Genetic Algorithms for Estimation Problems With Multiple Optima, Nondifferentiability, and Other Irregular Features

Dorsey, Robert E.; Mayer, Walter J.

doi:10.1080/07350015.1995.10524579

Cited by 121 publications

(29 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead, they are calibrated jointly to fit a set of data moments of equal size. This fit is very nonlinear in the parameters; so a genetic algorithm following Dorsey and Mayer (1995) is used to find the best fit. It turns out to be useful to calibrate c e and c f as the ratio c e /c f and the level c f .…”

Section: Calibrationmentioning

confidence: 99%

The Regulation of Entry and Aggregate Productivity

Poschke

2010

The Economic Journal

View full text Add to dashboard Cite

Euro area economies have lower total factor and labour productivity than the US. I argue that differences in entry cost contribute to this by affecting firmsÕ technology choice. Introducing technology choice into a standard heterogeneous-firm model, small differences in administrative entry cost can explain around one third of TFP differences. The productivity difference arises because entry costs reduce competition and the incentive to adopt more advanced technologies. Firm heterogeneity, technology choice and the competition channel all contribute to strengthening results compared to previous studies. The effects of entry costs are even larger when the labour market is not competitive.

show abstract

Section: Calibrationmentioning

confidence: 99%

The Regulation of Entry and Aggregate Productivity

Poschke

2010

The Economic Journal

View full text Add to dashboard Cite

show abstract

“…[11] Equation (5) describes the surface SP anomaly induced by a pumping test at rate Q in an unconfined homogeneous aquifer of hydraulic conductivity K, electrokinetic coupling parameter L and bedrock depth Z. Therefore, knowing the hydraulic head h 0 in the vicinity of the well (at r 0 ) and the surface SP anomaly during a pumping test of flow rate Q, we should be able to determine Z, K, and L. We used a genetic algorithm [Dorsey and Mayer, 1995] to find the best {Z, K, L} that minimizes a weighted quadratic error function f between the predicted and observed SP data.…”

Section: Inversion Of Sp Datamentioning

confidence: 99%

Estimating aquifer hydraulic properties from the inversion of surface Streaming Potential (SP) anomalies

Darnet

Marquis

Sailhac

2003

Geophysical Research Letters

View full text Add to dashboard Cite

[1] Electrokinetic effects of water flow during pumping tests have been shown to generate surface Streaming Potential (SP) anomalies of several tens of mV that are well correlated with the geometry of the water table. It follows that SP measurements can be used to estimate aquifer hydraulic properties. We have developed an inversion scheme for surface SP data generated by flow pumping and found that we are able to estimate the hydraulic conductivity and the depth and the thickness of the aquifer. We applied our inversion scheme to the data from Bogoslovsky and Ogilvy [1973] and found a hydraulic conductivity of 10 À5 m.s À1, an aquifer thickness of roughly 28 m and an electrokinetic coupling coefficient of À1 mV.m

show abstract

“…As a first step, the MGA procedure was used to train the NN on each of the 30 datasets. The training began after setting the parameters to values recommended by Dorsey and Mayer (1995) and , and after including the additional modifications. After training, the network's performance (as a function of error rates) was compared to a benchmark NN-the categorical learning network, or CATLRN, identified in earlier studies as a reliable performer (see Etheridge and Sriram, 1997).…”

Section: Data Experiment and The Resultsmentioning

confidence: 99%

“…The GA is a global search method that searches from one population of solutions to another while comparing the newly generated solution to the best solution obtained from the earlier search. It works well when finding solutions to functions with complex nonlinear relationships (Dorsey, Johnson, & Mayer, 1994;Dorsey, Johnson, & Van Boening, 1994;Dorsey & Mayer, 1995;Sexton, Alidaee, Dorsey, & Johnson, 1998;Sexton & Dorsey, 2000). A researcher can use the GA to improve the performance of a backpropagation NN or even as an alternative to backpropagation (Schaffer, Whitley, & Eshelman, 1992).…”

Section: The Modified Genetic Algorithm (Mga)mentioning

confidence: 99%

Improving Decision Effectiveness of Artificial Neural Networks: A Modified Genetic Algorithm Approach

Sexton¹,

Sriram²,

Etheridge³

2003

Decision Sciences

View full text Add to dashboard Cite

This study proposes the use of a modified genetic algorithm (MGA), a global search technique, as a training method to improve generalizability and to identify relevant inputs in a neural network (NN) model. Generalizability refers to the NN model's ability to perform well on exemplars (observations) that were not used during training (outof-sample); improved generalizability enhances NN's acceptability as a valid decisionsupport tool. The MGA improves generalizability by setting unnecessary weights (or connections) to zero and by eliminating these weights. Because the eliminated weights have no further impact on the training (in-sample or out-of-sample data), the relevant variables can be identified from the model. By eliminating unnecessary weights, the MGA is able to search and find a parsimonious model that generalizes well. Unlike the traditional NN, the MGA identifies the model variables that contribute to an outcome, helping decision makers to rationalize output and accept results with greater confidence. The study uses real-life data to demonstrate the use of MGA.

show abstract

Genetic Algorithms for Estimation Problems With Multiple Optima, Nondifferentiability, and Other Irregular Features

Cited by 121 publications

References 20 publications

The Regulation of Entry and Aggregate Productivity

The Regulation of Entry and Aggregate Productivity

Estimating aquifer hydraulic properties from the inversion of surface Streaming Potential (SP) anomalies

Improving Decision Effectiveness of Artificial Neural Networks: A Modified Genetic Algorithm Approach

Contact Info

Product

Resources

About