pyblp.BootstrappedResults

class pyblp.BootstrappedResults

Bootstrapped results of a solved problem.

This class has slightly modified versions of the following ProblemResults methods:

• ProblemResults.compute_aggregate_elasticities()

• ProblemResults.compute_elasticities()

• ProblemResults.compute_demand_jacobians()

• ProblemResults.compute_demand_hessians()

• ProblemResults.compute_profit_hessians()

• ProblemResults.compute_diversion_ratios()

• ProblemResults.compute_long_run_diversion_ratios()

• ProblemResults.compute_probabilities()

• ProblemResults.extract_diagonals()

• ProblemResults.extract_diagonal_means()

• ProblemResults.compute_delta()

• ProblemResults.compute_costs()

• ProblemResults.compute_passthrough()

• ProblemResults.compute_approximate_prices()

• ProblemResults.compute_prices()

• ProblemResults.compute_shares()

• ProblemResults.compute_hhi()

• ProblemResults.compute_markups()

• ProblemResults.compute_profits()

• ProblemResults.compute_consumer_surpluses()

The difference is that each method returns an array with an extra first dimension along which bootstrapped results are stacked These stacked results can be used to construct, for example, confidence intervals for post-estimation outputs. Similarly, arrays of data (except for firm IDs and ownership matrices) passed as arguments to methods should have an extra first dimension of size BootstrappedResults.draws.

problem_results

ProblemResults that was used to compute these bootstrapped results.

Type

ProblemResults

bootstrapped_sigma

Bootstrapped Cholesky decomposition of the covariance matrix for unobserved taste heterogeneity, \(\Sigma\).

Type

ndarray

bootstrapped_pi

Bootstrapped parameters that measures how agent tastes vary with demographics, \(\Pi\).

Type

ndarray

bootstrapped_rho

Bootstrapped parameters that measure within nesting group correlations, \(\rho\).

Type

ndarray

bootstrapped_beta

Bootstrapped demand-side linear parameters, \(\beta\).

Type

ndarray

bootstrapped_gamma

Bootstrapped supply-side linear parameters, \(\gamma\).

Type

ndarray

bootstrapped_prices

Bootstrapped prices, \(p\). If a supply side was not estimated, these are unchanged prices. Otherwise, they are equilibrium prices implied by each draw.

Type

ndarray

bootstrapped_shares

Bootstrapped market shares, \(s\), implied by each draw.

Type

ndarray

bootstrapped_delta

Bootstrapped mean utility, \(\delta\), implied by each draw.

Type

ndarray

computation_time

Number of seconds it took to compute the bootstrapped results.

Type

float

draws

Number of bootstrap draws.

Type

int

fp_converged

Flags for convergence of the iteration routine used to compute equilibrium prices in each market. Rows are in the same order as Problem.unique_market_ids and column indices correspond to draws.

Type

ndarray

fp_iterations

Number of major iterations completed by the iteration routine used to compute equilibrium prices in each market for each draw. Rows are in the same order as Problem.unique_market_ids and column indices correspond to draws.

Type

ndarray

contraction_evaluations

Number of times the contraction used to compute equilibrium prices was evaluated in each market for each draw. Rows are in the same order as Problem.unique_market_ids and column indices correspond to draws.

Type

ndarray

Examples

• Tutorial