leaderboard/irt/pyirt/three_param_logistic.py [22:65]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.priors = priors
        self.device = device
        self.num_items = num_items
        self.num_models = num_models

    def model_hierarchical(self, models, items, obs):
        mu_b = pyro.sample(
            "mu_b",
            dist.Normal(
                torch.tensor(0.0, device=self.device), torch.tensor(1.0e6, device=self.device),
            ),
        )
        u_b = pyro.sample(
            "u_b",
            dist.Gamma(
                torch.tensor(1.0, device=self.device), torch.tensor(1.0, device=self.device),
            ),
        )

        mu_theta = pyro.sample(
            "mu_theta",
            dist.Normal(
                torch.tensor(0.0, device=self.device), torch.tensor(1.0e6, device=self.device),
            ),
        )
        u_theta = pyro.sample(
            "u_theta",
            dist.Gamma(
                torch.tensor(1.0, device=self.device), torch.tensor(1.0, device=self.device),
            ),
        )

        mu_gamma = pyro.sample(
            "mu_gamma",
            dist.Normal(
                torch.tensor(0.0, device=self.device), torch.tensor(1.0e6, device=self.device),
            ),
        )
        u_gamma = pyro.sample(
            "u_gamma",
            dist.Gamma(
                torch.tensor(1.0, device=self.device), torch.tensor(1.0, device=self.device),
            ),
        )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



leaderboard/irt/pyirt/two_param_logistic.py [20:74]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.priors = priors
        self.device = device
        self.num_items = num_items
        self.num_models = num_models

    def model_hierarchical(self, models, items, obs):
        """
        This model differs from the 1PL model by introducing a "discriminability"
        parameter.

        y ~ bernoulli_logit(gamma[kk] .* (alpha[jj] - (beta[kk] + mu_beta)));

        v,

        y[n] ~ bernoulli_logit(alpha[jj] - beta[kk] + mu_beta);
        """

        mu_b = pyro.sample(
            "mu_b",
            dist.Normal(
                torch.tensor(0.0, device=self.device), torch.tensor(1.0e6, device=self.device),
            ),
        )
        u_b = pyro.sample(
            "u_b",
            dist.Gamma(
                torch.tensor(1.0, device=self.device), torch.tensor(1.0, device=self.device),
            ),
        )

        mu_theta = pyro.sample(
            "mu_theta",
            dist.Normal(
                torch.tensor(0.0, device=self.device), torch.tensor(1.0e6, device=self.device),
            ),
        )
        u_theta = pyro.sample(
            "u_theta",
            dist.Gamma(
                torch.tensor(1.0, device=self.device), torch.tensor(1.0, device=self.device),
            ),
        )

        mu_gamma = pyro.sample(
            "mu_gamma",
            dist.Normal(
                torch.tensor(0.0, device=self.device), torch.tensor(1.0e6, device=self.device),
            ),
        )
        u_gamma = pyro.sample(
            "u_gamma",
            dist.Gamma(
                torch.tensor(1.0, device=self.device), torch.tensor(1.0, device=self.device),
            ),
        )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -