Smartphone ALLFTD Renewal
Mark Sanderson-cimino
2024-08-16
LME models (Project 1: Familial)
Sample description for model 1 (familial)
LME model 1: Mutation pos, baseline CDR 0 or .5
Presents graphs first, then a print out of the models. Note the failure to converge/warnings of several models.
Removed condition requiring age<=45. Using original CDR+NACC-FTLD sum of boxes.
## [1] "y.plot = baseline_gonogo"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 251.4
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -11.9366 -0.0330 -0.0090 0.0061 3.4948
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 0.53221 0.72952
## monthssincebaseline 0.00107 0.03271 0.14
## Residual 0.03847 0.19614
## Number of obs: 315, groups: unique_id, 55
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -1.129275 0.768810 48.581986 -1.469 0.1483
## y.plot -0.195999 0.101091 50.562995 -1.939 0.0581 .
## monthssincebaseline 0.004859 0.005587 35.409451 0.870 0.3903
## baseline_age 0.002430 0.008818 48.810876 0.276 0.7840
## educ 0.086560 0.044815 49.263624 1.931 0.0592 .
## y.plot:monthssincebaseline 0.002863 0.005744 34.439278 0.498 0.6214
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.193
## mnthssncbsl 0.027 -0.003
## baseline_ag -0.374 0.236 0.007
## educ -0.846 0.069 -0.021 -0.162
## y.plt:mnths -0.002 0.075 -0.054 0.012 -0.005
## [1] "y.plot = baseline_strp"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 236.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -12.1883 -0.0349 -0.0077 0.0088 3.5878
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 0.4534602 0.67339
## monthssincebaseline 0.0009413 0.03068 0.29
## Residual 0.0370942 0.19260
## Number of obs: 317, groups: unique_id, 57
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -0.372014 0.740357 48.004741 -0.502 0.6176
## y.plot -0.266306 0.119745 53.344973 -2.224 0.0304 *
## monthssincebaseline 0.005653 0.005145 36.374904 1.099 0.2791
## baseline_age -0.012331 0.009431 50.106048 -1.307 0.1970
## educ 0.074560 0.040610 48.685336 1.836 0.0725 .
## y.plot:monthssincebaseline -0.009558 0.005332 37.178449 -1.792 0.0812 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.454
## mnthssncbsl 0.031 0.028
## baseline_ag -0.467 0.597 0.042
## educ -0.815 0.133 -0.036 -0.118
## y.plt:mnths 0.016 0.140 -0.040 -0.010 -0.010
## [1] "y.plot = baseline_flk"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 250.4
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -12.2762 -0.0356 -0.0073 0.0122 3.6129
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 0.4603744 0.67851
## monthssincebaseline 0.0009618 0.03101 0.12
## Residual 0.0363828 0.19074
## Number of obs: 337, groups: unique_id, 61
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -0.154308 0.728815 56.436500 -0.212 0.833085
## y.plot -0.438528 0.111227 58.620271 -3.943 0.000218 ***
## monthssincebaseline 0.004375 0.005053 40.248471 0.866 0.391809
## baseline_age -0.019853 0.009642 56.991685 -2.059 0.044070 *
## educ 0.090601 0.039699 56.524814 2.282 0.026263 *
## y.plot:monthssincebaseline -0.003819 0.005123 41.110974 -0.746 0.460211
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.421
## mnthssncbsl 0.014 0.011
## baseline_ag -0.477 0.611 0.015
## educ -0.786 0.048 -0.017 -0.155
## y.plt:mnths 0.010 0.032 -0.045 -0.010 -0.004
## [1] "y.plot = baseline_nback"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 215.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -11.8705 -0.0411 -0.0069 0.0183 3.4766
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 0.3647526 0.60395
## monthssincebaseline 0.0009174 0.03029 0.32
## Residual 0.0392482 0.19811
## Number of obs: 294, groups: unique_id, 50
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -0.796937 0.605602 40.944176 -1.316 0.19551
## y.plot -0.306141 0.089120 46.403800 -3.435 0.00126 **
## monthssincebaseline 0.007069 0.005300 31.896112 1.334 0.19171
## baseline_age -0.010809 0.007786 44.007780 -1.388 0.17209
## educ 0.095475 0.038279 42.979781 2.494 0.01655 *
## y.plot:monthssincebaseline -0.016081 0.005448 32.355291 -2.952 0.00584 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.068
## mnthssncbsl 0.057 0.024
## baseline_ag -0.259 0.420 0.032
## educ -0.821 -0.169 -0.043 -0.321
## y.plt:mnths 0.004 0.169 -0.076 -0.032 0.015
## [1] "y.plot = baseline_humi"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 251
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -12.1821 -0.0386 -0.0044 0.0120 3.5820
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 0.4784153 0.69168
## monthssincebaseline 0.0009995 0.03161 0.18
## Residual 0.0369540 0.19223
## Number of obs: 331, groups: unique_id, 59
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -1.079057 0.684477 52.286719 -1.576 0.12095
## y.plot -0.338245 0.106404 53.915213 -3.179 0.00245 **
## monthssincebaseline 0.004414 0.005189 38.766238 0.851 0.40016
## baseline_age -0.011306 0.009017 52.647863 -1.254 0.21542
## educ 0.120864 0.042390 52.899062 2.851 0.00620 **
## y.plot:monthssincebaseline -0.001969 0.005161 39.138119 -0.382 0.70484
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.087
## mnthssncbsl 0.030 0.019
## baseline_ag -0.295 0.508 0.022
## educ -0.808 -0.216 -0.028 -0.310
## y.plt:mnths 0.011 0.102 -0.021 0.012 -0.017
## [1] "y.plot = baseline_test3meanZ"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 252.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -12.2668 -0.0410 -0.0045 0.0123 3.6122
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 0.4745789 0.68890
## monthssincebaseline 0.0009692 0.03113 0.15
## Residual 0.0364319 0.19087
## Number of obs: 337, groups: unique_id, 61
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -0.811773 0.685696 55.152706 -1.184 0.241543
