Table 1a. GOSE by TIMEPOINT.
| Timepoint | variable | n | min | max | median | q1 | q3 | iqr | mad | mean | sd | se | ci |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Days 7 to 10 | GOSE | 237 | 1 | 8 | 5 | 3 | 6 | 3 | 1.483 | 4.620 | 2.131 | 0.138 | 0.273 |
| Month 3 | GOSE | 322 | 1 | 8 | 5 | 2 | 7 | 5 | 2.965 | 4.516 | 2.546 | 0.142 | 0.279 |
| Month 6 | GOSE | 338 | 1 | 8 | 5 | 2 | 7 | 5 | 3.706 | 4.530 | 2.649 | 0.144 | 0.283 |
| Month 12 | GOSE | 353 | 1 | 8 | 5 | 2 | 7 | 5 | 4.448 | 4.493 | 2.734 | 0.145 | 0.286 |
Table 1b. GOSE by TIMEPOINT and AGE GROUP.
| Version | Timepoint | variable | n | min | max | median | q1 | q3 | iqr | mad | mean | sd | se | ci |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Adult | Days 7 to 10 | GOSE | 146 | 1 | 8 | 5.5 | 4 | 7.00 | 3.00 | 2.224 | 5.438 | 1.827 | 0.151 | 0.299 |
| Pediatric | Days 7 to 10 | GOSE | 85 | 1 | 7 | 3.0 | 2 | 5.00 | 3.00 | 2.965 | 3.447 | 1.912 | 0.207 | 0.412 |
| pwee | Days 7 to 10 | GOSE | 6 | 1 | 2 | 1.0 | 1 | 1.75 | 0.75 | 0.000 | 1.333 | 0.516 | 0.211 | 0.542 |
| Adult | Month 3 | GOSE | 196 | 1 | 8 | 6.0 | 4 | 8.00 | 4.00 | 2.965 | 5.597 | 2.248 | 0.161 | 0.317 |
| Pediatric | Month 3 | GOSE | 121 | 1 | 8 | 2.0 | 1 | 4.00 | 3.00 | 1.483 | 2.909 | 2.025 | 0.184 | 0.364 |
| pwee | Month 3 | GOSE | 5 | 1 | 1 | 1.0 | 1 | 1.00 | 0.00 | 0.000 | 1.000 | 0.000 | 0.000 | 0.000 |
| Adult | Month 6 | GOSE | 209 | 1 | 8 | 6.0 | 5 | 8.00 | 3.00 | 2.965 | 5.727 | 2.301 | 0.159 | 0.314 |
| Pediatric | Month 6 | GOSE | 124 | 1 | 8 | 2.0 | 1 | 4.00 | 3.00 | 1.483 | 2.653 | 1.942 | 0.174 | 0.345 |
| pwee | Month 6 | GOSE | 5 | 1 | 1 | 1.0 | 1 | 1.00 | 0.00 | 0.000 | 1.000 | 0.000 | 0.000 | 0.000 |
| Adult | Month 12 | GOSE | 221 | 1 | 8 | 7.0 | 5 | 8.00 | 3.00 | 1.483 | 5.824 | 2.332 | 0.157 | 0.309 |
| Pediatric | Month 12 | GOSE | 132 | 1 | 8 | 2.0 | 1 | 3.00 | 2.00 | 1.483 | 2.265 | 1.720 | 0.150 | 0.296 |
Table 1c. GOSE by TIMEPOINT and SEVERITY.
| Timepoint | Severity | variable | n | min | max | median | q1 | q3 | iqr | mad | mean | sd | se | ci |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Days 7 to 10 | Mild | GOSE | 229 | 1 | 8 | 5.0 | 3.00 | 6.00 | 3.00 | 1.483 | 4.729 | 2.081 | 0.138 | 0.271 |
| Days 7 to 10 | Moderate | GOSE | 2 | 2 | 3 | 2.5 | 2.25 | 2.75 | 0.50 | 0.741 | 2.500 | 0.707 | 0.500 | 6.353 |
| Days 7 to 10 | Severe | GOSE | 6 | 1 | 2 | 1.0 | 1.00 | 1.00 | 0.00 | 0.000 | 1.167 | 0.408 | 0.167 | 0.428 |
| Month 3 | Mild | GOSE | 229 | 1 | 8 | 5.0 | 2.00 | 7.00 | 5.00 | 4.448 | 4.799 | 2.653 | 0.175 | 0.345 |
| Month 3 | Moderate | GOSE | 31 | 1 | 8 | 4.0 | 3.00 | 5.00 | 2.00 | 1.483 | 4.097 | 1.680 | 0.302 | 0.616 |
| Month 3 | Severe | GOSE | 62 | 1 | 8 | 3.0 | 1.00 | 5.75 | 4.75 | 2.965 | 3.677 | 2.303 | 0.292 | 0.585 |
| Month 6 | Mild | GOSE | 236 | 1 | 8 | 6.0 | 2.00 | 7.00 | 5.00 | 2.965 | 4.847 | 2.729 | 0.178 | 0.350 |
| Month 6 | Moderate | GOSE | 34 | 1 | 8 | 4.0 | 3.00 | 6.00 | 3.00 | 2.224 | 4.235 | 2.175 | 0.373 | 0.759 |
| Month 6 | Severe | GOSE | 68 | 1 | 8 | 3.0 | 1.00 | 5.00 | 4.00 | 2.965 | 3.574 | 2.346 | 0.284 | 0.568 |
| Month 12 | Mild | GOSE | 248 | 1 | 8 | 6.0 | 2.00 | 8.00 | 6.00 | 2.965 | 4.839 | 2.815 | 0.179 | 0.352 |
| Month 12 | Moderate | GOSE | 31 | 1 | 8 | 4.0 | 3.00 | 7.00 | 4.00 | 2.965 | 4.387 | 2.376 | 0.427 | 0.872 |
| Month 12 | Severe | GOSE | 74 | 1 | 8 | 3.0 | 1.00 | 5.00 | 4.00 | 2.965 | 3.378 | 2.286 | 0.266 | 0.530 |
Figure 1a Box-and-whisker, density, and raincloud plot of GOSE (ADULT vs. PEDIATRIC)
Figure 1b Box-and-whisker, density, and raincloud plot of ADULT GOSE (by SEVERITY)
Figure 1c Box-and-whicker, density, and raincloud plot of PEDIATRIC GOSE (by SEVERITY)
Figure 2a Overall GOSE trajectory, all ADULTS.
