Academia

Análise de regressão, na prática

Interessante esta do Mahalanobis (um dos links fixos ao lado).


During World War II, in investigating aiming errors made during bomber flights over Europe, one of the research organizations developed a regression equation with several carriers (explanatories). Among its nine or so carriers were altitude, type of aircraft, speed of the bombing group, size of group, and the amount of fighter opposition. On physical grounds, one might expect higher altitudes and higher speeds to produce larger aiming errors. It would not be surprising if different aircraft differed in performance. What the effect of size of group might be can be argued either way. But few people will believe that additional fighter opposition would help a pilot and bombardier do a better job. Nevertheless, amount of fighter opposition appeared as a strong term in the regression equation—the more opposition, the smaller the aiming error. The effect is generally regarded as a proxy phenomenon, arising because the equation had no variable for amount of cloud cover. If clouds obscured the target, the fighters usually did not come up and the aiming errors were ordinarily very large.

Mudando de assunto, o nosso “Mahalanobis” tem uma excelente crítica sobre o radicalismo de alguns muçulmanos, na mesma linha da crítica de Postrel que citei abaixo. Estou aguardando pelas explosões e incêndios na porta da revista Rolling Stones…

Claudio

Deixe um comentário

Preencha os seus dados abaixo ou clique em um ícone para log in:

Logotipo do WordPress.com

Você está comentando utilizando sua conta WordPress.com. Sair /  Alterar )

Foto do Google

Você está comentando utilizando sua conta Google. Sair /  Alterar )

Imagem do Twitter

Você está comentando utilizando sua conta Twitter. Sair /  Alterar )

Foto do Facebook

Você está comentando utilizando sua conta Facebook. Sair /  Alterar )

Conectando a %s