Interaction Analyses

# interaction
InteractAnalyses <- subset(climate_labels, Condition != "Control")
InteractAnalyses$Condition <- as.factor(InteractAnalyses$Condition)

# Dummy coded variables
InteractAnalyses$DWS <- ifelse (InteractAnalyses$Condition=="Direct With Support", 1,0)
InteractAnalyses$IWS <- ifelse (InteractAnalyses$Condition== "Indirect With Support", 1,0)

# both conditions with support
InteractAnalyses$Support<-InteractAnalyses$DWS+InteractAnalyses$IWS

# both conditions with direct harm 
InteractAnalyses$DNS <- ifelse(InteractAnalyses$Condition=="Direct Without Support", 1,0)
InteractAnalyses$DirectHarm<-InteractAnalyses$DNS+InteractAnalyses$DWS

#interaction
IN1_model <- lm(IN1 ~ Support*DirectHarm, data = InteractAnalyses)
summary(IN1_model)
## 
## Call:
## lm(formula = IN1 ~ Support * DirectHarm, data = InteractAnalyses)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -2.03242 -0.95489 -0.03242  0.96758  2.45387 
## 
## Coefficients:
##                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)         2.54613    0.05350  47.594  < 2e-16 ***
## Support             0.40875    0.07575   5.396 7.84e-08 ***
## DirectHarm          0.01496    0.07566   0.198    0.843    
## Support:DirectHarm  0.06257    0.10706   0.584    0.559    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.071 on 1598 degrees of freedom
##   (5 observations deleted due to missingness)
## Multiple R-squared:  0.04121,    Adjusted R-squared:  0.03941 
## F-statistic:  22.9 on 3 and 1598 DF,  p-value: 1.635e-14
IN2_model <- lm(IN2 ~ Support*DirectHarm, data = InteractAnalyses)
summary(IN2_model)
## 
## Call:
## lm(formula = IN2 ~ Support * DirectHarm, data = InteractAnalyses)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -2.15960 -0.79302 -0.09273  0.90727  2.23441 
## 
## Coefficients:
##                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)         2.76559    0.05577  49.588  < 2e-16 ***
## Support             0.32715    0.07897   4.143 3.61e-05 ***
## DirectHarm          0.02743    0.07887   0.348    0.728    
## Support:DirectHarm  0.03944    0.11161   0.353    0.724    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.117 on 1598 degrees of freedom
##   (5 observations deleted due to missingness)
## Multiple R-squared:  0.02412,    Adjusted R-squared:  0.02228 
## F-statistic: 13.16 on 3 and 1598 DF,  p-value: 1.717e-08
DN1_model <- lm(DN1 ~ Support*DirectHarm, data = InteractAnalyses)
summary(DN1_model)
## 
## Call:
## lm(formula = DN1 ~ Support * DirectHarm, data = InteractAnalyses)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.5910 -0.5288 -0.3017  0.4913  2.6983 
## 
## Coefficients:
##                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)         4.50873    0.05660  79.655  < 2e-16 ***
## Support             0.02009    0.08015   0.251  0.80207    
## DirectHarm         -0.20698    0.08005  -2.586  0.00981 ** 
## Support:DirectHarm  0.26918    0.11328   2.376  0.01760 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.133 on 1598 degrees of freedom
##   (5 observations deleted due to missingness)
## Multiple R-squared:  0.009149,   Adjusted R-squared:  0.007289 
## F-statistic: 4.918 on 3 and 1598 DF,  p-value: 0.0021
DN2_model <- lm(DN2 ~ Support*DirectHarm, data = InteractAnalyses)
summary(DN2_model)
## 
## Call:
## lm(formula = DN2 ~ Support * DirectHarm, data = InteractAnalyses)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -2.4464 -1.2569  0.5536  0.7431  2.7431 
## 
## Coefficients:
##                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)        3.256858   0.069076  47.149   <2e-16 ***
## Support            0.104044   0.097810   1.064    0.288    
## DirectHarm         0.082294   0.097688   0.842    0.400    
## Support:DirectHarm 0.003188   0.138238   0.023    0.982    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.383 on 1598 degrees of freedom
##   (5 observations deleted due to missingness)
## Multiple R-squared:  0.002381,   Adjusted R-squared:  0.0005082 
## F-statistic: 1.271 on 3 and 1598 DF,  p-value: 0.2826
DescN_model <- lm(DescN ~ Support*DirectHarm, data = InteractAnalyses)
summary(DescN_model)
## 
## Call:
## lm(formula = DescN ~ Support * DirectHarm, data = InteractAnalyses)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -48.292 -18.292   2.048  17.048  58.584 
## 
## Coefficients:
##                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)          43.414      1.140  38.088  < 2e-16 ***
## Support               4.538      1.614   2.812  0.00498 ** 
## DirectHarm           -1.998      1.612  -1.239  0.21547    
## Support:DirectHarm    2.337      2.281   1.024  0.30577    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 22.83 on 1598 degrees of freedom
##   (5 observations deleted due to missingness)
## Multiple R-squared:  0.01639,    Adjusted R-squared:  0.01454 
## F-statistic: 8.873 on 3 and 1598 DF,  p-value: 7.832e-06
ReduceDrive_model <- lm(ReduceDrive ~ Support*DirectHarm, data = InteractAnalyses)
summary(ReduceDrive_model)
## 
## Call:
## lm(formula = ReduceDrive ~ Support * DirectHarm, data = InteractAnalyses)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -1.5711 -1.5062 -0.5062  1.4289  2.4938 
## 
## Coefficients:
##                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)         2.52120    0.06587  38.278   <2e-16 ***
## Support             0.02380    0.09321   0.255    0.798    
## DirectHarm         -0.01496    0.09315  -0.161    0.872    
## Support:DirectHarm  0.04103    0.13177   0.311    0.756    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.319 on 1599 degrees of freedom
##   (4 observations deleted due to missingness)
## Multiple R-squared:  0.0003481,  Adjusted R-squared:  -0.001527 
## F-statistic: 0.1856 on 3 and 1599 DF,  p-value: 0.9062
EV_model <- lm(EV ~ Support*DirectHarm, data = InteractAnalyses)
summary(EV_model)
## 
## Call:
## lm(formula = EV ~ Support * DirectHarm, data = InteractAnalyses)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -1.5700 -1.4888 -0.4888  1.4300  2.5112 
## 
## Coefficients:
##                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)         2.52369    0.06640  38.006   <2e-16 ***
## Support             0.04631    0.09397   0.493    0.622    
## DirectHarm         -0.03491    0.09391  -0.372    0.710    
## Support:DirectHarm  0.02102    0.13285   0.158    0.874    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.33 on 1599 degrees of freedom
##   (4 observations deleted due to missingness)
## Multiple R-squared:  0.0005573,  Adjusted R-squared:  -0.001318 
## F-statistic: 0.2972 on 3 and 1599 DF,  p-value: 0.8274
Culp1_model <- lm(Culp1 ~ Support*DirectHarm, data = InteractAnalyses)
summary(Culp1_model)
## 
## Call:
## lm(formula = Culp1 ~ Support * DirectHarm, data = InteractAnalyses)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -1.7905 -0.7175  0.2095  1.2095  2.3367 
## 
## Coefficients:
##                     Estimate Std. Error t value Pr(>|t|)    
## (Intercept)         2.667500   0.057940  46.039   <2e-16 ***
## Support             0.050000   0.081939   0.610    0.542    
## DirectHarm         -0.004158   0.081888  -0.051    0.960    
## Support:DirectHarm  0.077182   0.115807   0.666    0.505    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.159 on 1598 degrees of freedom
##   (5 observations deleted due to missingness)
## Multiple R-squared:  0.001962,   Adjusted R-squared:  8.816e-05 
## F-statistic: 1.047 on 3 and 1598 DF,  p-value: 0.3707
Culp2_model <- lm(Culp2 ~ Support*DirectHarm, data = InteractAnalyses)
summary(Culp2_model)
## 
## Call:
## lm(formula = Culp2 ~ Support * DirectHarm, data = InteractAnalyses)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -2.0474 -0.9175  0.0500  1.0500  2.1222 
## 
## Coefficients:
##                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)         2.91750    0.05760  50.655   <2e-16 ***
## Support             0.03250    0.08145   0.399    0.690    
## DirectHarm         -0.03969    0.08140  -0.488    0.626    
## Support:DirectHarm  0.13708    0.11512   1.191    0.234    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.152 on 1598 degrees of freedom
##   (5 observations deleted due to missingness)
## Multiple R-squared:  0.002967,   Adjusted R-squared:  0.001095 
## F-statistic: 1.585 on 3 and 1598 DF,  p-value: 0.1911

Overall Summary

describe(climate_labels)
##                vars    n   mean     sd median trimmed   mad min  max range
## Duration          1 2012 245.35 327.86  177.0  195.48 85.99  16 8868  8852
## IN1               2 2003   2.73   1.08    3.0    2.71  1.48   1    5     4
## IN2               3 2003   2.92   1.12    3.0    2.92  1.48   1    5     4
## DN1               4 2003   4.49   1.11    4.0    4.52  1.48   1    7     6
## DN2               5 2002   3.36   1.38    4.0    3.37  1.48   1    6     5
## DescN             6 2003  43.93  23.48   46.0   44.01 28.17   0  100   100
## ReduceDrive       7 2005   2.55   1.30    2.0    2.44  1.48   1    5     4
## EV                8 2005   2.55   1.33    2.0    2.45  1.48   1    5     4
## Culp1             9 2004   2.74   1.16    3.0    2.71  1.48   1    5     4
## Culp2            10 2004   2.97   1.15    3.0    2.96  1.48   1    5     4
## Age              11 2000  41.13  13.56   38.0   40.10 13.34  18   88    70
## Gender           12 2001   1.52   0.53    2.0    1.50  1.48   1    3     2
## Gender_3_TEXT*   13   26   9.81   4.58   11.5   10.14  3.71   1   15    14
## Q48*             14 1998   3.01   4.05    1.0    2.05  0.00   1   14    13
## Race*            15 2001  21.35   6.75   25.0   22.32  0.00   1   29    28
## Race_7_TEXT*     16   22   8.09   4.30    8.5    8.00  5.19   1   16    15
## Politic          17 2000   3.36   1.71    3.0    3.27  1.48   1    7     6
## Income           18 1995   8.28   3.26    9.0    8.57  2.97   1   12    11
## Education        19 2001   4.55   1.24    5.0    4.66  1.48   1    6     5
## FinalComments*   20  585 198.61  91.20  197.0  201.36 81.54   1  375   374
## Condition*       21 2009   3.00   1.41    3.0    3.00  1.48   1    5     4
##                 skew kurtosis   se
## Duration       14.76   331.70 7.31
## IN1             0.24    -0.65 0.02
## IN2             0.09    -0.77 0.03
## DN1            -0.28     0.45 0.02
## DN2            -0.06    -0.79 0.03
## DescN          -0.06    -0.91 0.52
## ReduceDrive     0.40    -0.98 0.03
## EV              0.34    -1.09 0.03
## Culp1           0.21    -0.79 0.03
## Culp2           0.06    -0.83 0.03
## Age             0.62    -0.28 0.30
## Gender          0.21    -1.34 0.01
## Gender_3_TEXT* -0.62    -1.17 0.90
## Q48*            1.72     1.30 0.09
## Race*          -1.28     0.10 0.15
## Race_7_TEXT*    0.15    -1.12 0.92
## Politic         0.37    -0.83 0.04
## Income         -0.54    -0.96 0.07
## Education      -0.72    -0.53 0.03
## FinalComments* -0.29    -0.52 3.77
## Condition*      0.00    -1.30 0.03

Time taken by participants

summary(climate_labels$Duration)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    16.0   129.0   177.0   245.3   260.0  8868.0
climate_labels$Duration_in_minutes <- climate_labels$Duration / 60
summary(climate_labels$Duration_in_minutes)
##     Min.  1st Qu.   Median     Mean  3rd Qu.     Max. 
##   0.2667   2.1500   2.9500   4.0892   4.3333 147.8000

Outcome summary

describeBy(climate_labels$IN1, climate_labels$Condition)
## 
##  Descriptive statistics by group 
## group: Control
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401 2.55 1.01      2    2.52 1.48   1   5     4 0.35    -0.45 0.05
## ------------------------------------------------------------ 
## group: Direct With Support
##    vars   n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 401 3.03 1.14      3    3.03 1.48   1   5     4 -0.04    -0.83 0.06
## ------------------------------------------------------------ 
## group: Direct Without Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401 2.56 1.04      2    2.53 1.48   1   5     4 0.39    -0.45 0.05
## ------------------------------------------------------------ 
## group: Indirect With Support
##    vars   n mean  sd median trimmed  mad min max range skew kurtosis   se
## X1    1 399 2.95 1.1      3    2.95 1.48   1   5     4 0.07     -0.8 0.05
## ------------------------------------------------------------ 
## group: Indirect Without Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401 2.55 1.01      2    2.52 1.48   1   5     4  0.3    -0.41 0.05
describeBy(climate_labels$IN2, climate_labels$Condition)
## 
##  Descriptive statistics by group 
## group: Control
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401  2.8 1.08      3    2.79 1.48   1   5     4 0.15    -0.61 0.05
## ------------------------------------------------------------ 
## group: Direct With Support
##    vars   n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 401 3.16 1.11      3    3.17 1.48   1   5     4 -0.15    -0.75 0.06
## ------------------------------------------------------------ 
## group: Direct Without Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401 2.79 1.13      3    2.77 1.48   1   5     4 0.19    -0.74 0.06
## ------------------------------------------------------------ 
## group: Indirect With Support
##    vars   n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 399 3.09 1.15      3     3.1 1.48   1   5     4 -0.06    -0.88 0.06
## ------------------------------------------------------------ 
## group: Indirect Without Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401 2.77 1.08      3    2.74 1.48   1   5     4 0.32    -0.59 0.05
describeBy(climate_labels$DN1, climate_labels$Condition)
## 
##  Descriptive statistics by group 
## group: Control
##    vars   n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 401 4.51 0.97      4    4.53 1.48   1   7     6 -0.25     0.92 0.05
## ------------------------------------------------------------ 
## group: Direct With Support
##    vars   n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 401 4.59 1.16      5    4.63 1.48   1   7     6 -0.24     0.21 0.06
## ------------------------------------------------------------ 
## group: Direct Without Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401  4.3 1.15      4    4.32 1.48   1   7     6 -0.2     0.29 0.06
## ------------------------------------------------------------ 
## group: Indirect With Support
##    vars   n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 399 4.53 1.15      5    4.58 1.48   1   7     6 -0.35     0.22 0.06
## ------------------------------------------------------------ 
## group: Indirect Without Support
##    vars   n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 401 4.51 1.07      4    4.55 1.48   1   7     6 -0.33     0.65 0.05
describeBy(climate_labels$DN2, climate_labels$Condition)
## 
##  Descriptive statistics by group 
## group: Control
##    vars   n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 400 3.38 1.38      4     3.4 1.48   1   6     5 -0.12    -0.75 0.07
## ------------------------------------------------------------ 
## group: Direct With Support
##    vars   n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 401 3.45 1.39      4    3.47 1.48   1   6     5 -0.08    -0.82 0.07
## ------------------------------------------------------------ 
## group: Direct Without Support
##    vars   n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 401 3.34 1.44      4    3.35 1.48   1   6     5 -0.11    -0.94 0.07
## ------------------------------------------------------------ 
## group: Indirect With Support
##    vars   n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 399 3.36 1.33      3    3.37 1.48   1   6     5 -0.02    -0.67 0.07
## ------------------------------------------------------------ 
## group: Indirect Without Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401 3.26 1.37      3    3.26 1.48   1   6     5 0.02    -0.77 0.07
describeBy(climate_labels$DescN, climate_labels$Condition)
## 
##  Descriptive statistics by group 
## group: Control
##    vars   n mean    sd median trimmed   mad min max range skew kurtosis   se
## X1    1 401 38.6 24.64     40   37.77 29.65   0 100   100 0.25    -0.95 1.23
## ------------------------------------------------------------ 
## group: Direct With Support
##    vars   n  mean    sd median trimmed   mad min max range  skew kurtosis   se
## X1    1 401 48.29 22.36     51   48.89 22.24   0 100   100 -0.28    -0.76 1.12
## ------------------------------------------------------------ 
## group: Direct Without Support
##    vars   n  mean   sd median trimmed   mad min max range skew kurtosis   se
## X1    1 401 41.42 23.8     40   41.02 29.65   0 100   100 0.09    -0.92 1.19
## ------------------------------------------------------------ 
## group: Indirect With Support
##    vars   n  mean    sd median trimmed   mad min max range  skew kurtosis   se
## X1    1 399 47.95 21.58     50   48.62 22.24   0 100   100 -0.26    -0.65 1.08
## ------------------------------------------------------------ 
## group: Indirect Without Support
##    vars   n  mean    sd median trimmed   mad min max range  skew kurtosis   se
## X1    1 401 43.41 23.49     45   43.58 29.65   0 100   100 -0.02    -0.91 1.17
describeBy(climate_labels$ReduceDrive, climate_labels$Condition)
## 
##  Descriptive statistics by group 
## group: Control
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 402 2.59 1.25      3    2.51 1.48   1   5     4 0.33     -0.9 0.06
## ------------------------------------------------------------ 
## group: Direct With Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401 2.57 1.33      2    2.46 1.48   1   5     4  0.4    -1.01 0.07
## ------------------------------------------------------------ 
## group: Direct Without Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401 2.51 1.36      2    2.38 1.48   1   5     4 0.43     -1.1 0.07
## ------------------------------------------------------------ 
## group: Indirect With Support
##    vars   n mean  sd median trimmed  mad min max range skew kurtosis   se
## X1    1 400 2.54 1.3      2    2.43 1.48   1   5     4 0.45    -0.89 0.07
## ------------------------------------------------------------ 
## group: Indirect Without Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401 2.52 1.28      2    2.42 1.48   1   5     4 0.38       -1 0.06
describeBy(climate_labels$EV, climate_labels$Condition)
## 
##  Descriptive statistics by group 
## group: Control
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 402 2.61 1.31      3    2.52 1.48   1   5     4 0.27    -1.11 0.07
## ------------------------------------------------------------ 
## group: Direct With Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401 2.56 1.37      2    2.45 1.48   1   5     4 0.35    -1.16 0.07
## ------------------------------------------------------------ 
## group: Direct Without Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401 2.49 1.29      2    2.39 1.48   1   5     4 0.35    -1.06 0.06
## ------------------------------------------------------------ 
## group: Indirect With Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 400 2.57 1.31      2    2.47 1.48   1   5     4 0.36    -1.02 0.07
## ------------------------------------------------------------ 
## group: Indirect Without Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401 2.52 1.35      2    2.41 1.48   1   5     4 0.38    -1.13 0.07
describeBy(climate_labels$Culp1, climate_labels$Condition)
## 
##  Descriptive statistics by group 
## group: Control
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 402 2.88 1.16      3    2.86 1.48   1   5     4 0.09    -0.84 0.06
## ------------------------------------------------------------ 
## group: Direct With Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401 2.79 1.14      3    2.78 1.48   1   5     4 0.11    -0.86 0.06
## ------------------------------------------------------------ 
## group: Direct Without Support
##    vars   n mean  sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401 2.66 1.2      2     2.6 1.48   1   5     4 0.34    -0.83 0.06
## ------------------------------------------------------------ 
## group: Indirect With Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 400 2.72 1.14      3    2.69 1.48   1   5     4  0.2    -0.75 0.06
## ------------------------------------------------------------ 
## group: Indirect Without Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 400 2.67 1.15      3    2.61 1.48   1   5     4 0.31    -0.63 0.06
describeBy(climate_labels$Culp2, climate_labels$Condition)
## 
##  Descriptive statistics by group 
## group: Control
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 402 3.03 1.16      3    3.03 1.48   1   5     4 0.06    -0.86 0.06
## ------------------------------------------------------------ 
## group: Direct With Support
##    vars   n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 401 3.05 1.16      3    3.06 1.48   1   5     4 -0.08    -0.82 0.06
## ------------------------------------------------------------ 
## group: Direct Without Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401 2.88 1.17      3    2.86 1.48   1   5     4 0.11    -0.88 0.06
## ------------------------------------------------------------ 
## group: Indirect With Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 400 2.95 1.11      3    2.95 1.48   1   5     4 0.07    -0.77 0.06
## ------------------------------------------------------------ 
## group: Indirect Without Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 400 2.92 1.17      3     2.9 1.48   1   5     4 0.15    -0.83 0.06

