still making improvements to results section

CODE/SM.Rmd

@@ -1,13 +1,13 @@
 ---
 title: Supplementary Materials to Establishing the reliability and validity of measures extracted from long-form recordings
 output:
-  pdf_document:
-    toc: yes
-    toc_depth: 3
   html_document:
     toc: yes
     toc_depth: '3'
     df_print: paged
+  pdf_document:
+    toc: yes
+    toc_depth: 3
 ---
 
 ```{r setup, include=FALSE, eval=TRUE}
@@ -266,6 +266,7 @@ df.icc.mixed<-read.csv("../output/df.icc.mixed.csv")
 
 #df.icc.mixed[df.icc.mixed$formula=="no_exp",c("data_set","metric")]
 
+df.icc.mixed$Type<-get_type(df.icc.mixed)
 
 
 ```
@@ -278,7 +279,6 @@ Out of the `r dim(df.icc.mixed)[1]` fitted models, `r table(df.icc.mixed$formula
 
 ```{r icc-allexp-fig3, echo=F,fig.width=4, fig.height=3,fig.cap="Distribution of ICC attributed to corpus (a) and children (b), when combining data from all corpora."}
 
-df.icc.mixed$Type<-get_type(df.icc.mixed)
 
 
 ggplot(df.icc.mixed, aes(y = icc_child_id, x = toupper(data_set))) +
@@ -298,7 +298,7 @@ panel.background = element_blank(), legend.key=element_blank(), axis.line = elem
 
 The majority of measures had ICCs between .3 and .5. `r sum(df.icc.mixed$icc_child_id > .5)` measures had higher ICCs, and surprisingly, `r sum(df.icc.mixed$icc_child_id[grep("och",df.icc.mixed$metric)] > .5)` of them corresponded to the "other child" category, known to have the worst accuracy according to previous analyses (Cristia et al., 2020). 
 
-### Checking whether high ICC for other child measures are due to presence of other siblings
+### Checking whether high ICC for other child measures are due to number of siblings
 
 ```{r explo-och-sibn}
 
@@ -349,13 +349,30 @@ names(icc.result.split)=c("icc_child_id")
 ```
 
 
-We reasoned this may be because children in our corpora vary in terms of the number of siblings they have, and that siblings' presence may be stable across recordings. To address this possibility, we fit the full model again to predict number of vocalizations from other children, but this time including sibling number as a fixed effect $lmer(metric~ age + sibling_number + (1|corpus/child))$, so that individual variation that was actually due to sibling number was captured by that fixed effect instead of the random effect for child. We had sibling number data for `r sum(has_n_of_sib[,"TRUE"])` recordings from `r length(levels(factor(mydat2$child_id[!is.na(mydat2$n_of_siblings)])))` in `r length(levels(factor(mydat2$experiment[!is.na(mydat2$n_of_siblings)])))` corpora (`r corp_w_sib_clean`). We fit this model for the metric with the highest Child ICC, ACLEW's total vocalization duration by other children. Results indicated the full model was singular, so we fitted a No Corpus model to be able to extract a Child ICC. In fact, there was no difference in Child ICC in our original analysis (`r round(df.icc.mixed[df.icc.mixed$metric=="voc_dur_och_ph" & df.icc.mixed$data_set=="aclew","icc_child_id"],2)`) versus this re-analysis including the number of siblings (`r round(icc.result.split["icc_child_id"],2)`).
+We reasoned this may be because children in our corpora vary in terms of the number of siblings they have, that siblings' presence may be stable across recordings, and that a greater number of siblings would lead to more other child vocalizations. As a result, any measure based on other child vocalizations would result in stable relative ranking of children due to the number of siblings present. To test this hypothesis, we selected the metric with the highest Child ICC, namely ACLEW's total vocalization duration by other children. We fit the full model again to predict this metric, but this time, in addition to controlling for age, we included sibling number as a fixed effect $lmer(metric~ age + sibling_number + (1|corpus/child))$, so that individual variation that was actually due to sibling number was captured by that fixed effect instead of the random effect for child. We had sibling number data for `r sum(has_n_of_sib[,"TRUE"])` recordings from `r length(levels(factor(mydat2$child_id[!is.na(mydat2$n_of_siblings)])))` in `r length(levels(factor(mydat2$experiment[!is.na(mydat2$n_of_siblings)])))` corpora (`r corp_w_sib_clean`). The number of siblings varied from `r min(mydat2$n_of_siblings,na.rm=T)` to `r max(mydat2$n_of_siblings,na.rm=T)`, with a mean of `r round(mean(mydat2$n_of_siblings,na.rm=T),1)` and a median of `r round(median(mydat2$n_of_siblings,na.rm=T),1)`.  Results indicated the full model was singular, so we fitted a No Corpus model to be able to extract a Child ICC. As a sanity check, we verified that the number of siblings predicted the outcome, total vocalization duration by other children -- and found that it did: ß = `r round(summary(model)$coefficients["n_of_siblings","Estimate"],2)`, t = `r round(summary(model)$coefficients["n_of_siblings","t value"],2)`, p < .001. This effect is relatively small: It means that per additional sibling, there is a .2 standard deviation increase in this variable. Turning now to how much variance is allocated to the random factor of Child, there was no difference in Child ICC in our original analysis (`r round(df.icc.mixed[df.icc.mixed$metric=="voc_dur_och_ph" & df.icc.mixed$data_set=="aclew","icc_child_id"],2)`) versus this re-analysis including the number of siblings (`r round(icc.result.split["icc_child_id"],2)`).
