Merge pull request #6 from Bayer-Group/dev

pre-saved images does not get copied into articles-assets

Author: Zhenglei-BCS

inst/RStats/flowchars.qmd

@@ -267,6 +267,8 @@ This example demonstrates how variance decomposition in mixed models can affect
 
 ## Flowcharts generation
 
+https://stackoverflow.com/questions/1250079/how-to-escape-single-quotes-within-single-quoted-strings
+From the page above, I could not find a solution to handle sing quote in single quoted strings.
 
 ```{r eval=FALSE}
 # Load necessary library
@@ -280,7 +282,7 @@ digraph flowchart {
   node [shape = box, style = filled, fillcolor = lightblue]
   
   start [label = 'Are both solvent control and \n non-solvent control present?', shape = diamond]
-  compare_controls [label = 'Compare controls using \\n Fisher\\'s Exact Test']
+  compare_controls [label = 'Compare controls using \\n Fisher\"s Exact Test']
   controls_differ [label = 'Do the controls differ?', shape = diamond]
   drop_non_solvent [label = 'Drop non-solvent control from analysis']
   combine_controls [label = 'Combine controls while retaining subgroups']

vignettes/articles/LMM-GLMM-and-GAMM.Rmd

@@ -16,6 +16,9 @@ library(tidyverse)
 library(drcHelper)
 ```
 
+
+
+
 ## Mixed Models
 
 ## Variance Components

vignettes/articles/NOEC_Methods.Rmd

@@ -38,7 +38,7 @@ It is relatively straightforward to calulate and intepret NOEC, and it is widely
 4. It is heavily impacted by the sample size and test concentration selections. Poor experimental design may yield high NOEC due to decreased statistical sensitivity, which is not desired in a regulatory context.
 
 
-In this article, we focus on NOEC methods for continuous data, which can also be applied to count data. This can be achieved either by simply treating count data as continuous or by transforming the data to stabilize the variance. 
+In this article, we focus on NOEC methods for continuous data, which can also be applied to count data. This can be achieved either by simply treating count data as continuous or by transforming the data to stabilize the variance. For quantal data, please go to [Quantal Data](https://bayer-group.github.io/drcHelper/articles/Quantal-Data.html) for more information.
 
 Continuous data are numerical data that can take any value within a range (e.g., weight, height), while count data are discrete and represent the number of occurrences of an event (e.g., number of species observed in a pitfall). It is hard to determine a distribution of count data in real world. Poisson, negative-binomial are common distributions used to model count data. The Poisson distribution is often used when the mean and variance are equal, while the negative-binomial distribution is used when the data exhibit overdispersion (variance greater than the mean). Many count datasets have more zeros than expected under standard count models, leading to zero-inflated models or hurdle models that account for this excess. Small sample sizes can make it difficult to determine the underlying distribution of the data and can affect the robustness of statistical methods. There are also other challenges like non-constant variance that does not follow a mean variance relationship, issues caused by censoring or truncation, etc. Therefore, transformations, such as logarithmic or square root transformations, are often used to stabilize variance and meet the assumptions of standard statistical tests for continuous data when dealing with non-normal data distributions.
 

vignettes/articles/Quantal-Data.Rmd

@@ -1,5 +1,8 @@
 ---
 title: "Quantal Data"
+resource_files:
+  - ./../assets/quantal_NOEC.png
+  - ./../assets/binomial_tank_effects_visualization.png
 editor_options: 
   chunk_output_type: console
 ---
@@ -22,7 +25,7 @@ Analysis of quantal data typically involves the following steps as shown in the
 
 
 ```{r echo=FALSE,out.width="90%"}
-knitr::include_graphics("./assets/quantal_NOEC.png")
+knitr::include_graphics("./../assets/quantal_NOEC.png")
 ```
 
 ## An example dataset
@@ -431,7 +434,7 @@ ggsave("binomial_tank_effects_visualization.png", combined_plot, width = 12, hei
 ```
 
 ```{r echo=FALSE}
-knitr::include_graphics("./assets/binomial_tank_effects_visualization.png")
+knitr::include_graphics("./../assets/binomial_tank_effects_visualization.png")
 ```
 
 The plot on the upper left shows the survival proportions for each tank (colored points) at each dose level. The black diamonds represent the mean survival proportion at each dose level, and the dashed line shows the theoretical dose-response relationship without tank effects. The variation among tanks at the same dose level illustrates the tank effect.