Langlois and Roggman (1990) took facial photographs of males and females ...

      Langlois and Roggman (1990) took facial photographs of   males and females. They then created five groups of composite photographs by   computer-averaging the individual faces. For one group the computer averaged   32 randomly selected same-gender faces, producing a quite recognizable face   with average width, height, eyes, nose length, and so on. For the other   groups the composite faces were averaged over either 2, 4, 8, or 16   individual faces. Each group saw six separate photographs, all of which were computer-averaged   over the appropriate number of individual photographs. Langlois and Roggman   asked participants to rate the attractiveness of the faces on a 1–5 scale,   where 5 represents “very attractive.” The data have been constructed to have   the same means and variances as those reported by Langlois and Roggman.            Group 1 Group 2 Group 3 Group 4 Group 5     2.201 1.893 2.906 3.233 3.2     2.411 3.102 2.118 3.505 3.253     2.407 2.355 3.226 3.192 3.357     2.403 3.644 2.811 3.209 3.169     2.826 2.767 2.857 2.86 3.291     3.38 2.109 3.422 3.111 3.29              a) Run the   appropriate analysis of variance.
     b) What do   these data tell us about how people judge attractiveness?