Here are corrections to errors that have escaped attention in papers that I have participated.
Permutation inference for the general linear model.
Winkler AM, Ridgway GR, Webster MA, Smith SM, Nichols TE.
Neuroimage. 2014 May 15;92:381-97.
- In 2016, after the paper was published, it came to our attention that the orthogonalisation of with respect to before permutation had in fact been proposed in the cited reference of Dekker et al (2007), and also in an earlier working paper by the same authors. We deeply regret that we missed this contribution, in which case the Smith method would have been called Dekker method. We hope to further emphasise this naming issue in a future publication. The relevant citations are:
Dekker, D., Krackhardt, D., & Snijders, T. (2003). Multicollinearity robust QAP for multiple regression. Presented at 1st Annual Conference of the North American Association for Computational Social and Organizational Science (June 22–25, 2003), Pittsburgh, PA.
Dekker, D., Krackhardt, D., Snijders, T.A.B. (2007). Sensitivity of MRQAP tests to collinearity and autocorrelation conditions. Psychometrika. 72 (4), 563–581.
- The reference to Blair et al. (1994) is incorrect. In the paper it is shown as:
Blair, R.C., Higgins, J.J., Karniski, W., Kromrey, J.D., 1994. A study of multivariate permutation tests which may replace Hotelling’s T2 test in prescribed circumstances. Multivariate Behavioral Research. 29 (2), 141-163.
but instead it should be:
Blair R.C., Karniski, W., 1994. Distribution-free statistical analyses of surface and volumetric maps. In: Functional Neuroimaging: Technical Foundations (Thatcher RW et al., eds), San Diego, Academic Press, pp. 19-28.
- The the Pearson’s correlation coefficient (often known as r) and the coefficient of determination (R2) are not pivotal statistics (page 382).
Measuring and comparing brain cortical surface area and other areal quantities. Winkler AM, Sabuncu MR, Yeo BT, Fischl B, Greve DN, Kochunov P, Nichols TE, Blangero J, Glahn DC.
Neuroimage. 2012 Mar 15;61(4):1428-43.
- In page 1434, 2nd column, footnote 8, the abbreviation “HWMH” should be “HWHM”, that is, half-width at half maximum.
Cortical thickness or grey matter volume? The importance of selecting the phenotype for imaging genetics studies.
Winkler AM, Kochunov P, Blangero J, Almasy L, Zilles K, Fox PT, Duggirala R, Glahn DC.
Neuroimage. 2010 Nov 15;53(3):1135-46.
- In page 1142, 2nd column, where it reads:
Where cortical thickness and surface area mostly […]
it should instead be:
Were cortical thickness and surface area mostly […]
that is, the adverb “where” should have been a verb in the subjunctive, “were”.