-
-
Notifications
You must be signed in to change notification settings - Fork 43
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
p_function()
plot
#249
Comments
This comment was marked as outdated.
This comment was marked as outdated.
It's really good! I'd by default extend the plot to include the null hypothesis (e.g., 0) and have a vertical bar there (like in the paper) to show the position of the p-value reported by the model in regard to the other plausible values. It would give a sense of perspective |
Neat! I like it. Agree with Dom. Would use lower-case italicized p, but that's just an APA convention. |
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as resolved.
This comment was marked as resolved.
This comment was marked as outdated.
This comment was marked as outdated.
|
I think rather than color, the lines for different confidence levels should be differentiated by line thickness. Make 25/50/75 thin lines and the focal hypothesis line (95) a thick line. Don't include a legend for either of these (with
Yes
Yes, I think including a focal hypothesis line makes this sort of plot a lot more accessible to people new to it. We can include a |
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
Given that we use "grid" to mean data grids elsewhere, maybe name that argument "facet"? |
I think we have |
library(parameters)
library(see)
model <- lm(Sepal.Length ~ Species + Sepal.Width + Petal.Length, data = iris)
p <- p_function(model)
plot(p) plot(p, show_labels = FALSE) plot(p, n_columns = 1) plot(p, n_columns = 2) Created on 2022-11-05 with reprex v2.0.2 |
@bwiernik How would you describe the p value here? What would be a proper formulation? The point estimate has a p-value of 1, but of course we cannot say that with 100% prob. the point estimate is correct. Rather, I would say that "With a probability of p, the range of estimates most compatible with our data, given a correct model, is from [CI_low] to [CI_high]"? I think we need to add something like this to the docs of the |
@strengejacke These look so good! |
Like in https://journals.sagepub.com/doi/10.1177/02683962221105904
WDYT? @easystats/core-team
Created on 2022-11-02 with reprex v2.0.2
The text was updated successfully, but these errors were encountered: