log(A + x), not log(1 + x)

Statistical Modeling, Causal Inference, and Social Science 2024-08-31

Summary:

This recent discussion in comments reminds me of something that comes up in regression modeling from time to time. You have a predictor on an outcome which you’d like to model on the log scale—the usual reason, and it’s a … Continue reading

Link:

https://statmodeling.stat.columbia.edu/2024/08/31/loga-x-not-log1-x/

From feeds:

Statistics and Visualization » Statistical Modeling, Causal Inference, and Social Science

Tags:

miscellaneous

Authors:

Andrew

Date tagged:

08/31/2024, 19:40

Date published:

08/31/2024, 17:52