## `geom_smooth()` using formula = 'y ~ x'
Figure 2b Individual GOSE trajectory, 10% random sample of ADULTS.
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
Figure 3a Overall GOSE trajectory, all PEDIATRIC cases.
## `geom_smooth()` using formula = 'y ~ x'
Figure 3b Individual GOSE trajectory, 10% random sample of PEDIATRIC cases.
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
Table 2a. GOSE STATUS by TIMEPOINT in ADULT cases. UNFAVORABLE: GOSE 1-3; FAVORABLE: GOSE 4-8.
| Timepoint | n | n Unfavorable | % Unfavorable |
|---|---|---|---|
| Days 7 to 10 | 235 | 20 | 8.5 |
| Month 3 | 285 | 37 | 13.0 |
| Month 6 | 279 | 41 | 14.7 |
| Month 12 | 265 | 45 | 17.0 |
Table 2b. GOSE STATUS by TIMEPOINT and SEVERITY in ADULT cases. UNFAVORABLE: GOSE 1-3; FAVORABLE: GOSE 4-8.
## `summarise()` has grouped output by 'Timepoint'. You can override using the
## `.groups` argument.
| Timepoint | Sev | n | n Unfavorable | % Unfavorable |
|---|---|---|---|---|
| Days 7 to 10 | Mild | 199 | 15 | 7.5 |
| Days 7 to 10 | msTBI | 36 | 5 | 13.9 |
| Month 3 | Mild | 200 | 5 | 2.5 |
| Month 3 | msTBI | 85 | 32 | 37.6 |
| Month 6 | Mild | 195 | 6 | 3.1 |
| Month 6 | msTBI | 84 | 35 | 41.7 |
| Month 12 | Mild | 180 | 8 | 4.4 |
| Month 12 | msTBI | 85 | 37 | 43.5 |
Figure 4 GOSE STATUS, across time in ADULT cases. UNFAVORABLE: GOSE 1-3; FAVORABLE: GOSE 4-8.
Table 3a GOSE STATUS by TIMEPOINT in PEDIATRIC cases. UNFAVORABLE: GOSE 6-8; FAVORABLE: GOSE 1-5.
| Timepoint | n | n Unfavorable | % Unfavorable |
|---|---|---|---|
| Days 7 to 10 | 93 | 19 | 20.4 |
| Month 3 | 133 | 20 | 15.0 |
| Month 6 | 138 | 16 | 11.6 |
| Month 12 | 150 | 8 | 5.3 |
Table 3b. GOSE STATUS by TIMEPOINT and SEVERITY in PEDIATRIC cases. UNFAVORABLE: GOSE 6-8; FAVORABLE: GOSE 1-5.
## `summarise()` has grouped output by 'Timepoint'. You can override using the
## `.groups` argument.
| Timepoint | Sev | n | n Unfavorable | % Unfavorable |
|---|---|---|---|---|
| Days 7 to 10 | Mild | 89 | 19 | 21.3 |
| Days 7 to 10 | msTBI | 4 | 0 | 0.0 |
| Month 3 | Mild | 97 | 5 | 5.2 |
| Month 3 | msTBI | 36 | 15 | 41.7 |
| Month 6 | Mild | 98 | 5 | 5.1 |
| Month 6 | msTBI | 40 | 11 | 27.5 |
| Month 12 | Mild | 111 | 1 | 0.9 |
| Month 12 | msTBI | 39 | 7 | 17.9 |
Figure 5 GOSE STATUS, across time in PEDIATRIC cases. UNFAVORABLE: GOSE 6-8; FAVORABLE: GOSE 1-5.
