ESTIMATION OF EFFICIENT REGRESSION MODELS FOR APPLIED AGRICULTURAL ECONOMICS RESEARCH



numerically simulate the probability distribution from which they could have been drawn. Specifically, let

γi be the kx 1 vector of maximum likelihood estimators for Γi, the vector of true population parameters

^ ^

underlying the normal (i=N, k=10) or the non-normal (i=NN, k=14) regression model, and CM [ri ] be the
estimated covariance matrix for
γi. Then, the joint probability distribution of γi is simulated by:

~

(9)     Si= Z x Chol( CM[Γi ]) + Γi,

where Z is an mxk matrix of independently distributed standard normal random variables, Chol(.) denotes the
~                                          ^

Cholesky decomposition, and γi the kx 1 vector of parameter estimates obtained from γi. Equation (9) yields

~                      ^ ^

an mxk matrix of random variables with mean γi and covariance matrix CM[ri]. Since, under a correct

^                                ^ ^                              ^

model specification, γi is a consistent estimator for Γi and CM[ri] is a consistent estimator for CM[ri], Si
is a theoretically correct probabilistic statement about Γi. Thus, the boundaries of a (1-α)% confidence
interval for the expected price under the normal (non-normal) model at time period t can be obtained by
extracting the m sets of simulated parameter values from S
n (Snn), using them to obtain m “predicted” price
values for time t, and finding the (
a/2) x mth and the [(1-a)+a/2] x mth largest of these m price values.

Confidence intervals for the actual price realizations require simulation of m error term draws as well.
In the case of the normal regression model, these are obtained by extracting the m simulated values for the
standard deviation parameter (
σc or σs) from Sn and multiplying them by m independent draws from a
standard normal random variable. In the case of the non-normal model, the m sets of simulated values for
σc,
μ c and Θc (or σs, μ s and Θs) have to be extracted from Snn and coupled with m independent standard normal
draws. Then, m non-normal error term values are simulated by applying equation (2). The final step in
constructing the boundaries of a (1-
α)% confidence interval for the actual price observations is to add the m
simulated error term values to the corresponding m price “predictions” and find the (
a/2) x mth and the [(1-

15



More intriguing information

1. Experimental Evidence of Risk Aversion in Consumer Markets: The Case of Beef Tenderness
2. Skill and work experience in the European knowledge economy
3. The name is absent
4. Testing Panel Data Regression Models with Spatial Error Correlation
5. The name is absent
6. BUSINESS SUCCESS: WHAT FACTORS REALLY MATTER?
7. Regional differentiation in the Russian federation: A cluster-based typification
8. Problems of operationalizing the concept of a cost-of-living index
9. AN EXPLORATION OF THE NEED FOR AND COST OF SELECTED TRADE FACILITATION MEASURES IN ASIA AND THE PACIFIC IN THE CONTEXT OF THE WTO NEGOTIATIONS
10. The resources and strategies that 10-11 year old boys use to construct masculinities in the school setting