+
+### Checking whether high ICC for other child measures are due to presence of siblings
+
+```{r sib-presence}
+mydat2$sib_presence=ifelse(mydat2$n_of_siblings!=0,"present","absent")
+model_sib_presence<-lmer(voc_dur_och_ph~ age_s + sib_presence  + (1|experiment/child_id),data=mydat2)
+
+#is sing
+model_sib_presence<-lmer(voc_dur_och_ph~ age_s +sib_presence  + (1|child_id),data=mydat2)
+icc.result.split<- t(as.data.frame(icc(model_sib_presence, by_group=TRUE))$ICC)
+#names(icc.result.split)=c("icc_child_id", "icc_corpus")
+names(icc.result.split)=c("icc_child_id")
+
+
+```
 
 
-### Code to reproduce text before Table 3
+Perhaps it is not so much the sheer number of siblings that explains variance, but the sheer presence versus absence. After all, we can imagine that the effect of the number of siblings is not monotonic. We therefore repeated the analysis above but rather than adding the actual number of siblings, we had a binary variable that was "present" if the child had any siblings, and "absent" otherwise. As in the sibling number analysis, the full model was singular, so we fitted a No Corpus model to be able to extract a Child ICC. We again verified that sibling presence predicted the outcome, total vocalization duration by other children -- and found that it did: ß = `r round(summary(model_sib_presence)$coefficients["sib_presencepresent","Estimate"],2)`, t = `r round(summary(model_sib_presence)$coefficients["sib_presencepresent","t value"],2)`, p < .001. This effect is, as expected, sizable: It means that there is nearly one whole standard deviation increase in this variable when there are any siblings. In addition to being a better predictor, in this model, the amount of variance allocated to individual children as measured by Child ICC was considerably higher in our original analysis (`r round(df.icc.mixed[df.icc.mixed$metric=="voc_dur_och_ph" & df.icc.mixed$data_set=="aclew","icc_child_id"],2)`) than in this re-analysis including sibling presence (`r round(icc.result.split["icc_child_id"],2)`).
+
+
+## Code to reproduce text before Table 3
 
 ```{r reg model icc}
-#I moved this chunk here -- check that nothing is broken by it
 
 lr_icc_chi <- lm(icc_child_id ~ Type * data_set, data=df.icc.mixed) 
 #binomial could be used, but diagnostic plots look pretty good (other than some outliers)
@@ -363,10 +380,16 @@ reg_sum=summary(lr_icc_chi)
 
 reg_anova=Anova(lr_icc_chi)
 
+get_msd=function(x) paste0("M = ", round(mean(x),2),", SD = ", round(sd(x),2))
+
+msds = aggregate(df.icc.mixed$icc_child_id,by=list(df.icc.mixed$Type),get_msd)
+msds$x=gsub("0.",".",msds$x,fixed=T)
+rownames(msds)<-msds$Group.1
+
 ```
 
 
-Going back to our overarching analyses, we explored how similar Child ICCs were across different talker types and pipelines. We fit a linear model with the formula $lm(icc_child_id ~ type * pipeline)$, where type indicates whether the measure pertained to the key child, (female/male) adults, other children; and pipeline LENA or ACLEW. We found an adjusted R-squared of `r round(reg_sum$adj.r.squared*100)`%, suggesting much of the variance across Child ICCs was explained by this model. A Type 3 ANOVA on this model revealed only type was a signficant (F(`r reg_anova["Type","Df"]`)=`r round(reg_anova["Type","F value"],1)`, p<.001), whereas neither pipeline nor the interaction between type and pipeline were significant.