Table 4a GOSE STATUS by TIMEPOINT in PEDIATRIC cases. UNFAVORABLE: GOSE 5-8; FAVORABLE: GOSE 1-4.
| Timepoint | n | n Unfavorable | % Unfavorable |
|---|---|---|---|
| Days 7 to 10 | 93 | 30 | 32.3 |
| Month 3 | 133 | 25 | 18.8 |
| Month 6 | 138 | 21 | 15.2 |
| Month 12 | 150 | 9 | 6.0 |
Table 3b. GOSE STATUS by TIMEPOINT and SEVERITY in PEDIATRIC cases. UNFAVORABLE: GOSE 5-8; FAVORABLE: GOSE 1-4.
## `summarise()` has grouped output by 'Timepoint'. You can override using the
## `.groups` argument.
| Timepoint | Sev | n | n Unfavorable | % Unfavorable |
|---|---|---|---|---|
| Days 7 to 10 | Mild | 89 | 30 | 33.7 |
| Days 7 to 10 | msTBI | 4 | 0 | 0.0 |
| Month 3 | Mild | 97 | 6 | 6.2 |
| Month 3 | msTBI | 36 | 19 | 52.8 |
| Month 6 | Mild | 98 | 6 | 6.1 |
| Month 6 | msTBI | 40 | 15 | 37.5 |
| Month 12 | Mild | 111 | 1 | 0.9 |
| Month 12 | msTBI | 39 | 8 | 20.5 |
Figure 5 GOSE STATUS, across time in PEDIATRIC cases. UNFAVORABLE: GOSE 5-8; FAVORABLE: GOSE 1-4.
Table 4a. PEDSQOL by TIMEPOINT.
| Timepoint | variable | n | min | max | median | q1 | q3 | iqr | mad | mean | sd | se | ci |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Days 7 to 10 | PEDSQOL | 134 | 17.50 | 100 | 73.595 | 55.368 | 89.208 | 33.840 | 25.056 | 71.734 | 20.952 | 1.810 | 3.580 |
| Month 3 | PEDSQOL | 200 | 0.00 | 100 | 83.985 | 62.500 | 94.310 | 31.810 | 19.118 | 76.712 | 21.774 | 1.540 | 3.036 |
| Month 6 | PEDSQOL | 17 | 55.16 | 100 | 82.500 | 72.810 | 91.670 | 18.860 | 14.366 | 81.043 | 13.862 | 3.362 | 7.127 |
| Month 12 | PEDSQOL | 300 | 0.00 | 100 | 86.405 | 67.112 | 96.355 | 29.243 | 20.156 | 79.335 | 20.424 | 1.179 | 2.321 |
Table 4b PEDSQOL by TIMEPOINT and SEVERITY.
| Timepoint | Severity | variable | n | min | max | median | q1 | q3 | iqr | mad | mean | sd | se | ci |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Days 7 to 10 | Mild | PEDSQOL | 132 | 17.50 | 100.00 | 72.505 | 55.155 | 89.182 | 34.028 | 25.323 | 71.479 | 20.997 | 1.828 | 3.615 |
| Days 7 to 10 | Moderate | PEDSQOL | 1 | 83.33 | 83.33 | 83.330 | 83.330 | 83.330 | 0.000 | 0.000 | 83.330 | NA | NA | NaN |
| Days 7 to 10 | Severe | PEDSQOL | 1 | 93.75 | 93.75 | 93.750 | 93.750 | 93.750 | 0.000 | 0.000 | 93.750 | NA | NA | NaN |
| Month 3 | Mild | PEDSQOL | 152 | 27.35 | 100.00 | 86.720 | 69.452 | 95.510 | 26.057 | 16.101 | 81.102 | 17.834 | 1.447 | 2.858 |
| Month 3 | Moderate | PEDSQOL | 23 | 0.00 | 98.33 | 72.920 | 53.195 | 88.125 | 34.930 | 26.568 | 68.771 | 25.427 | 5.302 | 10.995 |
| Month 3 | Severe | PEDSQOL | 25 | 0.00 | 100.00 | 54.650 | 43.100 | 77.350 | 34.250 | 33.092 | 57.328 | 27.633 | 5.527 | 11.406 |
| Month 6 | Mild | PEDSQOL | 10 | 67.19 | 100.00 | 88.335 | 80.745 | 95.512 | 14.767 | 11.468 | 87.466 | 10.828 | 3.424 | 7.746 |
| Month 6 | Moderate | PEDSQOL | 2 | 66.79 | 86.41 | 76.600 | 71.695 | 81.505 | 9.810 | 14.544 | 76.600 | 13.873 | 9.810 | 124.648 |
| Month 6 | Severe | PEDSQOL | 5 | 55.16 | 87.50 | 72.810 | 56.900 | 77.500 | 20.600 | 21.779 | 69.974 | 13.804 | 6.173 | 17.140 |
| Month 12 | Mild | PEDSQOL | 231 | 10.16 | 100.00 | 88.130 | 70.705 | 97.500 | 26.795 | 17.598 | 81.791 | 18.885 | 1.243 | 2.448 |
| Month 12 | Moderate | PEDSQOL | 25 | 41.10 | 100.00 | 86.250 | 65.940 | 92.190 | 26.250 | 20.386 | 77.665 | 18.550 | 3.710 | 7.657 |
| Month 12 | Severe | PEDSQOL | 44 | 0.00 | 100.00 | 71.145 | 54.492 | 86.795 | 32.303 | 24.441 | 67.386 | 24.916 | 3.756 | 7.575 |
Figure 6a Box-and-whisker, density, and raincloud plot of PEDSQOL.
