Mstar: Mutiplier term for first deriviative of log-likelihood of...
In peterhalpin/BearShare: Psychometric models of small group collaborations

Description Usage Arguments Value

The gradient of the log-likelihood of the RSC model a single item can be computed as M * grad_IRF. This function computes (a matrix of values of) M. Called by functions that compute derivatives of the log-likelihood.

1	Mstar(resp, u, parms, theta1, theta2)

`resp`	a matrix or data.frame containing the (conjunctively-scored, binary) item responses.
`u`	the logit of the weight parameter of the RSC model.
`parms`	a data.frame with columns `parms$alpha` and `parms$beta` corresponding to the discrimination and difficulty parameters of the 2PL model, respectively.
`theta1`	the latent trait of member 1.
`theta2`	the latent trait of member 2.