15 The choice of weighting scheme for the districts is not central to the findings. The
analysis was also conducted using a production weighted average which as expected
produced slightly stronger aggregation effects.
16 Similar to previous research, the results are presented in terms of revenues assuming a
constant price. Thus, we do not address price risk, but rather restrict analysis to quantity
risk only. Evaluation of the price-quantity interaction effect, however, may be an
interesting area of future research.
17 In-sample estimates of two sub periods, 1971-1986 and 1987-2002, were highly
consistent with the out-of-sample estimates. For example, separate analysis of the in-
sample sub periods (not reported) revealed reductions in RMSL ranging from 3.88%
(26.02%) in the 1st half of the sample, to 42.59% (4.68%) for the 2nd half for district D20
(D80), whereas the State portfolio RMSL’s ranged only from 40.24% to 58.66%.
26
More intriguing information
1. Models of Cognition: Neurological possibility does not indicate neurological plausibility.2. The name is absent
3. Elicited bid functions in (a)symmetric first-price auctions
4. The name is absent
5. National curriculum assessment: how to make it better
6. The name is absent
7. The Distribution of Income of Self-employed, Entrepreneurs and Professions as Revealed from Micro Income Tax Statistics in Germany
8. Konjunkturprognostiker unter Panik: Kommentar
9. Beyond Networks? A brief response to ‘Which networks matter in education governance?’
10. Evaluating the Impact of Health Programmes