Figure 6b Box-and-whisker, density, and raincloud plot of PEDSQOL by SEVERITY.
Figure 7a Overall PEDSQOL trajectory. nb. the 6-month data were dropped owing to limited # of cases (n=17, across all severities)
## `geom_smooth()` using formula = 'y ~ x'
Figure 7b Individual PEDSQOL trajectory, 10% random sample. nb. the 6-month data were dropped owing to limited # of cases (n=17, across all severities)
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
## `geom_line()`: Each group consists of only one observation.
## ℹ Do you need to adjust the group aesthetic?
Table 5a ADULT: GOSExAGE SPEARMAN at DAYS7to10
## GOSE Age
## GOSE 1.00 -0.18
## Age -0.18 1.00
##
## n= 146
##
##
## P
## GOSE Age
## GOSE 0.0316
## Age 0.0316
Table 5b ADULT: GOSExAGE SPEARMAN at 3 MONTHS
## GOSE Age
## GOSE 1.00 -0.16
## Age -0.16 1.00
##
## n= 196
##
##
## P
## GOSE Age
## GOSE 0.0248
## Age 0.0248
Table 5c ADULT: GOSExAGE SPEARMAN at 6 MONTHS
## GOSE Age
## GOSE 1.00 -0.06
## Age -0.06 1.00
##
## n= 209
##
##
## P
## GOSE Age
## GOSE 0.3841
## Age 0.3841
Table 5d ADULT: GOSExAGE SPEARMAN at 12 MONTHS
## GOSE Age
## GOSE 1.00 -0.16
## Age -0.16 1.00
##
## n= 221
##
##
## P
## GOSE Age
## GOSE 0.016
## Age 0.016
Table 6a PEDIATRIC: GOSExAGE SPEARMAN at DAYS7to10
## GOSE Age
## GOSE 1.00 0.12
## Age 0.12 1.00
##
## n= 85
##
##
## P
## GOSE Age
## GOSE 0.2685
## Age 0.2685
Table 6b PEDIATRIC: GOSExAGE SPEARMAN at 3 MONTHS
## GOSE Age
## GOSE 1.00 -0.16
## Age -0.16 1.00
##
## n= 121
##
##
## P
## GOSE Age
## GOSE 0.0747
## Age 0.0747
Table 6c PEDIATRIC: GOSExAGE SPEARMAN at 6 MONTHS
## GOSE Age
## GOSE 1.00 -0.16
## Age -0.16 1.00
##
## n= 124
##
##
## P
## GOSE Age
## GOSE 0.0719
## Age 0.0719
Table 6d PEDIATRIC: GOSExAGE SPEARMAN at 12 MONTHS
## GOSE Age
## GOSE 1.00 0.07
## Age 0.07 1.00
##
## n= 132
##
##
## P
## GOSE Age
## GOSE 0.4369
## Age 0.4369
Table 7a ADULT: GOSExPEDSQOL PEARSON at DAYS7to10
## GOSE PEDSQOL
## GOSE 1.00 0.53
## PEDSQOL 0.53 1.00
##
## n= 79
##
##
## P
## GOSE PEDSQOL
## GOSE 0
## PEDSQOL 0
Table 7b ADULT: GOSExPEDSQOL PEARSON at 3 MONTHS
## GOSE PEDSQOL
## GOSE 1.00 0.62
## PEDSQOL 0.62 1.00
##
## n
## GOSE PEDSQOL
## GOSE 196 108
## PEDSQOL 108 108
##
## P
## GOSE PEDSQOL
## GOSE 0
## PEDSQOL 0
Table 7c ADULT: GOSExPEDSQOL PEARSON at 6 MONTHS
## GOSE PEDSQOL
## GOSE 1.00 0.58
## PEDSQOL 0.58 1.00
##
## n
## GOSE PEDSQOL
## GOSE 209 3
## PEDSQOL 3 3
##
## P
## GOSE PEDSQOL
## GOSE 0.6092
## PEDSQOL 0.6092
Table 7d ADULT: GOSExPEDSQOL PEARSON at 12 MONTHS
## GOSE PEDSQOL
## GOSE 1.00 0.65
## PEDSQOL 0.65 1.00
##
## n
## GOSE PEDSQOL
## GOSE 225 171
## PEDSQOL 171 171
##
## P
## GOSE PEDSQOL
## GOSE 0
## PEDSQOL 0
Table 8a PEDIATRIC: GOSExPEDSQOL PEARSON at DAYS7to10
## GOSE PEDSQOL
## GOSE 1.00 -0.56
## PEDSQOL -0.56 1.00
##
## n= 53
##
##
## P
## GOSE PEDSQOL
## GOSE 0
## PEDSQOL 0
Table 8b PEDIATRIC: GOSExPEDSQOL PEARSON at 3 MONTHS
## GOSE PEDSQOL
## GOSE 1.00 -0.71
## PEDSQOL -0.71 1.00
##
## n
## GOSE PEDSQOL
## GOSE 141 91
## PEDSQOL 91 91
##
## P
## GOSE PEDSQOL
## GOSE 0
## PEDSQOL 0
Table 8c PEDIATRIC: GOSExPEDSQOL PEARSON at 6 MONTHS
## GOSE PEDSQOL
## GOSE 1.00 -0.75
## PEDSQOL -0.75 1.00
##
## n
## GOSE PEDSQOL
## GOSE 125 14
## PEDSQOL 14 14
##
## P
## GOSE PEDSQOL
## GOSE 0.0018
## PEDSQOL 0.0018
Table 8d PEDIATRIC: GOSExPEDSQOL PEARSON at 12 MONTHS
