ANLY505 - Intro to Stan
Week 4
Neha Katti
2020-01-15
Intro to STAN Homework Part #1
After our Intro to Stan lecture I think it would be valuable to have you go through a similar exercise. Let’s test a second research question.
Research question: Is sea ice extent declining in the Southern Hemisphere over time? Is the same pattern happening in the Antarctic as in the Arctic? Fit a Stan model to find out!
Make sure you follow the steps we used in class.
What do your Stan model results indicate so far?
1. Load and Inspect Data
#place the code here
library(data.table)##
## Attaching package: 'data.table'## The following objects are masked from 'package:gdata':
##
## first, lastseaice_1_ <- read.csv("C:/Users/NehaKatti/Desktop/seaice (1).csv", stringsAsFactors = F)
colnames(seaice_1_) <- c("year", "extent_north", "extent_south")
head(seaice_1_)## year extent_north extent_south
## 1 1979 12.328 11.700
## 2 1980 12.337 11.230
## 3 1981 12.127 11.435
## 4 1982 12.447 11.640
## 5 1983 12.332 11.389
## 6 1984 11.910 11.4542. Plot the data
#plot data
plot(extent_north ~ year, pch = 20, data = seaice_1_)
3. Run a general linear model using lm()
#write the code
lm1 = lm(extent_north ~ year, data = seaice_1_)
summary(lm1)##
## Call:
## lm(formula = extent_north ~ year, data = seaice_1_)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.49925 -0.17713 0.04898 0.16923 0.32829
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 120.503036 6.267203 19.23 <2e-16 ***
## year -0.054574 0.003137 -17.40 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.2205 on 37 degrees of freedom
## Multiple R-squared: 0.8911, Adjusted R-squared: 0.8881
## F-statistic: 302.7 on 1 and 37 DF, p-value: < 2.2e-164. Index the data, re-run the lm(), extract summary statistics and turn the indexed data into a dataframe to pass into Stan
#write the code here
plot(extent_north ~ year, pch = 20, data = seaice_1_)
abline(lm1, col = 2, lty = 2, lw = 3)
x = I(seaice_1_$year - 1978)
y = seaice_1_$extent_north
N = length(seaice_1_$year)
lm1 = lm(y ~ x)
summary(lm1)##
## Call:
## lm(formula = y ~ x)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.49925 -0.17713 0.04898 0.16923 0.32829
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 12.555888 0.071985 174.4 <2e-16 ***
## x -0.054574 0.003137 -17.4 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.2205 on 37 degrees of freedom
## Multiple R-squared: 0.8911, Adjusted R-squared: 0.8881
## F-statistic: 302.7 on 1 and 37 DF, p-value: < 2.2e-16lm_alpha = summary(lm1)$coeff[1]
lm_beta = summary(lm1)$coeff[2]
lm_sigma = sigma(lm1)
stan_data = list(N = N, x = x, y = y)5. Write the Stan model
#write the code
write("// Stan model for simple linear regression
data {
int < lower = 1 > N; // Sample size
vector[N] x; // Predictor
vector[N] y; // Outcome
}
parameters {
real alpha; // Intercept
real beta; // Slope (regression coefficients)
real < lower = 0 > sigma; // Error SD
}
model {
y ~ normal(alpha + x * beta , sigma);
}
generated quantities {
} // The posterior predictive distribution",
"stan_model1.stan")
stanc("stan_model1.stan")## $status
## [1] TRUE
##
## $model_cppname
## [1] "model1d844be0698_stan_model1"
##
## $cppcode
## [1] "// Code generated by Stan version 2.19.1\n\n#include <stan/model/model_header.hpp>\n\nnamespace model1d844be0698_stan_model1_namespace {\n\nusing std::istream;\nusing std::string;\nusing std::stringstream;\nusing std::vector;\nusing stan::io::dump;\nusing stan::math::lgamma;\nusing stan::model::prob_grad;\nusing namespace stan::math;\n\nstatic int current_statement_begin__;\n\nstan::io::program_reader prog_reader__() {\n stan::io::program_reader reader;\n reader.add_event(0, 