diff --git a/test/test_utils/AllUtils.jl b/test/test_utils/AllUtils.jl
deleted file mode 100644
index 4ca57d838..000000000
--- a/test/test_utils/AllUtils.jl
+++ /dev/null
@@ -1,7 +0,0 @@
-# Import utility functions and reused models.
-include("staging.jl")
-include("numerical_tests.jl")
-include("ad_utils.jl")
-include("models.jl")
-include("random_measure_utils.jl")
-include("testing_functions.jl")
diff --git a/test/test_utils/random_measure_utils.jl b/test/test_utils/random_measure_utils.jl
deleted file mode 100644
index 63c84c11a..000000000
--- a/test/test_utils/random_measure_utils.jl
+++ /dev/null
@@ -1,34 +0,0 @@
-function compute_log_joint(observations, partition, tau0, tau1, sigma, theta)
-  n = length(observations)
-  k = length(partition)
-  prob = k*log(sigma) + lgamma(theta) + lgamma(theta/sigma + k) - lgamma(theta/sigma) - lgamma(theta + n)
-  for cluster in partition
-    prob += lgamma(length(cluster) - sigma) - lgamma(1 - sigma)
-    prob += compute_log_conditional_observations(observations, cluster, tau0, tau1)
-  end
-  prob
-end
-
-function compute_log_conditional_observations(observations, cluster, tau0, tau1)
-  nl = length(cluster)
-  prob = (nl/2)*log(tau1) - (nl/2)*log(2*pi) + 0.5*log(tau0) + 0.5*log(tau0+nl)
-  prob += -tau1/2*(sum(observations)) + 0.5*(tau0*mu_0+tau1*sum(observations[cluster]))^2/(tau0+nl*tau1)
-  prob
-end
-
-# Test of similarity between distributions
-function correct_posterior(empirical_probs, data, partitions, τ0, τ1, σ, θ)
-    true_log_probs = map(p -> compute_log_joint(data, p, τ0, τ1, σ, θ), partitions)
-    true_probs = exp.(true_log_probs)
-    true_probs /= sum(true_probs)
-
-    empirical_probs /= sum(empirical_probs)
-
-    # compare distribitions
-    # L2
-    L2 = sum((empirical_probs - true_probs).^2)
-
-    # Discrepancy
-    discr = maximum(abs.(empirical_probs - true_probs))
-    return L2, discr
-end
diff --git a/test/test_utils/staging.jl b/test/test_utils/staging.jl
deleted file mode 100644
index 15d5853d0..000000000
--- a/test/test_utils/staging.jl
+++ /dev/null
@@ -1,52 +0,0 @@
-function get_stage()
-    # Appveyor uses "True" for non-Ubuntu images.
-    if get(ENV, "APPVEYOR", "") == "True" || get(ENV, "APPVEYOR", "") == "true"
-        return "nonnumeric"
-    end
-
-    # Handle Travis and Github Actions specially.
-    if get(ENV, "TRAVIS", "") == "true" || get(ENV, "GITHUB_ACTIONS", "") == "true"
-        if "STAGE" in keys(ENV)
-            return ENV["STAGE"]
-        else
-            return "all"
-        end
-    end
-
-    return "all"
-end
-
-function do_test(stage_str)
-    stg = get_stage()
-
-    # If the tests are being run by Appveyor, don't run
-    # any numerical tests.
-    if stg == "nonnumeric"
-        if stage_str == "numerical"
-            return false
-        else
-            return true
-        end
-    end
-
-    # Otherwise run the regular testing procedure.
-    if stg == "all" || stg == stage_str
-        return true
-    end
-
-    return false
-end
-
-macro stage_testset(stage_string::String, args...)
-    if do_test(stage_string)
-        return esc(:(@testset($(args...))))
-    end
-end
-
-macro numerical_testset(args...)
-    esc(:(@stage_testset "numerical" $(args...)))
-end
-
-macro turing_testset(args...)
-    esc(:(@stage_testset "test" $(args...)))
-end