## y.plot -0.409466 0.111698 56.374295 -3.666 0.000547 ***
## monthssincebaseline 0.004224 0.005065 40.238648 0.834 0.409162
## baseline_age -0.017340 0.009527 55.400335 -1.820 0.074143 .
## educ 0.122535 0.040692 55.658041 3.011 0.003907 **
## y.plot:monthssincebaseline -0.003035 0.005137 40.771369 -0.591 0.557874
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.217
## mnthssncbsl 0.023 0.017
## baseline_ag -0.369 0.583 0.021
## educ -0.779 -0.160 -0.026 -0.281
## y.plt:mnths 0.007 0.075 -0.036 0.006 -0.011
## [1] "y.plot = baseline_test5meanZ"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 252.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -12.3608 -0.0371 -0.0093 0.0136 3.6318
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 0.4795919 0.69253
## monthssincebaseline 0.0009145 0.03024 0.04
## Residual 0.0358432 0.18932
## Number of obs: 343, groups: unique_id, 63
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -0.754767 0.696474 58.061637 -1.084 0.28298
## y.plot -0.366402 0.110560 58.338460 -3.314 0.00158 **
## monthssincebaseline 0.004592 0.004940 40.157402 0.930 0.35814
## baseline_age -0.013705 0.009450 58.143548 -1.450 0.15238
## educ 0.107476 0.040418 58.128838 2.659 0.01011 *
## y.plot:monthssincebaseline -0.007477 0.005057 40.265241 -1.478 0.14706
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.262
## mnthssncbsl 0.003 0.005
## baseline_ag -0.391 0.600 0.005
## educ -0.790 -0.114 -0.007 -0.241
## y.plt:mnths 0.002 -0.003 -0.046 -0.002 -0.001Sample description for model 2 (familial)
Model 2 same as model 1, but in a sample with baseline CDR+NACC-FTLD global scores >= 0.5 ( no zeros). Sample size was too small to look at 1+. Removed condition requiring age<=45. Using original CDR+NACC-FTLD sum of boxes.
## [1] "N participants at each visit (NOT chapter)"
##
## 1 2 3
## 39 33 24
## [1] "Gentic breakdown"
##
## C9 MAPT
## 46 19
## [1] "Baseline CDR-NACC+FTLD-motor global score"
##
## 0.5 1 2
## 21 6 2LME model 2: Mutation pos baseline CDR 0.5+ or greater
Presents graphs first, then a print out of the models. Note the failure to converge/warnings of several models.
Removed condition requiring age<=45. Using original CDR+NACC-FTLD sum of boxes.
## [1] "y.plot = baseline_gonogo"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 186.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -6.2664 -0.0479 -0.0005 0.0728 1.6413
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 2.748555 1.65788
## monthssincebaseline 0.009041 0.09508 -0.45
## Residual 0.141754 0.37650
## Number of obs: 74, groups: unique_id, 17
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -4.94013 1.96763 12.60271 -2.511 0.026553 *
## y.plot 0.33552 0.37304 12.01441 0.899 0.386090
## monthssincebaseline 0.03285 0.03069 7.67913 1.070 0.316967
## baseline_age 0.10239 0.03734 12.59098 2.742 0.017206 *
## educ 0.10492 0.01891 8.60358 5.550 0.000419 ***
## y.plot:monthssincebaseline 0.01761 0.03650 7.09191 0.482 0.644039
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.308
## mnthssncbsl -0.071 -0.020
## baseline_ag -0.957 0.350 0.005
## educ -0.043 -0.104 -0.047 -0.164
## y.plt:mnths -0.030 -0.262 0.012 0.028 -0.005
## [1] "y.plot = baseline_strp"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 135.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -5.5817 -0.1197 -0.0195 0.1068 1.5924
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 1.379838 1.17467
## monthssincebaseline 0.003946 0.06281 -0.78
## Residual 0.176073 0.41961
## Number of obs: 58, groups: unique_id, 12
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -5.85024 2.41644 7.43900 -2.421 0.0440 *
## y.plot -0.18699 0.45785 9.58896 -0.408 0.6919
## monthssincebaseline 0.02931 0.02209 8.25963 1.327 0.2202
## baseline_age 0.05066 0.02590 7.91096 1.956 0.0866 .
## educ 0.32634 0.11908 7.57539 2.740 0.0268 *
## y.plot:monthssincebaseline -0.05276 0.02815 8.45289 -1.875 0.0957 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.149
## mnthssncbsl -0.345 0.127
## baseline_ag -0.546 0.144 0.065
## educ -0.830 0.059 0.256 0.009
## y.plt:mnths -0.070 -0.646 -0.172 0.202 -0.029
## [1] "y.plot = baseline_flk"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 195
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -6.5657 -0.0708 -0.0021 0.0633 1.8293
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 2.440995 1.56237
## monthssincebaseline 0.004563 0.06755 -0.46
## Residual 0.127859 0.35757
## Number of obs: 83, groups: unique_id, 19
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -4.22328 2.27963 14.45922 -1.853 0.08446 .
