Snow geeese
Aerial survey methods are regularly used to estimate the number of snow geese in their summer range areas west of Hudson Bay in Canada. To obtain estimates, small aircraft fly over the range and, when a flock of geese is spotted, an experienced person estimates the number of geese in the stock. To investigate the reliability of this method of counting, an experiment was conducted in which an airplane carrying two observers flew over n = 45 flocks, and each observer made an independent estimate of the of birds in each flock. Also, a photograph of the flock was taken so that an exact count of the number of birds in the flock could be made. The resulting data are in given in geese.txt.
As a result of this experiment, the practice of using visual counts of flock size to determite population estimates was discontinued in favor of using photographs.
S. Weisberg: Applied Linear Regression. John Wiley & Sons, 1985.
R. D. Cook, J. O. Jacobsen: Analysis of 1977 West Hudson Bay snow goose surveys. Unpublished report, Canadian Wildlife Services, 1977.
PHOTO = c(1) + c(2) OBS1 + ε,
kde PHOTO je skutočný počet husí (získaný z fotografie) a OBS1 je počet odhadnutý prvým pozorovateľom, najskôr odhadneme klasickým odhadom:
Obr. 1: Regresia
Obr. 2: Regresia s Whitovym odhadom kovariančnej matice
Ak klikneme na View - Covariance Matrix, dostaneme odhad kovariančnej matice.
Obr. 3: Whitov odhad kovariančnej matice
c(1) = 0, c(2) = 1.
Pretože v modeli je heteroskedasticita, na testovanie tejto lineárnej hypotézy použijeme Waldov test.Klikneme na View - Coefficients Tests - Wald Coefficient Resctrictions
Obr. 4: Waldov test
a zapíšeme hypotézu, ktorú chceme testovať.
Obr. 5: Waldov test
Dostaneme:
Obr. 6: Waldov test
Beáta Stehlíková (www)
Cvičenia z ekonometrie, 3mef