media outlets change between party or over time of election?
10. Models: Does anger correlate with vote legitimacy, efficacy, timing, fox news exposure?
11. Models: Does hope correlate with vote legitimacy, efficacy, timing, or news exposure?
12. Models: Election expectations [biden, trump]
14. Media Exposure/Trust models for confidence in votes being counted

REMINDERS:

emotion_1 = Anger (1 = not at all; 7 = extremely)

emotion_6 = Hope (1 = not at all; 7 = extremely)

Vote Influence:

govtPolEff.c: mean-centered - How much influence do you believe you have over national government decisions? (1 = not at all; 7 = a great deal)

electPolEff.c: mean-centered - How much do you think you vote matters in national elections? (1 = not at all; 7 = a great deal)

Vote Count:

ownVote.c: mean-centered - How confident are you that your vote in the general election was counted as you intended? (1 = not at all confident; 5 = very confident)

overallvote.c: mean-centered - How confidence are you that votes nationwide in the general election was counted as voters intended? (1 = not at all confident; 5 = very confident)

ElectionWin [biden, trump]:

electPredictTB: Who do you think will/would win the election? (1 = Definitely Trump; 6 = unsure, toss-up; 9 = Definitely Biden)

Quick summary of findings:

Anger for Democrats decreases moving from pre, during, and post-election, while Republican anger increases from pre, during, to post-election. Independents’ anger remains stagnant across time.
As confidence in national vote and own vote being counted, anger decreases
The magnitude of the negative slope for anger and confidence of national/own vote being counted is greatest for Republicans, then for Democrats, then for Independents.
Democrats feel A LOT more hope post-election compared to pre/during. Republicans decrease feeling of hope step-wise from pre, during, to post-election. Independent hope remains stagnant.
Across party identity, as confidence in own vote, national vote counted along, general election efficacy, and general government efficacy, hope increases.
Across party identity, exposure to fox news is slightly pyramidal with the highest exposure during the election.
Republicans have MUCH more exposure to Fox than both independents or Democrats across the election, while Democrats have more exposure to other media sources.
Across party, pre-election people thought Trump slightly more likely to win (M ~ 4.9), then this changes to slightly more likely Biden would win during election (M ~ 5.3) and much more post-election (M ~ 5.9).
Democrats much more likely across the election to believe Biden would win (M ~ 7.1), while Republicans believed Trump would win (M~3). Independents thought slightly more that trump would win pre/during (M~4.8), but this flips to much more for Biden post-election (M~5.8).

# continuous party
d$partyCont <- NA
d$partyCont[d$demStrength == 1] <- -3
d$partyCont[d$demStrength == 2] <- -2
d$partyCont[d$partyClose == 1] <- -1
d$partyCont[d$partyClose == 3] <- 0
d$partyCont[d$repStrength == 1] <- 3
d$partyCont[d$repStrength == 2] <- 2
d$partyCont[d$partyClose == 2] <- 1

#### policy conditions
#table(d$FL_71_DO)
#table(d$FL_110_DO)

# policy group proposer
d$Policy_Group <- NA
d$Policy_Group[d$FL_71_DO == 'proportional_dem' | d$FL_71_DO == 'US1st_dem'] <- "Democratic"
d$Policy_Group[d$FL_71_DO == 'proportional_rep' | d$FL_71_DO == 'US1st_rep'] <- "Republican"
d$Policy_Group[d$FL_71_DO == 'proportional_bipart' | d$FL_71_DO == 'US1st_bipart'] <- "Bipartisan"
d$Policy_Group[d$FL_71_DO == 'proportional_expert' | d$FL_71_DO == 'US1st_expert'] <- "Expert"

d$Policy_Group <- factor(d$Policy_Group, levels = c('Democratic', 'Republican', 'Bipartisan','Expert'))

# policy frame
d$Policy_Frame <- NA
d$Policy_Frame[d$FL_71_DO == 'proportional_dem' | d$FL_71_DO == 'proportional_rep' | d$FL_71_DO == 'proportional_bipart' | d$FL_71_DO == 'proportional_expert'] <- "Proportional"
d$Policy_Frame[d$FL_71_DO == 'US1st_dem' | d$FL_71_DO == 'US1st_rep' | d$FL_71_DO == 'US1st_bipart' | d$FL_71_DO == 'US1st_expert'] <- "US1st"

# party factor
d$party_factor <- NA
d$party_factor[d$partyCont < 0] <- 'Democrat'
d$party_factor[d$partyCont == 0] <- 'Independent'
d$party_factor[d$partyCont > 0] <- 'Republican'


## Order of timing var
d$election_timing <- factor(d$election_timing, levels = c('Pre-election', 'During-election','Post-election'))


d$party_factor <- factor(d$party_factor, levels = c('Democrat', 'Republican','Independent'))

### Partisan framing codes
# Code 1: Left vs. Right

d$fDem_Rep <- NA
d$fDem_Rep[d$Policy_Group == 'Democratic'] <- -.5
d$fDem_Rep[d$Policy_Group == 'Republican'] <- .5
d$fDem_Rep[d$Policy_Group == 'Bipartisan' | d$Policy_Group == 'Expert'] <- 0

# Code 2: Bi vs. Exp

d$fBi_Exp <- NA
d$fBi_Exp[d$Policy_Group == 'Democratic' | d$Policy_Group == 'Republican'] <- 0
d$fBi_Exp[d$Policy_Group == 'Bipartisan'] <- -.5
d$fBi_Exp[d$Policy_Group == 'Expert'] <- .5

# Code 3 = Dem and Rep vs. Exp and Bi

d$fParties_BiExp <- NA
d$fParties_BiExp[d$Policy_Group == 'Democratic' | d$Policy_Group == 'Republican'] <- -.5
d$fParties_BiExp[d$Policy_Group == 'Bipartisan' | d$Policy_Group == 'Expert'] <- .5


### Policy framing codes
# contrasts
d$fProp_US <- NA
d$fProp_US[d$Policy_Frame == 'Proportional'] <- -.5
d$fProp_US[d$Policy_Frame == 'US1st'] <- .5

#dummies
d$fProportional <- NA
d$fProportional[d$Policy_Frame == 'Proportional'] <- 0
d$fProportional[d$Policy_Frame == 'US1st'] <- 1

d$fUS <- NA
d$fUS[d$Policy_Frame == 'Proportional'] <- 1
d$fUS[d$Policy_Frame == 'US1st'] <- 0


### Timing codes
## Contrast
d$tPre_Post <- NA
d$tPre_Post[d$election_timing == 'Pre-election'] <- -.5
d$tPre_Post[d$election_timing == 'During-election'] <- 0
d$tPre_Post[d$election_timing == 'Post-election'] <- .5

d$tDuring_Not <- NA
d$tDuring_Not[d$election_timing == 'Pre-election'] <- .33
d$tDuring_Not[d$election_timing == 'During-election'] <- -.67
d$tDuring_Not[d$election_timing == 'Post-election'] <- .33

# Dummy
# Post!
d$tPostP <- NA
d$tPostP[d$election_timing == 'Pre-election'] <- 1
d$tPostP[d$election_timing == 'During-election'] <- 0
d$tPostP[d$election_timing == 'Post-election'] <- 0

d$tPostD <- NA
d$tPostD[d$election_timing == 'Pre-election'] <- 0
d$tPostD[d$election_timing == 'During-election'] <- 1
d$tPostD[d$election_timing == 'Post-election'] <- 0

# During!
d$tDurPre <- NA
d$tDurPre[d$election_timing == 'Pre-election'] <- 1
d$tDurPre[d$election_timing == 'During-election'] <- 0
d$tDurPre[d$election_timing == 'Post-election'] <- 0

d$tDurPost <- NA
d$tDurPost[d$election_timing == 'Pre-election'] <- 0
d$tDurPost[d$election_timing == 'During-election'] <- 0
d$tDurPost[d$election_timing == 'Post-election'] <- 1


### Party Factor
d$pDem_Rep <- NA
d$pDem_Rep[d$party_factor == 'Democrat'] <- -.5
d$pDem_Rep[d$party_factor == 'Independent'] <- 0
d$pDem_Rep[d$party_factor == 'Republican'] <- .5

d$pInd_Not <- NA
d$pInd_Not[d$party_factor == 'Democrat'] <- .33
d$pInd_Not[d$party_factor == 'Independent'] <- -.67
d$pInd_Not[d$party_factor == 'Republican'] <- .33

### centering

d$vaxxAtt.c <- d$vaxxAttitudes - mean(d$vaxxAttitudes, na.rm = T)

d$ownvote.c <- d$ownvote_conf - mean(d$ownvote_conf, na.rm = T)

d$overallvote.c <- d$overallvote_conf - mean(d$overallvote_conf, na.rm = T)

d$govtPolEff.c <- d$polEfficacy_1 - mean(d$polEfficacy_1, na.rm = T)

d$electPolEff.c <- d$polEfficacy_2 - mean(d$polEfficacy_2, na.rm = T)

d$mediaExposure <- (d$mediaExposure_1 + 
                      d$mediaExposure_2 + 
                      d$mediaExposure_3 + 
                      d$mediaExposure_4 + 
                      d$mediaExposure_6 +
                      d$mediaExposure_7 + 
                      d$mediaExposure_8 + 
                      d$mediaExposure_9 + 
                      d$mediaExposure_10 +
                      d$mediaExposure_11 +
                      d$mediaExposure_12 + 
                      d$mediaExposure_13 + 
                      d$mediaExposure_14 + 
                      d$mediaExposure_15)/14

d$mediaTrust <-   (d$mediaTrust_1 + 
                      d$mediaTrust_2 + 
                      d$mediaTrust_3 + 
                      d$mediaTrust_4 + 
                      d$mediaTrust_6 +
                      d$mediaTrust_7 + 
                      d$mediaTrust_8 + 
                      d$mediaTrust_9 + 
                      d$mediaTrust_10 +
                      d$mediaTrust_11 +
                      d$mediaTrust_12 + 
                      d$mediaTrust_13 + 
                      d$mediaTrust_14 + 
                      d$mediaTrust_15)/14


#### Indices

Proportional <- d$Policy_Frame == 'Proportional'
US1st <- d$Policy_Frame == 'US1st'

Pre <- d$election_timing == 'Pre-election'
During <- d$election_timing == 'During-election'
Post <- d$election_timing == 'Post-election'


#contrast codes for party  ID

d$pDemR[d$party_factor == 'Democrat'] <- 0
d$pDemR[d$party_factor == 'Republican'] <- 1
d$pDemR[d$party_factor == 'Independent'] <- 0

d$pDemI[d$party_factor == 'Democrat'] <- 0
d$pDemI[d$party_factor == 'Republican'] <- 0
d$pDemI[d$party_factor == 'Independent'] <- 1


d$pRepD[d$party_factor == 'Democrat'] <- 1
d$pRepD[d$party_factor == 'Republican'] <- 0
d$pRepD[d$party_factor == 'Independent'] <- 0

d$pRepI[d$party_factor == 'Democrat'] <- 0
d$pRepI[d$party_factor == 'Republican'] <- 0
d$pRepI[d$party_factor == 'Independent'] <- 1

# mean center fox exposure
d$foxExposure.c <- d$mediaExposure_5 - mean(d$mediaExposure_5, na.rm = T)

# mean center other media exposure
d$otherMediaExposure.c <- d$mediaExposure - mean(d$mediaExposure, na.rm = T)

#create difference score
d$diffFoxOther <- d$mediaExposure_5 - d$mediaExposure

1. Graphs: Does anger change from pre, during, to post-election?

a. graph: anger vs. timing

## Warning: Removed 61 rows containing non-finite values (stat_summary).

## Warning: Removed 61 rows containing non-finite values (stat_summary).

b. graph: anger vs. party identity vs. timing

## Warning: Removed 23 rows containing non-finite values (stat_summary).

## Warning: Removed 23 rows containing non-finite values (stat_summary).

c. graph: anger vs. timing vs. party identity

## Warning: Removed 23 rows containing non-finite values (stat_summary).

## Warning: Removed 23 rows containing non-finite values (stat_summary).

2. Graphs: Does anger change depending on vote confidence?

a. graph: anger vs. own vote confidence

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 19 rows containing non-finite values (stat_smooth).

b. anger vs. national vote confidence

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 20 rows containing non-finite values (stat_smooth).

c. graph: anger vs. own vote confidence vs. party identity

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 19 rows containing non-finite values (stat_smooth).

d. graph: anger vs. national vote confidence vs. party identity

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 20 rows containing non-finite values (stat_smooth).

3. Graphs: Does anger change depending on vote influence?

a. graph: anger vs. government political efficacy

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 16 rows containing non-finite values (stat_smooth).

b. anger vs. national election efficacy

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 16 rows containing non-finite values (stat_smooth).

c. graph: anger vs. government political efficacy vs. party identity

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 16 rows containing non-finite values (stat_smooth).

d. graph: anger vs. national election efficacy vs. party identity

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 16 rows containing non-finite values (stat_smooth).

4. Graphs: Does hope change from pre, during, to post-election?

a. hope vs. election timing

## Warning: Removed 61 rows containing non-finite values (stat_summary).

## Warning: Removed 61 rows containing non-finite values (stat_summary).

b. hope vs. election timing vs. party identity

## Warning: Removed 23 rows containing non-finite values (stat_summary).

## Warning: Removed 23 rows containing non-finite values (stat_summary).

c. hope vs. party identity vs. election timing

## Warning: Removed 23 rows containing non-finite values (stat_summary).

## Warning: Removed 23 rows containing non-finite values (stat_summary).

5. Graphs: Does hope change depending on vote confidence?

a. hope vs. own vote confidence

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 20 rows containing non-finite values (stat_smooth).

b. hope vs. national vote confidence

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 21 rows containing non-finite values (stat_smooth).

c. hope vs. party identity vs. own vote confidence

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 20 rows containing non-finite values (stat_smooth).

d. hope vs. election timing vs. national vote confidence

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 21 rows containing non-finite values (stat_smooth).

6. Graphs: Does hope change depending on vote influence?

a. hope vs. government political efficacy

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 17 rows containing non-finite values (stat_smooth).

b. hope vs. national election efficacy

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 17 rows containing non-finite values (stat_smooth).

c. hope vs. party identity vs. government political efficacy

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 17 rows containing non-finite values (stat_smooth).

d. hope vs. election timing vs. national election efficacy

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 17 rows containing non-finite values (stat_smooth).

7. Graphs: Does exposure to Fox News change over timing of election?

a. exposure to fox vs. timing

## Warning: Use of `d$mediaExposure_5` is discouraged. Use `mediaExposure_5`
## instead.

## Warning: Use of `d$mediaExposure_5` is discouraged. Use `mediaExposure_5`
## instead.

## Warning: Removed 60 rows containing non-finite values (stat_summary).

## Warning: Removed 60 rows containing non-finite values (stat_summary).

b. exposure to fox vs. timing vs. party identity

## Warning: Removed 22 rows containing non-finite values (stat_summary).

## Warning: Removed 22 rows containing non-finite values (stat_summary).

c. exposure to other news stations vs. timing

## Warning: Use of `d$mediaExposure` is discouraged. Use `mediaExposure` instead.

## Warning: Use of `d$mediaExposure` is discouraged. Use `mediaExposure` instead.

## Warning: Removed 66 rows containing non-finite values (stat_summary).

## Warning: Removed 66 rows containing non-finite values (stat_summary).

d. exposure to other news stations vs. timing vs. party identity

## Warning: Removed 28 rows containing non-finite values (stat_summary).

## Warning: Removed 28 rows containing non-finite values (stat_summary).

8. Graphs: Does expected election win change over timing of election?

a. Trump win - Biden win vs. timing

## Warning: Use of `d$electPredictTB` is discouraged. Use `electPredictTB` instead.

## Warning: Use of `d$electPredictTB` is discouraged. Use `electPredictTB` instead.

## Warning: Removed 800 rows containing non-finite values (stat_summary).

## Warning: Removed 800 rows containing non-finite values (stat_summary).

b. Trump win - Biden win vs. timing vs. party identity

## Warning: Removed 759 rows containing non-finite values (stat_summary).

## Warning: Removed 759 rows containing non-finite values (stat_summary).

c. Trump win - Biden win vs. party identity vs. timing

## Warning: Removed 800 rows containing non-finite values (stat_summary).

## Warning: Removed 800 rows containing non-finite values (stat_summary).

9. Graphs: Does trust in media outlets change between party or over time of election?

a. trust in fox vs. timing

## Warning: Removed 61 rows containing non-finite values (stat_summary).

## Warning: Removed 61 rows containing non-finite values (stat_summary).

b. trust in fox vs. timing vs. party identity

## Warning: Removed 23 rows containing non-finite values (stat_summary).

## Warning: Removed 23 rows containing non-finite values (stat_summary).

c. trust in other news stations vs. timing

## Warning: Removed 70 rows containing non-finite values (stat_summary).

## Warning: Removed 70 rows containing non-finite values (stat_summary).

d. trust in other news stations vs. timing vs. party identity

## Warning: Removed 31 rows containing non-finite values (stat_summary).

## Warning: Removed 31 rows containing non-finite values (stat_summary).

e. FOX TRUST VIOLIN PLOT

## Warning: Removed 23 rows containing non-finite values (stat_ydensity).

## Warning: Removed 23 rows containing non-finite values (stat_summary).

## Warning: Removed 23 rows containing non-finite values (stat_summary).

f. FOX EXPOSURE VIOLIN PLOT

## Warning: Removed 22 rows containing non-finite values (stat_ydensity).

## Warning: Removed 22 rows containing non-finite values (stat_summary).

## Warning: Removed 22 rows containing non-finite values (stat_summary).

g. OTHER MEDIA TRUST VIOLIN PLOT

## Warning: Removed 28 rows containing non-finite values (stat_ydensity).

## Warning: Removed 28 rows containing non-finite values (stat_summary).

## Warning: Removed 28 rows containing non-finite values (stat_summary).

h. OTHER MEDIA TRUST VIOLIN PLOT

## Warning: Removed 31 rows containing non-finite values (stat_ydensity).

## Warning: Removed 31 rows containing non-finite values (stat_summary).

## Warning: Removed 31 rows containing non-finite values (stat_summary).

10. Models: Does anger correlate with vote legitimacy, efficacy, timing, fox news exposure?

a. basic models

i. anger ~ (pDvR + pIvDR) * (tDurPre + tDurPost)

anger2 <- lm(emotion_1 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost), data = d)
summary(anger2)