## GOSE PEDSQOL
## GOSE 1.00 -0.58
## PEDSQOL -0.58 1.00
##
## n
## GOSE PEDSQOL
## GOSE 150 129
## PEDSQOL 129 129
##
## P
## GOSE PEDSQOL
## GOSE 0
## PEDSQOL 0
## Loading required package: MASS
##
## Attaching package: 'MASS'
## The following object is masked from 'package:EnvStats':
##
## boxcox
## The following object is masked from 'package:dplyr':
##
## select
## The following object is masked from 'package:rstatix':
##
## select
Table 9a ADULT: GOSExPEDSQOL PARTIAL (AGE) at DAYS7to10
## estimate p.value statistic n gp Method
## 1 0.5407284 3.212006e-07 5.603872 79 1 pearson
Table 9b ADULT: GOSExPEDSQOL PARTIAL (AGE) at 3 MONTHS
## estimate p.value statistic n gp Method
## 1 0.6278758 4.546079e-13 8.266351 108 1 pearson
Table 9c ADULT: GOSExPEDSQOL PARTIAL (AGE) at 6 MONTHS
## estimate p.value statistic n gp Method
## 1 0.2680396 NaN 0 3 1 pearson
Table 9d ADULT: GOSExPEDSQOL PARTIAL (AGE) 12 MONTHS
## estimate p.value statistic n gp Method
## 1 0.6497485 9.193447e-22 11.07901 171 1 pearson
Table 10a PEDIATRIC: GOSExPEDSQOL PARTIAL (AGE) at DAYS7to10
## Loading required package: MASS
##
## Attaching package: 'MASS'
## The following object is masked from 'package:EnvStats':
##
## boxcox
## The following object is masked from 'package:dplyr':
##
## select
## The following object is masked from 'package:rstatix':
##
## select
## estimate p.value statistic n gp Method
## 1 -0.5438639 3.08543e-05 -4.582722 53 1 pearson
Table 10b PEDIATRIC: GOSExPEDSQOL PARTIAL (AGE) at 3 MONTHS
## estimate p.value statistic n gp Method
## 1 -0.7499019 1.816533e-17 -10.63368 91 1 pearson
Table 10c PEDIATRIC: GOSExPEDSQOL PARTIAL (AGE) at 6 MONTHS
## estimate p.value statistic n gp Method
## 1 -0.7891377 0.001340397 -4.261159 14 1 pearson
Table 10d PEDIATRIC: GOSExPEDSQOL PARTIAL (AGE) 12 MONTHS
## estimate p.value statistic n gp Method
## 1 -0.5758998 1.144913e-12 -7.907399 129 1 pearson
## This is lavaan 0.6-16
## lavaan is FREE software! Please report any bugs.
Figure 8 Group trajectories (observed data) for both ADULT and PEDIATRIC cases.
Table 11a Linear model fitted to ADULT cases. The model does not allow the null hypothesis to be rejected.
“The null hypothesis in an SEM analysis is that the covariance matrix implied or reproduced by the specified model is statistically the same as the input covariance matrix [where covariances are set to 0]. Contrary to usual hypothesis testing, we hope to retain the null hypothesis that the two matrices are statistically the same.”
## lavaan 0.6.16 ended normally after 25 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 5
##
## Used Total
## Number of observations 154 294
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 21.248 36.459
## Degrees of freedom 4 4
## P-value (Chi-square) 0.000 0.000
## Scaling correction factor 0.583
## Yuan-Bentler correction (Mplus variant)
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|)
## i =~
## T2 1.000
## T3 1.000
## T4 1.000
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|)
## .T2 0.000
## .T3 0.000
## .T4 0.000
## i 5.751 0.188 30.583 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .T2 0.637 0.140 4.540 0.000
## .T3 0.354 0.097 3.644 0.000
## .T4 0.354 0.095 3.718 0.000
## i 5.223 0.571 9.144 0.000
Table 11b Linear model fitted to PEDIATRIC cases. The model does not allow the null hypothesis to be rejected.
