Sorry? The natural generalization of a mean to a 2-dimensional space is surely the vector mean, which is a point. -Robert Dawson Perhaps I should be more careful with my language, but you know how mania is <grin>. Would it help if I replaced "mean" with "least squares estimator of individual Y given the individual's value(s) on all remaining (k-1) variables in k-dimensional space? Or might that confuse my students? Are there objections to the generalization in that case? In Cartesian space, the regression LINE is that which minimizes the sum of squared deviations (in the Y dimension) about it. If we drop the X dimension, our least squares estimator of Y becomes the mean, the POINT which minimizes the sum of squared deviations about it. If instead of dropping X we add X2, our regression surface is a plane in three dimensional space, ................. In Abbot's fanciful tale, Flatland is inhabited by men, who, according to their social status, are triangles, squares, or polygons, and women who are straight lines. The women can makes themselves almost invisible by rotating to the perpendicular, and in such an orientation present a threat to any man who might run into her point. Under law, they must wiggle their ends so that the men can see them and avoid such danger. Silly, yes. Sexist, yes. Latest edition written in 1884. A Flatland resident has a vision of Lineland (a one-dimensional world). Here men are small lines and women points, but inhabitants see both as points, so mating can be tricky. The inhabitant of Flatland is visited by an inhabitant of (three-dimensional) Spaceland. As you can imagine, it is quite difficult for the Flatlander to understand the Spacelander's description of his world. ============================================================ "Wuensch, Karl L." wrote (inter alia): > > If you have read Edwin Abbott's "Flatland," you might recognize that the > same concept (a mean) which looked like a point in one dimensional space now > looks like a line in two dimensional space. Then you would be ready to leap > into three dimensional space and even beyond, into hyperspace, but you might > want to sit down and have a good beer first. I promise that we shall travel > that space before the semester is out (as soon as we get started on multiple > regression). Sorry? The natural generalization of a mean to a 2-dimensional space is surely the vector mean, which is a point. -Robert Dawson +++++++++++++++++++++++++++++++++++++++++ Karl L. Wuensch, Department of Psychology, East Carolina University, Greenville NC 27858-4353 Voice: 252-328-4102 Fax: 252-328-6283 [EMAIL PROTECTED] <mailto:[EMAIL PROTECTED]> http://core.ecu.edu/psyc/wuenschk/klw.htm <http://core.ecu.edu/psyc/wuenschk/klw.htm> ---------- From: Robert J. MacG. Dawson [SMTP:[EMAIL PROTECTED]] Sent: Tuesday, October 10, 2000 8:01 AM To: Wuensch, Karl L. Cc: 'edstat' Subject: Re: memorizing formulas "Wuensch, Karl L." wrote (inter alia): > > If you have read Edwin Abbott's "Flatland," you might recognize that the > same concept (a mean) which looked like a point in one dimensional space now > looks like a line in two dimensional space. Then you would be ready to leap > into three dimensional space and even beyond, into hyperspace, but you might > want to sit down and have a good beer first. I promise that we shall travel > that space before the semester is out (as soon as we get started on multiple > regression). Sorry? The natural generalization of a mean to a 2-dimensional space is surely the vector mean, which is a point. -Robert Dawson ================================================================= Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =================================================================