Initial update

Author: Andrew Johnson

basic_estimators/bernoulli_new.stan

@@ -0,0 +1,11 @@
+data { 
+  int<lower=0> N; 
+  int<lower=0, upper=1> y[N];
+} 
+parameters {
+  real<lower=0, upper=1> theta;
+} 
+model {
+  theta ~ beta(1, 1);
+  y ~ bernoulli(theta);
+}

basic_estimators/negative_binomial2_new.stan

@@ -0,0 +1,14 @@
+data {
+  int<lower=1> N;
+  int<lower=0> y[N];
+}
+parameters {
+  real<lower=0> alpha;
+  real<lower=0, upper=1> p_success;
+}
+transformed parameters {
+   real<lower=0.0> beta = p_success / (1.0 - p_success);
+}
+model { 
+  y ~ neg_binomial(alpha, beta);
+}

basic_estimators/negative_binomial_new.stan

@@ -0,0 +1,13 @@
+data {
+  int<lower=1> N;
+  int<lower=0> y[N];
+}
+parameters {
+  real<lower=0> alpha;
+  real<lower=0> beta;
+}
+model { 
+  alpha ~ cauchy(0, 10);
+  beta ~ cauchy(0, 10);
+  y ~ neg_binomial(alpha, beta);
+}

basic_estimators/normal_censored

@@ -0,0 +1,17 @@
+data {
+  real U;
+  int<lower=0> N_censored;
+  int<lower=0> N_observed;
+  real<upper=U> y[N_observed];
+}
+parameters { 
+  real mu;
+}
+model {
+  // Vectorization with truncation is not yet supported
+  for (n in 1:N_observed)
+    y[n] ~ normal(mu,1.0) T[,U];
+  target += N_censored * normal_lccdf(U | mu, 1);
+}
+
+

basic_estimators/normal_censored_new

@@ -0,0 +1,9 @@
+transformed data {
+  vector[5] y = [2, 1, -0.5, 3, 0.25]';
+}
+parameters {
+  real mu;
+}
+model {
+  y ~ normal(mu, 1);
+}

basic_estimators/normal_censored_new.stan

@@ -0,0 +1,20 @@
+data {
+  int<lower=1> K;
+  int<lower=1> N;
+  vector[N] y;
+}
+parameters {
+  simplex[K] theta;
+  vector[K] mu;
+  vector<lower=0, upper=10>[K] sigma;
+}
+model {
+  vector[K] ps[N];              
+  mu ~ normal(0,10);
+  for (n in 1:N) {
+    for (k in 1:K) {
+      ps[n][k] = normal_log(y[n] | mu[k], sigma[k]);
+    }
+  }
+  target += log_mix(theta, ps);  
+}