A quick and dirty output for now - cleaner code will be inserted into main paper page later…

## Using StudentID, project, open.bin as id variables

Based on open bins for Report 0

What are the marks for Report 0 and do they differ between open bin categories?

##          means SEM
## long      69.7 0.7
## medium    67.7 0.8
## short     65.7 2.5
## unopened  63.6 1.6
##               Df Sum Sq Mean Sq F value  Pr(>F)   
## R0.open[, 6]   3   2404   801.5   5.157 0.00157 **
## Residuals    665 103348   155.4                   
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = R0.open[, 2] ~ R0.open[, 6])
## 
## $`R0.open[, 6]`
##                      diff        lwr        upr     p adj
## medium-long     -2.061859  -4.746658  0.6229411 0.1973514
## short-long      -4.002766 -10.447041  2.4415100 0.3794297
## unopened-long   -6.176342 -10.504587 -1.8480974 0.0014621
## short-medium    -1.940907  -8.424938  4.5431241 0.8675606
## unopened-medium -4.114484  -8.501701  0.2727336 0.0751509
## unopened-short  -2.173577  -9.492608  5.1454545 0.8702356
## Using StudentID, Report0.open.bin as id variables

For each open bin category, are there differences between report marks?

stat’s for unopened

##          means SEM
## Report 0  63.6 1.6
## Report 1  55.0 3.0
## Report 2  65.3 3.7
## Report 3  69.6 3.8
##              Df Sum Sq Mean Sq F value Pr(>F)  
## dfx[, 3]      3   7518  2506.0   3.825 0.0104 *
## Residuals   264 172948   655.1                 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = dfx[, 4] ~ dfx[, 3])
## 
## $`dfx[, 3]`
##                        diff        lwr       upr     p adj
## Report 1-Report 0 -8.567164 -20.000497  2.866169 0.2150092
## Report 2-Report 0  1.776119  -9.657214 13.209452 0.9780384
## Report 3-Report 0  5.985075  -5.448258 17.418408 0.5297859
## Report 2-Report 1 10.343284  -1.090049 21.776617 0.0919324
## Report 3-Report 1 14.552239   3.118906 25.985572 0.0062088
## Report 3-Report 2  4.208955  -7.224378 15.642288 0.7768197

stat’s for short

##          means SEM
## Report 0  65.7 2.5
## Report 1  67.1 2.3
## Report 2  71.5 3.5
## Report 3  76.1 4.5
##              Df Sum Sq Mean Sq F value Pr(>F)
## dfx[, 3]      3   1802   600.8   2.014  0.117
## Residuals   104  31021   298.3
##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = dfx[, 4] ~ dfx[, 3])
## 
## $`dfx[, 3]`
##                        diff        lwr      upr     p adj
## Report 1-Report 0  1.333333 -10.939995 13.60666 0.9919949
## Report 2-Report 0  5.777778  -6.495550 18.05111 0.6098289
## Report 3-Report 0 10.407407  -1.865921 22.68074 0.1261768
## Report 2-Report 1  4.444444  -7.828884 16.71777 0.7803678
## Report 3-Report 1  9.074074  -3.199254 21.34740 0.2217547
## Report 3-Report 2  4.629630  -7.643699 16.90296 0.7583392

stat’s for medium

##          means SEM
## Report 0  67.7 0.8
## Report 1  69.5 1.1
## Report 2  74.2 1.3
## Report 3  78.0 1.3
##               Df Sum Sq Mean Sq F value   Pr(>F)    
## dfx[, 3]       3  17643    5881   16.43 1.94e-10 ***
## Residuals   1064 380961     358                     
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = dfx[, 4] ~ dfx[, 3])
## 
## $`dfx[, 3]`
##                        diff        lwr       upr     p adj
## Report 1-Report 0  1.769663 -2.4442422  5.983568 0.7014900
## Report 2-Report 0  6.526217  2.3123121 10.740122 0.0004185
## Report 3-Report 0 10.363296  6.1493907 14.577201 0.0000000
## Report 2-Report 1  4.756554  0.5426492  8.970459 0.0196209
## Report 3-Report 1  8.593633  4.3797278 12.807538 0.0000011
## Report 3-Report 2  3.837079 -0.3768265  8.050984 0.0891347

stat’s for long

##          means SEM
## Report 0  69.7 0.7
## Report 1  76.1 0.9
## Report 2  80.7 1.0
## Report 3  82.4 1.1
##               Df Sum Sq Mean Sq F value Pr(>F)    
## dfx[, 3]       3  29502    9834   37.02 <2e-16 ***
## Residuals   1228 326179     266                   
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = dfx[, 4] ~ dfx[, 3])
## 
## $`dfx[, 3]`
##                        diff       lwr       upr     p adj
## Report 1-Report 0  6.379870  3.001300  9.758440 0.0000080
## Report 2-Report 0 10.915584  7.537014 14.294154 0.0000000
## Report 3-Report 0 12.659091  9.280521 16.037661 0.0000000
## Report 2-Report 1  4.535714  1.157144  7.914284 0.0032038
## Report 3-Report 1  6.279221  2.900651  9.657791 0.0000116
## Report 3-Report 2  1.743506 -1.635063  5.122076 0.5454696