Condition-wise summary

#1.control 
control<-filter(climate_labels,Condition == "Control")
describe(control)
##                     vars   n   mean     sd median trimmed   mad  min    max
## Duration               1 402 255.35 479.17 173.50  192.45 80.80 54.0 8868.0
## IN1                    2 401   2.55   1.01   2.00    2.52  1.48  1.0    5.0
## IN2                    3 401   2.80   1.08   3.00    2.79  1.48  1.0    5.0
## DN1                    4 401   4.51   0.97   4.00    4.53  1.48  1.0    7.0
## DN2                    5 400   3.38   1.38   4.00    3.40  1.48  1.0    6.0
## DescN                  6 401  38.60  24.64  40.00   37.77 29.65  0.0  100.0
## ReduceDrive            7 402   2.59   1.25   3.00    2.51  1.48  1.0    5.0
## EV                     8 402   2.61   1.31   3.00    2.52  1.48  1.0    5.0
## Culp1                  9 402   2.88   1.16   3.00    2.86  1.48  1.0    5.0
## Culp2                 10 402   3.03   1.16   3.00    3.03  1.48  1.0    5.0
## Age                   11 400  40.25  12.52  38.50   39.29 14.08 19.0   86.0
## Gender                12 401   1.51   0.52   2.00    1.50  1.48  1.0    3.0
## Gender_3_TEXT*        13   5   3.00   1.58   3.00    3.00  1.48  1.0    5.0
## Q48*                  14 401   2.25   2.59   1.00    1.65  0.00  1.0   10.0
## Race*                 15 401  11.74   4.48  14.00   12.26  0.00  1.0   18.0
## Race_7_TEXT*          16   7   3.14   1.95   3.00    3.14  2.97  1.0    6.0
## Politic               17 400   3.29   1.71   3.00    3.19  1.48  1.0    7.0
## Income                18 398   8.25   3.25   9.00    8.51  4.45  1.0   12.0
## Education             19 401   4.54   1.21   5.00    4.64  1.48  1.0    6.0
## FinalComments*        20 106  43.56  21.46  45.00   44.15 22.98  1.0   81.0
## Condition*            21 402   1.00   0.00   1.00    1.00  0.00  1.0    1.0
## Duration_in_minutes   22 402   4.26   7.99   2.89    3.21  1.35  0.9  147.8
##                      range  skew kurtosis    se
## Duration            8814.0 14.77   257.48 23.90
## IN1                    4.0  0.35    -0.45  0.05
## IN2                    4.0  0.15    -0.61  0.05
## DN1                    6.0 -0.25     0.92  0.05
## DN2                    5.0 -0.12    -0.75  0.07
## DescN                100.0  0.25    -0.95  1.23
## ReduceDrive            4.0  0.33    -0.90  0.06
## EV                     4.0  0.27    -1.11  0.07
## Culp1                  4.0  0.09    -0.84  0.06
## Culp2                  4.0  0.06    -0.86  0.06
## Age                   67.0  0.64    -0.01  0.63
## Gender                 2.0  0.20    -1.38  0.03
## Gender_3_TEXT*         4.0  0.00    -1.91  0.71
## Q48*                   9.0  1.76     1.41  0.13
## Race*                 17.0 -1.14    -0.19  0.22
## Race_7_TEXT*           5.0  0.18    -1.79  0.74
## Politic                6.0  0.42    -0.84  0.09
## Income                11.0 -0.45    -1.14  0.16
## Education              5.0 -0.70    -0.54  0.06
## FinalComments*        80.0 -0.27    -0.93  2.08
## Condition*             0.0   NaN      NaN  0.00
## Duration_in_minutes  146.9 14.77   257.48  0.40
describeBy(climate_labels$Culp1, climate_labels$Condition)
## 
##  Descriptive statistics by group 
## group: Control
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 402 2.88 1.16      3    2.86 1.48   1   5     4 0.09    -0.84 0.06
## ------------------------------------------------------------ 
## group: Direct With Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401 2.79 1.14      3    2.78 1.48   1   5     4 0.11    -0.86 0.06
## ------------------------------------------------------------ 
## group: Direct Without Support
##    vars   n mean  sd median trimmed  mad min max range skew kurtosis   se
## X1    1 401 2.66 1.2      2     2.6 1.48   1   5     4 0.34    -0.83 0.06
## ------------------------------------------------------------ 
## group: Indirect With Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 400 2.72 1.14      3    2.69 1.48   1   5     4  0.2    -0.75 0.06
## ------------------------------------------------------------ 
## group: Indirect Without Support
##    vars   n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 400 2.67 1.15      3    2.61 1.48   1   5     4 0.31    -0.63 0.06
#2. direct harm with support
direct_with_support<-filter(climate_labels,Condition == "Direct With Support")
describe(direct_with_support)
##                     vars   n   mean     sd median trimmed   mad   min     max
## Duration               1 402 232.64 192.29 179.00  194.56 91.92 50.00 1723.00
## IN1                    2 401   3.03   1.14   3.00    3.03  1.48  1.00    5.00
## IN2                    3 401   3.16   1.11   3.00    3.17  1.48  1.00    5.00
## DN1                    4 401   4.59   1.16   5.00    4.63  1.48  1.00    7.00
## DN2                    5 401   3.45   1.39   4.00    3.47  1.48  1.00    6.00
## DescN                  6 401  48.29  22.36  51.00   48.89 22.24  0.00  100.00
## ReduceDrive            7 401   2.57   1.33   2.00    2.46  1.48  1.00    5.00
## EV                     8 401   2.56   1.37   2.00    2.45  1.48  1.00    5.00
## Culp1                  9 401   2.79   1.14   3.00    2.78  1.48  1.00    5.00
## Culp2                 10 401   3.05   1.16   3.00    3.06  1.48  1.00    5.00
## Age                   11 401  41.30  14.18  38.00   40.15 14.83 18.00   88.00
## Gender                12 401   1.51   0.52   1.00    1.50  0.00  1.00    3.00
## Gender_3_TEXT*        13   4   2.25   0.96   2.50    2.25  0.74  1.00    3.00
## Q48*                  14 401   2.34   2.87   1.00    1.61  0.00  1.00   11.00
## Race*                 15 401  12.90   4.06  15.00   13.42  0.00  1.00   19.00
## Race_7_TEXT*          16   2   1.50   0.71   1.50    1.50  0.74  1.00    2.00
## Politic               17 401   3.45   1.70   3.00    3.39  1.48  1.00    7.00
## Income                18 401   8.34   3.23   9.00    8.65  2.97  1.00   12.00
## Education             19 401   4.58   1.26   5.00    4.71  1.48  1.00    6.00
## FinalComments*        20 134  50.06  23.98  49.00   50.44 21.50  1.00   96.00
## Condition*            21 402   1.00   0.00   1.00    1.00  0.00  1.00    1.00
## Duration_in_minutes   22 402   3.88   3.20   2.98    3.24  1.53  0.83   28.72
##                       range  skew kurtosis   se
## Duration            1673.00  3.63    18.93 9.59
## IN1                    4.00 -0.04    -0.83 0.06
## IN2                    4.00 -0.15    -0.75 0.06
## DN1                    6.00 -0.24     0.21 0.06
## DN2                    5.00 -0.08    -0.82 0.07
## DescN                100.00 -0.28    -0.76 1.12
## ReduceDrive            4.00  0.40    -1.01 0.07
## EV                     4.00  0.35    -1.16 0.07
## Culp1                  4.00  0.11    -0.86 0.06
## Culp2                  4.00 -0.08    -0.82 0.06
## Age                   70.00  0.66    -0.29 0.71
## Gender                 2.00  0.19    -1.48 0.03
## Gender_3_TEXT*         2.00 -0.32    -2.08 0.48
## Q48*                  10.00  1.90     2.02 0.14
## Race*                 18.00 -1.24     0.15 0.20
## Race_7_TEXT*           1.00  0.00    -2.75 0.50
## Politic                6.00  0.28    -0.88 0.08
## Income                11.00 -0.58    -0.87 0.16
## Education              5.00 -0.74    -0.53 0.06
## FinalComments*        95.00 -0.17    -0.67 2.07
## Condition*             0.00   NaN      NaN 0.00
## Duration_in_minutes   27.88  3.63    18.93 0.16
#3. indirect with support 
indirect_with_support<-filter(climate_labels,Condition == "Indirect With Support")
describe(indirect_with_support)
