diff --git a/pymc/tests/test_idata_conversion.py b/pymc/tests/test_idata_conversion.py
index 240976856d5..b846831f526 100644
--- a/pymc/tests/test_idata_conversion.py
+++ b/pymc/tests/test_idata_conversion.py
@@ -388,63 +388,6 @@ def test_multiple_observed_rv(self, log_likelihood):
         fails = check_multiple_attrs(test_dict, inference_data)
         assert not fails
 
-    @pytest.mark.xfail(reason="MultiObservedRV is no longer used in v4")
-    def test_multiple_observed_rv_without_observations(self):
-        with pm.Model():
-            mu = pm.Normal("mu")
-            x = pm.DensityDist(  # pylint: disable=unused-variable
-                "x", mu, logp=lambda value, mu: pm.Normal.logp(value, mu, 1), observed=0.1
-            )
-            inference_data = pm.sample(100, chains=2, return_inferencedata=True)
-        test_dict = {
-            "posterior": ["mu"],
-            "sample_stats": ["lp"],
-            "log_likelihood": ["x"],
-            "observed_data": ["value", "~x"],
-        }
-        fails = check_multiple_attrs(test_dict, inference_data)
-        assert not fails
-        assert inference_data.observed_data.value.dtype.kind == "f"
-
-    @pytest.mark.xfail(reason="MultiObservedRV is no longer used in v4")
-    @pytest.mark.parametrize("multiobs", (True, False))
-    def test_multiobservedrv_to_observed_data(self, multiobs):
-        # fake regression data, with weights (W)
-        np.random.seed(2019)
-        N = 100
-        X = np.random.uniform(size=N)
-        W = 1 + np.random.poisson(size=N)
-        a, b = 5, 17
-        Y = a + np.random.normal(b * X)
-
-        with pm.Model():
-            a = pm.Normal("a", 0, 10)
-            b = pm.Normal("b", 0, 10)
-            mu = a + b * X
-            sigma = pm.HalfNormal("sigma", 1)
-            w = W
-
-            def weighted_normal(value, mu, sigma, w):
-                return w * pm.Normal.logp(value, mu, sigma)
-
-            y_logp = pm.DensityDist(  # pylint: disable=unused-variable
-                "y_logp", mu, sigma, w, logp=weighted_normal, observed=Y, size=N
-            )
-            idata = pm.sample(
-                20, tune=20, return_inferencedata=True, idata_kwargs={"density_dist_obs": multiobs}
-            )
-        multiobs_str = "" if multiobs else "~"
-        test_dict = {
-            "posterior": ["a", "b", "sigma"],
-            "sample_stats": ["lp"],
-            "log_likelihood": ["y_logp"],
-            f"{multiobs_str}observed_data": ["y", "w"],
-        }
-        fails = check_multiple_attrs(test_dict, idata)
-        assert not fails
-        if multiobs:
-            assert idata.observed_data.y.dtype.kind == "f"
-
     def test_single_observation(self):
         with pm.Model():
             p = pm.Uniform("p", 0, 1)