stats_2023

[zenrabbit]

But here are the issues I'm having. To get graphs similar to the first set (difference between burned:control) I would need to create an index; but most diversity indices require presence-absence data, but I have presence-only data.

true, can you relative difference within each site, rowwise, ie see Bland-Altman plots

example here I used https://github.com/zenrabbit/Tracking_tech_test

df <- df %>% rowwise %>% mutate(means = mean(c(suunto, whoop)), diff = (whoop-suunto))

mean_diff <- mean(df$diff) lower <- mean_diff - 1.96sd(df$diff) upper <- mean_diff + 1.96sd(df$diff)

ggplot(df, aes(means, diff)) + geom_point(size = 2) + geom_hline(yintercept = mean_diff) + geom_hline(yintercept = lower, color = "red", linetype="dashed") + geom_hline(yintercept = upper, color = "red", linetype="dashed") + ggtitle("Bland-Altman Plot") + ylim(0, 90) + labs(x = "means", y = "Whoop-Suunto estimated recovery difference") + theme_classic() + theme(panel.border = element_rect(colour = "black", fill=NA, size=1))

And if I opted for just using species richness (like the second set of graphs), I don't have multiple sampling sites...

I welcome any suggestions.

good

[zenrabbit]

Options for pre-post within site contrasts

1. just do diff or pre-post for each site (the diff)
2. Sounds like a simple LRR would be also be super (within site, post vs pre Ln response ratio very common in ecology)
3. Sorensen's similarity index

[zenrabbit]

Does burn severity affect plant community diversity and composition in mixed conifer forests of the United States Intermountain West one decade post fire? https://fireecology.springeropen.com/articles/10.1186/s42408-019-0038-8

https://besjournals.onlinelibrary.wiley.com/doi/10.1111/1365-2745.13403

[zenrabbit]