Common distributions with typical uses and canonical link functions
Cosinor assumes a Normal distribution of Variance. The list below examines types of distributions.
Distribution Support of distribution Typical uses Link name
Normal real: Linear-response data Identity
Exponential real: Exponential-response data, scale parameters Inverse
Gamma
Inverse Gaussian real: Inverse squared
Poisson integer: count of occurrences in fixed amount of Log
time/space
Bernoulli integer: outcome a single yes/no occurrence Logit
Binomial integer: count of # of "yes" occurrences out of N
yes/no occurrences
Categorical integer: outcome of single K-way occurrence K-vector
of integer: , where exactly one element in the vector has the value 1
Multinomial K-vector of integer: count of occurrences of different types (1 .. K) out of N total K-way occurrences
http://en.wikipedia.org/wiki/Generalized_linear_model
Distribution Support of distribution Typical uses Link name
Normal real: Linear-response data Identity
Exponential real: Exponential-response data, scale parameters Inverse
Gamma
Inverse Gaussian real: Inverse squared
Poisson integer: count of occurrences in fixed amount of Log
time/space
Bernoulli integer: outcome a single yes/no occurrence Logit
Binomial integer: count of # of "yes" occurrences out of N
yes/no occurrences
Categorical integer: outcome of single K-way occurrence K-vector
of integer: , where exactly one element in the vector has the value 1
Multinomial K-vector of integer: count of occurrences of different types (1 .. K) out of N total K-way occurrences
http://en.wikipedia.org/wiki/Generalized_linear_model