Refer to Market share data set in Appendix C.3. Company executives want to be able to predict market share of their product (Y) based on merchandise price (X1), the gross Nielsen rating points (X2, an index of the amount of advertising exposure that the product received); the presence or absence of a wholesale pricing discount (X3 = 1 if discount present; otherwise X3 = 0); the presence or absence ofa package promotion during the period (X4 =1 ifpromotion present; otherwise X4 = 0); and year (X5). Code year as a nominal level variable and use 2000 as the referent year.

1 3.15 2.198 498 1 1 Sep 1999 2 2.52 2.186 510 0 0 Oct 1999 3 2.64 2.293 422 1 1 Nov 1999 4 2.55 2.420 858 0 1 Dec 1999 5 2.69 2.179 566 1 0 Jan 2000 6 2.38 2.207 536 0 0 Feb 2000 7 3.02 2.127 585 1 1 Mar 2000 8 2.52 2.206 310 1 0 Apr 2000 9 2.45 2.305 211 0 0 May 2000 10 2.42 2.260 504 0 1 Jun 2000 11 3.16 2.205 234 1 1 Jul 2000 12 2.60 2.340 347 0 0 Aug 2000 13 2.98 2.171 430 1 0 Sep 2000 14 2.50 2.201 518 0 1 Oct 2000 15 2.45 2.248 465 0 0 Nov 2000 16 3.06 2.184 684 1 1 Dec 2000 17 2.34 2.373 152 0 0 Jan 2001 18 2.88 2.157 453 1 1 Feb 2001 19 2.94 2.129 485 1 1 Mar 2001 20 2.72 2.557 78 1 0 Apr 2001 21 2.27 2.587 72 0 1 May 2001 22 2.33 2.255 391 0 0 Jun 2001 23 2.64 2.124 322 1 0 Jul 2001 24 2.76 2.683 317 1 1 Aug 2001 25 3.05 2.336 252 1 1 Sep 2001 26 2.48 2.266 446 0 1 Oct 2001 27 2.23 2.443 521 0 0 Nov 2001 28 2.65 2.478 435 1 1 Dec 2001 29 2.56 2.394 402 1 0 Jan 2002 30 2.66 2.414 468 1 1 Feb 2002 31 2.99 2.233 262 1 0 Mar 2002 32 2.30 2.302 182 0 1 Apr 2002 33 2.88 2.421 145 1 1 May 2002 34 2.80 2.518 270 1 0 Jun 2002 35 2.48 2.497 322 0 1 Jul 2002 36 2.85 2.781 317 1 1 Aug 2002