From 28c2ccc45871c06fe02adba438cf7268081ab3f0 Mon Sep 17 00:00:00 2001 From: jacobvjk Date: Thu, 12 Dec 2024 11:43:38 +0100 Subject: [PATCH] fix typos --- vignettes/cookbook_interpretation.Rmd | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vignettes/cookbook_interpretation.Rmd b/vignettes/cookbook_interpretation.Rmd index c3f56640..228475a5 100644 --- a/vignettes/cookbook_interpretation.Rmd +++ b/vignettes/cookbook_interpretation.Rmd @@ -267,7 +267,7 @@ knitr::include_graphics("../man/figures/plot_sankey_sector.png") #### Interpretation of the Sankey Plot -The sankey plot emphasizes the distribution of the financial exposure of the analyzed loan books across sectors and aligned or misaligned counterparties. The plot necessitate categorical variables for the types of nodes, which means that the net aggregate alignment metric is transformed into a binary variable. The size of each group in a node along the y axis is the financial exposure to that group and that is the only continuous variable in this plot. In effect, the statements you can make based on this plot are along the lines of "XY USD of the financial exposure of the loan books is concentrated in the power sector. Among the exposure to power companies, the largest share goes to companies that are misaligned with the selected scenario". As we can see, this reveals more about howw much money is lent to how many companies that are misaligned ins oem form. It says nothing about how misaligned these companies are. They might all be very close to, but just behind, the scenario target. Or they might all be grossly off target. The reason why this is still a useful plot is because you get a very quick over view, in which sectors are the largest shares of your misaligned companies. This makes it easier to prioritize which company analytics to look at first. Additionally, you can validate the severity of the misalignment in a given sector, by inspecting the alignment-by-exposure plots, which will be explained next. +The sankey plot emphasizes the distribution of the financial exposure of the analyzed loan books across sectors and aligned or misaligned counterparties. The plot necessitate categorical variables for the types of nodes, which means that the net aggregate alignment metric is transformed into a binary variable. The size of each group in a node along the y axis is the financial exposure to that group and that is the only continuous variable in this plot. In effect, the statements you can make based on this plot are along the lines of "XY USD of the financial exposure of the loan books is concentrated in the power sector. Among the exposure to power companies, the largest share goes to companies that are misaligned with the selected scenario". As we can see, this reveals more about how much money is lent to how many companies that are misaligned in some form. It says nothing about how misaligned these companies are. They might all be very close to, but just behind, the scenario target. Or they might all be grossly off target. The reason why this is still a useful plot is because you get a very quick over view, in which sectors are the largest shares of your misaligned companies. This makes it easier to prioritize which company analytics to look at first. Additionally, you can validate the severity of the misalignment in a given sector, by inspecting the alignment-by-exposure plots, which will be explained next. #### Mapping the Data Dictionary to the Sankey Plot