0, \"start\", \"model1d844be0698_stan_model1\");\n reader.add_event(22, 20, \"end\", \"model1d844be0698_stan_model1\");\n return reader;\n}\n\nclass model1d844be0698_stan_model1 : public prob_grad {\nprivate:\n int N;\n vector_d x;\n vector_d y;\npublic:\n model1d844be0698_stan_model1(stan::io::var_context& context__,\n std::ostream* pstream__ = 0)\n : prob_grad(0) {\n ctor_body(context__, 0, pstream__);\n }\n\n model1d844be0698_stan_model1(stan::io::var_context& context__,\n unsigned int random_seed__,\n std::ostream* pstream__ = 0)\n : prob_grad(0) {\n ctor_body(context__, random_seed__, pstream__);\n }\n\n void ctor_body(stan::io::var_context& context__,\n unsigned int random_seed__,\n std::ostream* pstream__) {\n typedef double local_scalar_t__;\n\n boost::ecuyer1988 base_rng__ =\n stan::services::util::create_rng(random_seed__, 0);\n (void) base_rng__; // suppress unused var warning\n\n current_statement_begin__ = -1;\n\n static const char* function__ = \"model1d844be0698_stan_model1_namespace::model1d844be0698_stan_model1\";\n (void) function__; // dummy to suppress unused var warning\n size_t pos__;\n (void) pos__; // dummy to suppress unused var warning\n std::vector<int> vals_i__;\n std::vector<double> vals_r__;\n local_scalar_t__ DUMMY_VAR__(std::numeric_limits<double>::quiet_NaN());\n (void) DUMMY_VAR__; // suppress unused var warning\n\n try {\n // initialize data block variables from context__\n current_statement_begin__ = 4;\n context__.validate_dims(\"data initialization\", \"N\", \"int\", context__.to_vec());\n N = int(0);\n vals_i__ = context__.vals_i(\"N\");\n pos__ = 0;\n N = vals_i__[pos__++];\n check_greater_or_equal(function__, \"N\", N, 1);\n\n current_statement_begin__ = 5;\n validate_non_negative_index(\"x\", \"N\", N);\n context__.validate_dims(\"data initialization\", \"x\", \"vector_d\", context__.to_vec(N));\n x = Eigen::Matrix<double, Eigen::Dynamic, 1>(N);\n vals_r__ = context__.vals_r(\"x\");\n pos__ = 0;\n size_t x_j_1_max__ = N;\n for (size_t j_1__ = 0; j_1__ < x_j_1_max__; ++j_1__) {\n x(j_1__) = vals_r__[pos__++];\n }\n\n current_statement_begin__ = 6;\n validate_non_negative_index(\"y\", \"N\", N);\n context__.validate_dims(\"data initialization\", \"y\", \"vector_d\", context__.to_vec(N));\n y = Eigen::Matrix<double, Eigen::Dynamic, 1>(N);\n vals_r__ = context__.vals_r(\"y\");\n pos__ = 0;\n size_t y_j_1_max__ = N;\n for (size_t j_1__ = 0; j_1__ < y_j_1_max__; ++j_1__) {\n y(j_1__) = vals_r__[pos__++];\n }\n\n\n // initialize transformed data variables\n // execute transformed data statements\n\n // validate transformed data\n\n // validate, set parameter ranges\n num_params_r__ = 0U;\n param_ranges_i__.clear();\n current_statement_begin__ = 10;\n num_params_r__ += 1;\n current_statement_begin__ = 11;\n num_params_r__ += 1;\n current_statement_begin__ = 12;\n num_params_r__ += 1;\n } catch (const std::exception& e) {\n stan::lang::rethrow_located(e, current_statement_begin__, prog_reader__());\n // Next line prevents compiler griping about no return\n throw std::runtime_error(\"*** IF YOU SEE THIS, PLEASE REPORT A BUG ***\");\n }\n }\n\n ~model1d844be0698_stan_model1() { }\n\n\n void transform_inits(const stan::io::var_context& context__,\n std::vector<int>& params_i__,\n std::vector<double>& params_r__,\n std::ostream* pstream__) const {\n typedef double local_scalar_t__;\n stan::io::writer<double> writer__(params_r__, params_i__);\n size_t pos__;\n (void) pos__; // dummy call to supress warning\n std::vector<double> vals_r__;\n std::vector<int> vals_i__;\n\n current_statement_begin__ = 10;\n if (!(context__.contains_r(\"alpha\")))\n stan::lang::rethrow_located(std::runtime_error(std::string(\"Variable alpha missing\")), current_statement_begin__, prog_reader__());\n vals_r__ = context__.vals_r(\"alpha\");\n pos__ = 0U;\n context__.validate_dims(\"parameter initialization\", \"alpha\", \"double\", context__.to_vec());\n double alpha(0);\n alpha = vals_r__[pos__++];\n try {\n writer__.scalar_unconstrain(alpha);\n } catch (const std::exception& e) {\n stan::lang::rethrow_located(std::runtime_error(std::string(\"Error transforming variable alpha: \") + e.what()), current_statement_begin__, prog_reader__());\n }\n\n current_statement_begin__ = 11;\n if (!(context__.contains_r(\"beta\")))\n stan::lang::rethrow_located(std::runtime_error(std::string(\"Variable beta missing\")), current_statement_begin__, prog_reader__());\n vals_r__ = context__.vals_r(\"beta\");\n pos__ = 0U;\n context__.validate_dims(\"parameter initialization\", \"beta\", \"double\", context__.to_vec());\n double beta(0);\n beta = vals_r__[pos__++];\n try {\n writer__.scalar_unconstrain(beta);\n } catch (const std::exception& e) {\n stan::lang::rethrow_located(std::runtime_error(std::string(\"Error transforming variable beta: \") + e.what()), current_statement_begin__, prog_reader__());\n }\n\n current_statement_begin__ = 12;\n if (!(context__.contains_r(\"sigma\")))\n stan::lang::rethrow_located(std::runtime_error(std::string(\"Variable sigma missing\")), current_statement_begin__, prog_reader__());\n vals_r__ = context__.vals_r(\"sigma\");\n pos__ = 0U;\n context__.validate_dims(\"parameter initialization\", \"sigma\", \"double\", context__.to_vec());\n double sigma(0);\n sigma = vals_r__[pos__++];\n try {\n writer__.scalar_lb_unconstrain(0, sigma);\n } catch (const std::exception& e) {\n stan::lang::rethrow_located(std::runtime_error(std::string(\"Error transforming variable sigma: \") + e.what()), current_statement_begin__, prog_reader__());\n }\n\n params_r__ = writer__.data_r();\n params_i__ = writer__.data_i();\n }\n\n void transform_inits(const stan::io::var_context& context,\n Eigen::Matrix<double, Eigen::Dynamic, 1>& params_r,\n std::ostream* pstream__) const {\n std::vector<double> params_r_vec;\n std::vector<int> params_i_vec;\n transform_inits(context, params_i_vec, params_r_vec, pstream__);\n params_r.resize(params_r_vec.size());\n for (int i = 0; i < params_r.size(); ++i)\n params_r(i) = params_r_vec[i];\n }\n\n\n template <bool propto__, bool jacobian__, typename T__>\n T__ log_prob(std::vector<T__>& params_r__,\n std::vector<int>& params_i__,\n std::ostream* pstream__ = 0) const {\n\n typedef T__ local_scalar_t__;\n\n local_scalar_t__ DUMMY_VAR__(std::numeric_limits<double>::quiet_NaN());\n (void) DUMMY_VAR__; // dummy to suppress unused var warning\n\n T__ lp__(0.0);\n stan::math::accumulator<T__> lp_accum__;\n try {\n stan::io::reader<local_scalar_t__> in__(params_r__, params_i__);\n\n // model parameters\n current_statement_begin__ = 10;\n local_scalar_t__ alpha;\n (void) alpha; // dummy to suppress unused var warning\n if (jacobian__)\n alpha = in__.scalar_constrain(lp__);\n else\n alpha = in__.scalar_constrain();\n\n current_statement_begin__ = 11;\n local_scalar_t__ beta;\n (void) beta; // dummy to suppress unused var warning\n if (jacobian__)\n beta = in__.scalar_constrain(lp__);\n else\n beta = in__.scalar_constrain();\n\n current_statement_begin__ = 12;\n local_scalar_t__ sigma;\n (void) sigma; // dummy to suppress unused var warning\n if (jacobian__)\n sigma = in__.scalar_lb_constrain(0, lp__);\n else\n sigma = in__.scalar_lb_constrain(0);\n\n // model body\n\n current_statement_begin__ = 16;\n lp_accum__.add(normal_log<propto__>(y, add(alpha, multiply(x, beta)), sigma));\n\n } catch (const std::exception& e) {\n