From the course: Machine Learning with Logistic Regression in Excel, R, and Power BI
Join today to access over 24,800 courses taught by industry experts.
Calculating probabilities for multinomial models
From the course: Machine Learning with Logistic Regression in Excel, R, and Power BI
Calculating probabilities for multinomial models
- Once we calculate the logit values for a log odds in our multinomial logistic regression model, we can now calculate the probabilities for each of these outcomes for each income level. To do so, we're going to use the formula to convert odds into probabilities. We take the odds for a particular event and divide it by the sum of odds for all the events. In Excel, let's calculate the probabilities using the values of the odds we calculated and the columns next to it. We first calculate the pier probability, which is equal to J3 divided by the sum of all the odds, including pier. Remember that we're calculating dummy values here, and the predicted probabilities will update once we run the model. However, we do want to make sure we set up the formulas correctly in our model first. We'll then fix bottom rows for the sum function. And we can copy these predicted probabilities for each of the outcomes for each of the income…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.