On 7 Jun 2003, wuzzy wrote: > Is it possible to draw a venn diagram with more than 3 vars? > I've tried and it seems impossible to me:
Depends on how you conceptualize "Venn diagram". If you only wish to describe the topology of the related spaces, it's not impossible: think of a 3- or 4- (or...) dimensional frequency table as a topological equivalent to the Venn diagram one has in mind. But if you ALSO want to insist that some quantitative measure of the diagram be proportional to some quantitative measure of the space being mapped (e.g., proportion of variance explained by various components), THAT is not possible: a point that has to do with trying to represent a multidimensional space in only two dimensions. > with 2 vars the distance between AB is a factor of the % explained. > Add the 3rd var, C by using trigonometry (cosine law) when AC and BC > are the sides of the triangle with a value the size of the % > explained. > > Adding a 4th seems impossible because maybe because of my my limited > trig. Limited topology, rather; and/or trying for impossible quantitative representation. ----------------------------------------------------------------------- Donald F. Burrill [EMAIL PROTECTED] 56 Sebbins Pond Drive, Bedford, NH 03110 (603) 626-0816 . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