+Next we explored how similar Child ICCs were across different talker types and pipelines. We fit a linear model with the formula $lm(icc\_child\_id ~ type * pipeline)$, where type indicates whether the measure pertained to the key child, (female/male) adults, other children; and pipeline LENA or ACLEW. We found an adjusted R-squared of `r round(reg_sum$adj.r.squared*100)`%, suggesting much of the variance across Child ICCs was explained by these factors. A Type 3 ANOVA on this model revealed type was a signficant predictor (F(`r reg_anova["Type","Df"]`) = `r round(reg_anova["Type","F value"],1)`, p<.001), whereas as was pipeline (F(`r reg_anova["data_set","Df"]`) = `r round(reg_anova["data_set","F value"],1)`, p = `r round(reg_anova["data_set","Pr(>F)"],3)`); the interaction between type and pipeline was not significant. The main effect of type emerged because output metrics tended to have higher Child ICC (`r msds["Output","x"]`)  than those associated to adults in general (`r msds["Adults","x"]`), females (`r msds["Female","x"]`), and males (`r msds["Male","x"]`); whereas those associated with other children had even higher Child ICCs (`r msds["Other children","x"]`).
 
 
 
@@ -392,7 +415,7 @@ kable(x,row.names = F,digits=2,caption="Most commonly used metrics.")
 ## Code to reproduce "Exploratory analyses: Correlations based on paired analyses of recordings done within two months"
 
 
-```{r correlation analysis for close recs, warning = F, echo=FALSE}
+```{r compute correlation analysis for close recs, warning = F, echo=FALSE}
 #to compare with Gilkerson, we just need to focus on AWC, CVC, CTC (in LENA, but for comparison purposes, we also include aclew)
 
 
@@ -476,6 +499,12 @@ for(i in 1:nsamples){#i=1
 }
 
 
+
+```
+
+```{r}
+
+
 #summary(all_rs)
 rval_tab=cbind(apply(all_rs[,1:20],1,mean),apply(all_rs[,1:20],1,sd),all_rs[,21:22])
 colnames(rval_tab) <-c("m","sd","p","met") 
@@ -493,15 +522,15 @@ colnames(mytab)<-c("aclew","lena")
 rownames(mytab)<-c("AWC","CVC","CTC","Chi vocs")
 print(mytab)
 
+rval_tab$Type<-get_type(rval_tab)
+
 ```
+
 Out of our `r length(levels(factor(mydat_aclew$experiment)))` corpora and `r length(levels(factor(mydat_aclew$child_id)))` children, `r length(levels(factor(dist_contig_lena$child_id)))` children (belonging to `r length(levels(factor(gsub(" .*","",dist_contig_lena$child_id))))`  corpora) could be included in this analysis, as some children did not have recordings less than two months apart (in particular, no child from the Warlaumont corpus did). 
 
 ## Code to reproduce Fig. 4
 
 ```{r r-fig4, echo=F,fig.width=4, fig.height=3,fig.cap="Distribution of correlation coefficients."}
-#bug here probably inherited from above
-
-rval_tab$Type<-get_type(rval_tab)
 
 
 ggplot(rval_tab, aes(y = m, x = toupper(p))) +
@@ -525,11 +554,14 @@ reg_sum_cor=summary(lr_cor)
 
 reg_anova_cor=Anova(lr_icc_chi)
 
+r_msds=aggregate(rval_tab$m,by=list(rval_tab$p),get_msd)
+rownames(r_msds)<-r_msds$Group.1
+
 cor_t=t.test(rval_tab$m ~ rval_tab$p)
 
 ```
 
-To see whether correlations in this analysis differed by talker types and pipelines, we fit a linear model with the formula $lm(cor ~ type * pipeline)$, where type indicates whether the measure pertained to the key child, (female/male) adults, other children; and pipeline LENA or ACLEW. We found an adjusted R-squared of `r round(reg_sum_cor$adj.r.squared*100)`%, suggesting this model did not explain a great deal of variance in correlation coefficients. A Type 3 ANOVA on this model revealed a significant effect of pipeline (F = `r round(reg_anova_cor["data_set","F value"],2)`, p = `r round(reg_anova_cor["data_set","Pr(>F)"],2)`), due to higher correlations for ACLEW (m = `r round(cor_t$estimate["mean in group aclew"],2)`) than for LENA metrics (m = `r round(cor_t$estimate["mean in group lena"],2)`). See below for fuller results.
+To see whether correlations in this analysis differed by talker types and pipelines, we fit a linear model with the formula $lm(cor ~ type * pipeline)$, where type indicates whether the measure pertained to the key child, (female/male) adults, other children; and pipeline LENA or ACLEW. We found an adjusted R-squared of `r round(reg_sum_cor$adj.r.squared*100)`%, suggesting this model did not explain a great deal of variance in correlation coefficients. A Type 3 ANOVA on this model revealed a significant effect of pipeline (F = `r round(reg_anova_cor["data_set","F value"],2)`, p = `r round(reg_anova_cor["data_set","Pr(>F)"],2)`), due to higher correlations for ACLEW (`r r_msds["aclew","x"]`) than for LENA metrics (m = `r r_msds["lena","x"]`). See below for fuller results.