## 
## Call:
## lm(formula = emotion_1 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost), 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -2.7807 -1.7308 -0.1571  1.3705  4.4138 
## 
## Coefficients:
##                   Estimate Std. Error t value Pr(>|t|)    
## (Intercept)        3.20523    0.09326  34.369  < 2e-16 ***
## pDem_Rep          -0.23873    0.18112  -1.318   0.1876    
## pInd_Not           0.92391    0.23294   3.966 7.52e-05 ***
## tDurPre            0.10083    0.11255   0.896   0.3704    
## tDurPost          -0.14125    0.12782  -1.105   0.2693    
## pDem_Rep:tDurPre  -0.38486    0.22163  -1.737   0.0826 .  
## pDem_Rep:tDurPost  1.25156    0.25200   4.966 7.30e-07 ***
## pInd_Not:tDurPre  -0.43053    0.27926  -1.542   0.1233    
## pInd_Not:tDurPost -0.42658    0.31697  -1.346   0.1785    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 2.002 on 2400 degrees of freedom
##   (67 observations deleted due to missingness)
## Multiple R-squared:  0.04068,    Adjusted R-squared:  0.03749 
## F-statistic: 12.72 on 8 and 2400 DF,  p-value: < 2.2e-16

ii. anger ~ (pDvR + pDvI) * (tDurPre + tDurPost)

anger2.D <- lm(emotion_1 ~ (pDemR + pDemI) * (tDurPre + tDurPost), data = d)
summary(anger2.D)

## 
## Call:
## lm(formula = emotion_1 ~ (pDemR + pDemI) * (tDurPre + tDurPost), 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -2.7807 -1.7308 -0.1571  1.3705  4.4138 
## 
## Coefficients:
##                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)      3.6295     0.1264  28.724  < 2e-16 ***
## pDemR           -0.2387     0.1811  -1.318  0.18761    
## pDemI           -1.0433     0.2491  -4.189 2.90e-05 ***
## tDurPre          0.1512     0.1530   0.988  0.32323    
## tDurPost        -0.9078     0.1701  -5.337 1.03e-07 ***
## pDemR:tDurPre   -0.3849     0.2216  -1.737  0.08260 .  
## pDemR:tDurPost   1.2516     0.2520   4.966 7.30e-07 ***
## pDemI:tDurPre    0.2381     0.2985   0.798  0.42520    
## pDemI:tDurPost   1.0524     0.3369   3.123  0.00181 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 2.002 on 2400 degrees of freedom
##   (67 observations deleted due to missingness)
## Multiple R-squared:  0.04068,    Adjusted R-squared:  0.03749 
## F-statistic: 12.72 on 8 and 2400 DF,  p-value: < 2.2e-16

iii. anger ~ (pRvD + pRvI) * (tDurPre + pDurPost)

anger2.R <- lm(emotion_1 ~ (pRepD + pRepI) * (tDurPre + tDurPost), data = d)
summary(anger2.R)

## 
## Call:
## lm(formula = emotion_1 ~ (pRepD + pRepI) * (tDurPre + tDurPost), 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -2.7807 -1.7308 -0.1571  1.3705  4.4138 
## 
## Coefficients:
##                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)      3.3908     0.1298  26.131  < 2e-16 ***
## pRepD            0.2387     0.1811   1.318  0.18761    
## pRepI           -0.8045     0.2508  -3.208  0.00135 ** 
## tDurPre         -0.2337     0.1603  -1.458  0.14510    
## tDurPost         0.3438     0.1859   1.849  0.06460 .  
## pRepD:tDurPre    0.3849     0.2216   1.737  0.08260 .  
## pRepD:tDurPost  -1.2516     0.2520  -4.966  7.3e-07 ***
## pRepI:tDurPre    0.6230     0.3023   2.060  0.03946 *  
## pRepI:tDurPost  -0.1992     0.3452  -0.577  0.56397    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 2.002 on 2400 degrees of freedom
##   (67 observations deleted due to missingness)
## Multiple R-squared:  0.04068,    Adjusted R-squared:  0.03749 
## F-statistic: 12.72 on 8 and 2400 DF,  p-value: < 2.2e-16

b. incuding ownVote.c & overalVote.c

i. anger ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * ownVote.c * overallVote.c

#Vote Confidence do not have entries for "pre election"
anger1 <- lm(emotion_1 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * ownvote.c * overallvote.c, data = d)
summary(anger1)

## 
## Call:
## lm(formula = emotion_1 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * 
##     ownvote.c * overallvote.c, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -4.2382 -1.6069 -0.5532  1.3931  4.8022 
## 
## Coefficients: (12 not defined because of singularities)
##                                           Estimate Std. Error t value Pr(>|t|)
## (Intercept)                                3.20621    0.12367  25.926  < 2e-16
## pDem_Rep                                  -0.99732    0.24443  -4.080  4.8e-05
## pInd_Not                                   0.90467    0.30627   2.954  0.00320
## tDurPre                                         NA         NA      NA       NA
## tDurPost                                  -0.34543    0.18121  -1.906  0.05686
## ownvote.c                                  0.16948    0.14028   1.208  0.22724
## overallvote.c                             -0.24523    0.13658  -1.796  0.07282
## pDem_Rep:tDurPre                                NA         NA      NA       NA
## pDem_Rep:tDurPost                          0.72169    0.39222   1.840  0.06602
## pInd_Not:tDurPre                                NA         NA      NA       NA
## pInd_Not:tDurPost                         -1.11200    0.42598  -2.610  0.00916
## pDem_Rep:ownvote.c                        -0.24590    0.25617  -0.960  0.33729
## pInd_Not:ownvote.c                         0.22896    0.35983   0.636  0.52470
## tDurPre:ownvote.c                               NA         NA      NA       NA
## tDurPost:ownvote.c                         0.12426    0.18708   0.664  0.50671
## pDem_Rep:overallvote.c                     0.21640    0.22747   0.951  0.34164
## pInd_Not:overallvote.c                    -0.74213    0.36180  -2.051  0.04047
## tDurPre:overallvote.c                           NA         NA      NA       NA
## tDurPost:overallvote.c                    -0.32549    0.17716  -1.837  0.06641
## ownvote.c:overallvote.c                   -0.01202    0.06315  -0.190  0.84913
## pDem_Rep:tDurPre:ownvote.c                      NA         NA      NA       NA
## pDem_Rep:tDurPost:ownvote.c                0.65961    0.40608   1.624  0.10457
## pInd_Not:tDurPre:ownvote.c                      NA         NA      NA       NA
## pInd_Not:tDurPost:ownvote.c               -0.11145    0.43895  -0.254  0.79962
## pDem_Rep:tDurPre:overallvote.c                  NA         NA      NA       NA
## pDem_Rep:tDurPost:overallvote.c           -0.51919    0.35335  -1.469  0.14201
## pInd_Not:tDurPre:overallvote.c                  NA         NA      NA       NA
## pInd_Not:tDurPost:overallvote.c            0.57148    0.43674   1.309  0.19096
## pDem_Rep:ownvote.c:overallvote.c           0.35371    0.13598   2.601  0.00941
## pInd_Not:ownvote.c:overallvote.c          -0.09243    0.14896  -0.621  0.53504
## tDurPre:ownvote.c:overallvote.c                 NA         NA      NA       NA
## tDurPost:ownvote.c:overallvote.c           0.13588    0.08481   1.602  0.10940
## pDem_Rep:tDurPre:ownvote.c:overallvote.c        NA         NA      NA       NA
## pDem_Rep:tDurPost:ownvote.c:overallvote.c -0.13365    0.19712  -0.678  0.49790
## pInd_Not:tDurPre:ownvote.c:overallvote.c        NA         NA      NA       NA
## pInd_Not:tDurPost:ownvote.c:overallvote.c  0.48354    0.18900   2.558  0.01064
##                                              
## (Intercept)                               ***
## pDem_Rep                                  ***
## pInd_Not                                  ** 
## tDurPre                                      
## tDurPost                                  .  
## ownvote.c                                    
## overallvote.c                             .  
## pDem_Rep:tDurPre                             
## pDem_Rep:tDurPost                         .  
## pInd_Not:tDurPre                             
## pInd_Not:tDurPost                         ** 
## pDem_Rep:ownvote.c                           
## pInd_Not:ownvote.c                           
## tDurPre:ownvote.c                            
## tDurPost:ownvote.c                           
## pDem_Rep:overallvote.c                       
## pInd_Not:overallvote.c                    *  
## tDurPre:overallvote.c                        
## tDurPost:overallvote.c                    .  
## ownvote.c:overallvote.c                      
## pDem_Rep:tDurPre:ownvote.c                   
## pDem_Rep:tDurPost:ownvote.c                  
## pInd_Not:tDurPre:ownvote.c                   
## pInd_Not:tDurPost:ownvote.c                  
## pDem_Rep:tDurPre:overallvote.c               
## pDem_Rep:tDurPost:overallvote.c              
## pInd_Not:tDurPre:overallvote.c               
## pInd_Not:tDurPost:overallvote.c              
## pDem_Rep:ownvote.c:overallvote.c          ** 
## pInd_Not:ownvote.c:overallvote.c             
## tDurPre:ownvote.c:overallvote.c              
## tDurPost:ownvote.c:overallvote.c             
## pDem_Rep:tDurPre:ownvote.c:overallvote.c     
## pDem_Rep:tDurPost:ownvote.c:overallvote.c    
## pInd_Not:tDurPre:ownvote.c:overallvote.c     
## pInd_Not:tDurPost:ownvote.c:overallvote.c *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.956 on 1184 degrees of freedom
##   (1268 observations deleted due to missingness)
## Multiple R-squared:  0.1293, Adjusted R-squared:  0.1124 
## F-statistic: 7.644 on 23 and 1184 DF,  p-value: < 2.2e-16

ii. anger ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * ownVote.c * overallVote.c + (1 | timing)

anger.mx <- lmer(emotion_1 ~ (pDem_Rep + pInd_Not) * ownvote.c * overallvote.c + (1 | election_timing), data = d)
summary(anger.mx)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: emotion_1 ~ (pDem_Rep + pInd_Not) * ownvote.c * overallvote.c +  
##     (1 | election_timing)
##    Data: d
## 
## REML criterion at convergence: 5090.5
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.0156 -0.8457 -0.2837  0.7090  2.4112 
## 
## Random effects:
##  Groups          Name        Variance Std.Dev.
##  election_timing (Intercept) 0.01094  0.1046  
##  Residual                    3.88206  1.9703  
## Number of obs: 1208, groups:  election_timing, 2
## 
## Fixed effects:
##                                    Estimate Std. Error         df t value
## (Intercept)                         3.09428    0.11534    2.22079  26.827
## pDem_Rep                           -0.75939    0.18747 1195.06964  -4.051
## pInd_Not                            0.36621    0.21050 1195.09434   1.740
## ownvote.c                           0.30343    0.08602 1195.00816   3.527
## overallvote.c                      -0.52577    0.08077 1195.70924  -6.509
## pDem_Rep:ownvote.c                 -0.07649    0.19536 1181.75644  -0.392
## pInd_Not:ownvote.c                  0.17247    0.19585 1195.22172   0.881
## pDem_Rep:overallvote.c              0.11850    0.16894 1014.08619   0.701
## pInd_Not:overallvote.c             -0.40479    0.19492 1195.58138  -2.077
## ownvote.c:overallvote.c             0.03386    0.04091 1183.99628   0.828
## pDem_Rep:ownvote.c:overallvote.c    0.33070    0.09638 1195.29342   3.431
## pInd_Not:ownvote.c:overallvote.c    0.16308    0.08962 1195.58836   1.820
##                                  Pr(>|t|)    
## (Intercept)                      0.000780 ***
## pDem_Rep                         5.44e-05 ***
## pInd_Not                         0.082165 .  
## ownvote.c                        0.000436 ***
## overallvote.c                    1.11e-10 ***
## pDem_Rep:ownvote.c               0.695459    
## pInd_Not:ownvote.c               0.378714    
## pDem_Rep:overallvote.c           0.483215    
## pInd_Not:overallvote.c           0.038041 *  
## ownvote.c:overallvote.c          0.408048    
## pDem_Rep:ownvote.c:overallvote.c 0.000621 ***
## pInd_Not:ownvote.c:overallvote.c 0.069042 .  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr) pDm_Rp pInd_N ownvt. ovrll. pDm_Rp:w. pInd_Nt:w. pDm_Rp:v.
## pDem_Rep     0.036                                                           
## pInd_Not    -0.236  0.029                                                    
## ownvote.c   -0.057 -0.212 -0.176                                             
## overallvt.c -0.041  0.256  0.192 -0.710                                      
## pDm_Rp:wnv. -0.156 -0.263 -0.128 -0.020  0.139                               
## pInd_Nt:wn. -0.140 -0.139  0.057 -0.188  0.179 -0.014                        
## pDm_Rp:vrl.  0.206  0.136  0.170  0.147 -0.224 -0.735     0.098              
## pInd_Nt:vr.  0.146  0.158 -0.164  0.169 -0.351  0.085    -0.699     -0.138   
## ownvt.c:vr. -0.430 -0.011  0.076  0.360 -0.061  0.266     0.015     -0.030   
## pDm_Rp:w.:. -0.007 -0.589 -0.006  0.250 -0.017  0.414     0.164     -0.284   
## pInd_Nt:.:.  0.065 -0.007 -0.539  0.016 -0.237  0.179     0.316     -0.016   
##             pInd_Nt:v. own.:. pD_R:.:
## pDem_Rep                             
## pInd_Not                             
## ownvote.c                            
## overallvt.c                          
## pDm_Rp:wnv.                          
## pInd_Nt:wn.                          
## pDm_Rp:vrl.                          
## pInd_Nt:vr.                          
## ownvt.c:vr. -0.214                   
## pDm_Rp:w.:. -0.011     -0.060        
## pInd_Nt:.:.  0.097     -0.088 -0.040

iii. anger ~ ownVote.c

cor.test(d$emotion_1, d$ownvote_conf)

## 
##  Pearson's product-moment correlation
## 
## data:  d$emotion_1 and d$ownvote_conf
## t = -4.3894, df = 1208, p-value = 1.236e-05
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.18037732 -0.06943082
## sample estimates:
##        cor 
## -0.1252958

iv. anger ~ overallVote.c

cor.test(d$emotion_1, d$overallvote_conf)

## 
##  Pearson's product-moment correlation
## 
## data:  d$emotion_1 and d$overallvote_conf
## t = -8.0568, df = 1207, p-value = 1.867e-15
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.2787367 -0.1717168
## sample estimates:
##        cor 
## -0.2259083

c. including govtPolEff.c & electPolEff.c

i. anger ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * govtPolEff.c * electPolEff.c

#Vote Confidence do not have entries for "pre election"
anger1 <- lm(emotion_1 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * govtPolEff.c * electPolEff.c, data = d)
summary(anger1)

## 
## Call:
## lm(formula = emotion_1 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * 
##     govtPolEff.c * electPolEff.c, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.4547 -1.7800 -0.2683  1.5629  5.0092 
## 
## Coefficients:
##                                                Estimate Std. Error t value
## (Intercept)                                   3.2178083  0.1122075  28.677
## pDem_Rep                                     -0.3136483  0.2167360  -1.447
## pInd_Not                                      0.5434420  0.2809810   1.934
## tDurPre                                       0.0051296  0.1368476   0.037
## tDurPost                                     -0.2092929  0.1604777  -1.304
## govtPolEff.c                                 -0.0815020  0.0791269  -1.030
## electPolEff.c                                 0.0087221  0.0685136   0.127
## pDem_Rep:tDurPre                             -0.1947035  0.2639945  -0.738
## pDem_Rep:tDurPost                             1.0949350  0.2960158   3.699
## pInd_Not:tDurPre                              0.0386467  0.3428845   0.113
## pInd_Not:tDurPost                             0.0268777  0.4099869   0.066
## pDem_Rep:govtPolEff.c                        -0.0561258  0.1479764  -0.379
## pInd_Not:govtPolEff.c                        -0.0829687  0.2010033  -0.413
## tDurPre:govtPolEff.c                          0.0043502  0.0960842   0.045
## tDurPost:govtPolEff.c                         0.1180011  0.1122329   1.051
## pDem_Rep:electPolEff.c                        0.1494365  0.1214831   1.230
## pInd_Not:electPolEff.c                       -0.1794157  0.1777233  -1.010
## tDurPre:electPolEff.c                         0.0270811  0.0807504   0.335
## tDurPost:electPolEff.c                       -0.0895978  0.0938186  -0.955
## govtPolEff.c:electPolEff.c                    0.0142000  0.0399754   0.355
## pDem_Rep:tDurPre:govtPolEff.c                 0.2878974  0.1811197   1.590
## pDem_Rep:tDurPost:govtPolEff.c                0.1283934  0.2021957   0.635
## pInd_Not:tDurPre:govtPolEff.c                 0.1338926  0.2432524   0.550
## pInd_Not:tDurPost:govtPolEff.c                0.0203494  0.2894084   0.070
## pDem_Rep:tDurPre:electPolEff.c               -0.3634666  0.1468466  -2.475
## pDem_Rep:tDurPost:electPolEff.c              -0.2077838  0.1611892  -1.289
## pInd_Not:tDurPre:electPolEff.c                0.0773658  0.2074749   0.373
## pInd_Not:tDurPost:electPolEff.c               0.2390855  0.2460609   0.972
## pDem_Rep:govtPolEff.c:electPolEff.c           0.0003659  0.0599301   0.006
## pInd_Not:govtPolEff.c:electPolEff.c           0.1550936  0.1089538   1.423
## tDurPre:govtPolEff.c:electPolEff.c            0.0336137  0.0460028   0.731
## tDurPost:govtPolEff.c:electPolEff.c          -0.0040786  0.0522056  -0.078
## pDem_Rep:tDurPre:govtPolEff.c:electPolEff.c  -0.0582259  0.0758973  -0.767
## pDem_Rep:tDurPost:govtPolEff.c:electPolEff.c  0.0938298  0.0827527   1.134
## pInd_Not:tDurPre:govtPolEff.c:electPolEff.c  -0.1911858  0.1222165  -1.564
## pInd_Not:tDurPost:govtPolEff.c:electPolEff.c -0.1325477  0.1402919  -0.945
##                                              Pr(>|t|)    
## (Intercept)                                   < 2e-16 ***
## pDem_Rep                                     0.147989    
## pInd_Not                                     0.053221 .  
## tDurPre                                      0.970102    
## tDurPost                                     0.192296    
## govtPolEff.c                                 0.303107    
## electPolEff.c                                0.898710    
## pDem_Rep:tDurPre                             0.460874    
## pDem_Rep:tDurPost                            0.000221 ***
## pInd_Not:tDurPre                             0.910270    
## pInd_Not:tDurPost                            0.947736    
## pDem_Rep:govtPolEff.c                        0.704507    
## pInd_Not:govtPolEff.c                        0.679810    
## tDurPre:govtPolEff.c                         0.963892    
## tDurPost:govtPolEff.c                        0.293185    
## pDem_Rep:electPolEff.c                       0.218781    
## pInd_Not:electPolEff.c                       0.312827    
## tDurPre:electPolEff.c                        0.737377    
## tDurPost:electPolEff.c                       0.339669    
## govtPolEff.c:electPolEff.c                   0.722458    
## pDem_Rep:tDurPre:govtPolEff.c                0.112072    
## pDem_Rep:tDurPost:govtPolEff.c               0.525493    
## pInd_Not:tDurPre:govtPolEff.c                0.582079    
## pInd_Not:tDurPost:govtPolEff.c               0.943950    
## pDem_Rep:tDurPre:electPolEff.c               0.013388 *  
## pDem_Rep:tDurPost:electPolEff.c              0.197500    
## pInd_Not:tDurPre:electPolEff.c               0.709262    
## pInd_Not:tDurPost:electPolEff.c              0.331323    
## pDem_Rep:govtPolEff.c:electPolEff.c          0.995129    
## pInd_Not:govtPolEff.c:electPolEff.c          0.154729    
## tDurPre:govtPolEff.c:electPolEff.c           0.465041    
## tDurPost:govtPolEff.c:electPolEff.c          0.937734    
## pDem_Rep:tDurPre:govtPolEff.c:electPolEff.c  0.443059    
## pDem_Rep:tDurPost:govtPolEff.c:electPolEff.c 0.256969    
## pInd_Not:tDurPre:govtPolEff.c:electPolEff.c  0.117876    
## pInd_Not:tDurPost:govtPolEff.c:electPolEff.c 0.344858    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.998 on 2368 degrees of freedom
##   (72 observations deleted due to missingness)
## Multiple R-squared:  0.05624,    Adjusted R-squared:  0.04229 
## F-statistic: 4.032 on 35 and 2368 DF,  p-value: 3.579e-14

