BayCANN: Streamlining Bayesian Calibration With Artificial Neural Network Metamodeling

Purpose: Bayesian calibration is generally superior to standard direct-search algorithms in that it estimates the full joint posterior distribution of the calibrated parameters. However, there are many barriers to using Bayesian calibration in health decision sciences stemming from the need to program complex models in probabilistic programming languages and the associated computational burden of applying Bayesian calibration. In this paper, we propose to use artificial neural networks (ANN) as one practical solution to these challenges.Methods: Bayesian Calibration using Artificial Neural Networks (BayCANN) involves (1) training an ANN metamodel on a sample of model inputs and outputs, and (2) then calibrating the trained ANN metamodel instead of the full model in a probabilistic programming language to obtain the posterior joint distribution of the calibrated parameters. We illustrate BayCANN using a colorectal cancer natural history model. We conduct a confirmatory simulation analysis by first obtaining parameter estimates from the literature and then using them to generate adenoma prevalence and cancer incidence targets. We compare the performance of BayCANN in recovering these “true” parameter values against performing a Bayesian calibration directly on the simulation model using an incremental mixture importance sampling (IMIS) algorithm.Results: We were able to apply BayCANN using only a dataset of the model inputs and outputs and minor modification of BayCANN's code. In this example, BayCANN was slightly more accurate in recovering the true posterior parameter estimates compared to IMIS. Obtaining the dataset of samples, and running BayCANN took 15 min compared to the IMIS which took 80 min. In applications involving computationally more expensive simulations (e.g., microsimulations), BayCANN may offer higher relative speed gains.Conclusions: BayCANN only uses a dataset of model inputs and outputs to obtain the calibrated joint parameter distributions. Thus, it can be adapted to models of various levels of complexity with minor or no change to its structure. In addition, BayCANN's efficiency can be especially useful in computationally expensive models. To facilitate BayCANN's wider adoption, we provide BayCANN's open-source implementation in R and Stan.

Download Full-text

The Use of Quantitative Methods in Investment Decisions

Handbook of Research on Global Issues in Financial Communication and Investment Decision Making - Advances in Finance, Accounting, and Economics ◽

10.4018/978-1-5225-9265-5.ch013 ◽

2019 ◽

pp. 256-275 ◽

Cited By ~ 5

Author(s):

Serkan Eti

Keyword(s):

Neural Networks ◽

Monte Carlo Simulation ◽

Monte Carlo ◽

Artificial Neural Networks ◽

Decision Tree ◽

Quantitative Methods ◽

Simulation Analysis ◽

Investment Decision ◽

Tree Algorithms ◽

Artificial Neural

Quantitative methods are mainly preferred in the literature. The main purpose of this chapter is to evaluate the usage of quantitative methods in the subject of the investment decision. Within this framework, the studies related to the investment decision in which quantitative methods are taken into consideration. As for the quantitative methods, probit, logit, decision tree algorithms, artificial neural networks methods, Monte Carlo simulation, and MARS approaches are taken into consideration. The findings show that MARS methodology provides a more accurate results in comparison with other techniques. In addition to this situation, it is also concluded that probit and logit methodologies were less preferred in comparison with decision tree algorithms, artificial neural networks methods, and Monte Carlo simulation analysis, especially in the last studies. Therefore, it is recommended that a new evaluation for investment analysis can be performed with MARS method because it is understood that this approach provides better results.

Download Full-text