Merge pull request #183 from LCBC-UiO/dev

Small fixes
LCBC-UiO · Apr 4, 2024 · 5be856c · 5be856c
2 parents 8a2dc5d + 82e581a
commit 5be856c
Show file tree

Hide file tree

Showing 17 changed files with 22 additions and 63 deletions.
diff --git a/R/data.R b/R/data.R
@@ -212,6 +212,7 @@
 #' \item{domain}{Cognitive domain being measured. One of \code{"epmem"} for
 #' episodic memory, \code{"wmem"} for working memory and \code{"execfun"} for
 #' executive function/speed.}
+#' \item{timepoint}{Integer indicating the timepoint number.}
 #' \item{age}{Age of participant at the timepoint.}
 #' \item{test}{The particular test at this observation.}
 #' \item{y}{Response. For \code{"epmem"} and \code{"wmem"} this is the number

diff --git a/R/gamm4-functions.R b/R/gamm4-functions.R
@@ -425,8 +425,9 @@ gamm4.wrapup <- function(gobj, ret, final_model) {
   }
 
   object$fitted.values <- fitted(ret)
-  object$linear.predictors <- vapply(object$family_mapping, function(i) {
-    object$family[[i]]$linkfun(object$fitted.values[[i]])
+  object$linear.predictors <- vapply(seq_along(object$family_mapping), function(i) {
+    family_index <- object$family_mapping[[i]]
+    object$family[[family_index]]$linkfun(object$fitted.values[[i]])
   }, numeric(1))
 
   object$residuals <- residuals(ret$mer)

diff --git a/data-raw/lifespan.R b/data-raw/lifespan.R
@@ -123,10 +123,11 @@ lifespan <- tibble(
     y = case_when(
       domain == "execfun" ~ -(y - mean(y)) / sd(y),
       TRUE ~ y
-    )
+    ),
+    id = factor(id)
   ) %>%
   ungroup() %>%
-  select(-nu, -timepoint) %>%
+  select(-nu) %>%
   as.data.frame()
 
 mm <- model.matrix(~ 0 + domain, data = lifespan)