ii. anger ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * govtPolEff.c * electPolEff.c + (1 | timing)

anger.mx <- lmer(emotion_1 ~ (pDem_Rep + pInd_Not) * govtPolEff.c * electPolEff.c + (1 | election_timing), data = d)
summary(anger.mx)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: emotion_1 ~ (pDem_Rep + pInd_Not) * govtPolEff.c * electPolEff.c +  
##     (1 | election_timing)
##    Data: d
## 
## REML criterion at convergence: 10248.2
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -1.4489 -0.9021 -0.1736  0.7695  2.2133 
## 
## Random effects:
##  Groups          Name        Variance Std.Dev.
##  election_timing (Intercept) 0.02815  0.1678  
##  Residual                    4.08308  2.0207  
## Number of obs: 2404, groups:  election_timing, 3
## 
## Fixed effects:
##                                       Estimate Std. Error         df t value
## (Intercept)                          3.140e+00  1.128e-01  2.552e+00  27.842
## pDem_Rep                            -1.511e-01  1.057e-01  2.390e+03  -1.430
## pInd_Not                             5.570e-01  1.426e-01  2.390e+03   3.907
## govtPolEff.c                        -5.065e-02  3.892e-02  2.390e+03  -1.301
## electPolEff.c                       -9.389e-03  3.132e-02  2.392e+03  -0.300
## pDem_Rep:govtPolEff.c                1.277e-01  7.208e-02  2.390e+03   1.772
## pInd_Not:govtPolEff.c               -1.519e-02  9.927e-02  2.390e+03  -0.153
## pDem_Rep:electPolEff.c              -9.530e-02  5.739e-02  2.392e+03  -1.660
## pInd_Not:electPolEff.c              -1.117e-01  8.015e-02  2.390e+03  -1.394
## govtPolEff.c:electPolEff.c           3.470e-02  1.657e-02  2.390e+03   2.095
## pDem_Rep:govtPolEff.c:electPolEff.c  1.904e-03  3.082e-02  2.391e+03   0.062
## pInd_Not:govtPolEff.c:electPolEff.c  9.229e-03  4.222e-02  2.391e+03   0.219
##                                     Pr(>|t|)    
## (Intercept)                         0.000308 ***
## pDem_Rep                            0.152911    
## pInd_Not                            9.62e-05 ***
## govtPolEff.c                        0.193278    
## electPolEff.c                       0.764397    
## pDem_Rep:govtPolEff.c               0.076598 .  
## pInd_Not:govtPolEff.c               0.878369    
## pDem_Rep:electPolEff.c              0.096966 .  
## pInd_Not:electPolEff.c              0.163409    
## govtPolEff.c:electPolEff.c          0.036295 *  
## pDem_Rep:govtPolEff.c:electPolEff.c 0.950735    
## pInd_Not:govtPolEff.c:electPolEff.c 0.827001    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##              (Intr) pDm_Rp pInd_N gvtPE. elcPE. pDm_Rp:gPE. pInd_Nt:gPE.
## pDem_Rep      0.038                                                     
## pInd_Not     -0.244  0.043                                              
## govtPlEff.c   0.116  0.028 -0.114                                       
## elctPlEff.c  -0.053  0.009 -0.014 -0.604                                
## pDm_Rp:gPE.   0.013  0.238  0.017  0.047 -0.066                         
## pInd_Nt:gPE. -0.058  0.016  0.233 -0.505  0.327  0.027                  
## pDm_Rp:lPE.   0.007 -0.224  0.004 -0.066  0.074 -0.578      -0.040      
## pInd_Nt:lPE. -0.007  0.005 -0.074  0.326 -0.517 -0.038      -0.615      
## gvtPlE.:PE.  -0.243 -0.054  0.239 -0.346  0.460  0.004       0.064      
## pD_R:PE.:PE  -0.030 -0.493 -0.032  0.005  0.064 -0.506       0.002      
## pI_N:PE.:PE   0.115 -0.032 -0.486  0.064 -0.321  0.003      -0.279      
##              pDm_Rp:lPE. pInd_Nt:lPE. gPE.:P pD_R:PE.:
## pDem_Rep                                              
## pInd_Not                                              
## govtPlEff.c                                           
## elctPlEff.c                                           
## pDm_Rp:gPE.                                           
## pInd_Nt:gPE.                                          
## pDm_Rp:lPE.                                           
## pInd_Nt:lPE.  0.042                                   
## gvtPlE.:PE.   0.066      -0.318                       
## pD_R:PE.:PE   0.336       0.038        0.044          
## pI_N:PE.:PE   0.039       0.511       -0.501  0.027

iii. anger ~ govtPolEff.c

cor.test(d$emotion_1, d$govtPolEff.c)

## 
##  Pearson's product-moment correlation
## 
## data:  d$emotion_1 and d$govtPolEff.c
## t = -0.83766, df = 2409, p-value = 0.4023
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.05694534  0.02287116
## sample estimates:
##         cor 
## -0.01706428

iv. anger ~ electPolEff.c

cor.test(d$emotion_1, d$electPolEff.c)

## 
##  Pearson's product-moment correlation
## 
## data:  d$emotion_1 and d$electPolEff.c
## t = -1.0233, df = 2408, p-value = 0.3062
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.06072717  0.01909445
## sample estimates:
##         cor 
## -0.02084959

d. includuing media exposure

i. anger ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * foxExposure

anger_fox <- lm(emotion_1 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * foxExposure.c, data = d)
summary(anger_fox)

## 
## Call:
## lm(formula = emotion_1 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * 
##     foxExposure.c, data = d)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -3.525 -1.743 -0.207  1.541  4.541 
## 
## Coefficients:
##                                 Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                      3.16495    0.09832  32.191  < 2e-16 ***
## pDem_Rep                        -0.27756    0.19549  -1.420  0.15579    
## pInd_Not                         0.79270    0.24276   3.265  0.00111 ** 
## tDurPre                          0.12326    0.11864   1.039  0.29894    
## tDurPost                        -0.14018    0.13450  -1.042  0.29740    
## foxExposure.c                    0.03137    0.07709   0.407  0.68408    
## pDem_Rep:tDurPre                -0.30000    0.23746  -1.263  0.20657    
## pDem_Rep:tDurPost                1.09242    0.26821   4.073 4.79e-05 ***
## pInd_Not:tDurPre                -0.35221    0.29197  -1.206  0.22780    
## pInd_Not:tDurPost               -0.36765    0.33161  -1.109  0.26768    
## pDem_Rep:foxExposure.c           0.31481    0.13485   2.334  0.01965 *  
## pInd_Not:foxExposure.c          -0.17654    0.20096  -0.879  0.37976    
## tDurPre:foxExposure.c           -0.05899    0.09270  -0.636  0.52459    
## tDurPost:foxExposure.c           0.13320    0.10660   1.250  0.21156    
## pDem_Rep:tDurPre:foxExposure.c  -0.14332    0.16425  -0.873  0.38298    
## pDem_Rep:tDurPost:foxExposure.c -0.07303    0.18894  -0.387  0.69915    
## pInd_Not:tDurPre:foxExposure.c   0.06702    0.24054   0.279  0.78057    
## pInd_Not:tDurPost:foxExposure.c  0.33120    0.27655   1.198  0.23119    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.995 on 2390 degrees of freedom
##   (68 observations deleted due to missingness)
## Multiple R-squared:  0.05115,    Adjusted R-squared:  0.0444 
## F-statistic: 7.578 on 17 and 2390 DF,  p-value: < 2.2e-16

ii. anger ~ (pDvR + pDvI) * (tDurPre + tDurPost) * foxExposure.c

angerFox2.D <- lm(emotion_1 ~ (pDemR + pDemI) * (tDurPre + tDurPost) * foxExposure.c, data = d)
summary(angerFox2.D)

## 
## Call:
## lm(formula = emotion_1 ~ (pDemR + pDemI) * (tDurPre + tDurPost) * 
##     foxExposure.c, data = d)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -3.525 -1.743 -0.207  1.541  4.541 
## 
## Coefficients:
##                              Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                   3.56532    0.13127  27.160  < 2e-16 ***
## pDemR                        -0.27756    0.19549  -1.420 0.155793    
## pDemI                        -0.93148    0.25809  -3.609 0.000314 ***
## tDurPre                       0.15703    0.15928   0.986 0.324300    
## tDurPost                     -0.80772    0.17740  -4.553 5.55e-06 ***
## foxExposure.c                -0.18429    0.10650  -1.730 0.083673 .  
## pDemR:tDurPre                -0.30000    0.23746  -1.263 0.206573    
## pDemR:tDurPost                1.09242    0.26821   4.073 4.79e-05 ***
## pDemI:tDurPre                 0.20221    0.31068   0.651 0.515183    
## pDemI:tDurPost                0.91386    0.35136   2.601 0.009354 ** 
## pDemR:foxExposure.c           0.31481    0.13485   2.334 0.019653 *  
## pDemI:foxExposure.c           0.33395    0.21721   1.537 0.124314    
## tDurPre:foxExposure.c         0.03478    0.12734   0.273 0.784767    
## tDurPost:foxExposure.c        0.27901    0.14418   1.935 0.053088 .  
## pDemR:tDurPre:foxExposure.c  -0.14332    0.16425  -0.873 0.382976    
## pDemR:tDurPost:foxExposure.c -0.07303    0.18894  -0.387 0.699152    
## pDemI:tDurPre:foxExposure.c  -0.13868    0.25948  -0.534 0.593087    
## pDemI:tDurPost:foxExposure.c -0.36771    0.29722  -1.237 0.216152    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.995 on 2390 degrees of freedom
##   (68 observations deleted due to missingness)
## Multiple R-squared:  0.05115,    Adjusted R-squared:  0.0444 
## F-statistic: 7.578 on 17 and 2390 DF,  p-value: < 2.2e-16

iii. anger ~ (pRvD + pRvI) * (tDurPre + pDurPost) * foxExposure.c

angerFox2.R <- lm(emotion_1 ~ (pRepD + pRepI) * (tDurPre + tDurPost) * foxExposure.c, data = d)
summary(angerFox2.R)

## 
## Call:
## lm(formula = emotion_1 ~ (pRepD + pRepI) * (tDurPre + tDurPost) * 
##     foxExposure.c, data = d)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -3.525 -1.743 -0.207  1.541  4.541 
## 
## Coefficients:
##                               Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                   3.287762   0.144860  22.696  < 2e-16 ***
## pRepD                         0.277558   0.195489   1.420   0.1558    
## pRepI                        -0.653919   0.265261  -2.465   0.0138 *  
## tDurPre                      -0.142969   0.176110  -0.812   0.4170    
## tDurPost                      0.284701   0.201162   1.415   0.1571    
## foxExposure.c                 0.130520   0.082726   1.578   0.1148    
## pRepD:tDurPre                 0.300000   0.237457   1.263   0.2066    
## pRepD:tDurPost               -1.092416   0.268211  -4.073 4.79e-05 ***
## pRepI:tDurPre                 0.502215   0.319630   1.571   0.1163    
## pRepI:tDurPost               -0.178557   0.363932  -0.491   0.6237    
## pRepD:foxExposure.c          -0.314810   0.134852  -2.334   0.0197 *  
## pRepI:foxExposure.c           0.019139   0.206595   0.093   0.9262    
## tDurPre:foxExposure.c        -0.108540   0.103744  -1.046   0.2956    
## tDurPost:foxExposure.c        0.205985   0.122108   1.687   0.0918 .  
## pRepD:tDurPre:foxExposure.c   0.143322   0.164249   0.873   0.3830    
## pRepD:tDurPost:foxExposure.c  0.073028   0.188940   0.387   0.6992    
## pRepI:tDurPre:foxExposure.c   0.004644   0.248755   0.019   0.9851    
## pRepI:tDurPost:foxExposure.c -0.294682   0.287165  -1.026   0.3049    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.995 on 2390 degrees of freedom
##   (68 observations deleted due to missingness)
## Multiple R-squared:  0.05115,    Adjusted R-squared:  0.0444 
## F-statistic: 7.578 on 17 and 2390 DF,  p-value: < 2.2e-16

iv. anger ~ foxExp

cor.test(d$emotion_6, d$mediaExposure_5)

## 
##  Pearson's product-moment correlation
## 
## data:  d$emotion_6 and d$mediaExposure_5
## t = 5.0335, df = 2412, p-value = 5.171e-07
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.06231474 0.14127670
## sample estimates:
##       cor 
## 0.1019563

v. anger ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * otherMediaExposure

anger_media <- lm(emotion_1 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * otherMediaExposure.c, data = d)
summary(anger_media)

## 
## Call:
## lm(formula = emotion_1 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * 
##     otherMediaExposure.c, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.6122 -1.7110 -0.2634  1.5409  4.8116 
## 
## Coefficients:
##                                         Estimate Std. Error t value Pr(>|t|)
## (Intercept)                             3.175393   0.094943  33.445  < 2e-16
## pDem_Rep                               -0.134138   0.189717  -0.707  0.47961
## pInd_Not                                0.846612   0.233841   3.620  0.00030
## tDurPre                                 0.172369   0.116320   1.482  0.13851
## tDurPost                               -0.176304   0.132505  -1.331  0.18346
## otherMediaExposure.c                    0.275500   0.101948   2.702  0.00693
## pDem_Rep:tDurPre                       -0.326216   0.235832  -1.383  0.16672
## pDem_Rep:tDurPost                       1.110882   0.267780   4.148 3.46e-05
## pInd_Not:tDurPre                       -0.434812   0.284313  -1.529  0.12631
## pInd_Not:tDurPost                      -0.466651   0.324432  -1.438  0.15046
## pDem_Rep:otherMediaExposure.c          -0.418264   0.212837  -1.965  0.04951
## pInd_Not:otherMediaExposure.c          -0.355670   0.245117  -1.451  0.14691
## tDurPre:otherMediaExposure.c            0.005253   0.130601   0.040  0.96792
## tDurPost:otherMediaExposure.c          -0.262931   0.144843  -1.815  0.06961
## pDem_Rep:tDurPre:otherMediaExposure.c   0.541095   0.266390   2.031  0.04234
## pDem_Rep:tDurPost:otherMediaExposure.c -0.187451   0.299093  -0.627  0.53090
## pInd_Not:tDurPre:otherMediaExposure.c   0.191187   0.318177   0.601  0.54797
## pInd_Not:tDurPost:otherMediaExposure.c  0.216404   0.350466   0.617  0.53698
##                                           
## (Intercept)                            ***
## pDem_Rep                                  
## pInd_Not                               ***
## tDurPre                                   
## tDurPost                                  
## otherMediaExposure.c                   ** 
## pDem_Rep:tDurPre                          
## pDem_Rep:tDurPost                      ***
## pInd_Not:tDurPre                          
## pInd_Not:tDurPost                         
## pDem_Rep:otherMediaExposure.c          *  
## pInd_Not:otherMediaExposure.c             
## tDurPre:otherMediaExposure.c              
## tDurPost:otherMediaExposure.c          .  
## pDem_Rep:tDurPre:otherMediaExposure.c  *  
## pDem_Rep:tDurPost:otherMediaExposure.c    
## pInd_Not:tDurPre:otherMediaExposure.c     
## pInd_Not:tDurPost:otherMediaExposure.c    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.992 on 2384 degrees of freedom
##   (74 observations deleted due to missingness)
## Multiple R-squared:  0.05364,    Adjusted R-squared:  0.04689 
## F-statistic: 7.949 on 17 and 2384 DF,  p-value: < 2.2e-16

vi. anger ~ (pDvR + pDvI) * (tDurPre + tDurPost) * otherMediaExposure.c

anger2.D <- lm(emotion_1 ~ (pDemR + pDemI) * (tDurPre + tDurPost) * otherMediaExposure.c, data = d)
summary(anger2.D)

## 
## Call:
## lm(formula = emotion_1 ~ (pDemR + pDemI) * (tDurPre + tDurPost) * 
##     otherMediaExposure.c, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.6122 -1.7110 -0.2634  1.5409  4.8116 
## 
## Coefficients:
##                                     Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                          3.52184    0.13314  26.452  < 2e-16 ***
## pDemR                               -0.13414    0.18972  -0.707 0.479609    
## pDemI                               -0.91368    0.25181  -3.628 0.000291 ***
## tDurPre                              0.19199    0.16228   1.183 0.236896    
## tDurPost                            -0.88574    0.17916  -4.944 8.19e-07 ***
## otherMediaExposure.c                 0.36726    0.14922   2.461 0.013915 *  
## pDemR:tDurPre                       -0.32622    0.23583  -1.383 0.166715    
## pDemR:tDurPost                       1.11088    0.26778   4.148 3.46e-05 ***
## pDemI:tDurPre                        0.27170    0.30539   0.890 0.373722    
## pDemI:tDurPost                       1.02209    0.34558   2.958 0.003131 ** 
## pDemR:otherMediaExposure.c          -0.41826    0.21284  -1.965 0.049509 *  
## pDemI:otherMediaExposure.c           0.14654    0.26650   0.550 0.582470    
## tDurPre:otherMediaExposure.c        -0.20220    0.17677  -1.144 0.252802    
## tDurPost:otherMediaExposure.c       -0.09779    0.19354  -0.505 0.613411    
## pDemR:tDurPre:otherMediaExposure.c   0.54110    0.26639   2.031 0.042344 *  
## pDemR:tDurPost:otherMediaExposure.c -0.18745    0.29909  -0.627 0.530896    
## pDemI:tDurPre:otherMediaExposure.c   0.07936    0.33874   0.234 0.814787    
## pDemI:tDurPost:otherMediaExposure.c -0.31013    0.37138  -0.835 0.403755    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.992 on 2384 degrees of freedom
##   (74 observations deleted due to missingness)
## Multiple R-squared:  0.05364,    Adjusted R-squared:  0.04689 
## F-statistic: 7.949 on 17 and 2384 DF,  p-value: < 2.2e-16

vii. anger ~ (pRvD + pRvI) * (tDurPre + pDurPost) * otherMediaExposure.c

anger2.R <- lm(emotion_1 ~ (pRepD + pRepI) * (tDurPre + tDurPost) * otherMediaExposure.c, data = d)
summary(anger2.R)

## 
## Call:
## lm(formula = emotion_1 ~ (pRepD + pRepI) * (tDurPre + tDurPost) * 
##     otherMediaExposure.c, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.6122 -1.7110 -0.2634  1.5409  4.8116 
## 
## Coefficients:
##                                     Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                          3.38771    0.13515  25.066  < 2e-16 ***
## pRepD                                0.13414    0.18972   0.707  0.47961    
## pRepI                               -0.77954    0.25288  -3.083  0.00208 ** 
## tDurPre                             -0.13423    0.17112  -0.784  0.43288    
## tDurPost                             0.22514    0.19902   1.131  0.25807    
## otherMediaExposure.c                -0.05100    0.15177  -0.336  0.73686    
## pRepD:tDurPre                        0.32622    0.23583   1.383  0.16672    
## pRepD:tDurPost                      -1.11088    0.26778  -4.148 3.46e-05 ***
## pRepI:tDurPre                        0.59792    0.31018   1.928  0.05402 .  
## pRepI:tDurPost                      -0.08879    0.35629  -0.249  0.80322    
## pRepD:otherMediaExposure.c           0.41826    0.21284   1.965  0.04951 *  
## pRepI:otherMediaExposure.c           0.56480    0.26794   2.108  0.03514 *  
## tDurPre:otherMediaExposure.c         0.33889    0.19928   1.701  0.08916 .  
## tDurPost:otherMediaExposure.c       -0.28524    0.22803  -1.251  0.21110    
## pRepD:tDurPre:otherMediaExposure.c  -0.54110    0.26639  -2.031  0.04234 *  
## pRepD:tDurPost:otherMediaExposure.c  0.18745    0.29909   0.627  0.53090    
## pRepI:tDurPre:otherMediaExposure.c  -0.46173    0.35101  -1.315  0.18849    
## pRepI:tDurPost:otherMediaExposure.c -0.12268    0.39046  -0.314  0.75340    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.992 on 2384 degrees of freedom
##   (74 observations deleted due to missingness)
## Multiple R-squared:  0.05364,    Adjusted R-squared:  0.04689 
## F-statistic: 7.949 on 17 and 2384 DF,  p-value: < 2.2e-16

viii. anger ~ otherMediaExp

cor.test(d$emotion_6, d$mediaExposure)

## 
##  Pearson's product-moment correlation
## 
## data:  d$emotion_6 and d$mediaExposure
## t = 13.396, df = 2406, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.2258910 0.3002435
## sample estimates:
##       cor 
## 0.2634585

ix. anger ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * (FoxExp - OtherMediaExp)

anger_diff <- lm(emotion_1 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * diffFoxOther, data = d)
summary(anger_diff)

## 
## Call:
## lm(formula = emotion_1 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * 
##     diffFoxOther, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -4.0196 -1.7224 -0.2146  1.5514  4.7227 
## 
## Coefficients:
##                                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                     3.08030    0.10016  30.754  < 2e-16 ***
## pDem_Rep                       -0.23311    0.21309  -1.094  0.27408    
## pInd_Not                        0.76281    0.23807   3.204  0.00137 ** 
## tDurPre                         0.20060    0.12113   1.656  0.09784 .  
## tDurPost                       -0.18399    0.13727  -1.340  0.18026    
## diffFoxOther                   -0.17370    0.08067  -2.153  0.03140 *  
## pDem_Rep:tDurPre               -0.20375    0.26064  -0.782  0.43444    
## pDem_Rep:tDurPost               0.81728    0.29385   2.781  0.00546 ** 
## pInd_Not:tDurPre               -0.33365    0.28585  -1.167  0.24323    
## pInd_Not:tDurPost              -0.49838    0.32502  -1.533  0.12532    
## pDem_Rep:diffFoxOther           0.56214    0.13897   4.045  5.4e-05 ***
## pInd_Not:diffFoxOther           0.12202    0.21138   0.577  0.56380    
## tDurPre:diffFoxOther            0.02182    0.09766   0.223  0.82319    
## tDurPost:diffFoxOther           0.29678    0.12021   2.469  0.01362 *  
## pDem_Rep:tDurPre:diffFoxOther  -0.36703    0.16791  -2.186  0.02893 *  
## pDem_Rep:tDurPost:diffFoxOther -0.06424    0.18808  -0.342  0.73272    
## pInd_Not:tDurPre:diffFoxOther  -0.10543    0.25608  -0.412  0.68060    
## pInd_Not:tDurPost:diffFoxOther  0.07179    0.32416   0.221  0.82474    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.982 on 2384 degrees of freedom
##   (74 observations deleted due to missingness)
## Multiple R-squared:  0.06284,    Adjusted R-squared:  0.05616 
## F-statistic: 9.403 on 17 and 2384 DF,  p-value: < 2.2e-16

x. anger ~ (foxExp - otherMediaExp)

cor.test(d$emotion_6, d$diffFoxOther)

## 
##  Pearson's product-moment correlation
## 
## data:  d$emotion_6 and d$diffFoxOther
## t = -3.1235, df = 2406, p-value = 0.001808
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.10323285 -0.02366553
## sample estimates:
##         cor 
## -0.06355018

e. timing –> fox exposure –> anger mediator analysis

i. X –> Y

foxMediator2 <- lm(emotion_1 ~ (pRepD + pRepI) * (tDurPre + tDurPost), data = d)
summary(foxMediator2)

## 
## Call:
## lm(formula = emotion_1 ~ (pRepD + pRepI) * (tDurPre + tDurPost), 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -2.7807 -1.7308 -0.1571  1.3705  4.4138 
## 
## Coefficients:
##                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)      3.3908     0.1298  26.131  < 2e-16 ***
## pRepD            0.2387     0.1811   1.318  0.18761    
## pRepI           -0.8045     0.2508  -3.208  0.00135 ** 
## tDurPre         -0.2337     0.1603  -1.458  0.14510    
## tDurPost         0.3438     0.1859   1.849  0.06460 .  
## pRepD:tDurPre    0.3849     0.2216   1.737  0.08260 .  
## pRepD:tDurPost  -1.2516     0.2520  -4.966  7.3e-07 ***
## pRepI:tDurPre    0.6230     0.3023   2.060  0.03946 *  
## pRepI:tDurPost  -0.1992     0.3452  -0.577  0.56397    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 2.002 on 2400 degrees of freedom
##   (67 observations deleted due to missingness)
## Multiple R-squared:  0.04068,    Adjusted R-squared:  0.03749 
## F-statistic: 12.72 on 8 and 2400 DF,  p-value: < 2.2e-16

ii. X –> M

foxMediator1 <- lm(foxExposure.c ~ (pRepD + pRepI) * (tDurPre + tDurPost), data = d)
summary(foxMediator1)

## 
## Call:
## lm(formula = foxExposure.c ~ (pRepD + pRepI) * (tDurPre + tDurPost), 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -1.9580 -0.7896 -0.7843  1.1793  3.2157 
## 
## Coefficients:
##                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)     0.78911    0.08563   9.216  < 2e-16 ***
## pRepD          -1.13727    0.11952  -9.515  < 2e-16 ***
## pRepI          -1.10741    0.16550  -6.691 2.74e-11 ***
## tDurPre        -0.23392    0.10576  -2.212   0.0271 *  
## tDurPost       -0.30754    0.12269  -2.507   0.0123 *  
## pRepD:tDurPre   0.19799    0.14620   1.354   0.1758    
## pRepD:tDurPost  0.27647    0.16629   1.663   0.0965 .  
## pRepI:tDurPre   0.16766    0.19949   0.840   0.4007    
## pRepI:tDurPost  0.27250    0.22815   1.194   0.2324    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.321 on 2401 degrees of freedom
##   (66 observations deleted due to missingness)
## Multiple R-squared:  0.1154, Adjusted R-squared:  0.1124 
## F-statistic: 39.14 on 8 and 2401 DF,  p-value: < 2.2e-16

iii. x + M –> Y

foxMediator3 <- lm(emotion_1 ~ (pRepD + pRepI) * (tDurPre + tDurPost) + foxExposure.c, data = d)
summary(foxMediator3)

## 
## Call:
## lm(formula = emotion_1 ~ (pRepD + pRepI) * (tDurPre + tDurPost) + 
##     foxExposure.c, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -2.8991 -1.7294 -0.2406  1.4007  4.4451 
## 
## Coefficients:
##                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)     3.36174    0.13205  25.458  < 2e-16 ***
## pRepD           0.28055    0.18452   1.520  0.12854    
## pRepI          -0.76383    0.25314  -3.017  0.00258 ** 
## tDurPre        -0.22521    0.16049  -1.403  0.16065    
## tDurPost        0.35507    0.18618   1.907  0.05663 .  
## foxExposure.c   0.03677    0.03098   1.187  0.23530    
## pRepD:tDurPre   0.37794    0.22171   1.705  0.08839 .  
## pRepD:tDurPost -1.26172    0.25216  -5.004 6.03e-07 ***
## pRepI:tDurPre   0.61693    0.30239   2.040  0.04144 *  
## pRepI:tDurPost -0.22154    0.34586  -0.641  0.52188    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 2.002 on 2398 degrees of freedom
##   (68 observations deleted due to missingness)
## Multiple R-squared:  0.04136,    Adjusted R-squared:  0.03777 
## F-statistic:  11.5 on 9 and 2398 DF,  p-value: < 2.2e-16

11. Models: Does hope correlate with vote legitimacy, efficacy, timing, or news exposure?

a. basic models

###. i. hope ~ (pDvR + pIvDR) * (tDurPre + pDurPost)

hope2 <- lm(emotion_6 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost), data = d)
summary(hope2)

## 
## Call:
## lm(formula = emotion_6 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost), 
##     data = d)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -4.110 -1.683 -0.110  1.748  4.317 
## 
## Coefficients:
##                   Estimate Std. Error t value Pr(>|t|)    
## (Intercept)        3.63077    0.08907  40.763  < 2e-16 ***
## pDem_Rep          -0.33518    0.17298  -1.938   0.0528 .  
## pInd_Not           1.13016    0.22248   5.080 4.07e-07 ***
## tDurPre            0.07879    0.10749   0.733   0.4636    
## tDurPost           0.01307    0.12212   0.107   0.9148    
## pDem_Rep:tDurPre   0.15145    0.21164   0.716   0.4743    
## pDem_Rep:tDurPost -1.65041    0.24083  -6.853 9.16e-12 ***
## pInd_Not:tDurPre   0.23617    0.26671   0.886   0.3760    
## pInd_Not:tDurPost  0.30438    0.30276   1.005   0.3148    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.912 on 2400 degrees of freedom
##   (67 observations deleted due to missingness)
## Multiple R-squared:  0.1185, Adjusted R-squared:  0.1156 
## F-statistic: 40.34 on 8 and 2400 DF,  p-value: < 2.2e-16

ii. hope ~ (pDvR + pDvI) * (tDurPre + tDurPost)

hope2.D <- lm(emotion_6 ~ (pDemR + pDemI) * (tDurPre + tDurPost), data = d)
summary(hope2.D)

## 
## Call:
## lm(formula = emotion_6 ~ (pDemR + pDemI) * (tDurPre + tDurPost), 
##     data = d)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -4.110 -1.683 -0.110  1.748  4.317 
## 
## Coefficients:
##                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)      4.1713     0.1207  34.565  < 2e-16 ***
## pDemR           -0.3352     0.1730  -1.938 0.052781 .  
## pDemI           -1.2977     0.2379  -5.456 5.37e-08 ***
## tDurPre          0.0810     0.1461   0.554 0.579328    
## tDurPost         0.9387     0.1625   5.778 8.53e-09 ***
## pDemR:tDurPre    0.1515     0.2116   0.716 0.474322    
## pDemR:tDurPost  -1.6504     0.2408  -6.853 9.16e-12 ***
## pDemI:tDurPre   -0.1605     0.2851  -0.563 0.573631    
## pDemI:tDurPost  -1.1296     0.3218  -3.510 0.000456 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.912 on 2400 degrees of freedom
##   (67 observations deleted due to missingness)
## Multiple R-squared:  0.1185, Adjusted R-squared:  0.1156 
## F-statistic: 40.34 on 8 and 2400 DF,  p-value: < 2.2e-16

iii. hope ~ (pRvD + pRvI) * (tDurPre + tDurPost)

hope2.R <- lm(emotion_6 ~ (pRepD + pRepI) * (tDurPre + tDurPost), data = d)
summary(hope2.R)

## 
## Call:
## lm(formula = emotion_6 ~ (pRepD + pRepI) * (tDurPre + tDurPost), 
##     data = d)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -4.110 -1.683 -0.110  1.748  4.317 
## 
## Coefficients:
##                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)      3.8361     0.1239  30.954  < 2e-16 ***
## pRepD            0.3352     0.1730   1.938   0.0528 .  
## pRepI           -0.9626     0.2395  -4.019 6.04e-05 ***
## tDurPre          0.2324     0.1531   1.518   0.1291    
## tDurPost        -0.7117     0.1778  -4.003 6.44e-05 ***
## pRepD:tDurPre   -0.1514     0.2116  -0.716   0.4743    
## pRepD:tDurPost   1.6504     0.2408   6.853 9.16e-12 ***
## pRepI:tDurPre   -0.3119     0.2888  -1.080   0.2802    
## pRepI:tDurPost   0.5208     0.3298   1.579   0.1144    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.912 on 2400 degrees of freedom
##   (67 observations deleted due to missingness)
## Multiple R-squared:  0.1185, Adjusted R-squared:  0.1156 
## F-statistic: 40.34 on 8 and 2400 DF,  p-value: < 2.2e-16

b. including ownVote.c & overallVote.c

i. hope ~ (pDvR + pIvDR) * (tDurPre + pDurPost) * ownVote.c * overallVote.c

#Vote Conf do not have entries for "pre election"
hope1 <- lm(emotion_6 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * ownvote.c * overallvote.c, data = d)
summary(hope1)

## 
## Call:
## lm(formula = emotion_6 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * 
##     ownvote.c * overallvote.c, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -4.5057 -1.5057 -0.0905  1.4943  4.4456 
## 
## Coefficients: (12 not defined because of singularities)
##                                           Estimate Std. Error t value Pr(>|t|)
## (Intercept)                                3.71793    0.11459  32.446  < 2e-16
## pDem_Rep                                  -0.16222    0.22648  -0.716  0.47397
## pInd_Not                                   0.66076    0.28379   2.328  0.02006
## tDurPre                                         NA         NA      NA       NA
## tDurPost                                  -0.20540    0.16800  -1.223  0.22173
## ownvote.c                                  0.04092    0.12998   0.315  0.75297
## overallvote.c                              0.40565    0.12655   3.205  0.00138
## pDem_Rep:tDurPre                                NA         NA      NA       NA
## pDem_Rep:tDurPost                         -1.10085    0.36382  -3.026  0.00253
## pInd_Not:tDurPre                                NA         NA      NA       NA
## pInd_Not:tDurPost                          0.46054    0.39480   1.167  0.24364
## pDem_Rep:ownvote.c                         0.05073    0.23736   0.214  0.83080
## pInd_Not:ownvote.c                         0.36499    0.33341   1.095  0.27387
## tDurPre:ownvote.c                               NA         NA      NA       NA
## tDurPost:ownvote.c                         0.15560    0.17346   0.897  0.36988
## pDem_Rep:overallvote.c                    -0.51292    0.21077  -2.434  0.01510
## pInd_Not:overallvote.c                    -0.33286    0.33524  -0.993  0.32096
## tDurPre:overallvote.c                           NA         NA      NA       NA
## tDurPost:overallvote.c                     0.04215    0.16417   0.257  0.79743
## ownvote.c:overallvote.c                   -0.09267    0.05852  -1.584  0.11353
## pDem_Rep:tDurPre:ownvote.c                      NA         NA      NA       NA
## pDem_Rep:tDurPost:ownvote.c                0.38762    0.37674   1.029  0.30374
## pInd_Not:tDurPre:ownvote.c                      NA         NA      NA       NA
## pInd_Not:tDurPost:ownvote.c               -0.10375    0.40684  -0.255  0.79876
## pDem_Rep:tDurPre:overallvote.c                  NA         NA      NA       NA
## pDem_Rep:tDurPost:overallvote.c            0.24830    0.32748   0.758  0.44847
## pInd_Not:tDurPre:overallvote.c                  NA         NA      NA       NA
## pInd_Not:tDurPost:overallvote.c            0.20974    0.40469   0.518  0.60437
## pDem_Rep:ownvote.c:overallvote.c           0.21532    0.12600   1.709  0.08772
## pInd_Not:ownvote.c:overallvote.c           0.14567    0.13803   1.055  0.29145
## tDurPre:ownvote.c:overallvote.c                 NA         NA      NA       NA
## tDurPost:ownvote.c:overallvote.c           0.18362    0.07862   2.336  0.01968
## pDem_Rep:tDurPre:ownvote.c:overallvote.c        NA         NA      NA       NA
## pDem_Rep:tDurPost:ownvote.c:overallvote.c  0.01971    0.18278   0.108  0.91413
## pInd_Not:tDurPre:ownvote.c:overallvote.c        NA         NA      NA       NA
## pInd_Not:tDurPost:ownvote.c:overallvote.c -0.07736    0.17516  -0.442  0.65883
##                                              
## (Intercept)                               ***
## pDem_Rep                                     
## pInd_Not                                  *  
## tDurPre                                      
## tDurPost                                     
## ownvote.c                                    
## overallvote.c                             ** 
## pDem_Rep:tDurPre                             
## pDem_Rep:tDurPost                         ** 
## pInd_Not:tDurPre                             
## pInd_Not:tDurPost                            
## pDem_Rep:ownvote.c                           
## pInd_Not:ownvote.c                           
## tDurPre:ownvote.c                            
## tDurPost:ownvote.c                           
## pDem_Rep:overallvote.c                    *  
## pInd_Not:overallvote.c                       
## tDurPre:overallvote.c                        
## tDurPost:overallvote.c                       
## ownvote.c:overallvote.c                      
## pDem_Rep:tDurPre:ownvote.c                   
## pDem_Rep:tDurPost:ownvote.c                  
## pInd_Not:tDurPre:ownvote.c                   
## pInd_Not:tDurPost:ownvote.c                  
## pDem_Rep:tDurPre:overallvote.c               
## pDem_Rep:tDurPost:overallvote.c              
## pInd_Not:tDurPre:overallvote.c               
## pInd_Not:tDurPost:overallvote.c              
## pDem_Rep:ownvote.c:overallvote.c          .  
## pInd_Not:ownvote.c:overallvote.c             
## tDurPre:ownvote.c:overallvote.c              
## tDurPost:ownvote.c:overallvote.c          *  
## pDem_Rep:tDurPre:ownvote.c:overallvote.c     
## pDem_Rep:tDurPost:ownvote.c:overallvote.c    
## pInd_Not:tDurPre:ownvote.c:overallvote.c     
## pInd_Not:tDurPost:ownvote.c:overallvote.c    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.813 on 1183 degrees of freedom
##   (1269 observations deleted due to missingness)
## Multiple R-squared:  0.2574, Adjusted R-squared:  0.2429 
## F-statistic: 17.82 on 23 and 1183 DF,  p-value: < 2.2e-16

ii. hope ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * ownvote.c * overallvote.c + (1 | timing)

anger.mx <- lmer(emotion_6 ~ (pDem_Rep + pInd_Not) * ownvote.c * overallvote.c + (1 | election_timing), data = d)

## boundary (singular) fit: see ?isSingular

summary(anger.mx)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: emotion_6 ~ (pDem_Rep + pInd_Not) * ownvote.c * overallvote.c +  
##     (1 | election_timing)
##    Data: d
## 
## REML criterion at convergence: 4919.2
## 
## Scaled residuals: 
##      Min       1Q   Median       3Q      Max 
## -2.33863 -0.71131 -0.08114  0.91879  2.38038 
## 
## Random effects:
##  Groups          Name        Variance Std.Dev.
##  election_timing (Intercept) 0.000    0.000   
##  Residual                    3.378    1.838   
## Number of obs: 1207, groups:  election_timing, 2
## 
## Fixed effects:
##                                    Estimate Std. Error         df t value
## (Intercept)                       3.619e+00  8.241e-02  1.195e+03  43.915
## pDem_Rep                         -5.765e-01  1.750e-01  1.195e+03  -3.295
## pInd_Not                          9.324e-01  1.961e-01  1.195e+03   4.754
## ownvote.c                         9.060e-02  8.028e-02  1.195e+03   1.129
## overallvote.c                     4.770e-01  7.527e-02  1.195e+03   6.337
## pDem_Rep:ownvote.c                1.545e-01  1.818e-01  1.195e+03   0.850
## pInd_Not:ownvote.c                1.764e-01  1.827e-01  1.195e+03   0.966
## pDem_Rep:overallvote.c           -3.992e-01  1.560e-01  1.195e+03  -2.560
## pInd_Not:overallvote.c           -1.103e-01  1.818e-01  1.195e+03  -0.607
## ownvote.c:overallvote.c           2.956e-03  3.805e-02  1.195e+03   0.078
## pDem_Rep:ownvote.c:overallvote.c  1.498e-01  8.992e-02  1.195e+03   1.666
## pInd_Not:ownvote.c:overallvote.c  6.166e-02  8.358e-02  1.195e+03   0.738
##                                  Pr(>|t|)    
## (Intercept)                       < 2e-16 ***
## pDem_Rep                          0.00101 ** 
## pInd_Not                         2.24e-06 ***
## ownvote.c                         0.25929    
## overallvote.c                    3.30e-10 ***
## pDem_Rep:ownvote.c                0.39556    
## pInd_Not:ownvote.c                0.33442    
## pDem_Rep:overallvote.c            0.01059 *  
## pInd_Not:overallvote.c            0.54404    
## ownvote.c:overallvote.c           0.93810    
## pDem_Rep:ownvote.c:overallvote.c  0.09599 .  
## pInd_Not:ownvote.c:overallvote.c  0.46085    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##             (Intr) pDm_Rp pInd_N ownvt. ovrll. pDm_Rp:w. pInd_Nt:w. pDm_Rp:v.
## pDem_Rep     0.048                                                           
## pInd_Not    -0.312  0.030                                                    
## ownvote.c   -0.075 -0.213 -0.176                                             
## overallvt.c -0.050  0.256  0.194 -0.711                                      
## pDm_Rp:wnv. -0.199 -0.265 -0.125 -0.019  0.135                               
## pInd_Nt:wn. -0.184 -0.140  0.056 -0.188  0.180 -0.013                        
## pDm_Rp:vrl.  0.262  0.139  0.164  0.148 -0.220 -0.733     0.097              
## pInd_Nt:vr.  0.192  0.158 -0.163  0.169 -0.353  0.083    -0.699     -0.136   
## ownvt.c:vr. -0.558 -0.012  0.080  0.362 -0.065  0.262     0.016     -0.019   
## pDm_Rp:w.:. -0.011 -0.590 -0.007  0.251 -0.017  0.417     0.164     -0.290   
## pInd_Nt:.:.  0.086 -0.008 -0.539  0.017 -0.238  0.178     0.316     -0.013   
##             pInd_Nt:v. own.:. pD_R:.:
## pDem_Rep                             
## pInd_Not                             
## ownvote.c                            
## overallvt.c                          
## pDm_Rp:wnv.                          
## pInd_Nt:wn.                          
## pDm_Rp:vrl.                          
## pInd_Nt:vr.                          
## ownvt.c:vr. -0.216                   
## pDm_Rp:w.:. -0.010     -0.058        
## pInd_Nt:.:.  0.096     -0.089 -0.040 
## convergence code: 0
## boundary (singular) fit: see ?isSingular

iii. hope ~ ownVote.c

cor.test(d$emotion_6, d$ownvote_conf)

## 
##  Pearson's product-moment correlation
## 
## data:  d$emotion_6 and d$ownvote_conf
## t = 13.146, df = 1207, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.3035752 0.4022495
## sample estimates:
##       cor 
## 0.3538967

iv. hope ~ overallVote.c

cor.test(d$emotion_6, d$overallvote_conf)

## 
##  Pearson's product-moment correlation
## 
## data:  d$emotion_6 and d$overallvote_conf
## t = 15.847, df = 1206, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.3673472 0.4607607
## sample estimates:
##       cor 
## 0.4151476

c. including govtPolEff.c & electPolEff.c

i. hope ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * govtPolEff.c * electPolEff.c

anger1 <- lm(emotion_6 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * govtPolEff.c * electPolEff.c, data = d)
summary(anger1)

## 
## Call:
## lm(formula = emotion_6 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * 
##     govtPolEff.c * electPolEff.c, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -4.7898 -1.2510 -0.0491  1.2292  5.1099 
## 
## Coefficients:
##                                               Estimate Std. Error t value
## (Intercept)                                   3.698312   0.100010  36.980
## pDem_Rep                                     -0.366334   0.193175  -1.896
## pInd_Not                                      0.599070   0.250436   2.392
## tDurPre                                       0.014582   0.121969   0.120
## tDurPost                                      0.124607   0.143045   0.871
## govtPolEff.c                                  0.150178   0.070525   2.129
## electPolEff.c                                 0.277845   0.061066   4.550
## pDem_Rep:tDurPre                              0.325924   0.235287   1.385
## pDem_Rep:tDurPost                            -1.268866   0.263900  -4.808
## pInd_Not:tDurPre                              0.408043   0.305608   1.335
## pInd_Not:tDurPost                             0.168188   0.365429   0.460
## pDem_Rep:govtPolEff.c                        -0.034386   0.131890  -0.261
## pInd_Not:govtPolEff.c                        -0.088906   0.179153  -0.496
## tDurPre:govtPolEff.c                         -0.013573   0.085639  -0.158
## tDurPost:govtPolEff.c                        -0.117183   0.100079  -1.171
## pDem_Rep:electPolEff.c                       -0.045917   0.108277  -0.424
## pInd_Not:electPolEff.c                        0.067173   0.158403   0.424
## tDurPre:electPolEff.c                         0.014718   0.071969   0.204
## tDurPost:electPolEff.c                        0.067406   0.083621   0.806
## govtPolEff.c:electPolEff.c                    0.016018   0.035630   0.450
## pDem_Rep:tDurPre:govtPolEff.c                 0.003525   0.161429   0.022
## pDem_Rep:tDurPost:govtPolEff.c                0.019745   0.180445   0.109
## pInd_Not:tDurPre:govtPolEff.c                -0.054296   0.216808  -0.250
## pInd_Not:tDurPost:govtPolEff.c                0.043752   0.257987   0.170
## pDem_Rep:tDurPre:electPolEff.c                0.135229   0.130870   1.033
## pDem_Rep:tDurPost:electPolEff.c               0.049010   0.143675   0.341
## pInd_Not:tDurPre:electPolEff.c                0.027763   0.184918   0.150
## pInd_Not:tDurPost:electPolEff.c              -0.109500   0.219313  -0.499
## pDem_Rep:govtPolEff.c:electPolEff.c           0.041365   0.053415   0.774
## pInd_Not:govtPolEff.c:electPolEff.c           0.104745   0.097110   1.079
## tDurPre:govtPolEff.c:electPolEff.c           -0.001553   0.040992  -0.038
## tDurPost:govtPolEff.c:electPolEff.c          -0.017830   0.046539  -0.383
## pDem_Rep:tDurPre:govtPolEff.c:electPolEff.c  -0.050628   0.067596  -0.749
## pDem_Rep:tDurPost:govtPolEff.c:electPolEff.c -0.038612   0.073804  -0.523
## pInd_Not:tDurPre:govtPolEff.c:electPolEff.c  -0.129437   0.108923  -1.188
## pInd_Not:tDurPost:govtPolEff.c:electPolEff.c -0.076320   0.125048  -0.610
##                                              Pr(>|t|)    
## (Intercept)                                   < 2e-16 ***
## pDem_Rep                                       0.0580 .  
## pInd_Not                                       0.0168 *  
## tDurPre                                        0.9048    
## tDurPost                                       0.3838    
## govtPolEff.c                                   0.0333 *  
## electPolEff.c                                5.64e-06 ***
## pDem_Rep:tDurPre                               0.1661    
## pDem_Rep:tDurPost                            1.62e-06 ***
## pInd_Not:tDurPre                               0.1819    
## pInd_Not:tDurPost                              0.6454    
## pDem_Rep:govtPolEff.c                          0.7943    
## pInd_Not:govtPolEff.c                          0.6198    
## tDurPre:govtPolEff.c                           0.8741    
## tDurPost:govtPolEff.c                          0.2418    
## pDem_Rep:electPolEff.c                         0.6716    
## pInd_Not:electPolEff.c                         0.6716    
## tDurPre:electPolEff.c                          0.8380    
## tDurPost:electPolEff.c                         0.4203    
## govtPolEff.c:electPolEff.c                     0.6531    
## pDem_Rep:tDurPre:govtPolEff.c                  0.9826    
## pDem_Rep:tDurPost:govtPolEff.c                 0.9129    
## pInd_Not:tDurPre:govtPolEff.c                  0.8023    
## pInd_Not:tDurPost:govtPolEff.c                 0.8653    
## pDem_Rep:tDurPre:electPolEff.c                 0.3016    
## pDem_Rep:tDurPost:electPolEff.c                0.7330    
## pInd_Not:tDurPre:electPolEff.c                 0.8807    
## pInd_Not:tDurPost:electPolEff.c                0.6176    
## pDem_Rep:govtPolEff.c:electPolEff.c            0.4388    
## pInd_Not:govtPolEff.c:electPolEff.c            0.2809    
## tDurPre:govtPolEff.c:electPolEff.c             0.9698    
## tDurPost:govtPolEff.c:electPolEff.c            0.7017    
## pDem_Rep:tDurPre:govtPolEff.c:electPolEff.c    0.4539    
## pDem_Rep:tDurPost:govtPolEff.c:electPolEff.c   0.6009    
## pInd_Not:tDurPre:govtPolEff.c:electPolEff.c    0.2348    
## pInd_Not:tDurPost:govtPolEff.c:electPolEff.c   0.5417    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.781 on 2368 degrees of freedom
##   (72 observations deleted due to missingness)
## Multiple R-squared:  0.2446, Adjusted R-squared:  0.2334 
## F-statistic:  21.9 on 35 and 2368 DF,  p-value: < 2.2e-16

ii. hope ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * govtPolEff.c * electPolEff.c + (1 | timing)

anger.mx <- lmer(emotion_6 ~ (pDem_Rep + pInd_Not) * govtPolEff.c * electPolEff.c + (1 | election_timing), data = d)
summary(anger.mx)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: emotion_6 ~ (pDem_Rep + pInd_Not) * govtPolEff.c * electPolEff.c +  
##     (1 | election_timing)
##    Data: d
## 
## REML criterion at convergence: 9698.3
## 
## Scaled residuals: 
##      Min       1Q   Median       3Q      Max 
## -2.60570 -0.75891 -0.03874  0.74877  2.77988 
## 
## Random effects:
##  Groups          Name        Variance Std.Dev.
##  election_timing (Intercept) 0.001549 0.03935 
##  Residual                    3.248497 1.80236 
## Number of obs: 2404, groups:  election_timing, 3
## 
## Fixed effects:
##                                       Estimate Std. Error         df t value
## (Intercept)                            3.74641    0.05550    4.02359  67.497
## pDem_Rep                              -0.52451    0.09428 2391.32306  -5.564
## pInd_Not                               0.87478    0.12716 2391.07755   6.879
## govtPolEff.c                           0.11515    0.03472 2390.49285   3.317
## electPolEff.c                          0.31423    0.02792 2384.53506  11.257
## pDem_Rep:govtPolEff.c                 -0.03877    0.06432 2390.47743  -0.603
## pInd_Not:govtPolEff.c                 -0.13075    0.08854 2390.95946  -1.477
## pDem_Rep:electPolEff.c                 0.05203    0.05114 2383.75674   1.017
## pInd_Not:electPolEff.c                 0.07668    0.07149 2390.55494   1.073
## govtPolEff.c:electPolEff.c             0.01460    0.01477 2389.97928   0.988
## pDem_Rep:govtPolEff.c:electPolEff.c    0.01400    0.02746 2391.91457   0.510
## pInd_Not:govtPolEff.c:electPolEff.c    0.01277    0.03763 2390.91835   0.339
##                                     Pr(>|t|)    
## (Intercept)                         2.68e-07 ***
## pDem_Rep                            2.94e-08 ***
## pInd_Not                            7.65e-12 ***
## govtPolEff.c                        0.000925 ***
## electPolEff.c                        < 2e-16 ***
## pDem_Rep:govtPolEff.c               0.546771    
## pInd_Not:govtPolEff.c               0.139901    
## pDem_Rep:electPolEff.c              0.309041    
## pInd_Not:electPolEff.c              0.283544    
## govtPolEff.c:electPolEff.c          0.323229    
## pDem_Rep:govtPolEff.c:electPolEff.c 0.610041    
## pInd_Not:govtPolEff.c:electPolEff.c 0.734441    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##              (Intr) pDm_Rp pInd_N gvtPE. elcPE. pDm_Rp:gPE. pInd_Nt:gPE.
## pDem_Rep      0.067                                                     
## pInd_Not     -0.442  0.043                                              
## govtPlEff.c   0.212  0.028 -0.114                                       
## elctPlEff.c  -0.103  0.008 -0.013 -0.605                                
## pDm_Rp:gPE.   0.025  0.239  0.017  0.047 -0.066                         
## pInd_Nt:gPE. -0.103  0.017  0.233 -0.505  0.328  0.028                  
## pDm_Rp:lPE.   0.009 -0.224  0.005 -0.066  0.074 -0.578      -0.039      
## pInd_Nt:lPE. -0.012  0.005 -0.075  0.326 -0.518 -0.038      -0.615      
## gvtPlE.:PE.  -0.441 -0.054  0.239 -0.346  0.460  0.005       0.064      
## pD_R:PE.:PE  -0.051 -0.493 -0.032  0.005  0.065 -0.506       0.003      
## pI_N:PE.:PE   0.213 -0.032 -0.486  0.064 -0.321  0.003      -0.279      
##              pDm_Rp:lPE. pInd_Nt:lPE. gPE.:P pD_R:PE.:
## pDem_Rep                                              
## pInd_Not                                              
## govtPlEff.c                                           
## elctPlEff.c                                           
## pDm_Rp:gPE.                                           
## pInd_Nt:gPE.                                          
## pDm_Rp:lPE.                                           
## pInd_Nt:lPE.  0.043                                   
## gvtPlE.:PE.   0.066      -0.318                       
## pD_R:PE.:PE   0.335       0.038        0.045          
## pI_N:PE.:PE   0.039       0.511       -0.501  0.027

iii. hope ~ govtPolEff.c

cor.test(d$emotion_6, d$govtPolEff.c)

## 
##  Pearson's product-moment correlation
## 
## data:  d$emotion_6 and d$govtPolEff.c
## t = 15.244, df = 2409, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.2597666 0.3325924
## sample estimates:
##       cor 
## 0.2966106

iv. hope ~ electPolEff.c

cor.test(d$emotion_6, d$electPolEff.c)

## 
##  Pearson's product-moment correlation
## 
## data:  d$emotion_6 and d$electPolEff.c
## t = 22.399, df = 2408, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.3816481 0.4477528
## sample estimates:
##       cor 
## 0.4152485

d. including media exposure

i. hope ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * foxExposure

hope_fox <- lm(emotion_6 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * foxExposure.c, data = d)
summary(hope_fox)

## 
## Call:
## lm(formula = emotion_6 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * 
##     foxExposure.c, data = d)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -4.136 -1.555 -0.136  1.528  4.445 
## 
## Coefficients:
##                                 Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                      3.57632    0.09325  38.351  < 2e-16 ***
## pDem_Rep                        -0.64629    0.18542  -3.485  0.00050 ***
## pInd_Not                         1.00030    0.23026   4.344 1.46e-05 ***
## tDurPre                          0.11763    0.11251   1.045  0.29592    
## tDurPost                         0.05357    0.12759   0.420  0.67460    
## foxExposure.c                    0.19714    0.07312   2.696  0.00707 ** 
## pDem_Rep:tDurPre                 0.22828    0.22514   1.014  0.31070    
## pDem_Rep:tDurPost               -1.39258    0.25447  -5.473 4.90e-08 ***
## pInd_Not:tDurPre                 0.23048    0.27691   0.832  0.40531    
## pInd_Not:tDurPost                0.35801    0.31454   1.138  0.25516    
## pDem_Rep:foxExposure.c           0.15314    0.12791   1.197  0.23130    
## pInd_Not:foxExposure.c           0.14161    0.19061   0.743  0.45759    
## tDurPre:foxExposure.c            0.02328    0.08790   0.265  0.79110    
## tDurPost:foxExposure.c          -0.11522    0.10112  -1.139  0.25466    
## pDem_Rep:tDurPre:foxExposure.c   0.01652    0.15561   0.106  0.91546    
## pDem_Rep:tDurPost:foxExposure.c  0.01797    0.17929   0.100  0.92018    
## pInd_Not:tDurPre:foxExposure.c  -0.10448    0.22812  -0.458  0.64699    
## pInd_Not:tDurPost:foxExposure.c -0.23019    0.26232  -0.878  0.38029    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.892 on 2390 degrees of freedom
##   (68 observations deleted due to missingness)
## Multiple R-squared:  0.1402, Adjusted R-squared:  0.134 
## F-statistic: 22.92 on 17 and 2390 DF,  p-value: < 2.2e-16

ii. hope ~ (pDvR + pDvI) * (tDurPre + tDurPost) * foxExposure.c

hopeFox2.D <- lm(emotion_6 ~ (pDemR + pDemI) * (tDurPre + tDurPost) * foxExposure.c, data = d)
summary(hopeFox2.D)