## y.plot 0.23288 0.57002 15.59500 0.409 0.68842
## monthssincebaseline 0.02333 0.02037 10.11459 1.145 0.27838
## baseline_age 0.08843 0.03824 14.37650 2.313 0.03602 *
## educ 0.10421 0.02820 13.05595 3.695 0.00268 **
## y.plot:monthssincebaseline -0.04446 0.01664 8.99733 -2.672 0.02556 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.656
## mnthssncbsl -0.116 0.030
## baseline_ag -0.958 0.541 0.056
## educ -0.563 0.742 0.027 0.355
## y.plt:mnths -0.043 -0.184 0.127 0.015 0.110
## [1] "y.plot = baseline_nback"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 120.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -5.2799 -0.0260 0.0394 0.1167 1.4651
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 2.28240 1.51076
## monthssincebaseline 0.00635 0.07969 -0.99
## Residual 0.19546 0.44211
## Number of obs: 50, groups: unique_id, 10
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -2.56658 1.69565 2.95324 -1.514 0.2287
## y.plot -1.13751 0.50097 8.09772 -2.271 0.0525 .
## monthssincebaseline 0.03364 0.02763 6.92034 1.218 0.2632
## baseline_age -0.06666 0.02108 1.58372 -3.162 0.1165
## educ 0.47404 0.07916 2.51783 5.989 0.0151 *
## y.plot:monthssincebaseline -0.04818 0.02600 6.39384 -1.853 0.1103
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.116
## mnthssncbsl -0.488 -0.179
## baseline_ag -0.560 0.315 0.003
## educ -0.736 -0.026 0.276 -0.067
## y.plt:mnths -0.184 -0.859 0.190 0.145 0.050
## [1] "y.plot = baseline_humi"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 193.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -6.5234 -0.0530 -0.0055 0.0484 1.7383
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 2.322839 1.52409
## monthssincebaseline 0.008087 0.08993 -0.06
## Residual 0.130791 0.36165
## Number of obs: 80, groups: unique_id, 18
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -2.09256 2.33540 13.89136 -0.896 0.385508
## y.plot -0.46670 0.42296 13.86123 -1.103 0.288640
## monthssincebaseline 0.03740 0.02966 8.82448 1.261 0.239585
## baseline_age 0.05541 0.04287 13.87223 1.293 0.217287
## educ 0.08533 0.01976 14.00994 4.318 0.000707 ***
## y.plot:monthssincebaseline -0.02183 0.03694 9.38151 -0.591 0.568421
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.643
## mnthssncbsl -0.022 -0.002
## baseline_ag -0.971 0.620 0.010
## educ -0.223 0.222 0.003 0.045
## y.plt:mnths -0.013 -0.054 0.236 0.008 0.018
## [1] "y.plot = baseline_test3meanZ"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 197.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -6.5835 -0.0533 0.0009 0.0796 1.8051
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 2.268839 1.50627
## monthssincebaseline 0.005484 0.07406 -0.21
## Residual 0.127960 0.35771
## Number of obs: 83, groups: unique_id, 19
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -2.34978 2.56290 14.65548 -0.917 0.37407
## y.plot -0.36322 0.50523 15.07081 -0.719 0.48319
## monthssincebaseline 0.02882 0.02300 9.71928 1.253 0.23942
## baseline_age 0.06116 0.04471 14.56386 1.368 0.19212
## educ 0.08280 0.02330 14.61692 3.554 0.00299 **
## y.plot:monthssincebaseline -0.04057 0.02146 9.67829 -1.891 0.08896 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.739
## mnthssncbsl -0.064 0.030
## baseline_ag -0.974 0.684 0.038
## educ -0.498 0.588 0.019 0.335
## y.plt:mnths -0.030 -0.069 0.136 0.015 0.084
## [1] "y.plot = baseline_test5meanZ"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 194.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -6.5763 -0.0596 0.0039 0.0767 1.7863
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 2.318587 1.5227
## monthssincebaseline 0.004213 0.0649 -0.33
## Residual 0.128369 0.3583
## Number of obs: 83, groups: unique_id, 19
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -2.44311 2.36608 14.84516 -1.033 0.318342
## y.plot -0.30728 0.47407 15.32826 -0.648 0.526470
## monthssincebaseline 0.02600 0.02005 9.34347 1.296 0.226002
## baseline_age 0.06018 0.04197 14.69852 1.434 0.172534
## educ 0.08977 0.02124 12.98832 4.227 0.000991 ***
## y.plot:monthssincebaseline -0.05239 0.01982 9.41783 -2.643 0.025808 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.682
## mnthssncbsl -0.100 0.044
## baseline_ag -0.971 0.631 0.059
## educ -0.414 0.486 0.016 0.240
## y.plt:mnths -0.070 -0.109 0.124 0.051 0.128LME models (Project 2: Sporadic)
Sample description for model 1 (Sporadic)
LME model 1: Mutation- baseline CDR <=0.5
Presents graphs first, then a print out of the models. Note the failure to converge/warnings of several models.
