Table 14.  Predictability of Market Advisory Service Performance by Winner and Loser Categories Between Pairs of Non-Overlapping Marketing Years, Corn, Soybeans and 50/50 Revenue, 1995-1998
                Two-tail  
Commodity Year t Year t+1   Winner t+1 Loser t+1 Odds Ratio Z-statistic p-value   se
---number of services---
Corn 1995 1997 Winner t 4 5 0.80 -0.24 0.81 0.921954 4 5 5 5
Loser t 5 5
1996 1998 Winner t 8 3 7.11 2.05 0.04 ** 0.957427
Loser t 3 8
1995-1998 Winner t 12 8 2.44 1.39 0.16 0.640513
Total Loser t 8 13
Soybeans 1995 1997 Winner t 4 5 0.80 -0.24 0.81 0.921954
Loser t 5 5
1996 1998 Winner t 5 5 1.00 0.00 1.00 0.894427
Loser t 5 5
1995-1998 Winner t 9 10 0.90 -0.16 0.87 0.641179
Total Loser t 10 10
50/50 Revenue 1995 1997 Winner t 4 5 0.80 -0.24 0.81 0.921954
Loser t 5 5
1996 1998 Winner t 5 5 1.00 0.00 1.00 0.894427
Loser t 5 5
1995-1998 Winner t 9 10 0.90 -0.16 0.87 0.641179
  Total Loser t 10 10        
Note:  The selection strategy consists of ranking services by pricing performance (net advisory price and return result in the same rankings) in the first year of the pair (e.g., t = 1995) and then forming two groups of services:  "winners" are those services in the top half of the rankings and "losers" are services in the bottom half. Next, the same services are ranked by pricing performance for the second year of the pair (e.g., t+1 = 1997), and again divided into "winners" and "losers."  For a given comparison, advisory services must fall in one of the following categories: winner t-winner t+1, winner t-loser t+1, loser t-winner t+1, loser t-loser t+1.  The odds ratio is the ratio of the odds of a winning service in t being a winning service in t+1 to the odds of a losing service in t being a winning service in t+1. Three stars indicates significance at the 1% level, two stars indicates significance at the 5% level, and one star indicates significance at the 10% level.