The squared distance (also called the Mahalanobis distance) of observation x to the center (mean) of group t for linear discriminant is given by the following general form:
The squared Mahalanobis distance from x to group t for the quadratic discriminant function is calculated as follows:
The generalized squared distance from x to group t for the linear discriminant function is calculated as follows:
The generalized squared distance from x to group t for the quadratic discriminant function is calculated as follows:
The posterior probability for x belonging to group t is calculated as follows:
The linear discriminant scores are calculated as follows:
Term | Description |
---|---|
x | column vector of length p containing the values of the predictors for this observation (this column vector is stored as one row) |
p | number of predictors |
n | total number of observations |
t | group subscript |
nt | number of observations in group t |
qt | the prior probability of group t, which equals nt/n |
Sp | pooled covariance matrix for linear discriminant analysis |
Si | covariance matrix of group i for quadratic discriminant analysis |
mt | column vector of length p containing the means of the predictors calculated from the data in group t |
St | covariance matrix of group t |
|St| | determinant of St |
For a given x, this rule allocates x to the group with largest linear discriminant function.
Term | Description |
---|---|
x | column vector of length p containing the values of the predictors for this observation (this column vector is stored as one row) |
mi | column vector of length p containing the means of the predictors calculated from the data in group i |
Sp | pooled covariance matrix |
ln pi | natural log of the prior probability for group i |
Term | Description |
---|---|
x | column vector of length p containing the values of the predictors for this observation (this column vector is stored as one row) |
mi | column vector of length p containing the means of the predictors calculated from the data in group i |
Sp | pooled covariance matrix f |
ln pi | natural log of the prior probability for group i |
The largest posterior probability is equivalent to the largest value of ln [pi fi (x)]
Term | Description |
---|---|
pi | prior probability of group i |
fi(x) | the joint density for the data in group i (with the population parameters replaced by the sample estimates) |