## 
## Call:
## lm(formula = emotion_6 ~ (pDemR + pDemI) * (tDurPre + tDurPost) * 
##     foxExposure.c, data = d)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -4.136 -1.555 -0.136  1.528  4.445 
## 
## Coefficients:
##                              Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                   4.22956    0.12451  33.970  < 2e-16 ***
## pDemR                        -0.64629    0.18542  -3.485  0.00050 ***
## pDemI                        -1.32345    0.24480  -5.406 7.07e-08 ***
## tDurPre                       0.07954    0.15095   0.527  0.59827    
## tDurPost                      0.86801    0.16826   5.159 2.69e-07 ***
## foxExposure.c                 0.16729    0.10101   1.656  0.09781 .  
## pDemR:tDurPre                 0.22828    0.22514   1.014  0.31070    
## pDemR:tDurPost               -1.39258    0.25447  -5.473 4.90e-08 ***
## pDemI:tDurPre                -0.11634    0.29461  -0.395  0.69296    
## pDemI:tDurPost               -1.05430    0.33326  -3.164  0.00158 ** 
## pDemR:foxExposure.c           0.15314    0.12791   1.197  0.23130    
## pDemI:foxExposure.c          -0.06504    0.20602  -0.316  0.75227    
## tDurPre:foxExposure.c        -0.01945    0.12055  -0.161  0.87181    
## tDurPost:foxExposure.c       -0.20016    0.13676  -1.464  0.14342    
## pDemR:tDurPre:foxExposure.c   0.01652    0.15561   0.106  0.91546    
## pDemR:tDurPost:foxExposure.c  0.01797    0.17929   0.100  0.92018    
## pDemI:tDurPre:foxExposure.c   0.11274    0.24601   0.458  0.64679    
## pDemI:tDurPost:foxExposure.c  0.23917    0.28192   0.848  0.39631    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.892 on 2390 degrees of freedom
##   (68 observations deleted due to missingness)
## Multiple R-squared:  0.1402, Adjusted R-squared:  0.134 
## F-statistic: 22.92 on 17 and 2390 DF,  p-value: < 2.2e-16

iii. hope ~ (pRvD + pRvI) * (tDurPre + pDurPost) * foxExposure.c

hopeFox2.R <- lm(emotion_6 ~ (pRepD + pRepI) * (tDurPre + tDurPost) * foxExposure.c, data = d)
summary(hopeFox2.R)

## 
## Call:
## lm(formula = emotion_6 ~ (pRepD + pRepI) * (tDurPre + tDurPost) * 
##     foxExposure.c, data = d)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -4.136 -1.555 -0.136  1.528  4.445 
## 
## Coefficients:
##                               Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                   3.583272   0.137400  26.079  < 2e-16 ***
## pRepD                         0.646287   0.185422   3.485  0.00050 ***
## pRepI                        -0.677161   0.251600  -2.691  0.00716 ** 
## tDurPre                       0.307825   0.167040   1.843  0.06548 .  
## tDurPost                     -0.524574   0.190894  -2.748  0.00604 ** 
## foxExposure.c                 0.320440   0.078465   4.084 4.58e-05 ***
## pRepD:tDurPre                -0.228282   0.225137  -1.014  0.31070    
## pRepD:tDurPost                1.392582   0.254466   5.473 4.90e-08 ***
## pRepI:tDurPre                -0.344621   0.303169  -1.137  0.25577    
## pRepI:tDurPost                0.338280   0.345240   0.980  0.32726    
## pRepD:foxExposure.c          -0.153145   0.127907  -1.197  0.23130    
## pRepI:foxExposure.c          -0.218184   0.195956  -1.113  0.26563    
## tDurPre:foxExposure.c        -0.002934   0.098401  -0.030  0.97621    
## tDurPost:foxExposure.c       -0.182194   0.115936  -1.571  0.11620    
## pRepD:tDurPre:foxExposure.c  -0.016520   0.155614  -0.106  0.91546    
## pRepD:tDurPost:foxExposure.c -0.017968   0.179285  -0.100  0.92018    
## pRepI:tDurPre:foxExposure.c   0.096222   0.235944   0.408  0.68344    
## pRepI:tDurPost:foxExposure.c  0.221203   0.272425   0.812  0.41689    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.892 on 2390 degrees of freedom
##   (68 observations deleted due to missingness)
## Multiple R-squared:  0.1402, Adjusted R-squared:  0.134 
## F-statistic: 22.92 on 17 and 2390 DF,  p-value: < 2.2e-16

iv. hope ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * otherMediaExposure.c

hopeMedia1 <- lm(emotion_6 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * otherMediaExposure.c, data = d)
summary(hopeMedia1)

## 
## Call:
## lm(formula = emotion_6 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) * 
##     otherMediaExposure.c, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -4.8547 -1.4705 -0.0583  1.4969  4.7757 
## 
## Coefficients:
##                                        Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                             3.62318    0.08877  40.817  < 2e-16 ***
## pDem_Rep                               -0.15753    0.17737  -0.888    0.375    
## pInd_Not                                1.07598    0.21863   4.922 9.17e-07 ***
## tDurPre                                 0.07660    0.10875   0.704    0.481    
## tDurPost                                0.10488    0.12407   0.845    0.398    
## otherMediaExposure.c                    0.44754    0.09532   4.695 2.81e-06 ***
## pDem_Rep:tDurPre                        0.20801    0.22049   0.943    0.346    
## pDem_Rep:tDurPost                      -1.40742    0.25117  -5.604 2.34e-08 ***
## pInd_Not:tDurPre                       -0.02136    0.26582  -0.080    0.936    
## pInd_Not:tDurPost                       0.27389    0.30349   0.902    0.367    
## pDem_Rep:otherMediaExposure.c          -0.17686    0.19899  -0.889    0.374    
## pInd_Not:otherMediaExposure.c          -0.33480    0.22917  -1.461    0.144    
## tDurPre:otherMediaExposure.c            0.04762    0.12206   0.390    0.696    
## tDurPost:otherMediaExposure.c           0.16097    0.13585   1.185    0.236    
## pDem_Rep:tDurPre:otherMediaExposure.c  -0.39601    0.24888  -1.591    0.112    
## pDem_Rep:tDurPost:otherMediaExposure.c  0.40810    0.28151   1.450    0.147    
## pInd_Not:tDurPre:otherMediaExposure.c  -0.20745    0.29744  -0.697    0.486    
## pInd_Not:tDurPost:otherMediaExposure.c  0.31105    0.32806   0.948    0.343    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.862 on 2384 degrees of freedom
##   (74 observations deleted due to missingness)
## Multiple R-squared:  0.1672, Adjusted R-squared:  0.1613 
## F-statistic: 28.15 on 17 and 2384 DF,  p-value: < 2.2e-16

v. hope ~ (pDvR + pDvI) * (tDurPre + tDurPost) * otherMediaExposure.c

hopeMedia2.D <- lm(emotion_6 ~ (pDemR + pDemI) * (tDurPre + tDurPost) * otherMediaExposure.c, data = d)
summary(hopeMedia2.D)

## 
## Call:
## lm(formula = emotion_6 ~ (pDemR + pDemI) * (tDurPre + tDurPost) * 
##     otherMediaExposure.c, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -4.8547 -1.4705 -0.0583  1.4969  4.7757 
## 
## Coefficients:
##                                      Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                          4.057016   0.124481  32.592  < 2e-16 ***
## pDemR                               -0.157533   0.177374  -0.888  0.37455    
## pDemI                               -1.154743   0.235431  -4.905 9.98e-07 ***
## tDurPre                             -0.034454   0.151721  -0.227  0.82037    
## tDurPost                             0.898975   0.167499   5.367 8.78e-08 ***
## otherMediaExposure.c                 0.425480   0.139508   3.050  0.00231 ** 
## pDemR:tDurPre                        0.208015   0.220488   0.943  0.34556    
## pDemR:tDurPost                      -1.407419   0.251168  -5.604 2.34e-08 ***
## pDemI:tDurPre                        0.125371   0.285523   0.439  0.66063    
## pDemI:tDurPost                      -0.977603   0.323097  -3.026  0.00251 ** 
## pDemR:otherMediaExposure.c          -0.176856   0.198990  -0.889  0.37422    
## pDemI:otherMediaExposure.c           0.246375   0.249163   0.989  0.32286    
## tDurPre:otherMediaExposure.c         0.177169   0.165006   1.074  0.28306    
## tDurPost:otherMediaExposure.c        0.059563   0.180950   0.329  0.74206    
## pDemR:tDurPre:otherMediaExposure.c  -0.396006   0.248881  -1.591  0.11171    
## pDemR:tDurPost:otherMediaExposure.c  0.408100   0.281506   1.450  0.14727    
## pDemI:tDurPre:otherMediaExposure.c   0.009445   0.316562   0.030  0.97620    
## pDemI:tDurPost:otherMediaExposure.c -0.106998   0.347214  -0.308  0.75799    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.862 on 2384 degrees of freedom
##   (74 observations deleted due to missingness)
## Multiple R-squared:  0.1672, Adjusted R-squared:  0.1613 
## F-statistic: 28.15 on 17 and 2384 DF,  p-value: < 2.2e-16

vi. hope ~ (pRvD + pRvI) * (tDurPre + pDurPost) * otherMediaExposure.c

hopeMedia2.R <- lm(emotion_6 ~ (pRepD + pRepI) * (tDurPre + tDurPost) * otherMediaExposure.c, data = d)
summary(hopeMedia2.R)

## 
## Call:
## lm(formula = emotion_6 ~ (pRepD + pRepI) * (tDurPre + tDurPost) * 
##     otherMediaExposure.c, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -4.8547 -1.4705 -0.0583  1.4969  4.7757 
## 
## Coefficients:
##                                     Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                          3.89948    0.12636  30.861  < 2e-16 ***
## pRepD                                0.15753    0.17737   0.888  0.37455    
## pRepI                               -0.99721    0.23643  -4.218 2.56e-05 ***
## tDurPre                              0.17356    0.15999   1.085  0.27810    
## tDurPost                            -0.50844    0.18716  -2.717  0.00664 ** 
## otherMediaExposure.c                 0.24862    0.14190   1.752  0.07988 .  
## pRepD:tDurPre                       -0.20801    0.22049  -0.943  0.34556    
## pRepD:tDurPost                       1.40742    0.25117   5.604 2.34e-08 ***
## pRepI:tDurPre                       -0.08264    0.29000  -0.285  0.77569    
## pRepI:tDurPost                       0.42982    0.33371   1.288  0.19788    
## pRepD:otherMediaExposure.c           0.17686    0.19899   0.889  0.37422    
## pRepI:otherMediaExposure.c           0.42323    0.25051   1.689  0.09126 .  
## tDurPre:otherMediaExposure.c        -0.21884    0.18632  -1.175  0.24030    
## tDurPost:otherMediaExposure.c        0.46766    0.21564   2.169  0.03021 *  
## pRepD:tDurPre:otherMediaExposure.c   0.39601    0.24888   1.591  0.11171    
## pRepD:tDurPost:otherMediaExposure.c -0.40810    0.28151  -1.450  0.14727    
## pRepI:tDurPre:otherMediaExposure.c   0.40545    0.32818   1.235  0.21678    
## pRepI:tDurPost:otherMediaExposure.c -0.51510    0.36649  -1.405  0.16001    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.862 on 2384 degrees of freedom
##   (74 observations deleted due to missingness)
## Multiple R-squared:  0.1672, Adjusted R-squared:  0.1613 
## F-statistic: 28.15 on 17 and 2384 DF,  p-value: < 2.2e-16

vii. hope ~ (pDvR + pIvDR) * (tDurPre + tDurPost) + (FoxExp - OtherMediaExp)

hope_fox <- lm(emotion_6 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) + diffFoxOther, data = d)
summary(hope_fox)

## 
## Call:
## lm(formula = emotion_6 ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) + 
##     diffFoxOther, data = d)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -4.120 -1.678 -0.110  1.755  4.334 
## 
## Coefficients:
##                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)        3.632872   0.089512  40.585  < 2e-16 ***
## pDem_Rep          -0.348396   0.180697  -1.928    0.054 .  
## pInd_Not           1.133072   0.223105   5.079 4.09e-07 ***
## tDurPre            0.075281   0.107675   0.699    0.485    
## tDurPost           0.006235   0.122378   0.051    0.959    
## diffFoxOther       0.002274   0.030088   0.076    0.940    
## pDem_Rep:tDurPre   0.159594   0.212134   0.752    0.452    
## pDem_Rep:tDurPost -1.640704   0.241224  -6.802 1.30e-11 ***
## pInd_Not:tDurPre   0.218140   0.267160   0.817    0.414    
## pInd_Not:tDurPost  0.313849   0.303632   1.034    0.301    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.913 on 2392 degrees of freedom
##   (74 observations deleted due to missingness)
## Multiple R-squared:  0.1183, Adjusted R-squared:  0.115 
## F-statistic: 35.67 on 9 and 2392 DF,  p-value: < 2.2e-16

e. timing –> Fox exposure –> hope mediator analysis for republicans

X –> Y

foxMediator1 <- lm(emotion_5 ~ (pRepD + pRepI) * (tDurPre + tDurPost), data = d)
summary(foxMediator1)

## 
## Call:
## lm(formula = emotion_5 ~ (pRepD + pRepI) * (tDurPre + tDurPost), 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.5049 -1.5049 -0.5049  1.4951  4.7931 
## 
## Coefficients:
##                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)     2.89916    0.12377  23.424  < 2e-16 ***
## pRepD           0.06498    0.17276   0.376  0.70683    
## pRepI          -0.69226    0.23922  -2.894  0.00384 ** 
## tDurPre         0.10305    0.15292   0.674  0.50045    
## tDurPost       -0.43456    0.17735  -2.450  0.01434 *  
## pRepD:tDurPre  -0.13213    0.21136  -0.625  0.53194    
## pRepD:tDurPost  1.97527    0.24037   8.218 3.35e-16 ***
## pRepI:tDurPre  -0.04524    0.28838  -0.157  0.87535    
## pRepI:tDurPost  0.45843    0.32927   1.392  0.16397    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.909 on 2401 degrees of freedom
##   (66 observations deleted due to missingness)
## Multiple R-squared:  0.1021, Adjusted R-squared:  0.09916 
## F-statistic: 34.14 on 8 and 2401 DF,  p-value: < 2.2e-16

X –> M

foxMediator2 <- lm(foxExposure.c ~ (pRepD + pRepI) * (tDurPre + tDurPost), data = d)
summary(foxMediator2)

## 
## Call:
## lm(formula = foxExposure.c ~ (pRepD + pRepI) * (tDurPre + tDurPost), 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -1.9580 -0.7896 -0.7843  1.1793  3.2157 
## 
## Coefficients:
##                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)     0.78911    0.08563   9.216  < 2e-16 ***
## pRepD          -1.13727    0.11952  -9.515  < 2e-16 ***
## pRepI          -1.10741    0.16550  -6.691 2.74e-11 ***
## tDurPre        -0.23392    0.10576  -2.212   0.0271 *  
## tDurPost       -0.30754    0.12269  -2.507   0.0123 *  
## pRepD:tDurPre   0.19799    0.14620   1.354   0.1758    
## pRepD:tDurPost  0.27647    0.16629   1.663   0.0965 .  
## pRepI:tDurPre   0.16766    0.19949   0.840   0.4007    
## pRepI:tDurPost  0.27250    0.22815   1.194   0.2324    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.321 on 2401 degrees of freedom
##   (66 observations deleted due to missingness)
## Multiple R-squared:  0.1154, Adjusted R-squared:  0.1124 
## F-statistic: 39.14 on 8 and 2401 DF,  p-value: < 2.2e-16

x + M –> Y

foxMediator3 <- lm(emotion_5 ~ (pRepD + pRepI) * (tDurPre + tDurPost) + foxExposure.c, data = d)
summary(foxMediator3)

## 
## Call:
## lm(formula = emotion_5 ~ (pRepD + pRepI) * (tDurPre + tDurPost) + 
##     foxExposure.c, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -4.3184 -1.5643 -0.5582  1.3436  5.0087 
## 
## Coefficients:
##                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)     2.69918    0.12402  21.764  < 2e-16 ***
## pRepD           0.35319    0.17330   2.038   0.0417 *  
## pRepI          -0.41162    0.23776  -1.731   0.0835 .  
## tDurPre         0.16137    0.15074   1.071   0.2845    
## tDurPost       -0.35662    0.17487  -2.039   0.0415 *  
## foxExposure.c   0.25342    0.02906   8.721  < 2e-16 ***
## pRepD:tDurPre  -0.18134    0.20822  -0.871   0.3839    
## pRepD:tDurPost  1.90521    0.23684   8.044 1.35e-15 ***
## pRepI:tDurPre  -0.08677    0.28402  -0.305   0.7600    
## pRepI:tDurPost  0.37220    0.32485   1.146   0.2520    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.88 on 2399 degrees of freedom
##   (67 observations deleted due to missingness)
## Multiple R-squared:   0.13,  Adjusted R-squared:  0.1267 
## F-statistic: 39.82 on 9 and 2399 DF,  p-value: < 2.2e-16

12. Models: Election expectations [biden, trump]

a. electPredictTB ~ (pDvR + pIvDR) * (tDurPre + tDurPost)

predict1 <- lm(electPredictTB ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost), data = d)
summary(predict1)

## 
## Call:
## lm(formula = electPredictTB ~ (pDem_Rep + pInd_Not) * (tDurPre + 
##     tDurPost), data = d)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -6.581 -1.661  0.339  1.419  6.339 
## 
## Coefficients:
##                   Estimate Std. Error t value Pr(>|t|)    
## (Intercept)         5.2235     0.1169  44.669  < 2e-16 ***
## pDem_Rep           -3.5288     0.2308 -15.292  < 2e-16 ***
## pInd_Not            0.5228     0.2898   1.804  0.07146 .  
## tDurPre            -0.4770     0.1548  -3.082  0.00209 ** 
## tDurPost            0.4235     0.1527   2.774  0.00560 ** 
## pDem_Rep:tDurPre   -0.5875     0.3068  -1.915  0.05568 .  
## pDem_Rep:tDurPost  -0.4196     0.3029  -1.385  0.16620    
## pInd_Not:tDurPre   -0.6057     0.3828  -1.582  0.11375    
## pInd_Not:tDurPost  -0.6440     0.3773  -1.707  0.08805 .  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 2.24 on 1664 degrees of freedom
##   (803 observations deleted due to missingness)
## Multiple R-squared:  0.404,  Adjusted R-squared:  0.4011 
## F-statistic:   141 on 8 and 1664 DF,  p-value: < 2.2e-16

b. electPredictTB ~ (pDvR + pDvI) * (tDurPre + tDurPost)

predict2.D <- lm(electPredictTB ~ (pDemR + pDemI) * (tDurPre + tDurPost), data = d)
summary(predict2.D)