 
 ```{r print out anova results rec on cor}
 

CODE/SM.html

@@ -1643,12 +1643,15 @@ reliability</a></li>
 <li><a href="#code-to-reproduce-text-under-figure-3" id="toc-code-to-reproduce-text-under-figure-3">Code to reproduce text
 under Figure 3</a>
 <ul>
-<li><a href="#checking-whether-high-icc-for-other-child-measures-are-due-to-presence-of-other-siblings" id="toc-checking-whether-high-icc-for-other-child-measures-are-due-to-presence-of-other-siblings">Checking
-whether high ICC for other child measures are due to presence of other
+<li><a href="#checking-whether-high-icc-for-other-child-measures-are-due-to-number-of-siblings" id="toc-checking-whether-high-icc-for-other-child-measures-are-due-to-number-of-siblings">Checking
+whether high ICC for other child measures are due to number of
 siblings</a></li>
+<li><a href="#checking-whether-high-icc-for-other-child-measures-are-due-to-presence-of-siblings" id="toc-checking-whether-high-icc-for-other-child-measures-are-due-to-presence-of-siblings">Checking
+whether high ICC for other child measures are due to presence of
+siblings</a></li>
+</ul></li>
 <li><a href="#code-to-reproduce-text-before-table-3" id="toc-code-to-reproduce-text-before-table-3">Code to reproduce text
 before Table 3</a></li>
-</ul></li>
 <li><a href="#code-to-reproduce-table-3" id="toc-code-to-reproduce-table-3">Code to reproduce Table 3</a></li>
 <li><a href="#code-to-reproduce-exploratory-analyses-correlations-based-on-paired-analyses-of-recordings-done-within-two-months" id="toc-code-to-reproduce-exploratory-analyses-correlations-based-on-paired-analyses-of-recordings-done-within-two-months">Code
 to reproduce “Exploratory analyses: Correlations based on paired
@@ -1876,38 +1879,72 @@ combining data from all corpora.
 higher ICCs, and surprisingly, 6 of them corresponded to the “other
 child” category, known to have the worst accuracy according to previous
 analyses (Cristia et al., 2020).</p>
-<div id="checking-whether-high-icc-for-other-child-measures-are-due-to-presence-of-other-siblings" class="section level3">
-<h3>Checking whether high ICC for other child measures are due to
-presence of other siblings</h3>
+<div id="checking-whether-high-icc-for-other-child-measures-are-due-to-number-of-siblings" class="section level3">
+<h3>Checking whether high ICC for other child measures are due to number
+of siblings</h3>
 <p>We reasoned this may be because children in our corpora vary in terms
-of the number of siblings they have, and that siblings’ presence may be
-stable across recordings. To address this possibility, we fit the full
-model again to predict number of vocalizations from other children, but
-this time including sibling number as a fixed effect <span class="math inline">\(lmer(metric~ age + sibling_number +
+of the number of siblings they have, that siblings’ presence may be
+stable across recordings, and that a greater number of siblings would
+lead to more other child vocalizations. As a result, any measure based
+on other child vocalizations would result in stable relative ranking of
+children due to the number of siblings present. To test this hypothesis,
+we selected the metric with the highest Child ICC, namely ACLEW’s total
+vocalization duration by other children. We fit the full model again to
+predict this metric, but this time, in addition to controlling for age,
+we included sibling number as a fixed effect <span class="math inline">\(lmer(metric~ age + sibling_number +
 (1|corpus/child))\)</span>, so that individual variation that was
 actually due to sibling number was captured by that fixed effect instead
 of the random effect for child. We had sibling number data for 874
 recordings from 120 in 5 corpora (bergelson, lucid, quechua, warlaumont,
-winnipeg). We fit this model for the metric with the highest Child ICC,
-ACLEW’s total vocalization duration by other children. Results indicated
-the full model was singular, so we fitted a No Corpus model to be able
-to extract a Child ICC. In fact, there was no difference in Child ICC in
-our original analysis (0.64) versus this re-analysis including the
-number of siblings (0.64).</p>
+winnipeg). The number of siblings varied from 0 to 7, with a mean of 0.9
+and a median of 1. Results indicated the full model was singular, so we
+fitted a No Corpus model to be able to extract a Child ICC. As a sanity
+check, we verified that the number of siblings predicted the outcome,
+total vocalization duration by other children – and found that it did: ß
+= 0.2, t = 4.73, p &lt; .001. This effect is relatively small: It means