##                     vars   n   mean     sd median trimmed   mad   min     max
## Duration               1 402 260.76 412.02 181.00  199.98 90.44 16.00 6998.00
## IN1                    2 399   2.95   1.10   3.00    2.95  1.48  1.00    5.00
## IN2                    3 399   3.09   1.15   3.00    3.10  1.48  1.00    5.00
## DN1                    4 399   4.53   1.15   5.00    4.58  1.48  1.00    7.00
## DN2                    5 399   3.36   1.33   3.00    3.37  1.48  1.00    6.00
## DescN                  6 399  47.95  21.58  50.00   48.62 22.24  0.00  100.00
## ReduceDrive            7 400   2.54   1.30   2.00    2.43  1.48  1.00    5.00
## EV                     8 400   2.57   1.31   2.00    2.47  1.48  1.00    5.00
## Culp1                  9 400   2.72   1.14   3.00    2.69  1.48  1.00    5.00
## Culp2                 10 400   2.95   1.11   3.00    2.95  1.48  1.00    5.00
## Age                   11 398  41.59  13.39  40.00   40.81 14.83 19.00   81.00
## Gender                12 398   1.53   0.55   2.00    1.51  1.48  1.00    3.00
## Gender_3_TEXT*        13   9   4.89   2.57   5.00    4.89  2.97  1.00    8.00
## Q48*                  14 398   2.84   3.37   1.00    2.14  0.00  1.00   11.00
## Race*                 15 398  11.96   3.77  14.00   12.43  0.00  1.00   17.00
## Race_7_TEXT*          16   2   1.50   0.71   1.50    1.50  0.74  1.00    2.00
## Politic               17 398   3.28   1.69   3.00    3.18  1.48  1.00    7.00
## Income                18 398   8.32   3.32   9.00    8.64  2.97  1.00   12.00
## Education             19 398   4.48   1.24   5.00    4.60  1.48  1.00    6.00
## FinalComments*        20 100  36.60  18.14  35.50   36.75 18.53  1.00   71.00
## Condition*            21 402   1.00   0.00   1.00    1.00  0.00  1.00    1.00
## Duration_in_minutes   22 402   4.35   6.87   3.02    3.33  1.51  0.27  116.63
##                       range  skew kurtosis    se
## Duration            6982.00 11.85   179.85 20.55
## IN1                    4.00  0.07    -0.80  0.05
## IN2                    4.00 -0.06    -0.88  0.06
## DN1                    6.00 -0.35     0.22  0.06
## DN2                    5.00 -0.02    -0.67  0.07
## DescN                100.00 -0.26    -0.65  1.08
## ReduceDrive            4.00  0.45    -0.89  0.07
## EV                     4.00  0.36    -1.02  0.07
## Culp1                  4.00  0.20    -0.75  0.06
## Culp2                  4.00  0.07    -0.77  0.06
## Age                   62.00  0.52    -0.38  0.67
## Gender                 2.00  0.34    -1.00  0.03
## Gender_3_TEXT*         7.00 -0.13    -1.68  0.86
## Q48*                  10.00  1.49     0.52  0.17
## Race*                 16.00 -1.16    -0.12  0.19
## Race_7_TEXT*           1.00  0.00    -2.75  0.50
## Politic                6.00  0.47    -0.78  0.08
## Income                11.00 -0.59    -0.91  0.17
## Education              5.00 -0.73    -0.50  0.06
## FinalComments*        70.00 -0.05    -0.81  1.81
## Condition*             0.00   NaN      NaN  0.00
## Duration_in_minutes  116.37 11.85   179.85  0.34
#4. direct without support 
direct_without_support<-filter(climate_labels, Condition == "Direct Without Support")
describe(direct_without_support)
##                     vars   n   mean     sd median trimmed   mad   min     max
## Duration               1 401 235.83 185.79 179.00  199.03 90.44 34.00 1286.00
## IN1                    2 401   2.56   1.04   2.00    2.53  1.48  1.00    5.00
## IN2                    3 401   2.79   1.13   3.00    2.77  1.48  1.00    5.00
## DN1                    4 401   4.30   1.15   4.00    4.32  1.48  1.00    7.00
## DN2                    5 401   3.34   1.44   4.00    3.35  1.48  1.00    6.00
## DescN                  6 401  41.42  23.80  40.00   41.02 29.65  0.00  100.00
## ReduceDrive            7 401   2.51   1.36   2.00    2.38  1.48  1.00    5.00
## EV                     8 401   2.49   1.29   2.00    2.39  1.48  1.00    5.00
## Culp1                  9 401   2.66   1.20   2.00    2.60  1.48  1.00    5.00
## Culp2                 10 401   2.88   1.17   3.00    2.86  1.48  1.00    5.00
## Age                   11 401  41.42  13.43  38.00   40.43 14.83 19.00   82.00
## Gender                12 401   1.51   0.53   1.00    1.49  0.00  1.00    3.00
## Gender_3_TEXT*        13   6   3.33   1.63   3.50    3.33  2.22  1.00    5.00
## Q48*                  14 400   2.06   2.10   1.00    1.57  0.00  1.00    8.00
## Race*                 15 401  11.99   3.82  14.00   12.41  0.00  1.00   17.00
## Race_7_TEXT*          16   7   3.29   1.80   3.00    3.29  1.48  1.00    6.00
## Politic               17 401   3.40   1.74   3.00    3.31  1.48  1.00    7.00
## Income                18 399   8.27   3.29   9.00    8.57  2.97  1.00   12.00
## Education             19 401   4.55   1.24   5.00    4.66  1.48  1.00    6.00
## FinalComments*        20 134  53.81  26.43  53.00   54.49 28.17  1.00  101.00
## Condition*            21 401   1.00   0.00   1.00    1.00  0.00  1.00    1.00
## Duration_in_minutes   22 401   3.93   3.10   2.98    3.32  1.51  0.57   21.43
##                       range  skew kurtosis   se
## Duration            1252.00  2.69     8.97 9.28
## IN1                    4.00  0.39    -0.45 0.05
## IN2                    4.00  0.19    -0.74 0.06
## DN1                    6.00 -0.20     0.29 0.06
## DN2                    5.00 -0.11    -0.94 0.07
## DescN                100.00  0.09    -0.92 1.19
## ReduceDrive            4.00  0.43    -1.10 0.07
## EV                     4.00  0.35    -1.06 0.06
## Culp1                  4.00  0.34    -0.83 0.06
## Culp2                  4.00  0.11    -0.88 0.06
## Age                   63.00  0.58    -0.41 0.67
## Gender                 2.00  0.27    -1.27 0.03
## Gender_3_TEXT*         4.00 -0.21    -1.86 0.67
## Q48*                   7.00  1.75     1.56 0.11
## Race*                 16.00 -1.09    -0.28 0.19
## Race_7_TEXT*           5.00  0.23    -1.69 0.68
## Politic                6.00  0.30    -0.84 0.09
## Income                11.00 -0.59    -0.92 0.16
## Education              5.00 -0.70    -0.61 0.06
## FinalComments*       100.00 -0.24    -0.88 2.28
## Condition*             0.00   NaN      NaN 0.00
## Duration_in_minutes   20.87  2.69     8.97 0.15
#5. indirect without support 
indirect_without_support<-filter(climate_labels, Condition == "Indirect Without Support")
describe(indirect_without_support)
##                     vars   n   mean     sd median trimmed   mad   min     max
## Duration               1 402 233.71 225.79 175.00  191.43 80.06 56.00 2792.00
## IN1                    2 401   2.55   1.01   2.00    2.52  1.48  1.00    5.00
## IN2                    3 401   2.77   1.08   3.00    2.74  1.48  1.00    5.00
## DN1                    4 401   4.51   1.07   4.00    4.55  1.48  1.00    7.00
## DN2                    5 401   3.26   1.37   3.00    3.26  1.48  1.00    6.00
## DescN                  6 401  43.41  23.49  45.00   43.58 29.65  0.00  100.00
## ReduceDrive            7 401   2.52   1.28   2.00    2.42  1.48  1.00    5.00
## EV                     8 401   2.52   1.35   2.00    2.41  1.48  1.00    5.00
## Culp1                  9 400   2.67   1.15   3.00    2.61  1.48  1.00    5.00
## Culp2                 10 400   2.92   1.17   3.00    2.90  1.48  1.00    5.00
## Age                   11 400  41.08  14.21  38.00   39.93 13.34 18.00   82.00
## Gender                12 400   1.53   0.51   2.00    1.53  0.00  1.00    3.00
## Gender_3_TEXT*        13   2   1.50   0.71   1.50    1.50  0.74  1.00    2.00
## Q48*                  14 398   2.60   3.32   1.00    1.80  0.00  1.00   12.00
## Race*                 15 400   8.36   3.29  10.00    8.67  0.00  1.00   14.00
## Race_7_TEXT*          16   4   2.50   1.29   2.50    2.50  1.48  1.00    4.00
## Politic               17 400   3.36   1.74   3.00    3.27  1.48  1.00    7.00
## Income                18 399   8.22   3.21   9.00    8.48  2.97  1.00   12.00
## Education             19 400   4.58   1.24   5.00    4.70  1.48  1.00    6.00
## FinalComments*        20 111  42.86  22.31  39.00   42.71 23.72  1.00   86.00
## Condition*            21 402   1.00   0.00   1.00    1.00  0.00  1.00    1.00
## Duration_in_minutes   22 402   3.90   3.76   2.92    3.19  1.33  0.93   46.53
##                      range  skew kurtosis    se
## Duration            2736.0  5.55    46.78 11.26
## IN1                    4.0  0.30    -0.41  0.05
## IN2                    4.0  0.32    -0.59  0.05
## DN1                    6.0 -0.33     0.65  0.05
## DN2                    5.0  0.02    -0.77  0.07
## DescN                100.0 -0.02    -0.91  1.17
## ReduceDrive            4.0  0.38    -1.00  0.06
## EV                     4.0  0.38    -1.13  0.07
## Culp1                  4.0  0.31    -0.63  0.06
## Culp2                  4.0  0.15    -0.83  0.06
## Age                   64.0  0.67    -0.41  0.71
## Gender                 2.0  0.00    -1.72  0.03
## Gender_3_TEXT*         1.0  0.00    -2.75  0.50
## Q48*                  11.0  1.80     1.61  0.17
## Race*                 13.0 -0.96    -0.31  0.16
## Race_7_TEXT*           3.0  0.00    -2.08  0.65
## Politic                6.0  0.40    -0.84  0.09
## Income                11.0 -0.49    -1.00  0.16
## Education              5.0 -0.75    -0.51  0.06
## FinalComments*        85.0  0.09    -0.84  2.12
## Condition*             0.0   NaN      NaN  0.00
## Duration_in_minutes   45.6  5.55    46.78  0.19