## 
## Call:
## lm(formula = electPredictTB ~ (pDemR + pDemI) * (tDurPre + tDurPost), 
##     data = d)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -6.581 -1.661  0.339  1.419  6.339 
## 
## Coefficients:
##                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)      7.1604     0.1638  43.707  < 2e-16 ***
## pDemR           -3.5288     0.2308 -15.292  < 2e-16 ***
## pDemI           -2.2872     0.3123  -7.324 3.74e-13 ***
## tDurPre         -0.3831     0.2155  -1.778   0.0757 .  
## tDurPost         0.4207     0.2077   2.026   0.0429 *  
## pDemR:tDurPre   -0.5875     0.3068  -1.915   0.0557 .  
## pDemR:tDurPost  -0.4196     0.3029  -1.385   0.1662    
## pDemI:tDurPre    0.3119     0.4116   0.758   0.4487    
## pDemI:tDurPost   0.4342     0.4032   1.077   0.2817    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 2.24 on 1664 degrees of freedom
##   (803 observations deleted due to missingness)
## Multiple R-squared:  0.404,  Adjusted R-squared:  0.4011 
## F-statistic:   141 on 8 and 1664 DF,  p-value: < 2.2e-16

c. electPredictTB ~ (pRvD + pRvI) * (tDurPre + pDurPost)

predict2.R <- lm(electPredictTB ~ (pRepD + pRepI) * (tDurPre + tDurPost), data = d)
summary(predict2.R)

## 
## Call:
## lm(formula = electPredictTB ~ (pRepD + pRepI) * (tDurPre + tDurPost), 
##     data = d)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -6.581 -1.661  0.339  1.419  6.339 
## 
## Coefficients:
##                 Estimate Std. Error t value Pr(>|t|)    
## (Intercept)     3.631579   0.162529  22.344  < 2e-16 ***
## pRepD           3.528849   0.230771  15.292  < 2e-16 ***
## pRepI           1.241660   0.311617   3.985 7.05e-05 ***
## tDurPre        -0.970562   0.218363  -4.445 9.38e-06 ***
## tDurPost        0.001164   0.220507   0.005   0.9958    
## pRepD:tDurPre   0.587478   0.306802   1.915   0.0557 .  
## pRepD:tDurPost  0.419577   0.302916   1.385   0.1662    
## pRepI:tDurPre   0.899406   0.413102   2.177   0.0296 *  
## pRepI:tDurPost  0.853751   0.409928   2.083   0.0374 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 2.24 on 1664 degrees of freedom
##   (803 observations deleted due to missingness)
## Multiple R-squared:  0.404,  Adjusted R-squared:  0.4011 
## F-statistic:   141 on 8 and 1664 DF,  p-value: < 2.2e-16

b. electPredictTB ~ (pDvR + pIvDR) * (tDurPre + tDurPost) + (1 | timing)

predict.mx <- lmer(electPredictTB ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) + (1 | election_timing), data = d)
summary(predict.mx)

## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: electPredictTB ~ (pDem_Rep + pInd_Not) * (tDurPre + tDurPost) +  
##     (1 | election_timing)
##    Data: d
## 
## REML criterion at convergence: 7452.7
## 
## Scaled residuals: 
##     Min      1Q  Median      3Q     Max 
## -2.9376 -0.7414  0.1513  0.6333  2.8295 
## 
## Random effects:
##  Groups          Name        Variance Std.Dev.
##  election_timing (Intercept) 0.4364   0.6606  
##  Residual                    5.0190   2.2403  
## Number of obs: 1673, groups:  election_timing, 3
## 
## Fixed effects:
##                     Estimate Std. Error         df t value Pr(>|t|)    
## (Intercept)        5.223e+00  6.709e-01  1.011e-08   7.786   1.0000    
## pDem_Rep          -3.529e+00  2.308e-01  1.664e+03 -15.292   <2e-16 ***
## pInd_Not           5.228e-01  2.898e-01  1.664e+03   1.804   0.0715 .  
## tDurPre           -4.770e-01  9.470e-01  1.004e-08  -0.504   1.0000    
## tDurPost           4.235e-01  9.467e-01  1.002e-08   0.447   1.0000    
## pDem_Rep:tDurPre  -5.875e-01  3.068e-01  1.664e+03  -1.915   0.0557 .  
## pDem_Rep:tDurPost -4.196e-01  3.029e-01  1.664e+03  -1.385   0.1662    
## pInd_Not:tDurPre  -6.057e-01  3.828e-01  1.664e+03  -1.582   0.1138    
## pInd_Not:tDurPost -6.440e-01  3.773e-01  1.664e+03  -1.707   0.0881 .  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Correlation of Fixed Effects:
##               (Intr) pDm_Rp pInd_N tDurPr tDrPst pDm_Rp:tDrPr pDm_Rp:tDrPs
## pDem_Rep      -0.001                                                      
## pInd_Not      -0.074 -0.003                                               
## tDurPre       -0.708  0.001  0.052                                        
## tDurPost      -0.709  0.001  0.053  0.502                                 
## pDm_Rp:tDrPr   0.001 -0.752  0.002  0.001  0.000                          
## pDm_Rp:tDrPs   0.001 -0.762  0.002  0.000  0.006  0.573                   
## pInd_Nt:tDrPr  0.056  0.002 -0.757 -0.068 -0.040  0.005       -0.002      
## pInd_Nt:tDrPs  0.057  0.002 -0.768 -0.040 -0.067 -0.002        0.024      
##               pInd_Nt:tDrPr
## pDem_Rep                   
## pInd_Not                   
## tDurPre                    
## tDurPost                   
## pDm_Rp:tDrPr               
## pDm_Rp:tDrPs               
## pInd_Nt:tDrPr              
## pInd_Nt:tDrPs  0.582

14. Media Exposure/Trust models for confidence in votes being counted

a. Exposure to media sources

#Vote Confidence do not have entries for "pre election"

d$durPost <- NA
d$durPost[d$election_timing == 'During-election'] <- -.5
d$durPost[d$election_timing == 'Post-election'] <- .5

d$foxTrust.c <- d$mediaTrust_5 - mean(d$mediaTrust_5, na.rm = TRUE)

d$otherMediaTrust.c <- d$mediaTrust - mean(d$mediaTrust, na.rm = TRUE)

i. overallvote.c ~ (DvR + IvDR) * tDurPost * foxExposure.c

voteConf1 <- lm(overallvote.c ~ (pDem_Rep + pInd_Not) * durPost * foxExposure.c, data = d)
summary(voteConf1)

## 
## Call:
## lm(formula = overallvote.c ~ (pDem_Rep + pInd_Not) * durPost * 
##     foxExposure.c, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.5222 -0.7916  0.0906  0.6821  2.6862 
## 
## Coefficients:
##                                 Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                    -0.145529   0.040195  -3.621 0.000306 ***
## pDem_Rep                       -1.543509   0.080018 -19.290  < 2e-16 ***
## pInd_Not                        0.358305   0.099190   3.612 0.000316 ***
## durPost                         0.059230   0.080391   0.737 0.461407    
## foxExposure.c                  -0.038285   0.031866  -1.201 0.229819    
## pDem_Rep:durPost               -0.808778   0.160036  -5.054 5.01e-07 ***
## pInd_Not:durPost                0.041973   0.198380   0.212 0.832470    
## pDem_Rep:foxExposure.c          0.036878   0.056362   0.654 0.513040    
## pInd_Not:foxExposure.c         -0.008878   0.082735  -0.107 0.914561    
## durPost:foxExposure.c          -0.066373   0.063732  -1.041 0.297885    
## pDem_Rep:durPost:foxExposure.c  0.319441   0.112723   2.834 0.004676 ** 
## pInd_Not:durPost:foxExposure.c -0.191306   0.165471  -1.156 0.247858    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.189 on 1196 degrees of freedom
##   (1268 observations deleted due to missingness)
## Multiple R-squared:  0.3119, Adjusted R-squared:  0.3056 
## F-statistic: 49.29 on 11 and 1196 DF,  p-value: < 2.2e-16

ii. ownvote.c ~ (DvR + IvDR) * tDurPost * foxExposure.c

voteConf3 <- lm(ownvote.c ~ (pDem_Rep + pInd_Not) * durPost * foxExposure.c, data = d)
summary(voteConf3)

## 
## Call:
## lm(formula = ownvote.c ~ (pDem_Rep + pInd_Not) * durPost * foxExposure.c, 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.5279 -1.0155  0.4721  0.8890  2.0190 
## 
## Coefficients:
##                                 Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                    -0.195957   0.041818  -4.686 3.11e-06 ***
## pDem_Rep                       -0.869549   0.083306 -10.438  < 2e-16 ***
## pInd_Not                        0.758925   0.103159   7.357 3.49e-13 ***
## durPost                         0.043767   0.083637   0.523   0.6009    
## foxExposure.c                  -0.066991   0.033148  -2.021   0.0435 *  
## pDem_Rep:durPost               -0.380983   0.166612  -2.287   0.0224 *  
## pInd_Not:durPost                0.002739   0.206318   0.013   0.9894    
## pDem_Rep:foxExposure.c          0.118013   0.058677   2.011   0.0445 *  
## pInd_Not:foxExposure.c          0.001476   0.086036   0.017   0.9863    
## durPost:foxExposure.c           0.009840   0.066295   0.148   0.8820    
## pDem_Rep:durPost:foxExposure.c  0.206511   0.117355   1.760   0.0787 .  
## pInd_Not:durPost:foxExposure.c -0.188241   0.172073  -1.094   0.2742    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.238 on 1197 degrees of freedom
##   (1267 observations deleted due to missingness)
## Multiple R-squared:  0.1646, Adjusted R-squared:  0.1569 
## F-statistic: 21.44 on 11 and 1197 DF,  p-value: < 2.2e-16

iii. overallvote.c ~ (DvR + IvDR) * tDurPost * otherMediaExposure.c

voteConf2 <- lm(overallvote.c ~ (pDem_Rep + pInd_Not) * durPost * otherMediaExposure.c, data = d)
summary(voteConf2)

## 
## Call:
## lm(formula = overallvote.c ~ (pDem_Rep + pInd_Not) * durPost * 
##     otherMediaExposure.c, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.4580 -0.9113  0.1031  0.6958  3.0864 
## 
## Coefficients:
##                                       Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                           -0.08046    0.03838  -2.096 0.036259 *  
## pDem_Rep                              -1.36685    0.07740 -17.660  < 2e-16 ***
## pInd_Not                               0.33962    0.09409   3.610 0.000319 ***
## durPost                                0.20494    0.07677   2.670 0.007694 ** 
## otherMediaExposure.c                   0.38046    0.04196   9.068  < 2e-16 ***
## pDem_Rep:durPost                      -0.74428    0.15479  -4.808 1.72e-06 ***
## pInd_Not:durPost                       0.12192    0.18818   0.648 0.517179    
## pDem_Rep:otherMediaExposure.c          0.32446    0.08640   3.755 0.000181 ***
## pInd_Not:otherMediaExposure.c         -0.10758    0.10168  -1.058 0.290271    
## durPost:otherMediaExposure.c           0.13390    0.08392   1.596 0.110819    
## pDem_Rep:durPost:otherMediaExposure.c  0.52344    0.17280   3.029 0.002505 ** 
## pInd_Not:durPost:otherMediaExposure.c -0.03354    0.20336  -0.165 0.869046    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.15 on 1194 degrees of freedom
##   (1270 observations deleted due to missingness)
## Multiple R-squared:  0.3575, Adjusted R-squared:  0.3516 
## F-statistic:  60.4 on 11 and 1194 DF,  p-value: < 2.2e-16

iv. ownvote.c ~ (DvR + IvDR) * tDurPost * otherMediaExposure.c

voteConf4 <- lm(ownvote.c ~ (pDem_Rep + pInd_Not) * durPost * otherMediaExposure.c, data = d)
summary(voteConf4)

## 
## Call:
## lm(formula = ownvote.c ~ (pDem_Rep + pInd_Not) * durPost * otherMediaExposure.c, 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.3805 -0.9971  0.3384  0.7746  2.3384 
## 
## Coefficients:
##                                       Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                           -0.15017    0.04110  -3.654  0.00027 ***
## pDem_Rep                              -0.83646    0.08293 -10.086  < 2e-16 ***
## pInd_Not                               0.70850    0.10071   7.035 3.35e-12 ***
## durPost                                0.13667    0.08220   1.663  0.09664 .  
## otherMediaExposure.c                   0.19765    0.04492   4.400 1.18e-05 ***
## pDem_Rep:durPost                      -0.30484    0.16587  -1.838  0.06634 .  
## pInd_Not:durPost                       0.04358    0.20142   0.216  0.82874    
## pDem_Rep:otherMediaExposure.c          0.04274    0.09258   0.462  0.64441    
## pInd_Not:otherMediaExposure.c         -0.16867    0.10880  -1.550  0.12133    
## durPost:otherMediaExposure.c           0.17903    0.08984   1.993  0.04651 *  
## pDem_Rep:durPost:otherMediaExposure.c  0.33307    0.18517   1.799  0.07231 .  
## pInd_Not:durPost:otherMediaExposure.c -0.20724    0.21759  -0.952  0.34108    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.232 on 1195 degrees of freedom
##   (1269 observations deleted due to missingness)
## Multiple R-squared:  0.173,  Adjusted R-squared:  0.1654 
## F-statistic: 22.73 on 11 and 1195 DF,  p-value: < 2.2e-16

v. overallVote.c ~ foxExp

cor.test(d$overallvote.c, d$mediaExposure_5)

## 
##  Pearson's product-moment correlation
## 
## data:  d$overallvote.c and d$mediaExposure_5
## t = -6.7218, df = 1207, p-value = 2.761e-11
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.2437243 -0.1350234
## sample estimates:
##        cor 
## -0.1899559

vi. ownVote.c ~ foxExp

cor.test(d$ownvote.c, d$mediaExposure_5)

## 
##  Pearson's product-moment correlation
## 
## data:  d$ownvote.c and d$mediaExposure_5
## t = -4.7402, df = 1208, p-value = 2.389e-06
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.19004052 -0.07938187
## sample estimates:
##        cor 
## -0.1351326

vii. overallVote.c ~ otherMediaExp

cor.test(d$overallvote.c, d$mediaExposure)

## 
##  Pearson's product-moment correlation
## 
## data:  d$overallvote.c and d$mediaExposure
## t = 13.331, df = 1205, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.3083242 0.4067102
## sample estimates:
##       cor 
## 0.3585123

viii. ownVote.c ~ otherMediaExp

cor.test(d$ownvote.c, d$mediaExposure)

## 
##  Pearson's product-moment correlation
## 
## data:  d$ownvote.c and d$mediaExposure
## t = 7.5462, df = 1206, p-value = 8.796e-14
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.1578317 0.2655645
## sample estimates:
##       cor 
## 0.2123432

b. Trust in media sources

i. overallvote.c ~ (DvR + IvDR) * tDurPost * foxTrust.c

voteConf5 <- lm(overallvote.c ~ (pDem_Rep + pInd_Not) * durPost * foxTrust.c, data = d)
summary(voteConf5)

## 
## Call:
## lm(formula = overallvote.c ~ (pDem_Rep + pInd_Not) * durPost * 
##     foxTrust.c, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.5337 -0.8244  0.1439  0.7767  2.7994 
## 
## Coefficients:
##                             Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                 -0.15840    0.03950  -4.011 6.43e-05 ***
## pDem_Rep                    -1.58110    0.08035 -19.677  < 2e-16 ***
## pInd_Not                     0.34824    0.09636   3.614 0.000314 ***
## durPost                      0.05698    0.07899   0.721 0.470865    
## foxTrust.c                  -0.05587    0.03311  -1.688 0.091719 .  
## pDem_Rep:durPost            -0.80499    0.16070  -5.009 6.29e-07 ***
## pInd_Not:durPost             0.05808    0.19271   0.301 0.763179    
## pDem_Rep:foxTrust.c          0.07989    0.05933   1.347 0.178362    
## pInd_Not:foxTrust.c          0.16640    0.08554   1.945 0.051965 .  
## durPost:foxTrust.c          -0.04850    0.06621  -0.733 0.463964    
## pDem_Rep:durPost:foxTrust.c  0.27931    0.11866   2.354 0.018739 *  
## pInd_Not:durPost:foxTrust.c -0.12242    0.17107  -0.716 0.474390    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.189 on 1196 degrees of freedom
##   (1268 observations deleted due to missingness)
## Multiple R-squared:  0.3119, Adjusted R-squared:  0.3056 
## F-statistic: 49.28 on 11 and 1196 DF,  p-value: < 2.2e-16

ii. ownvote.c ~ (DvR + IvDR) * tDurPost * foxTrust.c

voteConf6 <- lm(ownvote.c ~ (pDem_Rep + pInd_Not) * durPost * foxTrust.c, data = d)
summary(voteConf6)

## 
## Call:
## lm(formula = ownvote.c ~ (pDem_Rep + pInd_Not) * durPost * foxTrust.c, 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.5576 -1.0140  0.4424  0.8485  2.1393 
## 
## Coefficients:
##                             Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                 -0.21103    0.04101  -5.146 3.10e-07 ***
## pDem_Rep                    -0.90087    0.08350 -10.788  < 2e-16 ***
## pInd_Not                     0.73027    0.09999   7.303 5.11e-13 ***
## durPost                      0.04230    0.08201   0.516  0.60607    
## foxTrust.c                  -0.07157    0.03433  -2.085  0.03727 *  
## pDem_Rep:durPost            -0.38362    0.16701  -2.297  0.02179 *  
## pInd_Not:durPost             0.02907    0.19998   0.145  0.88444    
## pDem_Rep:foxTrust.c          0.18623    0.06166   3.020  0.00258 ** 
## pInd_Not:foxTrust.c          0.13610    0.08861   1.536  0.12481    
## durPost:foxTrust.c           0.06228    0.06865   0.907  0.36446    
## pDem_Rep:durPost:foxTrust.c  0.17417    0.12331   1.412  0.15810    
## pInd_Not:durPost:foxTrust.c -0.23398    0.17722  -1.320  0.18700    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.236 on 1197 degrees of freedom
##   (1267 observations deleted due to missingness)
## Multiple R-squared:  0.1675, Adjusted R-squared:  0.1598 
## F-statistic: 21.89 on 11 and 1197 DF,  p-value: < 2.2e-16

iii. overallVote.c ~ (DvR + IvDR) * tDurPost * otherMediaTrust.c

voteConf7 <- lm(overallvote.c ~ (pDem_Rep + pInd_Not) * otherMediaTrust.c, data = d)
summary(voteConf7)