+that per additional sibling, there is a .2 standard deviation increase
+in this variable. Turning now to how much variance is allocated to the
+random factor of Child, there was no difference in Child ICC in our
+original analysis (0.64) versus this re-analysis including the number of
+siblings (0.64).</p>
+</div>
+<div id="checking-whether-high-icc-for-other-child-measures-are-due-to-presence-of-siblings" class="section level3">
+<h3>Checking whether high ICC for other child measures are due to
+presence of siblings</h3>
+<p>Perhaps it is not so much the sheer number of siblings that explains
+variance, but the sheer presence versus absence. After all, we can
+imagine that the effect of the number of siblings is not monotonic. We
+therefore repeated the analysis above but rather than adding the actual
+number of siblings, we had a binary variable that was “present” if the
+child had any siblings, and “absent” otherwise. As in the sibling number
+analysis, the full model was singular, so we fitted a No Corpus model to
+be able to extract a Child ICC. We again verified that sibling presence
+predicted the outcome, total vocalization duration by other children –
+and found that it did: ß = 0.97, t = 9.91, p &lt; .001. This effect is,
+as expected, sizable: It means that there is nearly one whole standard
+deviation increase in this variable when there are any siblings. In
+addition to being a better predictor, in this model, the amount of
+variance allocated to individual children as measured by Child ICC was
+considerably higher in our original analysis (0.64) than in this
+re-analysis including sibling presence (0.52).</p>
 </div>
-<div id="code-to-reproduce-text-before-table-3" class="section level3">
-<h3>Code to reproduce text before Table 3</h3>
-<p>Going back to our overarching analyses, we explored how similar Child
-ICCs were across different talker types and pipelines. We fit a linear
-model with the formula <span class="math inline">\(lm(icc_child_id ~
-type * pipeline)\)</span>, where type indicates whether the measure
-pertained to the key child, (female/male) adults, other children; and
-pipeline LENA or ACLEW. We found an adjusted R-squared of 65%,
-suggesting much of the variance across Child ICCs was explained by this
-model. A Type 3 ANOVA on this model revealed only type was a signficant
-(F(4)=31.2, p&lt;.001), whereas neither pipeline nor the interaction
-between type and pipeline were significant.</p>
 </div>
+<div id="code-to-reproduce-text-before-table-3" class="section level2">
+<h2>Code to reproduce text before Table 3</h2>
+<p>Next we explored how similar Child ICCs were across different talker
+types and pipelines. We fit a linear model with the formula <span class="math inline">\(lm(icc\_child\_id ~ type * pipeline)\)</span>,
+where type indicates whether the measure pertained to the key child,
+(female/male) adults, other children; and pipeline LENA or ACLEW. We
+found an adjusted R-squared of 65%, suggesting much of the variance
+across Child ICCs was explained by these factors. A Type 3 ANOVA on this
+model revealed type was a signficant predictor (F(4) = 31.2, p&lt;.001),
+whereas as was pipeline (F(1) = 5.1, p = 0.027) nor the interaction
+between type and pipeline were significant. The main effect of type
+emerged because output metrics tended to have higher Child ICC (M = .4,
+SD = .06) than those associated to adults in general (M = .32, SD =
+.05), females (M = .36, SD = .06), and males (M = .36, SD = .04);
+whereas those associated with other children had even higher Child ICCs
+(M = .58, SD = .06).</p>
 </div>
 <div id="code-to-reproduce-table-3" class="section level2">
 <h2>Code to reproduce Table 3</h2>

CODE/SM.log

@@ -1,4 +1,4 @@
-This is pdfTeX, Version 3.14159265-2.6-1.40.18 (TeX Live 2017) (preloaded format=pdflatex 2017.11.29)  19 AUG 2023 12:47
+This is pdfTeX, Version 3.14159265-2.6-1.40.18 (TeX Live 2017) (preloaded format=pdflatex 2017.11.29)  24 AUG 2023 23:00
 entering extended mode
  restricted \write18 enabled.
  %&-line parsing enabled.
@@ -1101,90 +1101,91 @@ File: ts1lmr.fd 2009/10/30 v1.6 Font defs for Latin Modern
 ) [1
 
 {/usr/local/texlive/2017/texmf-var/fonts/map/pdftex/updmap/pdftex.map}]
-<SM_files/figure-latex/unnamed-chunk-2-1.pdf, id=52, 440.64626pt x 255.95625pt>
+<SM_files/figure-latex/unnamed-chunk-2-1.pdf, id=54, 440.64626pt x 255.95625pt>
 File: SM_files/figure-latex/unnamed-chunk-2-1.pdf Graphic file (type pdf)
 <use SM_files/figure-latex/unnamed-chunk-2-1.pdf>
 Package pdftex.def Info: SM_files/figure-latex/unnamed-chunk-2-1.pdf used on in
 put line 154.
