Talk:Rank product

	This article is within the scope of WikiProject Molecular Biology, a collaborative effort to improve the coverage of Molecular Biology 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.Molecular BiologyWikipedia:WikiProject Molecular BiologyTemplate:WikiProject Molecular BiologyMolecular Biology
???	This article has not yet received a rating on the importance scale.
	This article is supported by the Genetics task force (assessed as Low-importance).

Statistics Low‑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
Low	This article has been rated as Low-importance on the importance scale.

Untitled

Why rank products as opposed to rank sums?

It seems that the product approach weights things quite differently from sums.

Both sums and products have advantages, what are the tradeoffs?

Answer: In general, both rank sums and rank products work quite well. Their performance on simulated data is compared in Breitling and Herzyk (J Bioinform Comput Biol. 2005 Oct;3(5):1171-89). The major difference is that the rank sums give high ranks to those entities that very consistently score highly, while the rank products favor those that get very high ranks most of the time, but allows some exceptions. That means that negative "outliers" get less weight in rank products that in rank sums. The choice between the two approaches depends on the aim of the study and the expected pattern of noise. E.g., the rank product approach is recommended for most gene expression studies. Note that the rank sums as discussed here are very different from the rank sums used in the traditional Wilcoxon rank-sum test. RainerBreitling (talk) 07:59, 9 October 2008 (UTC)[reply]