## 
## Call:
## lm(formula = overallvote.c ~ (pDem_Rep + pInd_Not) * otherMediaTrust.c, 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.4266 -0.8139  0.0742  0.7964  3.2729 
## 
## Coefficients:
##                            Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                -0.08774    0.03927  -2.234   0.0257 *  
## pDem_Rep                   -0.95491    0.08555 -11.163  < 2e-16 ***
## pInd_Not                    0.38261    0.09194   4.162 3.39e-05 ***
## otherMediaTrust.c           0.56338    0.04158  13.550  < 2e-16 ***
## pDem_Rep:otherMediaTrust.c  0.05556    0.08512   0.653   0.5141    
## pInd_Not:otherMediaTrust.c -0.04641    0.10109  -0.459   0.6462    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.111 on 1198 degrees of freedom
##   (1272 observations deleted due to missingness)
## Multiple R-squared:  0.3965, Adjusted R-squared:  0.394 
## F-statistic: 157.4 on 5 and 1198 DF,  p-value: < 2.2e-16

iv. ownvote.c ~ (DvR + IvDR) * timeDurPost * otherMediaTrust.c

voteConf8 <- lm(ownvote.c ~ (pDem_Rep + pInd_Not) * durPost * otherMediaTrust.c, data = d)
summary(voteConf8)

## 
## Call:
## lm(formula = ownvote.c ~ (pDem_Rep + pInd_Not) * durPost * otherMediaTrust.c, 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.4213 -0.8067  0.1933  0.7956  2.9788 
## 
## Coefficients:
##                                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                        -0.21522    0.04225  -5.094 4.07e-07 ***
## pDem_Rep                           -0.45452    0.09206  -4.937 9.04e-07 ***
## pInd_Not                            0.65506    0.09887   6.625 5.23e-11 ***
## durPost                             0.12514    0.08450   1.481  0.13885    
## otherMediaTrust.c                   0.40597    0.04534   8.954  < 2e-16 ***
## pDem_Rep:durPost                   -0.35017    0.18412  -1.902  0.05742 .  
## pInd_Not:durPost                    0.10554    0.19774   0.534  0.59364    
## pDem_Rep:otherMediaTrust.c         -0.32427    0.09216  -3.519  0.00045 ***
## pInd_Not:otherMediaTrust.c          0.02986    0.11066   0.270  0.78736    
## durPost:otherMediaTrust.c           0.10931    0.09068   1.205  0.22826    
## pDem_Rep:durPost:otherMediaTrust.c  0.36830    0.18431   1.998  0.04592 *  
## pInd_Not:durPost:otherMediaTrust.c -0.25383    0.22133  -1.147  0.25168    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.192 on 1193 degrees of freedom
##   (1271 observations deleted due to missingness)
## Multiple R-squared:  0.2241, Adjusted R-squared:  0.2169 
## F-statistic: 31.32 on 11 and 1193 DF,  p-value: < 2.2e-16

v. overallVote.c ~ foxTrust.c

cor.test(d$overallvote.c, d$foxTrust.c)

## 
##  Pearson's product-moment correlation
## 
## data:  d$overallvote.c and d$foxTrust.c
## t = -6.8121, df = 1207, p-value = 1.514e-11
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.2461214 -0.1375261
## sample estimates:
##        cor 
## -0.1924128

vi. ownVote.c ~ foxTrust.c

cor.test(d$ownvote.c, d$foxTrust.c)

## 
##  Pearson's product-moment correlation
## 
## data:  d$ownvote.c and d$foxTrust.c
## t = -5.0728, df = 1208, p-value = 4.535e-07
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.19915668 -0.08878985
## sample estimates:
##        cor 
## -0.1444224

vii. overallVote.c ~ otherMediaTrust.c

cor.test(d$overallvote.c, d$otherMediaTrust.c)

## 
##  Pearson's product-moment correlation
## 
## data:  d$overallvote.c and d$otherMediaTrust.c
## t = 23.814, df = 1203, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.5263756 0.6032130
## sample estimates:
##       cor 
## 0.5660223

viii. ownVote.c ~ otherMediaTrust.c

cor.test(d$ownvote.c, d$otherMediaTrust.c)

## 
##  Pearson's product-moment correlation
## 
## data:  d$ownvote.c and d$otherMediaTrust.c
## t = 14.125, df = 1204, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.3275564 0.4244487
## sample estimates:
##       cor 
## 0.3770336

c. Dem/Rep Identity -> FoxExposure -> overallVote

No mediation

X –> Y

legit1 <- lm(overallvote.c ~ pDem_Rep + pInd_Not * otherMediaExposure.c, data = d)
summary(legit1)

## 
## Call:
## lm(formula = overallvote.c ~ pDem_Rep + pInd_Not * otherMediaExposure.c, 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.3709 -0.9744  0.0740  0.8934  2.7163 
## 
## Coefficients:
##                               Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                   -0.10819    0.03797  -2.849  0.00446 ** 
## pDem_Rep                      -1.42630    0.07865 -18.134  < 2e-16 ***
## pInd_Not                       0.30553    0.09463   3.229  0.00128 ** 
## otherMediaExposure.c           0.35319    0.04227   8.356  < 2e-16 ***
## pInd_Not:otherMediaExposure.c -0.13571    0.10306  -1.317  0.18815    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.177 on 1201 degrees of freedom
##   (1270 observations deleted due to missingness)
## Multiple R-squared:  0.3226, Adjusted R-squared:  0.3203 
## F-statistic:   143 on 4 and 1201 DF,  p-value: < 2.2e-16

X –> M

legit2 <- lm(foxExposure.c ~ (pDem_Rep + pInd_Not) * otherMediaExposure.c, data = d)
summary(legit2)

## 
## Call:
## lm(formula = foxExposure.c ~ (pDem_Rep + pInd_Not) * otherMediaExposure.c, 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.0078 -0.8235 -0.3244  0.7113  3.8539 
## 
## Coefficients:
##                                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                    0.002599   0.029173   0.089   0.9290    
## pDem_Rep                       1.317180   0.059965  21.966  < 2e-16 ***
## pInd_Not                       0.340356   0.070770   4.809 1.61e-06 ***
## otherMediaExposure.c           0.578605   0.033436  17.305  < 2e-16 ***
## pDem_Rep:otherMediaExposure.c  0.027023   0.067322   0.401   0.6882    
## pInd_Not:otherMediaExposure.c -0.199843   0.082027  -2.436   0.0149 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.24 on 2398 degrees of freedom
##   (72 observations deleted due to missingness)
## Multiple R-squared:  0.2206, Adjusted R-squared:  0.219 
## F-statistic: 135.8 on 5 and 2398 DF,  p-value: < 2.2e-16

X + M –> Y

legit3 <- lm(overallvote.c ~ (pDem_Rep + pInd_Not) * otherMediaExposure.c + foxExposure.c, data = d)
summary(legit3)

## 
## Call:
## lm(formula = overallvote.c ~ (pDem_Rep + pInd_Not) * otherMediaExposure.c + 
##     foxExposure.c, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.2639 -0.9542  0.0416  0.8719  3.1804 
## 
## Coefficients:
##                               Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                   -0.07216    0.03845  -1.877 0.060781 .  
## pDem_Rep                      -1.23320    0.08536 -14.448  < 2e-16 ***
## pInd_Not                       0.40454    0.09470   4.272 2.09e-05 ***
## otherMediaExposure.c           0.44745    0.04464  10.023  < 2e-16 ***
## foxExposure.c                 -0.13462    0.02712  -4.964 7.90e-07 ***
## pDem_Rep:otherMediaExposure.c  0.32953    0.08610   3.827 0.000136 ***
## pInd_Not:otherMediaExposure.c -0.13675    0.10196  -1.341 0.180087    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.16 on 1199 degrees of freedom
##   (1270 observations deleted due to missingness)
## Multiple R-squared:  0.3436, Adjusted R-squared:  0.3403 
## F-statistic: 104.6 on 6 and 1199 DF,  p-value: < 2.2e-16

d. Dem/Rep Identity -> FoxExposure -> ownVote

No mediation

X –> Y

legit1 <- lm(ownvote.c ~ pDem_Rep + pInd_Not * otherMediaExposure.c, data = d)
summary(legit1)

## 
## Call:
## lm(formula = ownvote.c ~ pDem_Rep + pInd_Not * otherMediaExposure.c, 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.3339 -1.1311  0.3506  0.8076  2.2466 
## 
## Coefficients:
##                               Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                   -0.15672    0.03983  -3.935 8.79e-05 ***
## pDem_Rep                      -0.86369    0.08259 -10.457  < 2e-16 ***
## pInd_Not                       0.72099    0.09920   7.268 6.56e-13 ***
## otherMediaExposure.c           0.18827    0.04434   4.246 2.34e-05 ***
## pInd_Not:otherMediaExposure.c -0.17040    0.10803  -1.577    0.115    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.236 on 1202 degrees of freedom
##   (1269 observations deleted due to missingness)
## Multiple R-squared:  0.1626, Adjusted R-squared:  0.1599 
## F-statistic: 58.37 on 4 and 1202 DF,  p-value: < 2.2e-16

X –> M

legit2 <- lm(foxExposure.c ~ (pDem_Rep + pInd_Not) * otherMediaExposure.c, data = d)
summary(legit2)

## 
## Call:
## lm(formula = foxExposure.c ~ (pDem_Rep + pInd_Not) * otherMediaExposure.c, 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.0078 -0.8235 -0.3244  0.7113  3.8539 
## 
## Coefficients:
##                                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                    0.002599   0.029173   0.089   0.9290    
## pDem_Rep                       1.317180   0.059965  21.966  < 2e-16 ***
## pInd_Not                       0.340356   0.070770   4.809 1.61e-06 ***
## otherMediaExposure.c           0.578605   0.033436  17.305  < 2e-16 ***
## pDem_Rep:otherMediaExposure.c  0.027023   0.067322   0.401   0.6882    
## pInd_Not:otherMediaExposure.c -0.199843   0.082027  -2.436   0.0149 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.24 on 2398 degrees of freedom
##   (72 observations deleted due to missingness)
## Multiple R-squared:  0.2206, Adjusted R-squared:  0.219 
## F-statistic: 135.8 on 5 and 2398 DF,  p-value: < 2.2e-16

X + M –> Y

legit3 <- lm(ownvote.c ~ (pDem_Rep + pInd_Not) * otherMediaExposure.c + foxExposure.c, data = d)
summary(legit3)

## 
## Call:
## lm(formula = ownvote.c ~ (pDem_Rep + pInd_Not) * otherMediaExposure.c + 
##     foxExposure.c, data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.3548 -1.0238  0.2652  0.8142  2.3876 
## 
## Coefficients:
##                               Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                   -0.15074    0.04071  -3.703 0.000223 ***
## pDem_Rep                      -0.71447    0.09047  -7.898 6.39e-15 ***
## pInd_Not                       0.76798    0.10022   7.663 3.72e-14 ***
## otherMediaExposure.c           0.25384    0.04728   5.369 9.48e-08 ***
## foxExposure.c                 -0.11268    0.02874  -3.920 9.35e-05 ***
## pDem_Rep:otherMediaExposure.c  0.04131    0.09126   0.453 0.650860    
## pInd_Not:otherMediaExposure.c -0.19139    0.10788  -1.774 0.076310 .  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.229 on 1200 degrees of freedom
##   (1269 observations deleted due to missingness)
## Multiple R-squared:  0.1733, Adjusted R-squared:  0.1692 
## F-statistic: 41.93 on 6 and 1200 DF,  p-value: < 2.2e-16

e. Dem/Rep Identity -> FoxExposure -> Anger

No mediation

X –> Y

angerMediator1 <- lm(emotion_1 ~ (pDem_Rep + pInd_Not) * otherMediaExposure.c, data = d)
summary(angerMediator1)

## 
## Call:
## lm(formula = emotion_1 ~ (pDem_Rep + pInd_Not) * otherMediaExposure.c, 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.1078 -1.7370 -0.3501  1.6287  4.4288 
## 
## Coefficients:
##                                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                    3.208138   0.047585  67.419  < 2e-16 ***
## pDem_Rep                       0.006411   0.097825   0.066  0.94775    
## pInd_Not                       0.475621   0.115428   4.121 3.91e-05 ***
## otherMediaExposure.c           0.200665   0.054560   3.678  0.00024 ***
## pDem_Rep:otherMediaExposure.c -0.218398   0.109922  -1.987  0.04705 *  
## pInd_Not:otherMediaExposure.c -0.195488   0.133807  -1.461  0.14415    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 2.022 on 2396 degrees of freedom
##   (74 observations deleted due to missingness)
## Multiple R-squared:  0.01975,    Adjusted R-squared:  0.01771 
## F-statistic: 9.657 on 5 and 2396 DF,  p-value: 3.841e-09

X –> M

angerMediator2 <- lm(foxExposure.c ~ (pDem_Rep + pInd_Not) * otherMediaExposure.c, data = d)
summary(angerMediator2)

## 
## Call:
## lm(formula = foxExposure.c ~ (pDem_Rep + pInd_Not) * otherMediaExposure.c, 
##     data = d)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.0078 -0.8235 -0.3244  0.7113  3.8539 
## 
## Coefficients:
##                                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                    0.002599   0.029173   0.089   0.9290    
## pDem_Rep                       1.317180   0.059965  21.966  < 2e-16 ***
## pInd_Not                       0.340356   0.070770   4.809 1.61e-06 ***
## otherMediaExposure.c           0.578605   0.033436  17.305  < 2e-16 ***
## pDem_Rep:otherMediaExposure.c  0.027023   0.067322   0.401   0.6882    
## pInd_Not:otherMediaExposure.c -0.199843   0.082027  -2.436   0.0149 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.24 on 2398 degrees of freedom
##   (72 observations deleted due to missingness)
## Multiple R-squared:  0.2206, Adjusted R-squared:  0.219 
## F-statistic: 135.8 on 5 and 2398 DF,  p-value: < 2.2e-16

X + M –> Y

angerMediator3 <- lm(emotion_1 ~ (pDem_Rep + pInd_Not) * otherMediaExposure.c + foxExposure.c, data = d)
summary(angerMediator3)

## 
## Call:
## lm(formula = emotion_1 ~ (pDem_Rep + pInd_Not) * otherMediaExposure.c + 
##     foxExposure.c, data = d)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -3.100 -1.740 -0.353  1.628  4.436 
## 
## Coefficients:
##                                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                    3.208168   0.047594  67.406  < 2e-16 ***
## pDem_Rep                       0.018826   0.107278   0.175 0.860709    
## pInd_Not                       0.478833   0.116009   4.128 3.79e-05 ***
## otherMediaExposure.c           0.206093   0.057861   3.562 0.000375 ***
## foxExposure.c                 -0.009411   0.033346  -0.282 0.777802    
## pDem_Rep:otherMediaExposure.c -0.218093   0.109948  -1.984 0.047415 *  
## pInd_Not:otherMediaExposure.c -0.197393   0.134002  -1.473 0.140867    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 2.022 on 2395 degrees of freedom
##   (74 observations deleted due to missingness)
## Multiple R-squared:  0.01979,    Adjusted R-squared:  0.01733 
## F-statistic: 8.057 on 6 and 2395 DF,  p-value: 1.236e-08

Covid-19_NSF_RAPID_US_LongitudinalAnalyses

Quick summary of findings:

1. Graphs: Does anger change from pre, during, to post-election?

a. graph: anger vs. timing

b. graph: anger vs. party identity vs. timing

c. graph: anger vs. timing vs. party identity

2. Graphs: Does anger change depending on vote confidence?

a. graph: anger vs. own vote confidence

b. anger vs. national vote confidence

c. graph: anger vs. own vote confidence vs. party identity

d. graph: anger vs. national vote confidence vs. party identity

3. Graphs: Does anger change depending on vote influence?

a. graph: anger vs. government political efficacy

b. anger vs. national election efficacy

c. graph: anger vs. government political efficacy vs. party identity

d. graph: anger vs. national election efficacy vs. party identity

4. Graphs: Does hope change from pre, during, to post-election?

a. hope vs. election timing

b. hope vs. election timing vs. party identity

c. hope vs. party identity vs. election timing

5. Graphs: Does hope change depending on vote confidence?

a. hope vs. own vote confidence

b. hope vs. national vote confidence

c. hope vs. party identity vs. own vote confidence

d. hope vs. election timing vs. national vote confidence

6. Graphs: Does hope change depending on vote influence?

a. hope vs. government political efficacy

b. hope vs. national election efficacy

c. hope vs. party identity vs. government political efficacy

d. hope vs. election timing vs. national election efficacy

7. Graphs: Does exposure to Fox News change over timing of election?

a. exposure to fox vs. timing

b. exposure to fox vs. timing vs. party identity

c. exposure to other news stations vs. timing

d. exposure to other news stations vs. timing vs. party identity

8. Graphs: Does expected election win change over timing of election?

a. Trump win - Biden win vs. timing

b. Trump win - Biden win vs. timing vs. party identity

c. Trump win - Biden win vs. party identity vs. timing

9. Graphs: Does trust in media outlets change between party or over time of election?

a. trust in fox vs. timing

b. trust in fox vs. timing vs. party identity

c. trust in other news stations vs. timing

d. trust in other news stations vs. timing vs. party identity

e. FOX TRUST VIOLIN PLOT

f. FOX EXPOSURE VIOLIN PLOT

g. OTHER MEDIA TRUST VIOLIN PLOT

h. OTHER MEDIA TRUST VIOLIN PLOT

10. Models: Does anger correlate with vote legitimacy, efficacy, timing, fox news exposure?

a. basic models

i. anger ~ (pDvR + pIvDR) * (tDurPre + tDurPost)

ii. anger ~ (pDvR + pDvI) * (tDurPre + tDurPost)

iii. anger ~ (pRvD + pRvI) * (tDurPre + pDurPost)

b. incuding ownVote.c & overalVote.c

i. anger ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * ownVote.c * overallVote.c

ii. anger ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * ownVote.c * overallVote.c + (1 | timing)

iii. anger ~ ownVote.c

iv. anger ~ overallVote.c

c. including govtPolEff.c & electPolEff.c

i. anger ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * govtPolEff.c * electPolEff.c

ii. anger ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * govtPolEff.c * electPolEff.c + (1 | timing)

iii. anger ~ govtPolEff.c

iv. anger ~ electPolEff.c

d. includuing media exposure

i. anger ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * foxExposure

ii. anger ~ (pDvR + pDvI) * (tDurPre + tDurPost) * foxExposure.c

iii. anger ~ (pRvD + pRvI) * (tDurPre + pDurPost) * foxExposure.c

iv. anger ~ foxExp

v. anger ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * otherMediaExposure

vi. anger ~ (pDvR + pDvI) * (tDurPre + tDurPost) * otherMediaExposure.c

vii. anger ~ (pRvD + pRvI) * (tDurPre + pDurPost) * otherMediaExposure.c

viii. anger ~ otherMediaExp

ix. anger ~ (pDvR + pIvDR) * (tDurPre + tDurPost) * (FoxExp - OtherMediaExp)

x. anger ~ (foxExp - otherMediaExp)

e. timing –> fox exposure –> anger mediator analysis

i. X –> Y

ii. X –> M

iii. x + M –> Y

11. Models: Does hope correlate with vote legitimacy, efficacy, timing, or news exposure?

a. basic models