Talk:Projection pursuit regression: Difference between revisions

Content deleted Content added

Inline

Revision as of 02:16, 4 November 2022

Statistics Start‑class

	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 articles
Start	This article has been rated as Start-class on Wikipedia's content assessment scale.
???	This article has not yet received a rating on the importance scale.

Is there a typo here?: "It has also been shown that βj converges at an order of n^\frac{1}{2}, while βj converges at a slightly worse order."

Model overview inconsistency

if x_i is a row vector, the result of the matrix product in the argument of f_j cannot be a scalar. But f_j are scalar functions of scalar arguments. i believe the description of x_i is not correct. it should be something in the line of: x_i is a column vector formed from the i-th row of the design matrix. That is, it is the features vector. Alternatively, if the idea is to stick to the rows of the design matrix, one should change the formula and write x_i beta_j without any transpose. To make all consistent one would state that the beta_j are column weight vectors Kakila (talk) 02:16, 4 November 2022 (UTC)[reply]

@@ Line 2: / Line 2: @@
 Is there a typo here?: "It has also been shown that βj converges at an order of n^\frac{1}{2}, while βj converges at a slightly worse order."
+== Model overview inconsistency ==
+if x_i is a row vector, the result of the matrix product in the argument of f_j cannot be a scalar. But f_j are scalar functions of scalar arguments. i believe the description of x_i is not correct. it should be something in the line of: x_i is a column vector formed from the i-th row of the design matrix. That is, it is the features vector.
+Alternatively, if the idea is to stick to the rows of the design matrix, one should change the formula and write x_i beta_j without any transpose. To make all consistent one would state that the beta_j are column weight vectors [[User:Kakila|Kakila]] ([[User talk:Kakila|talk]]) 02:16, 4 November 2022 (UTC)