Visualizing Logistic Regression In Action

Sebastian Sauer shows using ggplot2 visuals what happens when there are interaction effects in a logistic regression:

Of course, probabilities greater 1 do not make sense. That’s the reason why we prefer a “bended” graph, such as the s-type ogive in logistic regression. Let’s plot that instead.

First, we need to get the survival probabilities:

d %>% mutate(pred_prob = predict(glm1, type = "response")) -> d

Notice that type = "response gives you the probabilities of survival (ie., of the modeled event).

Read the whole thing.

Related Posts

Issues Starting ML Services

Jen Stirrup has a quick rundown of some reasons why Machine Learning Services might give you an error when you try to start it up: Msg 39023, Level 16, State 1, Procedure sp_execute_external_script, Line 1 [Batch Start Line 3] ‘sp_execute_external_script’ is disabled on this instance of SQL Server. Use sp_configure ‘external scripts enabled’ to enable […]

Read More

Using Have I Been Pwned In R

Maelle Salmon shows us how to use the HIBPwned library in R: The alternative title of this blog post is HIBPwned version 0.1.7 has been released! W00t!. Steph’s HIBPwned package utilises the HaveIBeenPwned.com API to check whether email addresses and/or user names have been present in any publicly disclosed data breach. In other words, this package potentially delivers bad news, but useful […]

Read More

Leave a Reply

Your email address will not be published. Required fields are marked *

Categories

April 2018
MTWTFSS
« Mar  
 1
2345678
9101112131415
16171819202122
23242526272829
30