stan::lang::rethrow_located(e, current_statement_begin__, prog_reader__());\n // Next line prevents compiler griping about no return\n throw std::runtime_error(\"*** IF YOU SEE THIS, PLEASE REPORT A BUG ***\");\n }\n\n lp_accum__.add(lp__);\n return lp_accum__.sum();\n\n } // log_prob()\n\n template <bool propto, bool jacobian, typename T_>\n T_ log_prob(Eigen::Matrix<T_,Eigen::Dynamic,1>& params_r,\n std::ostream* pstream = 0) const {\n std::vector<T_> vec_params_r;\n vec_params_r.reserve(params_r.size());\n for (int i = 0; i < params_r.size(); ++i)\n vec_params_r.push_back(params_r(i));\n std::vector<int> vec_params_i;\n return log_prob<propto,jacobian,T_>(vec_params_r, vec_params_i, pstream);\n }\n\n\n void get_param_names(std::vector<std::string>& names__) const {\n names__.resize(0);\n names__.push_back(\"alpha\");\n names__.push_back(\"beta\");\n names__.push_back(\"sigma\");\n }\n\n\n void get_dims(std::vector<std::vector<size_t> >& dimss__) const {\n dimss__.resize(0);\n std::vector<size_t> dims__;\n dims__.resize(0);\n dimss__.push_back(dims__);\n dims__.resize(0);\n dimss__.push_back(dims__);\n dims__.resize(0);\n dimss__.push_back(dims__);\n }\n\n template <typename RNG>\n void write_array(RNG& base_rng__,\n std::vector<double>& params_r__,\n std::vector<int>& params_i__,\n std::vector<double>& vars__,\n bool include_tparams__ = true,\n bool include_gqs__ = true,\n std::ostream* pstream__ = 0) const {\n typedef double local_scalar_t__;\n\n vars__.resize(0);\n stan::io::reader<local_scalar_t__> in__(params_r__, params_i__);\n static const char* function__ = \"model1d844be0698_stan_model1_namespace::write_array\";\n (void) function__; // dummy to suppress unused var warning\n\n // read-transform, write parameters\n double alpha = in__.scalar_constrain();\n vars__.push_back(alpha);\n\n double beta = in__.scalar_constrain();\n vars__.push_back(beta);\n\n double sigma = in__.scalar_lb_constrain(0);\n vars__.push_back(sigma);\n\n double lp__ = 0.0;\n (void) lp__; // dummy to suppress unused var warning\n stan::math::accumulator<double> lp_accum__;\n\n local_scalar_t__ DUMMY_VAR__(std::numeric_limits<double>::quiet_NaN());\n (void) DUMMY_VAR__; // suppress unused var warning\n\n if (!include_tparams__ && !include_gqs__) return;\n\n try {\n if (!include_gqs__ && !include_tparams__) return;\n if (!include_gqs__) return;\n } catch (const std::exception& e) {\n stan::lang::rethrow_located(e, current_statement_begin__, prog_reader__());\n // Next line prevents compiler griping about no return\n throw std::runtime_error(\"*** IF YOU SEE THIS, PLEASE REPORT A BUG ***\");\n }\n }\n\n template <typename RNG>\n void write_array(RNG& base_rng,\n Eigen::Matrix<double,Eigen::Dynamic,1>& params_r,\n Eigen::Matrix<double,Eigen::Dynamic,1>& vars,\n bool include_tparams = true,\n bool include_gqs = true,\n std::ostream* pstream = 0) const {\n std::vector<double> params_r_vec(params_r.size());\n for (int i = 0; i < params_r.size(); ++i)\n params_r_vec[i] = params_r(i);\n std::vector<double> vars_vec;\n std::vector<int> params_i_vec;\n write_array(base_rng, params_r_vec, params_i_vec, vars_vec, include_tparams, include_gqs, pstream);\n vars.resize(vars_vec.size());\n for (int i = 0; i < vars.size(); ++i)\n vars(i) = vars_vec[i];\n }\n\n static std::string model_name() {\n return \"model1d844be0698_stan_model1\";\n }\n\n\n void constrained_param_names(std::vector<std::string>& param_names__,\n bool include_tparams__ = true,\n bool include_gqs__ = true) const {\n std::stringstream param_name_stream__;\n param_name_stream__.str(std::string());\n param_name_stream__ << \"alpha\";\n param_names__.push_back(param_name_stream__.str());\n param_name_stream__.str(std::string());\n param_name_stream__ << \"beta\";\n param_names__.push_back(param_name_stream__.str());\n param_name_stream__.str(std::string());\n param_name_stream__ << \"sigma\";\n param_names__.push_back(param_name_stream__.str());\n\n if (!include_gqs__ && !include_tparams__) return;\n\n if (include_tparams__) {\n }\n\n if (!include_gqs__) return;\n }\n\n\n void unconstrained_param_names(std::vector<std::string>& param_names__,\n bool include_tparams__ = true,\n bool include_gqs__ = true) const {\n std::stringstream param_name_stream__;\n param_name_stream__.str(std::string());\n param_name_stream__ << \"alpha\";\n param_names__.push_back(param_name_stream__.str());\n param_name_stream__.str(std::string());\n param_name_stream__ << \"beta\";\n param_names__.push_back(param_name_stream__.str());\n param_name_stream__.str(std::string());\n param_name_stream__ << \"sigma\";\n param_names__.push_back(param_name_stream__.str());\n\n if (!include_gqs__ && !include_tparams__) return;\n\n if (include_tparams__) {\n }\n\n if (!include_gqs__) return;\n }\n\n}; // model\n\n} // namespace\n\ntypedef model1d844be0698_stan_model1_namespace::model1d844be0698_stan_model1 stan_model;\n\n"
##
## $model_name
## [1] "stan_model1"
##
## $model_code
## [1] "// Stan model for simple linear regression\n\ndata {\n int < lower = 1 > N; // Sample size\n vector[N] x; // Predictor\n vector[N] y; // Outcome\n}\n\nparameters {\n real alpha; // Intercept\n real beta; // Slope (regression coefficients)\n real < lower = 0 > sigma; // Error SD\n}\n\nmodel {\n y ~ normal(alpha + x * beta , sigma);\n}\n\ngenerated quantities {\n} // The posterior predictive distribution"
## attr(,"model_name2")
## [1] "stan_model1"stan_model1 <- "stan_model1.stan"6. Run the Stan model and inspect the results
#code here
fi <- stan(file = stan_model1, data = stan_data, warmup = 500, iter = 1000, chains = 4, cores = 2, thin = 1)
fi## Inference for Stan model: stan_model1.
## 4 chains, each with iter=1000; warmup=500; thin=1;
## post-warmup draws per chain=500, total post-warmup draws=2000.
##
## mean se_mean sd 2.5% 25% 50% 75% 97.5% n_eff Rhat
## alpha 12.56 0.00 0.08 12.41 12.51 12.56 12.61 12.72 941 1.01
## beta -0.05 0.00 0.00 -0.06 -0.06 -0.05 -0.05 -0.05 922 1.01
## sigma 0.23 0.00 0.03 0.18 0.21 0.22 0.24 0.29 791 1.00
## lp__ 37.32 0.06 1.34 33.73 36.67 37.68 38.29 38.84 591 1.00
##
## Samples were drawn using NUTS(diag_e) at Wed Jan 15 19:10:10 2020.
## For each parameter, n_eff is a crude measure of effective sample size,
## and Rhat is the potential scale reduction factor on split chains (at
## convergence, Rhat=1).7. Extract the posterior estimates into a list so we can plot them
#code here
post <- rstan::extract(fi)
str(post)## List of 4
## $ alpha: num [1:2000(1d)] 12.5 12.7 12.6 12.7 12.5 ...
## ..- attr(*, "dimnames")=List of 1
## .. ..$ iterations: NULL
## $ beta : num [1:2000(1d)] -0.0523 -0.0591 -0.057 -0.0618 -0.0543 ...
## ..- attr(*, "dimnames")=List of 1
## .. ..$ iterations: NULL
## $ sigma: num [1:2000(1d)] 0.227 0.218 0.228 0.233 0.208 ...
## ..- attr(*, "dimnames")=List of 1
## .. ..$ iterations: NULL
## $ lp__ : num [1:2000(1d)] 37.4 37.8 38.4 36.1 38.7 ...
## ..- attr(*, "dimnames")=List of 1
## .. ..$ iterations: NULL8. Compare your results to our results to “lm”
#code here
par(mfrow=c(1,2))
plot(extent_north ~ year, data= seaice_1_, pch = 20)
abline(lm1 , col = 6, lw = 2)
plot(y~x , pch = 20)
abline(mean(post$alpha), mean(post$beta), col = 6, lw = 2)
9. Plot multiple estimates from the posterior
#code here
plot(y ~ x, pch = 20)
for (i in 1:500) {
abline(post$alpha[i], post$beta[i], col = "gray", lty =1)
}
abline(mean(post$alpha), mean(post$beta), col = 6, lw = 2)