Linear models

climate_labels$Condition <- factor(climate_labels$Condition, 
                                   levels = c("Control", 
                                              "Direct With Support", 
                                              "Indirect With Support", 
                                              "Direct Without Support", 
                                              "Indirect Without Support"))

# Linear models
# here is the outcome for the measure: IN1
# to what extent if at all would you think people in your community disapprove of using fossil fuels for personal vehicles?
describe(climate_labels$IN1)
##    vars    n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 2003 2.73 1.08      3    2.71 1.48   1   5     4 0.24    -0.65 0.02
tapply(climate_labels$IN1, climate_labels$Condition, summary)
## $Control
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   2.000   2.000   2.551   3.000   5.000       1 
## 
## $`Direct With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   2.000   3.000   3.032   4.000   5.000       1 
## 
## $`Indirect With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   2.000   3.000   2.955   4.000   5.000       3 
## 
## $`Direct Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   2.000   2.000   2.561   3.000   5.000 
## 
## $`Indirect Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   2.000   2.000   2.546   3.000   5.000       1
model_in1 <- lm(IN1 ~ Condition, data = climate_labels)
summary(model_in1)
## 
## Call:
## lm(formula = IN1 ~ Condition, data = climate_labels)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -2.03242 -0.56110 -0.03242  0.45387  2.45387 
## 
## Coefficients:
##                                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                        2.551122   0.052936  48.193  < 2e-16 ***
## ConditionDirect With Support       0.481297   0.074863   6.429 1.60e-10 ***
## ConditionIndirect With Support     0.403765   0.074956   5.387 8.02e-08 ***
## ConditionDirect Without Support    0.009975   0.074863   0.133    0.894    
## ConditionIndirect Without Support -0.004988   0.074863  -0.067    0.947    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.06 on 1998 degrees of freedom
##   (9 observations deleted due to missingness)
## Multiple R-squared:  0.04046,    Adjusted R-squared:  0.03854 
## F-statistic: 21.06 on 4 and 1998 DF,  p-value: < 2.2e-16
# here is the outcome for the measure: IN2 
# to what extent would you think people in your community feel that people should transition away from using fossil fuels?
describe(climate_labels$IN2)
##    vars    n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 2003 2.92 1.12      3    2.92 1.48   1   5     4 0.09    -0.77 0.03
tapply(climate_labels$IN2, climate_labels$Condition, summary)
## $Control
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   2.000   3.000   2.798   4.000   5.000       1 
## 
## $`Direct With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    1.00    2.00    3.00    3.16    4.00    5.00       1 
## 
## $`Indirect With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   2.000   3.000   3.093   4.000   5.000       3 
## 
## $`Direct Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   2.000   3.000   2.793   4.000   5.000 
## 
## $`Indirect Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   2.000   3.000   2.766   3.000   5.000       1
model_in2 <- lm(IN2 ~ Condition, data = climate_labels)
summary(model_in2)
## 
## Call:
## lm(formula = IN2 ~ Condition, data = climate_labels)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -2.1596 -0.7980  0.2020  0.9073  2.2344 
## 
## Coefficients:
##                                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                        2.798005   0.055431  50.477  < 2e-16 ***
## ConditionDirect With Support       0.361596   0.078392   4.613 4.23e-06 ***
## ConditionIndirect With Support     0.294727   0.078490   3.755 0.000178 ***
## ConditionDirect Without Support   -0.004988   0.078392  -0.064 0.949277    
## ConditionIndirect Without Support -0.032419   0.078392  -0.414 0.679247    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.11 on 1998 degrees of freedom
##   (9 observations deleted due to missingness)
## Multiple R-squared:  0.0226, Adjusted R-squared:  0.02064 
## F-statistic: 11.55 on 4 and 1998 DF,  p-value: 2.857e-09
# here is the outcome for the measure: DN1
# would you think the number of people in your community who disapprove of using fossil fuels for personal vehicles will increase, decrease or stay the same in the near future?
describe(climate_labels$DN1)
##    vars    n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 2003 4.49 1.11      4    4.52 1.48   1   7     6 -0.28     0.45 0.02
tapply(climate_labels$DN1, climate_labels$Condition, summary)
## $Control
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   4.000   4.000   4.506   5.000   7.000       1 
## 
## $`Direct With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   4.000   5.000   4.591   5.000   7.000       1 
## 
## $`Indirect With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   4.000   5.000   4.529   5.000   7.000       3 
## 
## $`Direct Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   4.000   4.000   4.302   5.000   7.000 
## 
## $`Indirect Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   4.000   4.000   4.509   5.000   7.000       1
model_dn1 <- lm(DN1 ~ Condition, data = climate_labels)
summary(model_dn1)
## 
## Call:
## lm(formula = DN1 ~ Condition, data = climate_labels)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.5910 -0.5288 -0.3017  0.4938  2.6983 
## 
## Coefficients:
##                                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                        4.506234   0.055064  81.836  < 2e-16 ***
## ConditionDirect With Support       0.084788   0.077873   1.089  0.27637    
## ConditionIndirect With Support     0.022588   0.077970   0.290  0.77208    
## ConditionDirect Without Support   -0.204489   0.077873  -2.626  0.00871 ** 
## ConditionIndirect Without Support  0.002494   0.077873   0.032  0.97446    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.103 on 1998 degrees of freedom
##   (9 observations deleted due to missingness)
## Multiple R-squared:  0.007816,   Adjusted R-squared:  0.005829 
## F-statistic: 3.935 on 4 and 1998 DF,  p-value: 0.003472
# here is the outcome for the measure: DN2
# how likely or unlikely do you think using fossil fuels for personal vehicles will become “a thing of the past” over the next 10-15 years?
describe(climate_labels$DN2)
##    vars    n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 2002 3.36 1.38      4    3.37 1.48   1   6     5 -0.06    -0.79 0.03
tapply(climate_labels$DN2, climate_labels$Condition, summary)
## $Control
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    1.00    2.00    4.00    3.38    4.00    6.00       2 
## 
## $`Direct With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   2.000   4.000   3.446   4.000   6.000       1 
## 
## $`Indirect With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   2.000   3.000   3.361   4.000   6.000       3 
## 
## $`Direct Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   2.000   4.000   3.339   4.000   6.000 
## 
## $`Indirect Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   2.000   3.000   3.257   4.000   6.000       1
model_dn2 <- lm(DN2 ~ Condition, data = climate_labels)
summary(model_dn2)
## 
## Call:
## lm(formula = DN2 ~ Condition, data = climate_labels)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -2.4464 -1.3392  0.5536  0.7431  2.7431 
## 
## Coefficients:
##                                   Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                        3.38000    0.06913  48.891   <2e-16 ***
## ConditionDirect With Support       0.06638    0.09771   0.679    0.497    
## ConditionIndirect With Support    -0.01910    0.09783  -0.195    0.845    
## ConditionDirect Without Support   -0.04085    0.09771  -0.418    0.676    
## ConditionIndirect Without Support -0.12314    0.09771  -1.260    0.208    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.383 on 1997 degrees of freedom
##   (10 observations deleted due to missingness)
## Multiple R-squared:  0.001979,   Adjusted R-squared:  -2.005e-05 
## F-statistic:  0.99 on 4 and 1997 DF,  p-value: 0.4117
# here is the outcome for the measure: DescN
# what percent of voters from your municipality would you think believe that the use of fossil fuels causes childhood asthma in your area and harms future generations due to climate change?
describe(climate_labels$DescN)
##    vars    n  mean    sd median trimmed   mad min max range  skew kurtosis   se
## X1    1 2003 43.93 23.48     46   44.01 28.17   0 100   100 -0.06    -0.91 0.52
tapply(climate_labels$DescN, climate_labels$Condition, summary)
## $Control
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##     0.0    20.0    40.0    38.6    60.0   100.0       1 
## 
## $`Direct With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    0.00   30.00   51.00   48.29   65.00  100.00       1 
## 
## $`Indirect With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    0.00   30.00   50.00   47.95   65.00  100.00       3 
## 
## $`Direct Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    0.00   20.00   40.00   41.42   60.00  100.00 
## 
## $`Indirect Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    0.00   25.00   45.00   43.41   60.00  100.00       1
model_descn <- lm(DescN ~ Condition, data = climate_labels)
summary(model_descn)
## 
## Call:
## lm(formula = DescN ~ Condition, data = climate_labels)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -48.292 -18.603   1.708  17.048  61.397 
## 
## Coefficients:
##                                   Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                         38.603      1.159  33.319  < 2e-16 ***
## ConditionDirect With Support         9.688      1.638   5.913 3.94e-09 ***
## ConditionIndirect With Support       9.349      1.641   5.699 1.39e-08 ***
## ConditionDirect Without Support      2.813      1.638   1.717  0.08617 .  
## ConditionIndirect Without Support    4.810      1.638   2.936  0.00336 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 23.2 on 1998 degrees of freedom
##   (9 observations deleted due to missingness)
## Multiple R-squared:  0.02546,    Adjusted R-squared:  0.02351 
## F-statistic: 13.05 on 4 and 1998 DF,  p-value: 1.703e-10
# here is the outcome for the measure: ReduceDrive
# to what extent if at all would you like to reduce your use of fossil fuels for driving?
describe(climate_labels$ReduceDrive)
##    vars    n mean  sd median trimmed  mad min max range skew kurtosis   se
## X1    1 2005 2.55 1.3      2    2.44 1.48   1   5     4  0.4    -0.98 0.03
tapply(climate_labels$ReduceDrive, climate_labels$Condition, summary)
## $Control
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   2.000   3.000   2.592   3.000   5.000 
## 
## $`Direct With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   1.000   2.000   2.571   4.000   5.000       1 
## 
## $`Indirect With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   1.000   2.000   2.545   3.000   5.000       2 
## 
## $`Direct Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   1.000   2.000   2.506   4.000   5.000 
## 
## $`Indirect Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   1.000   2.000   2.521   4.000   5.000       1
model_reducedrive<- lm(ReduceDrive ~ Condition, data = climate_labels)
summary(model_reducedrive)
## 
## Call:
## lm(formula = ReduceDrive ~ Condition, data = climate_labels)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -1.5920 -1.5062 -0.5062  1.4080  2.4938 
## 
## Coefficients:
##                                   Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                        2.59204    0.06511  39.808   <2e-16 ***
## ConditionDirect With Support      -0.02097    0.09214  -0.228    0.820    
## ConditionIndirect With Support    -0.04704    0.09220  -0.510    0.610    
## ConditionDirect Without Support   -0.08581    0.09214  -0.931    0.352    
## ConditionIndirect Without Support -0.07084    0.09214  -0.769    0.442    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.306 on 2000 degrees of freedom
##   (7 observations deleted due to missingness)
## Multiple R-squared:  0.0005813,  Adjusted R-squared:  -0.001418 
## F-statistic: 0.2908 on 4 and 2000 DF,  p-value: 0.8841
# here is the outcome for the measure: EV
# to what extent if at all would you be interested in switching to a fully electric vehicle?
describe(climate_labels$EV)
##    vars    n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 2005 2.55 1.33      2    2.45 1.48   1   5     4 0.34    -1.09 0.03
tapply(climate_labels$EV, climate_labels$Condition, summary)
## $Control
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   1.000   3.000   2.612   4.000   5.000 
## 
## $`Direct With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   1.000   2.000   2.556   4.000   5.000       1 
## 
## $`Indirect With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    1.00    1.00    2.00    2.57    4.00    5.00       2 
## 
## $`Direct Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   1.000   2.000   2.489   3.000   5.000 
## 
## $`Indirect Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   1.000   2.000   2.524   4.000   5.000       1
model_ev<- lm(EV ~ Condition, data = climate_labels)
summary(model_ev)
## 
## Call:
## lm(formula = EV ~ Condition, data = climate_labels)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -1.6119 -1.4888 -0.4888  1.3881  2.5112 
## 
## Coefficients:
##                                   Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                        2.61194    0.06616  39.482   <2e-16 ***
## ConditionDirect With Support      -0.05583    0.09362  -0.596    0.551    
## ConditionIndirect With Support    -0.04194    0.09367  -0.448    0.654    
## ConditionDirect Without Support   -0.12316    0.09362  -1.316    0.188    
## ConditionIndirect Without Support -0.08825    0.09362  -0.943    0.346    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.326 on 2000 degrees of freedom
##   (7 observations deleted due to missingness)
## Multiple R-squared:  0.0009931,  Adjusted R-squared:  -0.001005 
## F-statistic: 0.497 on 4 and 2000 DF,  p-value: 0.7379
# here is the outcome for the measure: Culp1
# to what extent if at all would you think drivers (including yourself) are responsible for any harms that come from using fossil fuels?
describe(climate_labels$Culp1)
##    vars    n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 2004 2.74 1.16      3    2.71 1.48   1   5     4 0.21    -0.79 0.03
tapply(climate_labels$Culp1, climate_labels$Condition, summary)
## $Control
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   2.000   3.000   2.876   4.000   5.000 
## 
## $`Direct With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   2.000   3.000   2.791   4.000   5.000       1 
## 
## $`Indirect With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   2.000   3.000   2.717   4.000   5.000       2 
## 
## $`Direct Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   2.000   2.000   2.663   4.000   5.000 
## 
## $`Indirect Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   2.000   3.000   2.667   3.000   5.000       2
model_culp1<- lm(Culp1 ~ Condition, data = climate_labels)
summary(model_culp1)
## 
## Call:
## lm(formula = Culp1 ~ Condition, data = climate_labels)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -1.8756 -0.7905  0.1244  1.1244  2.3367 
## 
## Coefficients:
##                                   Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                        2.87562    0.05777  49.780  < 2e-16 ***
## ConditionDirect With Support      -0.08510    0.08175  -1.041  0.29799    
## ConditionIndirect With Support    -0.15812    0.08180  -1.933  0.05336 .  
## ConditionDirect Without Support   -0.21228    0.08175  -2.597  0.00948 ** 
## ConditionIndirect Without Support -0.20812    0.08180  -2.544  0.01102 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.158 on 1999 degrees of freedom
##   (8 observations deleted due to missingness)
## Multiple R-squared:  0.004847,   Adjusted R-squared:  0.002856 
## F-statistic: 2.434 on 4 and 1999 DF,  p-value: 0.04546
# here is the outcome for the measure: Culp2 
# to what extent if at all would you think driving a fossil fuel vehicle harms others?
describe(climate_labels$Culp2)
##    vars    n mean   sd median trimmed  mad min max range skew kurtosis   se
## X1    1 2004 2.97 1.15      3    2.96 1.48   1   5     4 0.06    -0.83 0.03
tapply(climate_labels$Culp2, climate_labels$Condition, summary)
## $Control
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   2.000   3.000   3.035   4.000   5.000 
## 
## $`Direct With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   2.000   3.000   3.047   4.000   5.000       1 
## 
## $`Indirect With Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    1.00    2.00    3.00    2.95    4.00    5.00       2 
## 
## $`Direct Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   2.000   3.000   2.878   4.000   5.000 
## 
## $`Indirect Without Support`
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.000   2.000   3.000   2.917   4.000   5.000       2
model_culp2<- lm(Culp2 ~ Condition, data = climate_labels)
summary(model_culp2)
## 
## Call:
## lm(formula = Culp2 ~ Condition, data = climate_labels)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -2.0474 -0.9500  0.0500  0.9652  2.1222 
## 
## Coefficients:
##                                   Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                        3.03483    0.05751  52.770   <2e-16 ***
## ConditionDirect With Support       0.01256    0.08138   0.154   0.8774    
## ConditionIndirect With Support    -0.08483    0.08143  -1.042   0.2977    
## ConditionDirect Without Support   -0.15702    0.08138  -1.929   0.0538 .  
## ConditionIndirect Without Support -0.11733    0.08143  -1.441   0.1498    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.153 on 1999 degrees of freedom
##   (8 observations deleted due to missingness)
## Multiple R-squared:  0.003271,   Adjusted R-squared:  0.001276 
## F-statistic:  1.64 on 4 and 1999 DF,  p-value: 0.1615