 (pdftex.def)             Requested size: 440.64517pt x 255.95561pt.
 [2 <./SM_files/figure-latex/unnamed-chunk-2-1.pdf>] [3] <SM_files/figure-latex/
-icc-examples-fig2-1.pdf, id=70, 289.08pt x 206.7725pt>
+icc-examples-fig2-1.pdf, id=72, 289.08pt x 206.7725pt>
 File: SM_files/figure-latex/icc-examples-fig2-1.pdf Graphic file (type pdf)
 <use SM_files/figure-latex/icc-examples-fig2-1.pdf>
 Package pdftex.def Info: SM_files/figure-latex/icc-examples-fig2-1.pdf used on 
 input line 291.
 (pdftex.def)             Requested size: 289.0881pt x 206.77829pt.
 
-<SM_files/figure-latex/icc-allexp-fig3-1.pdf, id=71, 272.01625pt x 206.7725pt>
+<SM_files/figure-latex/icc-allexp-fig3-1.pdf, id=73, 272.01625pt x 206.7725pt>
 File: SM_files/figure-latex/icc-allexp-fig3-1.pdf Graphic file (type pdf)
 <use SM_files/figure-latex/icc-allexp-fig3-1.pdf>
 Package pdftex.def Info: SM_files/figure-latex/icc-allexp-fig3-1.pdf used on in
 put line 313.
 (pdftex.def)             Requested size: 272.02388pt x 206.77829pt.
-[4 <./SM_files/figure-latex/icc-examples-fig2-1.pdf>]
-LaTeX Font Info:    Try loading font information for T1+lmtt on input line 393.
+[4 <./SM_files/figure-latex/icc-examples-fig2-1.pdf>] [5 <./SM_files/figure-lat
+ex/icc-allexp-fig3-1.pdf>]
+LaTeX Font Info:    Try loading font information for T1+lmtt on input line 429.
 
 (/usr/local/texlive/2017/texmf-dist/tex/latex/lm/t1lmtt.fd
 File: t1lmtt.fd 2009/10/30 v1.6 Font defs for Latin Modern
-) [5 <./SM_files/figure-latex/icc-allexp-fig3-1.pdf>] <SM_files/figure-latex/r-
-fig4-1.pdf, id=117, 271.0125pt x 206.7725pt>
+) <SM_files/figure-latex/r-fig4-1.pdf, id=116, 271.0125pt x 206.7725pt>
 File: SM_files/figure-latex/r-fig4-1.pdf Graphic file (type pdf)
 <use SM_files/figure-latex/r-fig4-1.pdf>
 Package pdftex.def Info: SM_files/figure-latex/r-fig4-1.pdf used on input line 
-411.
+447.
 (pdftex.def)             Requested size: 271.0201pt x 206.77829pt.
-[6 <./SM_files/figure-latex/r-fig4-1.pdf>] <SM_files/figure-latex/icc-bycor-fig
-5-1.pdf, id=137, 285.065pt x 707.64375pt>
+[6] <SM_files/figure-latex/icc-bycor-fig5-1.pdf, id=128, 285.065pt x 707.64375p
+t>
 File: SM_files/figure-latex/icc-bycor-fig5-1.pdf Graphic file (type pdf)
 <use SM_files/figure-latex/icc-bycor-fig5-1.pdf>
 Package pdftex.def Info: SM_files/figure-latex/icc-bycor-fig5-1.pdf used on inp
-ut line 459.
+ut line 495.
 (pdftex.def)             Requested size: 262.0194pt x 650.43549pt.
 
-LaTeX Warning: Float too large for page by 23.9499pt on input line 462.
+LaTeX Warning: Float too large for page by 23.9499pt on input line 498.
 
-<SM_files/figure-latex/icc-bycor-fig6-1.pdf, id=138, 277.035pt x 712.6625pt>
+<SM_files/figure-latex/icc-bycor-fig6-1.pdf, id=129, 277.035pt x 712.6625pt>
 File: SM_files/figure-latex/icc-bycor-fig6-1.pdf Graphic file (type pdf)
 <use SM_files/figure-latex/icc-bycor-fig6-1.pdf>
 Package pdftex.def Info: SM_files/figure-latex/icc-bycor-fig6-1.pdf used on inp
-ut line 466.
+ut line 502.
 (pdftex.def)             Requested size: 252.85468pt x 650.45953pt.
 
-LaTeX Warning: Float too large for page by 35.97395pt on input line 470.
+LaTeX Warning: Float too large for page by 35.97395pt on input line 506.
