The Probit Model of Modal Choice In the bi-modal case, the probit model equates the probability that a given traveler chooses mode 1 instead of mode 2 to the probability that a standardized normal random variable takes on a value less than some critical level called the "utility" of mode 1. The utility of mode 1 is evaluated as a function of the characteristics of the traveler and the relative advantages (or disadvantages) of mode lover mode 2. Recall from your introductory statistics class that for a particular observation (or variate) X* on a normally distributed random variable X with mean ~ and variance oe--i.e., X -N(~ra)--the "z score" for this observation is computed according to the formula Z*=(X*-~)/o. Z scores, which are measured in standard-deviation units from the mean of X, or ~, are distributed according to a standardized normal distribution--i.e., Z -S.N.(Orl). Z scores are tabulated to correspond to a cumulative standardized normal distribution which gives the proportion
This is the end of the preview. Sign up
access the rest of the document.
This note was uploaded on 03/16/2010 for the course CRP 3210 at Cornell University (Engineering School).