Pairwise comparisons

#here are the pair-wise comparisons for IN1
pairwise_in1 <- emmeans(model_in1, pairwise ~ Condition)
summary(pairwise_in1)
## $emmeans
##  Condition                emmean     SE   df lower.CL upper.CL
##  Control                    2.55 0.0529 1998     2.45     2.65
##  Direct With Support        3.03 0.0529 1998     2.93     3.14
##  Indirect With Support      2.95 0.0531 1998     2.85     3.06
##  Direct Without Support     2.56 0.0529 1998     2.46     2.66
##  Indirect Without Support   2.55 0.0529 1998     2.44     2.65
## 
## Confidence level used: 0.95 
## 
## $contrasts
##  contrast                                          estimate     SE   df t.ratio
##  Control - Direct With Support                     -0.48130 0.0749 1998  -6.429
##  Control - Indirect With Support                   -0.40376 0.0750 1998  -5.387
##  Control - Direct Without Support                  -0.00998 0.0749 1998  -0.133
##  Control - Indirect Without Support                 0.00499 0.0749 1998   0.067
##  Direct With Support - Indirect With Support        0.07753 0.0750 1998   1.034
##  Direct With Support - Direct Without Support       0.47132 0.0749 1998   6.296
##  Direct With Support - Indirect Without Support     0.48628 0.0749 1998   6.496
##  Indirect With Support - Direct Without Support     0.39379 0.0750 1998   5.254
##  Indirect With Support - Indirect Without Support   0.40875 0.0750 1998   5.453
##  Direct Without Support - Indirect Without Support  0.01496 0.0749 1998   0.200
##  p.value
##   <.0001
##   <.0001
##   0.9999
##   1.0000
##   0.8394
##   <.0001
##   <.0001
##   <.0001
##   <.0001
##   0.9996
## 
## P value adjustment: tukey method for comparing a family of 5 estimates
#here are the pair-wise comparisons for IN2
pairwise_in2 <- emmeans(model_in2, pairwise ~ Condition)
summary(pairwise_in2)
## $emmeans
##  Condition                emmean     SE   df lower.CL upper.CL
##  Control                    2.80 0.0554 1998     2.69     2.91
##  Direct With Support        3.16 0.0554 1998     3.05     3.27
##  Indirect With Support      3.09 0.0556 1998     2.98     3.20
##  Direct Without Support     2.79 0.0554 1998     2.68     2.90
##  Indirect Without Support   2.77 0.0554 1998     2.66     2.87
## 
## Confidence level used: 0.95 
## 
## $contrasts
##  contrast                                          estimate     SE   df t.ratio
##  Control - Direct With Support                     -0.36160 0.0784 1998  -4.613
##  Control - Indirect With Support                   -0.29473 0.0785 1998  -3.755
##  Control - Direct Without Support                   0.00499 0.0784 1998   0.064
##  Control - Indirect Without Support                 0.03242 0.0784 1998   0.414
##  Direct With Support - Indirect With Support        0.06687 0.0785 1998   0.852
##  Direct With Support - Direct Without Support       0.36658 0.0784 1998   4.676
##  Direct With Support - Indirect Without Support     0.39402 0.0784 1998   5.026
##  Indirect With Support - Direct Without Support     0.29971 0.0785 1998   3.819
##  Indirect With Support - Indirect Without Support   0.32715 0.0785 1998   4.168
##  Direct Without Support - Indirect Without Support  0.02743 0.0784 1998   0.350
##  p.value
##   <.0001
##   0.0017
##   1.0000
##   0.9939
##   0.9141
##   <.0001
##   <.0001
##   0.0013
##   0.0003
##   0.9968
## 
## P value adjustment: tukey method for comparing a family of 5 estimates
#here are the pair-wise comparisons for DN1
pairwise_dn1 <- emmeans(model_dn1, pairwise ~ Condition)
summary(pairwise_dn1)
## $emmeans
##  Condition                emmean     SE   df lower.CL upper.CL
##  Control                    4.51 0.0551 1998     4.40     4.61
##  Direct With Support        4.59 0.0551 1998     4.48     4.70
##  Indirect With Support      4.53 0.0552 1998     4.42     4.64
##  Direct Without Support     4.30 0.0551 1998     4.19     4.41
##  Indirect Without Support   4.51 0.0551 1998     4.40     4.62
## 
## Confidence level used: 0.95 
## 
## $contrasts
##  contrast                                          estimate     SE   df t.ratio
##  Control - Direct With Support                     -0.08479 0.0779 1998  -1.089
##  Control - Indirect With Support                   -0.02259 0.0780 1998  -0.290
##  Control - Direct Without Support                   0.20449 0.0779 1998   2.626
##  Control - Indirect Without Support                -0.00249 0.0779 1998  -0.032
##  Direct With Support - Indirect With Support        0.06220 0.0780 1998   0.798
##  Direct With Support - Direct Without Support       0.28928 0.0779 1998   3.715
##  Direct With Support - Indirect Without Support     0.08229 0.0779 1998   1.057
##  Indirect With Support - Direct Without Support     0.22708 0.0780 1998   2.912
##  Indirect With Support - Indirect Without Support   0.02009 0.0780 1998   0.258
##  Direct Without Support - Indirect Without Support -0.20698 0.0779 1998  -2.658
##  p.value
##   0.8124
##   0.9985
##   0.0661
##   1.0000
##   0.9313
##   0.0020
##   0.8286
##   0.0298
##   0.9990
##   0.0608
## 
## P value adjustment: tukey method for comparing a family of 5 estimates
#here are the pair-wise comparisons for DN2
pairwise_dn2 <- emmeans(model_dn2, pairwise ~ Condition)
summary(pairwise_dn2)
## $emmeans
##  Condition                emmean     SE   df lower.CL upper.CL
##  Control                    3.38 0.0691 1997     3.24     3.52
##  Direct With Support        3.45 0.0690 1997     3.31     3.58
##  Indirect With Support      3.36 0.0692 1997     3.23     3.50
##  Direct Without Support     3.34 0.0690 1997     3.20     3.47
##  Indirect Without Support   3.26 0.0690 1997     3.12     3.39
## 
## Confidence level used: 0.95 
## 
## $contrasts
##  contrast                                          estimate     SE   df t.ratio
##  Control - Direct With Support                      -0.0664 0.0977 1997  -0.679
##  Control - Indirect With Support                     0.0191 0.0978 1997   0.195
##  Control - Direct Without Support                    0.0408 0.0977 1997   0.418
##  Control - Indirect Without Support                  0.1231 0.0977 1997   1.260
##  Direct With Support - Indirect With Support         0.0855 0.0978 1997   0.874
##  Direct With Support - Direct Without Support        0.1072 0.0976 1997   1.098
##  Direct With Support - Indirect Without Support      0.1895 0.0976 1997   1.941
##  Indirect With Support - Direct Without Support      0.0218 0.0978 1997   0.222
##  Indirect With Support - Indirect Without Support    0.1040 0.0978 1997   1.064
##  Direct Without Support - Indirect Without Support   0.0823 0.0976 1997   0.843
##  p.value
##   0.9609
##   0.9997
##   0.9936
##   0.7156
##   0.9064
##   0.8076
##   0.2960
##   0.9995
##   0.8249
##   0.9172
## 
## P value adjustment: tukey method for comparing a family of 5 estimates
#here are the pair-wise comparisons for DescN
pairwise_descn <- emmeans(model_descn, pairwise ~ Condition)
summary(pairwise_descn)