 
-<SM_files/figure-latex/relBYage-fig7-1.pdf, id=139, 421.575pt x 712.6625pt>
+[7 <./SM_files/figure-latex/r-fig4-1.pdf>] [8 <./SM_files/figure-latex/icc-byco
+r-fig5-1.pdf>] [9 <./SM_files/figure-latex/icc-bycor-fig6-1.pdf>] <SM_files/fig
+ure-latex/relBYage-fig7-1.pdf, id=179, 421.575pt x 712.6625pt>
 File: SM_files/figure-latex/relBYage-fig7-1.pdf Graphic file (type pdf)
 <use SM_files/figure-latex/relBYage-fig7-1.pdf>
 Package pdftex.def Info: SM_files/figure-latex/relBYage-fig7-1.pdf used on inpu
-t line 521.
+t line 557.
 (pdftex.def)             Requested size: 384.77885pt x 650.45953pt.
 
-LaTeX Warning: Float too large for page by 24.52953pt on input line 524.
+LaTeX Warning: Float too large for page by 24.52953pt on input line 560.
 
-<SM_files/figure-latex/icc-bycor-fig8-1.pdf, id=140, 277.035pt x 279.0425pt>
+<SM_files/figure-latex/icc-bycor-fig8-1.pdf, id=180, 277.035pt x 279.0425pt>
 File: SM_files/figure-latex/icc-bycor-fig8-1.pdf Graphic file (type pdf)
 <use SM_files/figure-latex/icc-bycor-fig8-1.pdf>
 Package pdftex.def Info: SM_files/figure-latex/icc-bycor-fig8-1.pdf used on inp
-ut line 528.
+ut line 564.
 (pdftex.def)             Requested size: 277.03432pt x 279.04181pt.
-[7] [8 <./SM_files/figure-latex/icc-bycor-fig5-1.pdf>] [9 <./SM_files/figure-la
-tex/icc-bycor-fig6-1.pdf>] [10 <./SM_files/figure-latex/relBYage-fig7-1.pdf>]
-Package atveryend Info: Empty hook `BeforeClearDocument' on input line 570.
-[11 <./SM_files/figure-latex/icc-bycor-fig8-1.pdf>]
-Package atveryend Info: Empty hook `AfterLastShipout' on input line 570.
+Package atveryend Info: Empty hook `BeforeClearDocument' on input line 606.
+[10] [11 <./SM_files/figure-latex/relBYage-fig7-1.pdf>] [12 <./SM_files/figure-
+latex/icc-bycor-fig8-1.pdf>]
+Package atveryend Info: Empty hook `AfterLastShipout' on input line 606.
 (./SM.aux)
-Package atveryend Info: Executing hook `AtVeryEndDocument' on input line 570.
-Package atveryend Info: Empty hook `AtEndAfterFileList' on input line 570.
-Package atveryend Info: Empty hook `AtVeryVeryEnd' on input line 570.
+Package atveryend Info: Executing hook `AtVeryEndDocument' on input line 606.
+Package atveryend Info: Empty hook `AtEndAfterFileList' on input line 606.
+Package atveryend Info: Empty hook `AtVeryVeryEnd' on input line 606.
  ) 
 Here is how much of TeX's memory you used:
- 14602 strings out of 492995
- 212178 string characters out of 6132703
- 331674 words of memory out of 5000000
- 17751 multiletter control sequences out of 15000+600000
- 54067 words of font info for 99 fonts, out of 8000000 for 9000
+ 14615 strings out of 492995
+ 212452 string characters out of 6132703
+ 327773 words of memory out of 5000000
+ 17757 multiletter control sequences out of 15000+600000
+ 60123 words of font info for 102 fonts, out of 8000000 for 9000
  1141 hyphenation exceptions out of 8191
- 34i,9n,38p,1391b,462s stack positions out of 5000i,500n,10000p,200000b,80000s
+ 34i,9n,38p,1391b,386s stack positions out of 5000i,500n,10000p,200000b,80000s
 {/usr/local/texlive/2017/texmf-dist/fonts/enc/dvips/lm/lm-ec.enc}{/usr/local/
 texlive/2017/texmf-dist/fonts/enc/dvips/lm/lm-mathsy.enc}{/usr/local/texlive/20
 17/texmf-dist/fonts/enc/dvips/lm/lm-mathit.enc}{/usr/local/texlive/2017/texmf-d
@@ -1197,10 +1198,10 @@ l/texlive/2017/texmf-dist/fonts/type1/public/lm/lmmi7.pfb></usr/local/texlive/2
 ist/fonts/type1/public/lm/lmr17.pfb></usr/local/texlive/2017/texmf-dist/fonts/t
 ype1/public/lm/lmsy10.pfb></usr/local/texlive/2017/texmf-dist/fonts/type1/publi
 c/lm/lmtt10.pfb>
-Output written on SM.pdf (11 pages, 518301 bytes).
