Skip to main content
Cross Validated

Return to Answer

replaced R^2 with ICC, as per the 2013 paper
Source Link
user1205901 - Слава Україні
user1205901 - Слава Україні
  • 13.2k
  • 30
  • 104
  • 180

Nakagawa and Schielzeth (2013) call intra-class correlation $R^2$ as($ICC$) "closely connected to $R^2$" and refer to their 2010 paper. From posting this question I already seen few mentions of $ICC$ treated as "variance explained" since it in fact is a part of total variance explained by all the random effects and residuals. So it seems $ICC$ is used as an analog to $R^2$ while one have to remember that both statistics have their flaws (e.g. here and here).

Nakagawa, S. & Schielzeth, H. (2010). Repeatability for Gaussian and non-Gaussian data: a practical guide for biologists. Biological Reviews, 85, 935–956.

Nakagawa and Schielzeth (2013) call $R^2$ as "closely connected to $R^2$" and refer to their 2010 paper. From posting this question I already seen few mentions of $ICC$ treated as "variance explained" since it in fact is a part of total variance explained by all the random effects and residuals. So it seems $ICC$ is used as an analog to $R^2$ while one have to remember that both statistics have their flaws (e.g. here and here).

Nakagawa, S. & Schielzeth, H. (2010). Repeatability for Gaussian and non-Gaussian data: a practical guide for biologists. Biological Reviews, 85, 935–956.

Nakagawa and Schielzeth (2013) call intra-class correlation ($ICC$) "closely connected to $R^2$" and refer to their 2010 paper. From posting this question I already seen few mentions of $ICC$ treated as "variance explained" since it in fact is a part of total variance explained by all the random effects and residuals. So it seems $ICC$ is used as an analog to $R^2$ while one have to remember that both statistics have their flaws (e.g. here and here).

Nakagawa, S. & Schielzeth, H. (2010). Repeatability for Gaussian and non-Gaussian data: a practical guide for biologists. Biological Reviews, 85, 935–956.

replaced http://stats.stackexchange.com/ with https://stats.stackexchange.com/
Source Link
Community Bot
Community Bot
  • 1

Nakagawa and Schielzeth (2013) call $R^2$ as "closely connected to $R^2$" and refer to their 2010 paper. From posting this question I already seen few mentions of $ICC$ treated as "variance explained" since it in fact is a part of total variance explained by all the random effects and residuals. So it seems $ICC$ is used as an analog to $R^2$ while one have to remember that both statistics have their flaws (e.g. herehere and herehere).

Nakagawa, S. & Schielzeth, H. (2010). Repeatability for Gaussian and non-Gaussian data: a practical guide for biologists. Biological Reviews, 85, 935–956.

Nakagawa and Schielzeth (2013) call $R^2$ as "closely connected to $R^2$" and refer to their 2010 paper. From posting this question I already seen few mentions of $ICC$ treated as "variance explained" since it in fact is a part of total variance explained by all the random effects and residuals. So it seems $ICC$ is used as an analog to $R^2$ while one have to remember that both statistics have their flaws (e.g. here and here).

Nakagawa, S. & Schielzeth, H. (2010). Repeatability for Gaussian and non-Gaussian data: a practical guide for biologists. Biological Reviews, 85, 935–956.

Nakagawa and Schielzeth (2013) call $R^2$ as "closely connected to $R^2$" and refer to their 2010 paper. From posting this question I already seen few mentions of $ICC$ treated as "variance explained" since it in fact is a part of total variance explained by all the random effects and residuals. So it seems $ICC$ is used as an analog to $R^2$ while one have to remember that both statistics have their flaws (e.g. here and here).

Nakagawa, S. & Schielzeth, H. (2010). Repeatability for Gaussian and non-Gaussian data: a practical guide for biologists. Biological Reviews, 85, 935–956.

Source Link
Tim
Tim
  • 141.2k
  • 26
  • 270
  • 512

Nakagawa and Schielzeth (2013) call $R^2$ as "closely connected to $R^2$" and refer to their 2010 paper. From posting this question I already seen few mentions of $ICC$ treated as "variance explained" since it in fact is a part of total variance explained by all the random effects and residuals. So it seems $ICC$ is used as an analog to $R^2$ while one have to remember that both statistics have their flaws (e.g. here and here).

Nakagawa, S. & Schielzeth, H. (2010). Repeatability for Gaussian and non-Gaussian data: a practical guide for biologists. Biological Reviews, 85, 935–956.