Removed age 45 restriction. using OG FTLD CDR
## [1] "y.plot = baseline_gonogo"## boundary (singular) fit: see help('isSingular')## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 352.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -5.1363 -0.0633 -0.0145 0.0496 4.2756
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 8.190e-01 0.904985
## monthssincebaseline 1.263e-05 0.003553 1.00
## Residual 1.238e-01 0.351805
## Number of obs: 239, groups: unique_id, 40
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.591e-01 1.041e+00 4.020e+01 0.249 0.805
## y.plot -2.972e-01 1.941e-01 3.616e+01 -1.531 0.135
## monthssincebaseline 2.202e-03 1.776e-03 1.003e+02 1.240 0.218
## baseline_age 2.650e-02 1.214e-02 3.917e+01 2.184 0.035 *
## educ -6.743e-02 4.426e-02 4.037e+01 -1.524 0.135
## y.plot:monthssincebaseline -7.838e-04 1.402e-03 3.659e+01 -0.559 0.580
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.214
## mnthssncbsl 0.057 -0.046
## baseline_ag -0.689 0.377 -0.008
## educ -0.764 -0.057 -0.030 0.080
## y.plt:mnths 0.011 0.398 0.324 0.075 -0.098
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')## [1] "y.plot = baseline_strp"## Warning in checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, :
## Model failed to converge with max|grad| = 0.305282 (tol = 0.002, component 1)
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: -331.6
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.2507 -0.0339 0.0009 0.0281 5.3383
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 6.482e-01 0.805135
## monthssincebaseline 7.308e-06 0.002703 0.04
## Residual 3.145e-03 0.056084
## Number of obs: 237, groups: unique_id, 43
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -0.0486082 0.9408195 42.2921312 -0.052 0.9590
## y.plot -0.0752999 0.1823556 42.3154071 -0.413 0.6817
## monthssincebaseline 0.0009251 0.0006622 29.5490405 1.397 0.1728
## baseline_age 0.0227123 0.0131775 42.3149213 1.724 0.0921 .
## educ -0.0444999 0.0379225 42.2797956 -1.173 0.2472
## y.plot:monthssincebaseline -0.0005979 0.0006415 33.4886890 -0.932 0.3580
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.472
## mnthssncbsl -0.003 0.003
## baseline_ag -0.722 0.724 0.005
## educ -0.670 -0.094 0.002 -0.014
## y.plt:mnths -0.004 0.011 -0.016 0.004 0.002
## optimizer (nloptwrap) convergence code: 0 (OK)
## Model failed to converge with max|grad| = 0.305282 (tol = 0.002, component 1)## [1] "y.plot = baseline_flk"## boundary (singular) fit: see help('isSingular')
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 366.4
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -5.2944 -0.0729 -0.0183 0.0597 4.5454
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 7.065e-01 0.840532
## monthssincebaseline 1.222e-05 0.003496 1.00
## Residual 1.123e-01 0.335145
## Number of obs: 265, groups: unique_id, 47
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.573e-01 9.396e-01 4.805e+01 0.487 0.6287
## y.plot -3.787e-01 1.537e-01 4.520e+01 -2.463 0.0177 *
## monthssincebaseline 1.349e-03 1.587e-03 9.753e+01 0.850 0.3973
## baseline_age 1.420e-02 1.261e-02 4.631e+01 1.126 0.2659
## educ -4.298e-02 4.125e-02 4.864e+01 -1.042 0.3026
## y.plot:monthssincebaseline 5.029e-04 1.732e-03 1.336e+02 0.290 0.7719
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.272
## mnthssncbsl -0.031 0.109
## baseline_ag -0.658 0.639 0.130
## educ -0.701 -0.233 -0.042 -0.058
## y.plt:mnths -0.025 0.098 -0.212 -0.019 0.056
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')## [1] "y.plot = baseline_nback"## Warning in checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, :
## Model failed to converge with max|grad| = 0.353007 (tol = 0.002, component 1)
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: -288.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.0315 -0.0516 0.0018 0.0450 5.0650
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 7.005e-01 0.836940
## monthssincebaseline 6.899e-06 0.002627 0.02
## Residual 3.485e-03 0.059038
## Number of obs: 212, groups: unique_id, 36
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -0.0123290 0.9872214 35.7601143 -0.012 0.9901
## y.plot -0.2142567 0.1552653 35.7497869 -1.380 0.1762
## monthssincebaseline 0.0011118 0.0006917 23.6524519 1.607 0.1213
## baseline_age 0.0234561 0.0120227 35.7604521 1.951 0.0589 .
## educ -0.0468761 0.0415493 35.7687096 -1.128 0.2667
## y.plot:monthssincebaseline -0.0011302 0.0006677 31.0891969 -1.693 0.1005
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.241
## mnthssncbsl 0.000 0.000
## baseline_ag -0.691 0.429 0.000
## educ -0.747 -0.060 -0.001 0.057
## y.plt:mnths 0.000 -0.004 -0.062 0.001 0.000
## optimizer (nloptwrap) convergence code: 0 (OK)
## Model failed to converge with max|grad| = 0.353007 (tol = 0.002, component 1)## [1] "y.plot = baseline_humi"## boundary (singular) fit: see help('isSingular')
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 359.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -5.2937 -0.0696 -0.0062 0.0435 4.3660
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 6.742e-01 0.82108
## monthssincebaseline 6.001e-06 0.00245 1.00
## Residual 1.179e-01 0.34340
## Number of obs: 256, groups: unique_id, 44
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 0.645979 0.987742 46.312541 0.654 0.5163
## y.plot -0.469061 0.179866 47.078637 -2.608 0.0122 *
## monthssincebaseline 0.002417 0.001527 91.961965 1.583 0.1169
## baseline_age 0.010116 0.014028 47.004536 0.721 0.4744
## educ -0.035017 0.042861 46.187331 -0.817 0.4181
## y.plot:monthssincebaseline -0.002485 0.001693 107.155892 -1.467 0.1452
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.334
## mnthssncbsl 0.023 -0.039
## baseline_ag -0.683 0.704 -0.016
## educ -0.624 -0.311 0.008 -0.130
## y.plt:mnths 0.023 0.030 0.108 -0.043 0.008
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')## [1] "y.plot = baseline_test3meanZ"## boundary (singular) fit: see help('isSingular')
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 362.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -5.3749 -0.0624 -0.0145 0.0509 4.4769
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 6.376e-01 0.79848
## monthssincebaseline 8.879e-06 0.00298 1.00
## Residual 1.131e-01 0.33624
## Number of obs: 265, groups: unique_id, 47
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 0.922155 0.943352 46.026088 0.978 0.33342
## y.plot -0.562510 0.178985 45.546519 -3.143 0.00294 **
## monthssincebaseline 0.002110 0.001507 90.358536 1.400 0.16492
## baseline_age 0.002053 0.014127 45.646609 0.145 0.88510
## educ -0.027796 0.040954 46.123168 -0.679 0.50071
## y.plot:monthssincebaseline -0.001395 0.001714 113.650800 -0.814 0.41735
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.377
## mnthssncbsl -0.001 0.006
## baseline_ag -0.684 0.751 0.033
## educ -0.596 -0.324 -0.004 -0.164
## y.plt:mnths 0.017 0.029 0.010 -0.057 0.035
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')## [1] "y.plot = baseline_test5meanZ"## boundary (singular) fit: see help('isSingular')
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 376.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -5.5812 -0.0568 -0.0101 0.0273 4.6051
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 7.519e-01 0.867139
## monthssincebaseline 9.193e-06 0.003032 1.00
## Residual 1.059e-01 0.325470
## Number of obs: 282, groups: unique_id, 50
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 0.562143 0.978772 50.415477 0.574 0.568
## y.plot -0.275245 0.178927 49.125787 -1.538 0.130
## monthssincebaseline 0.002050 0.001440 112.248083 1.424 0.157
## baseline_age 0.016344 0.013443 50.155597 1.216 0.230
## educ -0.055348 0.040740 50.544704 -1.359 0.180
## y.plot:monthssincebaseline -0.001841 0.001659 154.405959 -1.109 0.269
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.432
## mnthssncbsl -0.014 0.017
## baseline_ag -0.707 0.719 0.051
## educ -0.661 -0.160 0.003 -0.047
## y.plt:mnths 0.000 0.077 -0.016 -0.021 0.018
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')
Sample description for model 2 (Sporadic)
## [1] "N participants at each visit (NOT chapter)"
##
## 1 2 3 4 5 6
## 86 72 51 3 4 1
## [1] "Gentic breakdown"
##
## NONE
## 118
## [1] "Baseline CDR-NACC+FTLD-motor global score"
##
## 0.5 1
## 28 54LME model 2: Mutation-, baseline CDR 0.5 or greater
Presents graphs first, then a print out of the models. Note the failure to converge/warnings of several models.
Models do not converge. We see a trend for the interaction of Nback and time.
## [1] "y.plot = baseline_gonogo"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 468.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.03520 -0.08189 -0.01522 0.08050 2.74173
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 8.35959 2.8913
## monthssincebaseline 0.03757 0.1938 0.20
## Residual 0.31739 0.5634
## Number of obs: 155, groups: unique_id, 28
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.01840 5.42202 24.63614 0.372 0.712882
## y.plot -1.60975 0.41076 24.51363 -3.919 0.000627 ***
## monthssincebaseline 0.07529 0.05149 12.29476 1.462 0.168768
## baseline_age -0.01735 0.07396 24.45492 -0.235 0.816448
## educ 0.20826 0.22616 24.03798 0.921 0.366293
## y.plot:monthssincebaseline 0.01286 0.04346 12.64899 0.296 0.772177
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot 0.048
## mnthssncbsl 0.034 0.032
## baseline_ag -0.728 -0.055 -0.013
## educ -0.496 0.038 -0.013 -0.225
## y.plt:mnths -0.028 0.104 0.065 0.026 0.011
## [1] "y.plot = baseline_strp"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 16
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.35671 -0.04215 -0.00046 0.02026 3.10288
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 4.316715 2.07767
## monthssincebaseline 0.025870 0.16084 0.37
## Residual 0.009775 0.09887
## Number of obs: 87, groups: unique_id, 13
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -6.59978 7.11677 8.53587 -0.927 0.37922
## y.plot -1.20256 0.57758 9.05144 -2.082 0.06686 .
## monthssincebaseline 0.05336 0.05388 9.40692 0.990 0.34673
## baseline_age 0.11739 0.07851 7.80165 1.495 0.17415
## educ 0.09866 0.26645 7.17584 0.370 0.72187
## y.plot:monthssincebaseline -0.15454 0.04601 8.60732 -3.359 0.00895 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot 0.182
## mnthssncbsl 0.082 0.132
## baseline_ag -0.795 0.190 -0.028
## educ -0.726 -0.467 -0.056 0.170
## y.plt:mnths -0.001 0.273 0.243 0.041 -0.028
## [1] "y.plot = baseline_flk"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 523.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.10396 -0.08419 -0.00910 0.05452 2.81571
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 8.9851 2.9975
## monthssincebaseline 0.0343 0.1852 0.27
## Residual 0.3020 0.5496
## Number of obs: 170, groups: unique_id, 35
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.4846866 4.9588885 30.1457731 0.904 0.373
## y.plot -2.2711980 0.4129668 30.8309498 -5.500 5.21e-06
## monthssincebaseline 0.0776902 0.0460160 14.0460918 1.688 0.113
## baseline_age -0.0761805 0.0713495 28.3182950 -1.068 0.295
## educ 0.3112957 0.2142331 27.8531390 1.453 0.157
## y.plot:monthssincebaseline 0.0006305 0.0359966 14.6064641 0.018 0.986
##
## (Intercept)
## y.plot ***
## monthssincebaseline
## baseline_age
## educ
## y.plot:monthssincebaseline
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot -0.021
## mnthssncbsl 0.049 0.060
## baseline_ag -0.713 0.220 -0.017
## educ -0.442 -0.207 -0.020 -0.305
## y.plt:mnths -0.019 0.163 0.126 0.024 0.004
## [1] "y.plot = baseline_nback"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 13.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.33027 -0.06868 0.00231 0.01858 3.06867
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 3.415036 1.84798
## monthssincebaseline 0.057421 0.23963 0.74
## Residual 0.009937 0.09969
## Number of obs: 85, groups: unique_id, 12
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.57529 5.87054 6.50924 0.609 0.563
## y.plot -0.36496 0.56164 9.57600 -0.650 0.531
## monthssincebaseline 0.10145 0.07678 10.47417 1.321 0.215
## baseline_age 0.03490 0.06541 5.76912 0.534 0.614
## educ -0.21546 0.17191 6.69622 -1.253 0.252
## y.plot:monthssincebaseline -0.03110 0.07208 10.03201 -0.431 0.675
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot 0.287
## mnthssncbsl 0.116 0.246
## baseline_ag -0.904 -0.256 -0.051
## educ -0.765 -0.161 -0.027 0.431
## y.plt:mnths 0.028 0.696 0.261 0.002 -0.011
## [1] "y.plot = baseline_humi"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 514.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.11416 -0.08299 -0.00647 0.05428 2.79101
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 8.69817 2.9493
## monthssincebaseline 0.03143 0.1773 -0.04
## Residual 0.30421 0.5516
## Number of obs: 168, groups: unique_id, 34
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) -1.65359 5.06217 30.09184 -0.327 0.7462
## y.plot -1.90318 0.40704 30.18182 -4.676 5.74e-05 ***
## monthssincebaseline 0.05837 0.04466 13.83295 1.307 0.2125
## baseline_age -0.01322 0.06942 30.00158 -0.190 0.8503
## educ 0.42870 0.22202 29.74840 1.931 0.0631 .
## y.plot:monthssincebaseline -0.04407 0.04601 14.21126 -0.958 0.3542
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot 0.101
## mnthssncbsl -0.008 -0.011
## baseline_ag -0.693 0.012 0.001
## educ -0.493 -0.109 0.003 -0.277
## y.plt:mnths 0.004 -0.046 0.039 0.000 -0.006
## [1] "y.plot = baseline_test3meanZ"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 516.4
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.10735 -0.08072 -0.00504 0.06190 2.81223
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 7.22189 2.6874
## monthssincebaseline 0.03335 0.1826 0.15
## Residual 0.30218 0.5497
## Number of obs: 170, groups: unique_id, 35
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.209997 4.496914 30.313916 0.491 0.6266
## y.plot -2.443881 0.363698 30.650571 -6.720 1.71e-07 ***
## monthssincebaseline 0.067644 0.045811 13.926695 1.477 0.1620
## baseline_age -0.061409 0.063994 29.351913 -0.960 0.3451
## educ 0.379899 0.196088 28.939392 1.937 0.0625 .
## y.plot:monthssincebaseline -0.009143 0.041266 14.570022 -0.222 0.8277
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot 0.067
## mnthssncbsl 0.032 0.036
## baseline_ag -0.704 0.158 -0.013
## educ -0.456 -0.241 -0.014 -0.303
## y.plt:mnths -0.005 0.059 0.092 0.003 0.008
## [1] "y.plot = baseline_test5meanZ"
## [1] "ftldcdr_box.computed~y.plot*monthssincebaseline+baseline_age+educ+(1+monthssincebaseline | unique_id)"
## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: fml.lme
## Data: df.lme.loop
##
## REML criterion at convergence: 523
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.11383 -0.08561 -0.00505 0.05974 2.81166
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## unique_id (Intercept) 9.35522 3.0586
## monthssincebaseline 0.03138 0.1771 -0.17
## Residual 0.30180 0.5494
## Number of obs: 170, groups: unique_id, 35
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 0.72957 5.11478 30.84430 0.143 0.8875
## y.plot -2.18408 0.40845 31.02515 -5.347 7.91e-06 ***
## monthssincebaseline 0.04889 0.04454 13.74394 1.098 0.2912
## baseline_age -0.04218 0.07170 30.29845 -0.588 0.5607
## educ 0.40346 0.22300 29.95461 1.809 0.0805 .
## y.plot:monthssincebaseline -0.04531 0.03925 14.52246 -1.154 0.2669
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) y.plot mnthss bsln_g educ
## y.plot 0.139
## mnthssncbsl -0.033 -0.044
## baseline_ag -0.700 0.098 0.009
## educ -0.470 -0.264 0.014 -0.293
## y.plt:mnths 0.015 -0.113 0.095 -0.015 -0.006Power analysis
Power anlaysis with Full Sample
Presents change over 1 year. Difference scores were calculated as annualized change ([~1 year score - baseline]/time). First presents a plot with all tests. Then presents a restricted plot showing only sample sizes <1000
## Warning: Using one column matrices in `filter()` was deprecated in dplyr 1.1.0.
## ℹ Please use one dimensional logical vectors instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.## Warning: Use of `df.model$Task` is discouraged.
## ℹ Use `Task` instead.
## Use of `df.model$Task` is discouraged.
## ℹ Use `Task` instead.
## Warning: Use of `df.model.rest$Task` is discouraged.
## ℹ Use `Task` instead.## Warning: Use of `df.model.rest$Task` is discouraged.
## ℹ Use `Task` instead.
| Task | n.with.test | Z.Decline | CI.low | CI.high | sample_size.25 | sample_size.40 |
|---|---|---|---|---|---|---|
| change_moca | 44 | 0.0104035 | -0.6478557 | 0.6686627 | 1005529 | 392785 |
| change_ftlcdrm_sob | 46 | 0.1713188 | -0.3363173 | 0.6789549 | 2206 | 862 |
| change_strp | 37 | 0.0780440 | -0.0809017 | 0.2369897 | 1042 | 407 |
| change_flk | 45 | -0.1117156 | -0.2102493 | -0.0131818 | 196 | 77 |
| change_nback | 35 | 0.2691843 | -0.1892757 | 0.7276443 | 729 | 285 |
| change_humi | 44 | 0.0788197 | -0.0475274 | 0.2051669 | 646 | 253 |
| change_gonogo | 37 | -27.1431066 | -33.4097271 | -20.8764860 | 14 | 6 |
| change_trailsb | 38 | 3.0008595 | -10.9294388 | 16.9311578 | 5413 | 2115 |
| change_animals | 41 | 0.2891625 | -1.3849230 | 1.9632480 | 8419 | 3289 |
| change_uds3ef | 43 | 0.0257309 | -0.1291771 | 0.1806390 | 9104 | 3556 |
| change_trailsb_ratio | 38 | -0.0039344 | -0.0466109 | 0.0387421 | 29552 | 11544 |
| change_test3meanZ | 45 | -0.0422802 | -0.1904704 | 0.1059100 | 3086 | 1206 |
| change_test5meanZ | 46 | 0.0256067 | -0.1537859 | 0.2049993 | 12327 | 4816 |
Power Familial
Presents change over 1 year. Difference scores were calculated as annualized change ([~1 year score - baseline]/time). First presents a plot with all tests. Then presents a restricted plot showing only sample sizes <1000