## $emmeans
##  Condition                emmean   SE   df lower.CL upper.CL
##  Control                    38.6 1.16 1998     36.3     40.9
##  Direct With Support        48.3 1.16 1998     46.0     50.6
##  Indirect With Support      48.0 1.16 1998     45.7     50.2
##  Direct Without Support     41.4 1.16 1998     39.1     43.7
##  Indirect Without Support   43.4 1.16 1998     41.1     45.7
## 
## Confidence level used: 0.95 
## 
## $contrasts
##  contrast                                          estimate   SE   df t.ratio
##  Control - Direct With Support                       -9.688 1.64 1998  -5.913
##  Control - Indirect With Support                     -9.349 1.64 1998  -5.699
##  Control - Direct Without Support                    -2.813 1.64 1998  -1.717
##  Control - Indirect Without Support                  -4.810 1.64 1998  -2.936
##  Direct With Support - Indirect With Support          0.339 1.64 1998   0.207
##  Direct With Support - Direct Without Support         6.875 1.64 1998   4.196
##  Direct With Support - Indirect Without Support       4.878 1.64 1998   2.977
##  Indirect With Support - Direct Without Support       6.536 1.64 1998   3.984
##  Indirect With Support - Indirect Without Support     4.538 1.64 1998   2.766
##  Direct Without Support - Indirect Without Support   -1.998 1.64 1998  -1.219
##  p.value
##   <.0001
##   <.0001
##   0.4237
##   0.0278
##   0.9996
##   0.0003
##   0.0246
##   0.0007
##   0.0453
##   0.7403
## 
## P value adjustment: tukey method for comparing a family of 5 estimates
#here are the pair-wise comparisons for reducedrive
pairwise_reducedrive <- emmeans(model_reducedrive, pairwise ~ Condition)
summary(pairwise_reducedrive)
## $emmeans
##  Condition                emmean     SE   df lower.CL upper.CL
##  Control                    2.59 0.0651 2000     2.46     2.72
##  Direct With Support        2.57 0.0652 2000     2.44     2.70
##  Indirect With Support      2.54 0.0653 2000     2.42     2.67
##  Direct Without Support     2.51 0.0652 2000     2.38     2.63
##  Indirect Without Support   2.52 0.0652 2000     2.39     2.65
## 
## Confidence level used: 0.95 
## 
## $contrasts
##  contrast                                          estimate     SE   df t.ratio
##  Control - Direct With Support                       0.0210 0.0921 2000   0.228
##  Control - Indirect With Support                     0.0470 0.0922 2000   0.510
##  Control - Direct Without Support                    0.0858 0.0921 2000   0.931
##  Control - Indirect Without Support                  0.0708 0.0921 2000   0.769
##  Direct With Support - Indirect With Support         0.0261 0.0923 2000   0.283
##  Direct With Support - Direct Without Support        0.0648 0.0922 2000   0.703
##  Direct With Support - Indirect Without Support      0.0499 0.0922 2000   0.541
##  Indirect With Support - Direct Without Support      0.0388 0.0923 2000   0.420
##  Indirect With Support - Indirect Without Support    0.0238 0.0923 2000   0.258
##  Direct Without Support - Indirect Without Support  -0.0150 0.0922 2000  -0.162
##  p.value
##   0.9994
##   0.9864
##   0.8848
##   0.9395
##   0.9986
##   0.9558
##   0.9830
##   0.9935
##   0.9990
##   0.9998
## 
## P value adjustment: tukey method for comparing a family of 5 estimates
#here are the pair-wise comparisons for ev
pairwise_ev <- emmeans(model_ev, pairwise ~ Condition)
summary(pairwise_ev)
## $emmeans
##  Condition                emmean     SE   df lower.CL upper.CL
##  Control                    2.61 0.0662 2000     2.48     2.74
##  Direct With Support        2.56 0.0662 2000     2.43     2.69
##  Indirect With Support      2.57 0.0663 2000     2.44     2.70
##  Direct Without Support     2.49 0.0662 2000     2.36     2.62
##  Indirect Without Support   2.52 0.0662 2000     2.39     2.65
## 
## Confidence level used: 0.95 
## 
## $contrasts
##  contrast                                          estimate     SE   df t.ratio
##  Control - Direct With Support                       0.0558 0.0936 2000   0.596
##  Control - Indirect With Support                     0.0419 0.0937 2000   0.448
##  Control - Direct Without Support                    0.1232 0.0936 2000   1.316
##  Control - Indirect Without Support                  0.0882 0.0936 2000   0.943
##  Direct With Support - Indirect With Support        -0.0139 0.0937 2000  -0.148
##  Direct With Support - Direct Without Support        0.0673 0.0937 2000   0.719
##  Direct With Support - Indirect Without Support      0.0324 0.0937 2000   0.346
##  Indirect With Support - Direct Without Support      0.0812 0.0937 2000   0.867
##  Indirect With Support - Indirect Without Support    0.0463 0.0937 2000   0.494
##  Direct Without Support - Indirect Without Support  -0.0349 0.0937 2000  -0.373
##  p.value
##   0.9757
##   0.9917
##   0.6815
##   0.8802
##   0.9999
##   0.9522
##   0.9969
##   0.9091
##   0.9879
##   0.9959
## 
## P value adjustment: tukey method for comparing a family of 5 estimates
#here are the pair-wise comparisons for Culp1
pairwise_culp1 <- emmeans(model_culp1, pairwise ~ Condition)
summary(pairwise_culp1)
## $emmeans
##  Condition                emmean     SE   df lower.CL upper.CL
##  Control                    2.88 0.0578 1999     2.76     2.99
##  Direct With Support        2.79 0.0578 1999     2.68     2.90
##  Indirect With Support      2.72 0.0579 1999     2.60     2.83
##  Direct Without Support     2.66 0.0578 1999     2.55     2.78
##  Indirect Without Support   2.67 0.0579 1999     2.55     2.78
## 
## Confidence level used: 0.95 
## 
## $contrasts
##  contrast                                          estimate     SE   df t.ratio
##  Control - Direct With Support                      0.08510 0.0817 1999   1.041
##  Control - Indirect With Support                    0.15812 0.0818 1999   1.933
##  Control - Direct Without Support                   0.21228 0.0817 1999   2.597
##  Control - Indirect Without Support                 0.20812 0.0818 1999   2.544
##  Direct With Support - Indirect With Support        0.07302 0.0818 1999   0.892
##  Direct With Support - Direct Without Support       0.12718 0.0818 1999   1.555
##  Direct With Support - Indirect Without Support     0.12302 0.0818 1999   1.503
##  Indirect With Support - Direct Without Support     0.05416 0.0818 1999   0.662
##  Indirect With Support - Indirect Without Support   0.05000 0.0819 1999   0.611
##  Direct Without Support - Indirect Without Support -0.00416 0.0818 1999  -0.051
##  p.value
##   0.8362
##   0.3000
##   0.0713
##   0.0815
##   0.8999
##   0.5268
##   0.5606
##   0.9645
##   0.9735
##   1.0000
## 
## P value adjustment: tukey method for comparing a family of 5 estimates
#here are the pair-wise comparisons for Culp2
pairwise_culp2 <- emmeans(model_culp2, pairwise ~ Condition)
summary(pairwise_culp2)
## $emmeans
##  Condition                emmean     SE   df lower.CL upper.CL
##  Control                    3.03 0.0575 1999     2.92     3.15
##  Direct With Support        3.05 0.0576 1999     2.93     3.16
##  Indirect With Support      2.95 0.0577 1999     2.84     3.06
##  Direct Without Support     2.88 0.0576 1999     2.76     2.99
##  Indirect Without Support   2.92 0.0577 1999     2.80     3.03
## 
## Confidence level used: 0.95 
## 
## $contrasts
##  contrast                                          estimate     SE   df t.ratio
##  Control - Direct With Support                      -0.0126 0.0814 1999  -0.154
##  Control - Indirect With Support                     0.0848 0.0814 1999   1.042
##  Control - Direct Without Support                    0.1570 0.0814 1999   1.929
##  Control - Indirect Without Support                  0.1173 0.0814 1999   1.441
##  Direct With Support - Indirect With Support         0.0974 0.0815 1999   1.195
##  Direct With Support - Direct Without Support        0.1696 0.0814 1999   2.082
##  Direct With Support - Indirect Without Support      0.1299 0.0815 1999   1.594
##  Indirect With Support - Direct Without Support      0.0722 0.0815 1999   0.886
##  Indirect With Support - Indirect Without Support    0.0325 0.0815 1999   0.399
##  Direct Without Support - Indirect Without Support  -0.0397 0.0815 1999  -0.487
##  p.value
##   0.9999
##   0.8359
##   0.3020
##   0.6013
##   0.7543
##   0.2281
##   0.5014
##   0.9022
##   0.9947
##   0.9886
## 
## P value adjustment: tukey method for comparing a family of 5 estimates

