Logo
Munich Personal RePEc Archive

A Markov Model of the Learning Curve

Larsen, Harry (2026): A Markov Model of the Learning Curve. Published in: Journal of Cost Analysis & Parametrics , Vol. 13, No. 1 (18 March 2026): pp. 104-113.

[thumbnail of MPRA_paper_128435.pdf]
Preview
PDF
MPRA_paper_128435.pdf

Download (900kB) | Preview

Abstract

A learning curve is the labor hours per unit of production in the production sequence. Before its cost realization, it is typically forecast using the power function, hours(unit) = a unitb, with a and b derived from historical data via regressions. After the first unit’s cost is realized, future costs can be projected from the sequence of actualized units. This paper transforms the power function into a Markov model and applies a Kalman Filter to estimate the expected value, slope, and variance of a learning curve projection. To exemplify the solution, the parameters of the Kalman Filter are estimated from a set of twenty 1000-unit learning curves derived from The Theory of Complex Work. For those responsible for predicting future values of an ongoing production program, this procedure provides optimal estimates of unit labor hours and their variances.

Atom RSS 1.0 RSS 2.0

Contact us: mpra@ub.uni-muenchen.de

This repository has been built using EPrints software.

MPRA is a RePEc service hosted by Logo of the University Library LMU Munich.