Talk:Poisson regression

Statistics Start‑class Mid‑importance

	This article is within the scope of WikiProject Statistics, a collaborative effort to improve the coverage of statistics on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.StatisticsWikipedia:WikiProject StatisticsTemplate:WikiProject StatisticsStatistics
Start	This article has been rated as Start-class on Wikipedia's content assessment scale.
Mid	This article has been rated as Mid-importance on the importance scale.

Rating

I gave this a "Start-Class" rating on the quality scale. To improve in quality, this article needs at least the following:

A picture showing the conditional Poisson distribution as x changes.
A separate section on maximum likelihood estimation, giving the likelihood function with graphs of its surface, and going into greater detail on numerical methods for finding its maximum.
Discussion of the relationship to proportional hazard models.
A section on the use of Poisson regression in spatial models.
A section giving more examples in detail.
Better and deeper references.

This is a good topic, and it deserves a thorough treatment. —Aetheling (talk) 05:45, 26 June 2010 (UTC)[reply]

Ridge regularization

The present article states: "Regularization can be added to this optimization problem by instead maximizing

\sum _{i=1}^{m}\log(p(y_{i};e^{\theta 'x}))+\lambda ||\theta ||^{2}

,"

But maximizing and a positive sign on the penalty term seem not to go hand in hand. Shouldn't it be a minus instead? — fnielsen (talk) 13:37, 6 April 2011 (UTC)[reply]

Yes, I believe you are correct. I've changed it. -BlueScreenD