Correlation matrix

cor_matrix <- cor(climate_labels[, c("IN1", "IN2", "DN1","DN2","ReduceDrive", "EV", "Culp1", "Culp2")], use = "pairwise.complete.obs")
print(cor_matrix)
##                   IN1       IN2       DN1       DN2 ReduceDrive        EV
## IN1         1.0000000 0.7330038 0.3403338 0.4634391   0.4565967 0.4519696
## IN2         0.7330038 1.0000000 0.3340303 0.5058141   0.5105959 0.5093250
## DN1         0.3403338 0.3340303 1.0000000 0.2999791   0.2483679 0.2509037
## DN2         0.4634391 0.5058141 0.2999791 1.0000000   0.4994589 0.5320793
## ReduceDrive 0.4565967 0.5105959 0.2483679 0.4994589   1.0000000 0.7358545
## EV          0.4519696 0.5093250 0.2509037 0.5320793   0.7358545 1.0000000
## Culp1       0.4211577 0.4570611 0.1857102 0.4533616   0.6061753 0.5600057
## Culp2       0.4313957 0.4680638 0.2390210 0.4723404   0.6428699 0.6085404
##                 Culp1     Culp2
## IN1         0.4211577 0.4313957
## IN2         0.4570611 0.4680638
## DN1         0.1857102 0.2390210
## DN2         0.4533616 0.4723404
## ReduceDrive 0.6061753 0.6428699
## EV          0.5600057 0.6085404
## Culp1       1.0000000 0.7488125
## Culp2       0.7488125 1.0000000
# correlation visualization
ggcorrplot(cor_matrix, 
           method = "circle",     
           type = "lower",        
           lab = TRUE,            
           lab_size = 4,          
           colors = c("#6D9EC1", "white", "#E46726"), 
           title = "Correlation Matrix",
           ggtheme = ggplot2::theme_minimal()
)