+Output written on SM.pdf (12 pages, 520005 bytes).
 PDF statistics:
- 310 PDF objects out of 1000 (max. 8388607)
- 262 compressed objects within 3 object streams
- 55 named destinations out of 1000 (max. 500000)
- 10417 words of extra memory for PDF output out of 12000 (max. 10000000)
+ 320 PDF objects out of 1000 (max. 8388607)
+ 271 compressed objects within 3 object streams
+ 58 named destinations out of 1000 (max. 500000)
+ 10425 words of extra memory for PDF output out of 12000 (max. 10000000)
 

CODE/sessionInfo.txt

@@ -23,19 +23,21 @@ other attached packages:
 [13] lme4_1.1-34           Matrix_1.6-0         
 
 loaded via a namespace (and not attached):
- [1] beeswarm_0.4.0    gtable_0.3.3      xfun_0.39         insight_0.19.3   
- [5] rstatix_0.7.2     lattice_0.21-8    vctrs_0.6.3       tools_4.3.1      
- [9] generics_0.1.3    parallel_4.3.1    tibble_3.2.1      fansi_1.0.4      
-[13] highr_0.10        pkgconfig_2.0.3   webshot_0.5.5     lifecycle_1.0.3  
-[17] farver_2.1.1      compiler_4.3.1    munsell_0.5.0     mnormt_2.1.1     
-[21] vipor_0.4.5       htmltools_0.5.5   yaml_2.3.7        pillar_1.9.0     
-[25] nloptr_2.0.3      MASS_7.3-60       boot_1.3-28.1     abind_1.4-5      
-[29] nlme_3.1-162      tidyselect_1.2.0  rvest_1.0.3       digest_0.6.33    
-[33] stringi_1.7.12    purrr_1.0.1       labeling_0.4.2    splines_4.3.1    
-[37] cowplot_1.1.1     fastmap_1.1.1     grid_4.3.1        colorspace_2.1-0 
-[41] cli_3.6.1         magrittr_2.0.3    utf8_1.2.3        broom_1.0.5      
-[45] withr_2.5.0       scales_1.2.1      backports_1.4.1   rmarkdown_2.23   
-[49] httr_1.4.6        gridExtra_2.3     ggsignif_0.6.4    evaluate_0.21    
-[53] knitr_1.43        viridisLite_0.4.2 mgcv_1.8-42       rlang_1.1.1      
-[57] Rcpp_1.0.11       glue_1.6.2        xml2_1.3.5        svglite_2.1.1    
-[61] rstudioapi_0.15.0 minqa_1.2.5       R6_2.5.1          systemfonts_1.0.4
+ [1] beeswarm_0.4.0    gtable_0.3.3      xfun_0.39         bslib_0.5.0      
+ [5] insight_0.19.3    rstatix_0.7.2     lattice_0.21-8    vctrs_0.6.3      
+ [9] tools_4.3.1       generics_0.1.3    parallel_4.3.1    tibble_3.2.1     
+[13] fansi_1.0.4       highr_0.10        pkgconfig_2.0.3   webshot_0.5.5    
+[17] lifecycle_1.0.3   farver_2.1.1      compiler_4.3.1    mnormt_2.1.1     
+[21] munsell_0.5.0     vipor_0.4.5       htmltools_0.5.5   sass_0.4.7       
+[25] yaml_2.3.7        pillar_1.9.0      nloptr_2.0.3      jquerylib_0.1.4  
+[29] MASS_7.3-60       cachem_1.0.8      boot_1.3-28.1     abind_1.4-5      
+[33] nlme_3.1-162      tidyselect_1.2.0  rvest_1.0.3       digest_0.6.33    
+[37] stringi_1.7.12    purrr_1.0.1       labeling_0.4.2    splines_4.3.1    
+[41] cowplot_1.1.1     fastmap_1.1.1     grid_4.3.1        colorspace_2.1-0 
+[45] cli_3.6.1         magrittr_2.0.3    utf8_1.2.3        broom_1.0.5      
+[49] withr_2.5.0       scales_1.2.1      backports_1.4.1   rmarkdown_2.23   
+[53] httr_1.4.6        gridExtra_2.3     ggsignif_0.6.4    evaluate_0.21    
+[57] knitr_1.43        viridisLite_0.4.2 mgcv_1.8-42       rlang_1.1.1      
+[61] Rcpp_1.0.11       glue_1.6.2        xml2_1.3.5        svglite_2.1.1    
+[65] rstudioapi_0.15.0 minqa_1.2.5       jsonlite_1.8.7    R6_2.5.1         
+[69] systemfonts_1.0.4