## Warning: Use of `df.model$Task` is discouraged.
## ℹ Use `Task` instead.
## Use of `df.model$Task` is discouraged.
## ℹ Use `Task` instead.
## Warning: Use of `df.model.rest$Task` is discouraged.
## ℹ Use `Task` instead.## Warning: Use of `df.model.rest$Task` is discouraged.
## ℹ Use `Task` instead.
| Task | n.with.test | Z.Decline | CI.low | CI.high | sample_size.25 | sample_size.40 |
|---|---|---|---|---|---|---|
| change_moca | 20 | 0.3263958 | -0.2228450 | 0.8756366 | 712 | 278 |
| change_ftlcdrm_sob | 21 | 0.1289899 | -0.4621162 | 0.7200961 | 5275 | 2061 |
| change_strp | 20 | 0.0651410 | -0.0706241 | 0.2009061 | 1091 | 427 |
| change_flk | 21 | -0.1211937 | -0.2148427 | -0.0275448 | 150 | 59 |
| change_nback | 19 | 0.4156407 | -0.0022629 | 0.8335442 | 254 | 100 |
| change_humi | 21 | 0.0700139 | -0.0509873 | 0.1910151 | 751 | 294 |
| change_gonogo | 17 | -27.1124517 | -33.8396853 | -20.3852182 | 16 | 7 |
| change_trailsb | 17 | 1.3883653 | -9.5696159 | 12.3463465 | 15647 | 6112 |
| change_animals | 19 | 0.1046917 | -1.6717601 | 1.8811435 | 72317 | 28249 |
| change_uds3ef | 20 | 0.0185432 | -0.1236633 | 0.1607497 | 14772 | 5771 |
| change_trailsb_ratio | 17 | -0.0075054 | -0.0483390 | 0.0333281 | 7435 | 2904 |
| change_test3meanZ | 21 | -0.0459534 | -0.1516137 | 0.0597068 | 1328 | 519 |
| change_test5meanZ | 21 | 0.0631541 | -0.0634504 | 0.1897587 | 1010 | 395 |
Power Sporadic
Presents change over 1 year. Difference scores were calculated as annualized change ([~1 year score - baseline]/time). First presents a plot with all tests. Then presents a restricted plot showing only sample sizes <1000
## Warning: Use of `df.model$Task` is discouraged.
## ℹ Use `Task` instead.
## Use of `df.model$Task` is discouraged.
## ℹ Use `Task` instead.
## Warning: Use of `df.model.rest$Task` is discouraged.
## ℹ Use `Task` instead.## Warning: Use of `df.model.rest$Task` is discouraged.
## ℹ Use `Task` instead.
| Task | n.with.test | Z.Decline | CI.low | CI.high | sample_size.25 | sample_size.40 |
|---|---|---|---|---|---|---|
| change_moca | 22 | -0.2067335 | -0.8050542 | 0.3915872 | 2104 | 822 |
| change_ftlcdrm_sob | 23 | 0.2165820 | -0.2353659 | 0.6685299 | 1094 | 428 |
| change_strp | 16 | 0.0875933 | -0.1027420 | 0.2779286 | 1186 | 464 |
| change_flk | 22 | -0.1000289 | -0.2080684 | 0.0080107 | 293 | 115 |
| change_nback | 15 | 0.0977832 | -0.3735157 | 0.5690821 | 5835 | 2280 |
| change_humi | 21 | 0.0860915 | -0.0524747 | 0.2246578 | 651 | 255 |
| change_gonogo | 18 | -26.9446090 | -33.2694596 | -20.6197583 | 14 | 6 |
| change_trailsb | 19 | 4.1781463 | -12.7440309 | 21.1003236 | 4121 | 1610 |
| change_animals | 20 | 0.3790547 | -1.2732363 | 2.0313457 | 4773 | 1865 |
| change_uds3ef | 21 | 0.0258267 | -0.1487428 | 0.2003961 | 11476 | 4483 |
| change_trailsb_ratio | 19 | 0.0017167 | -0.0447079 | 0.0481413 | 183676 | 71749 |
| change_test3meanZ | 22 | -0.0482329 | -0.2331190 | 0.1366533 | 3691 | 1442 |
| change_test5meanZ | 23 | -0.0130740 | -0.2319168 | 0.2057689 | 70374 | 27490 |
Power baseline CDR 0.5 and 1
Presents change over 1 year. Difference scores were calculated as annualized change ([~1 year score - baseline]/time). First presents a plot with all tests. Then presents a restricted plot showing only sample sizes <1000
## Warning: Use of `df.model$Task` is discouraged.
## ℹ Use `Task` instead.
## Use of `df.model$Task` is discouraged.
## ℹ Use `Task` instead.
## Warning: Use of `df.model.rest$Task` is discouraged.
## ℹ Use `Task` instead.## Warning: Use of `df.model.rest$Task` is discouraged.
## ℹ Use `Task` instead.
| Task | n.with.test | Z.Decline | CI.low | CI.high | sample_size.25 | sample_size.40 |
|---|---|---|---|---|---|---|
| change_moca | 11 | -0.1676607 | -1.0987822 | 0.7634607 | 7747 | 3026 |
| change_ftlcdrm_sob | 12 | 0.3499182 | -0.1888556 | 0.8886921 | 596 | 233 |
| change_strp | 8 | 0.1796356 | 0.0144110 | 0.3448603 | 213 | 83 |
| change_flk | 12 | -0.0786802 | -0.1741220 | 0.0167617 | 370 | 145 |
| change_nback | 8 | 0.0965442 | -0.5117842 | 0.7048726 | 9972 | 3896 |
| change_humi | 12 | 0.0567625 | -0.0844454 | 0.1979705 | 1555 | 608 |
| change_gonogo | 11 | -26.7714457 | -32.7198005 | -20.8230910 | 13 | 5 |
| change_trailsb | 10 | 9.2536561 | -12.6574901 | 31.1648023 | 1409 | 551 |
| change_animals | 11 | 0.1985917 | -1.6048098 | 2.0019932 | 20712 | 8091 |
| change_uds3ef | 11 | -0.0031339 | -0.2118314 | 0.2055636 | 1113853 | 435099 |
| change_trailsb_ratio | 10 | -0.0100370 | -0.0522874 | 0.0322135 | 4451 | 1739 |
| change_test3meanZ | 12 | -0.0581246 | -0.2767255 | 0.1604762 | 3553 | 1388 |
| change_test5meanZ | 12 | -0.0195084 | -0.2790557 | 0.2400389 | 44458 | 17367 |