“The null hypothesis in an SEM analysis is that the covariance matrix implied or reproduced by the specified model is statistically the same as the input covariance matrix [where covariances are set to 0]. Contrary to usual hypothesis testing, we hope to retain the null hypothesis that the two matrices are statistically the same.”
## lavaan 0.6.16 ended normally after 24 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 5
##
## Used Total
## Number of observations 69 159
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 44.237 53.062
## Degrees of freedom 4 4
## P-value (Chi-square) 0.000 0.000
## Scaling correction factor 0.834
## Yuan-Bentler correction (Mplus variant)
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|)
## i =~
## T1 1.000
## T2 1.000
## T4 1.000
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|)
## .T1 0.000
## .T2 0.000
## .T4 0.000
## i 2.025 0.134 15.092 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .T1 4.289 0.734 5.846 0.000
## .T2 0.967 0.298 3.246 0.001
## .T4 0.437 0.170 2.568 0.010
## i 0.693 0.174 3.987 0.000
Table 12a Linear model fitted to ADULT cases. The model DOES allow the null hypothesis to be rejected.
## lavaan 0.6.16 ended normally after 57 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 8
##
## Used Total
## Number of observations 154 294
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 1.305 1.464
## Degrees of freedom 1 1
## P-value (Chi-square) 0.253 0.226
## Scaling correction factor 0.891
## Yuan-Bentler correction (Mplus variant)
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|)
## i =~
## T2 1.000
## T3 1.000
## T4 1.000
## s =~
## T2 3.000
## T3 6.000
## T4 12.000
##
## Covariances:
## Estimate Std.Err z-value P(>|z|)
## i ~~
## s -0.009 0.027 -0.320 0.749
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|)
## .T2 0.000
## .T3 0.000
## .T4 0.000
## i 5.475 0.192 28.515 0.000
## s 0.034 0.008 4.374 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .T2 0.423 0.149 2.843 0.004
## .T3 0.498 0.116 4.300 0.000
## .T4 -0.053 0.258 -0.206 0.837
## i 5.028 0.578 8.701 0.000
## s 0.006 0.005 1.328 0.184
Table 12b Linear model fitted to PEDIATRIC cases. The model does not allow the null hypothesis to be rejected.
“The null hypothesis in an SEM analysis is that the covariance matrix implied or reproduced by the specified model is statistically the same as the input covariance matrix [where covariances are set to 0]. Contrary to usual hypothesis testing, we hope to retain the null hypothesis that the two matrices are statistically the same.”
## lavaan 0.6.16 ended normally after 54 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 8
##
## Used Total
## Number of observations 69 159
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 24.514 33.879
## Degrees of freedom 1 1
## P-value (Chi-square) 0.000 0.000
## Scaling correction factor 0.724
## Yuan-Bentler correction (Mplus variant)
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|)
## i =~
## T1 1.000
## T2 1.000
## T4 1.000
## s =~
## T1 0.000
## T2 3.000
## T4 12.000
##
## Covariances:
## Estimate Std.Err z-value P(>|z|)
## i ~~
## s -0.018 0.031 -0.576 0.565
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|)
## .T1 0.000
## .T2 0.000
## .T4 0.000
## i 2.603 0.258 10.082 0.000
## s -0.065 0.020 -3.219 0.001
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .T1 2.913 0.715 4.073 0.000
## .T2 1.002 0.345 2.908 0.004
## .T4 0.604 0.959 0.630 0.529
## i 1.002 0.386 2.596 0.009
## s -0.001 0.009 -0.107 0.915
Table 13a Quadratic model fitted to ADULT cases. The model does not allow the null hypothesis to be rejected.
“The null hypothesis in an SEM analysis is that the covariance matrix implied or reproduced by the specified model is statistically the same as the input covariance matrix [where covariances are set to 0]. Contrary to usual hypothesis testing, we hope to retain the null hypothesis that the two matrices are statistically the same.”
## lavaan 0.6.16 ended normally after 64 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 12
##
## Used Total
## Number of observations 154 294
##
## Model Test User Model:
##
## Test statistic NA
## Degrees of freedom -3
## P-value (Unknown) NA
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|)
## i =~
## T2 1.000
## T3 1.000
## T4 1.000
## s =~
## T2 3.000
## T3 6.000
## T4 12.000
## q =~
## T2 0.000
## T3 1.000
## T4 4.000
##
## Covariances:
## Estimate Std.Err z-value P(>|z|)
## i ~~
## s 0.359 NA
## q -0.704 NA
## s ~~
## q -0.368 NA
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|)
## .T2 0.000
## .T3 0.000
## .T4 0.000
## i 5.130 NA
## s 0.139 NA
## q -0.227 NA
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .T2 1.323 NA
## .T3 -0.309 NA
## .T4 3.063 NA
## i 0.313 NA
## s 0.185 NA
## q 0.500 NA
Table 13b Quadratic model fitted to PEDIATRIC cases. The model does not allow the null hypothesis to be rejected.
“The null hypothesis in an SEM analysis is that the covariance matrix implied or reproduced by the specified model is statistically the same as the input covariance matrix [where covariances are set to 0]. Contrary to usual hypothesis testing, we hope to retain the null hypothesis that the two matrices are statistically the same.”
## lavaan 0.6.16 ended normally after 50 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 12
##
## Used Total
## Number of observations 69 159
##
## Model Test User Model:
##
## Test statistic NA
## Degrees of freedom -3
## P-value (Unknown) NA
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|)
## i =~
## T1 1.000
## T2 1.000
## T4 1.000
## s =~
## T1 0.000
## T2 3.000
## T4 12.000
## q =~
## T1 0.000
## T2 1.000
## T4 4.000
##
## Covariances:
## Estimate Std.Err z-value P(>|z|)
## i ~~
## s -0.016 NA
## q -0.005 NA
## s ~~
## q -0.026 NA
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|)
## .T1 0.000
## .T2 0.000
## .T4 0.000
## i 2.603 NA
## s -0.059 NA
## q -0.020 NA
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .T1 2.913 NA
## .T2 1.002 NA
## .T4 0.604 NA
## i 1.002 NA
## s 0.011 NA
## q 0.046 NA
Table 14a Linear model fitted to ADULT cases, with Age as a time-invariant covariate and Severity as a time-varying covariate. The model is significant, allowing the null to be rejected.
## lavaan 0.6.16 ended normally after 74 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 13
##
## Used Total
## Number of observations 207 294
## Number of missing patterns 8
##
## Model Test User Model:
##
## Test statistic 5.583
## Degrees of freedom 8
## P-value (Chi-square) 0.694
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|)
## i =~
## T2 1.000
## T3 1.000
## T4 1.000
## s =~
## T2 3.000
## T3 6.000
## T4 12.000
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## i ~
## Age_1 -0.012 0.006 -1.852 0.064
## s ~
## Age_1 -0.000 0.000 -0.733 0.464
## T2 ~
## Sev_2 -2.827 0.358 -7.890 0.000
## T3 ~
## Sev_3 -2.674 0.341 -7.843 0.000
## T4 ~
## Sev_4 -2.717 0.361 -7.527 0.000
##
## Covariances:
## Estimate Std.Err z-value P(>|z|)
## .i ~~
## .s -0.007 0.041 -0.173 0.863
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|)
## .T2 0.000
## .T3 0.000
## .T4 0.000
## .i 9.777 0.559 17.483 0.000
## .s 0.040 0.039 1.034 0.301
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .T2 0.749 0.217 3.450 0.001
## .T3 0.589 0.145 4.060 0.000
## .T4 -0.048 0.410 -0.116 0.908
## .i 1.943 0.388 5.007 0.000
## .s 0.006 0.008 0.810 0.418
Table 14b Linear model fitted to PEDIATRIC cases, with Age as a time-invariant covariate and Severity as a time-varying covariate. The model does not perform significantly well.
## lavaan 0.6.16 did NOT end normally after 67 iterations
## ** WARNING ** Estimates below are most likely unreliable
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 13
##
## Used Total
## Number of observations 85 159
## Number of missing patterns 8
##
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|)
## i =~
## T2 1.000
## T3 1.000
## T4 1.000
## s =~
## T2 3.000
## T3 6.000
## T4 12.000
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## i ~
## Age_1 -0.031 NA
## s ~
## Age_1 0.003 NA
## T2 ~
## Sev_2 0.818 NA
## T3 ~
## Sev_3 0.547 NA
## T4 ~
## Sev_4 0.171 NA
##
## Covariances:
## Estimate Std.Err z-value P(>|z|)
## .i ~~
## .s -0.132 NA
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|)
## .T2 0.000
## .T3 0.000
## .T4 0.000
## .i 1.418 NA
## .s 0.017 NA
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .T2 0.411 NA
## .T3 0.509 NA
## .T4 0.002 NA
## .i 2.272 NA
## .s 0.013 NA
Table 15a Comparison of the linear and quadratic models, for ADULT cases.
##
## Scaled Chi-Squared Difference Test (method = "satorra.bentler.2001")
##
## lavaan NOTE:
## The "Chisq" column contains standard test statistics, not the
## robust test that should be reported per model. A robust difference
## test is a function of two standard (not robust) statistics.
##
## Df AIC BIC Chisq Chisq diff Df diff Pr(>Chisq)
## gose_adult_gc_lin 1 1481.0 1505.2 1.3046
## gose_adult_gc_int 4 1494.9 1510.1 21.2485 41.543 3 5.016e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Table 15b Comparison of the linear and quadratic models, for PEDIATRIC cases.
##
## Scaled Chi-Squared Difference Test (method = "satorra.bentler.2001")
##
## lavaan NOTE:
## The "Chisq" column contains standard test statistics, not the
## robust test that should be reported per model. A robust difference
## test is a function of two standard (not robust) statistics.
##
## Df AIC BIC Chisq Chisq diff Df diff Pr(>Chisq)
## gose_ped_gc_lin 1 710.50 728.38 24.514
## gose_ped_gc_int 4 724.23 735.40 44.237 22.66 3 4.753e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Figure 9a Model-estimated plots for ADULT cases.
Figure 9b Model-estimated plots for PEDIATRIC cases.
Figure 10 Group trajectories (observed data) for the PEDSQOL.
Table 16 Linear model fitted to all PEDSQOL cases. The model does not allow the null hypothesis to be rejected.
“The null hypothesis in an SEM analysis is that the covariance matrix implied or reproduced by the specified model is statistically the same as the input covariance matrix [where covariances are set to 0]. Contrary to usual hypothesis testing, we hope to retain the null hypothesis that the two matrices are statistically the same.”
## lavaan 0.6.16 ended normally after 127 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 8
##
## Used Total
## Number of observations 71 267
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 7.343 6.646
## Degrees of freedom 1 1
## P-value (Chi-square) 0.007 0.010
## Scaling correction factor 1.105
## Yuan-Bentler correction (Mplus variant)
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|)
## i =~
## T1 1.000
## T2 1.000
## T4 1.000
## s =~
## T1 0.000
## T2 1.000
## T4 2.000
##
## Covariances:
## Estimate Std.Err z-value P(>|z|)
## i ~~
## s -45.348 24.374 -1.861 0.063
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|)
## .T1 0.000
## .T2 0.000
## .T4 0.000
## i 70.740 2.550 27.740 0.000
## s 3.829 1.131 3.386 0.001
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .T1 93.260 55.403 1.683 0.092
## .T2 111.722 27.383 4.080 0.000
## .T4 -22.125 51.716 -0.428 0.669
## i 290.400 66.010 4.399 0.000
## s 73.038 23.463 3.113 0.002
Table 17 Quadratic model fitted to PEDSQOL cases. The model does not allow the null hypothesis to be rejected.
“The null hypothesis in an SEM analysis is that the covariance matrix implied or reproduced by the specified model is statistically the same as the input covariance matrix [where covariances are set to 0]. Contrary to usual hypothesis testing, we hope to retain the null hypothesis that the two matrices are statistically the same.”
## lavaan 0.6.16 ended normally after 117 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 12
##
## Used Total
## Number of observations 71 267
##
## Model Test User Model:
##
## Test statistic NA
## Degrees of freedom -3
## P-value (Unknown) NA
##
## Parameter Estimates:
##
## Standard errors Sandwich
## Information bread Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|)
## i =~
## T1 1.000
## T2 1.000
## T4 1.000
## s =~
## T1 0.000
## T2 1.000
## T4 2.000
## q =~
## T1 0.000
## T2 1.000
## T4 4.000
##
## Covariances:
## Estimate Std.Err z-value P(>|z|)
## i ~~
## s 110.510 NA
## q -53.140 NA
## s ~~
## q 4.479 NA
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|)
## .T1 0.000
## .T2 0.000
## .T4 0.000
## i 69.456 NA
## s 11.757 NA
## q -3.567 NA
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .T1 190.377 NA
## .T2 55.100 NA
## .T4 44.289 NA
## i 191.634 NA
## s 1.547 NA
## q 3.015 NA
Table 18 Linear model fitted to ALL cases, with Age as a time-invariant covariate and Severity as a time-varying covariate. The model is significant, allowing the null to be rejected.
## lavaan 0.6.16 ended normally after 143 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 13
##
## Used Total
## Number of observations 107 267
## Number of missing patterns 7
##
## Model Test User Model:
##
## Test statistic 0.703
## Degrees of freedom 8
## P-value (Chi-square) 1.000
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Observed
## Observed information based on Hessian
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|)
## i =~
## T1 1.000
## T2 1.000
## T4 1.000
## s =~
## T1 1.000
## T2 3.000
## T4 12.000
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## i ~
## Age_1 -0.169 0.088 -1.925 0.054
## s ~
## Age_1 -0.002 0.006 -0.375 0.708
## T1 ~
## Sev_1 -47.735 920.788 -0.052 0.959
## T2 ~
## Sev_2 -41.011 13.108 -3.129 0.002
## T4 ~
## Sev_4 -51.188 4143.616 -0.012 0.990
##
## Covariances:
## Estimate Std.Err z-value P(>|z|)
## .i ~~
## .s -10.346 4.054 -2.552 0.011
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|)
## .T1 0.000
## .T2 0.000
## .T4 0.000
## .i 122.195 1381.150 0.088 0.930
## .s 1.366 460.390 0.003 0.998
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .T1 152.242 42.791 3.558 0.000
## .T2 99.015 30.600 3.236 0.001
## .T4 -323.975 163.531 -1.981 0.048
## .i 257.720 53.174 4.847 0.000
## .s 4.560 1.708 2.669 0.008
Table 16 Comparison of the linear and quadratic models, for ADULT cases.
Figure 10 Model-estimated plots for PEDSQOL cases.