diff --git a/data/lifespan.rda b/data/lifespan.rda
diff --git a/man/lifespan.Rd b/man/lifespan.Rd
diff --git a/vignettes/glmm_factor.Rmd b/vignettes/glmm_factor.Rmd
@@ -347,11 +347,6 @@ In this case we can confirm that the `galamm` function is correctly implemented
 ```r
 library(lme4)
 #> Loading required package: Matrix
-#> 
-#> Attaching package: 'lme4'
-#> The following object is masked from 'package:galamm':
-#> 
-#>     llikAIC
 count_mod_lme4 <- glmer(
   formula = y ~ lbas * treat + lage + v4 + (1 | subj),
   data = epilep,
@@ -395,7 +390,7 @@ summary(count_mod_lme4)
 #> (Intercept)   1.7937     0.1045  17.165  < 2e-16 ***
 #> lbas          0.8844     0.1308   6.764 1.34e-11 ***
 #> treat        -0.3349     0.1474  -2.272  0.02311 *  
-#> lage          0.4845     0.3458   1.401  0.16121    
+#> lage          0.4845     0.3458   1.401  0.16122    
 #> v4           -0.1611     0.0543  -2.966  0.00301 ** 
 #> lbas:treat    0.3382     0.2025   1.671  0.09479 .  
 #> ---

diff --git a/vignettes/glmm_factor_poisson_diagnostic_lme4-1.png b/vignettes/glmm_factor_poisson_diagnostic_lme4-1.png
diff --git a/vignettes/mixed_response.Rmd b/vignettes/mixed_response.Rmd
@@ -115,10 +115,6 @@ summary(mixed_resp)
 #>      AIC      BIC   logLik deviance df.resid 
 #>   9248.7   9280.2  -4619.3   3633.1     3995 
 #> 
-#> Scaled residuals: 
-#>     Min      1Q  Median      3Q     Max 
-#> -3.5360 -0.7078  0.2156  0.6456  2.5978 
-#> 
 #> Lambda:
 #>         level      SE
 #> lambda1 1.000       .
@@ -179,10 +175,6 @@ summary(mod)
 #>      AIC      BIC   logLik deviance df.resid 
 #>  12356.9  12388.3  -6173.4  31426.4     3995 
 #> 
-#> Scaled residuals: 
-#>      Min       1Q   Median       3Q      Max 
-#> -15.2275  -0.4025   0.1262   0.6757  16.0284 
-#> 
 #> Random effects:
 #>  Groups Name        Variance Std.Dev.
 #>  id     (Intercept) 0        0       
@@ -353,10 +345,6 @@ summary(mod)
 #>      AIC      BIC   logLik deviance df.resid 
 #>   2837.6   2892.9  -1406.8  12529.3      730 
 #> 
-#> Scaled residuals: 
-#>      Min       1Q   Median       3Q      Max 
-#> -10.1375  -0.4389  -0.3522   0.2743  27.3350 
-#> 
 #> Lambda:
 #>         loading SE
 #> lambda1   1.000  .
@@ -472,10 +460,6 @@ summary(mod)
 #>      AIC      BIC   logLik deviance df.resid 
 #>   2768.3   2823.6  -1372.2   2002.9      730 
 #> 
-#> Scaled residuals: 
-#>     Min      1Q  Median      3Q     Max 
-#> -258547      -1       0       0      66 
-#> 
 #> Lambda:
 #>         loading      SE
 #> lambda1  1.0000       .
@@ -567,10 +551,6 @@ summary(mod0)
 #>      AIC      BIC   logLik deviance df.resid 
 #>   2764.0   2805.5  -1373.0   2007.9      733 
 #> 
-#> Scaled residuals: 
-#>     Min      1Q  Median      3Q     Max 
-#> -280306      -1       0       0      66 
-#> 
 #> Lambda:
 #>         loading      SE
 #> lambda1   1.000       .

diff --git a/vignettes/optimization.Rmd b/vignettes/optimization.Rmd
@@ -68,10 +68,6 @@ summary(mod)
 #>      AIC      BIC   logLik deviance df.resid 
 #>   2837.6   2892.9  -1406.8  12529.3      730 
 #> 
-#> Scaled residuals: 
-#>      Min       1Q   Median       3Q      Max 
-#> -10.1375  -0.4389  -0.3522   0.2743  27.3350 
-#> 
 #> Lambda:
 #>         loading SE
 #> lambda1   1.000  .
@@ -213,10 +209,6 @@ summary(mod)
 #>      AIC      BIC   logLik deviance df.resid 
 #>   2837.6   2892.9  -1406.8  12529.3      730 
 #> 
-#> Scaled residuals: 
-#>      Min       1Q   Median       3Q      Max 
-#> -10.1374  -0.4390  -0.3523   0.2743  27.3347 
-#> 
 #> Lambda:
 #>         loading SE
 #> lambda1   1.000  .
@@ -292,10 +284,6 @@ summary(mod)
 #>      AIC      BIC   logLik deviance df.resid 
 #>   2768.3   2823.6  -1372.2   2002.9      730 
 #> 
-#> Scaled residuals: 
-#>     Min      1Q  Median      3Q     Max 
-#> -258522      -1       0       0      66 
-#> 
 #> Lambda:
 #>         loading      SE
 #> lambda1  1.0000       .
@@ -391,10 +379,6 @@ summary(mod_nm)
 #>      AIC      BIC   logLik deviance df.resid 
 #>   2768.3   2823.6  -1372.2   2002.9      730 
 #> 
-#> Scaled residuals: 
-#>     Min      1Q  Median      3Q     Max 
-#> -258524      -1       0       0      66 
-#> 
 #> Lambda:
 #>         loading      SE
 #> lambda1  1.0000       .
@@ -407,16 +391,16 @@ summary(mod_nm)
 #> Number of obs: 742, groups:  id, 333
 #> 
 #> Fixed effects:
-#>               Estimate Std. Error  z value   Pr(>|z|)
-#> chd           -1.91525    0.27229 -7.03373  2.011e-12
-#> fiber         17.94851    0.48686 36.86604 1.618e-297
-#> fiber2         0.22398    0.41783  0.53604  5.919e-01
-#> chd:age        0.06614    0.05931  1.11527  2.647e-01
-#> chd:bus       -0.02893    0.34355 -0.08421  9.329e-01
-#> fiber:age     -0.21203    0.10090 -2.10130  3.561e-02
-#> fiber:bus     -1.68305    0.63721 -2.64126  8.260e-03
-#> chd:age:bus   -0.04998    0.06507 -0.76815  4.424e-01
-#> fiber:age:bus  0.16817    0.11223  1.49847  1.340e-01
+#>               Estimate Std. Error z value   Pr(>|z|)
+#> chd           -1.91525    0.27229 -7.0337  2.011e-12
+#> fiber         17.94851    0.48686 36.8660 1.618e-297
+#> fiber2         0.22398    0.41783  0.5360  5.919e-01
+#> chd:age        0.06614    0.05931  1.1153  2.647e-01
+#> chd:bus       -0.02893    0.34355 -0.0842  9.329e-01
+#> fiber:age     -0.21203    0.10090 -2.1013  3.561e-02
+#> fiber:bus     -1.68305    0.63721 -2.6413  8.260e-03
+#> chd:age:bus   -0.04998    0.06507 -0.7682  4.424e-01
+#> fiber:age:bus  0.16817    0.11223  1.4985  1.340e-01
 ```
 
 

diff --git a/vignettes/scaling-glmm-plot-1.png b/vignettes/scaling-glmm-plot-1.png
diff --git a/vignettes/scaling-hsced-plot-1.png b/vignettes/scaling-hsced-plot-1.png
diff --git a/vignettes/scaling-lmm-plot-1.png b/vignettes/scaling-lmm-plot-1.png
diff --git a/vignettes/scaling-semiparametric-binomial-plot-1.png b/vignettes/scaling-semiparametric-binomial-plot-1.png
diff --git a/vignettes/scaling-semiparametric-gaussian-plot-1.png b/vignettes/scaling-semiparametric-gaussian-plot-1.png
diff --git a/vignettes/semiparametric-mixed-by-factor1-1.png b/vignettes/semiparametric-mixed-by-factor1-1.png
diff --git a/vignettes/semiparametric-mixed-by-factor2-1.png b/vignettes/semiparametric-mixed-by-factor2-1.png
diff --git a/vignettes/semiparametric.Rmd b/vignettes/semiparametric.Rmd
@@ -779,10 +779,6 @@ summary(mod_byvar_mixed)
 #>      AIC      BIC   logLik deviance df.resid 
 #>   9476.1   9566.9  -4725.0  98981.3     7987 
 #> 
-#> Scaled residuals: 
-#>     Min      1Q  Median      3Q     Max 
-#> -13.543   0.426   1.987   6.127  18.637 
-#> 
 #> Lambda:
 #>         ability1      SE ability2      SE
 #> lambda1   1.0000       .        .       .
@@ -807,9 +803,9 @@ summary(mod_byvar_mixed)
 #> s(x):domain2:ability2Fx1  2.10045    0.47649  4.4082 1.042e-05
 #> 
 #> Approximate significance of smooth terms:
-#>                         edf Ref.df    F p-value
-#> s(x):domain1:ability1 7.865  7.865  880  <2e-16
-#> s(x):domain2:ability2 6.442  6.442 8007  <2e-16
+#>                         edf Ref.df   F p-value
+#> s(x):domain1:ability1 7.865  7.865 880  <2e-16
+#> s(x):domain2:ability2 3.036  3.036 285  <2e-16
 ```
 
 We can plot the estimated smooth terms: