Estimation of gravity models by OLS estimation, NLS estimation, Poisson and neural network specifications

• When assessing infrastructure investment, it is crucial to forecast the flows on the links after the suggested improvements. In freight flow analysis, the impact on the flows in the network is conditional on the size of the investment and the complexity of the network. If the investment has a critical impact on the flows, the change may be substantial and hard to predict by linear models. In economic geography and regional economics, the gravity model has gained wide acceptance as a reasonable (although simple) model of spatial interaction between nodes in a network (Haynes and Fotheringham, 1984 or Sen and Smith, 1995).

Subject headings

SAMHÄLLSVETENSKAP  -- Ekonomi och näringsliv -- Nationalekonomi (hsv//swe)

SOCIAL SCIENCES  -- Economics and Business -- Economics (hsv//eng)

SAMHÄLLSVETENSKAP  -- Annan samhällsvetenskap -- Tvärvetenskapliga studier inom samhällsvetenskap (hsv//swe)

SOCIAL SCIENCES  -- Other Social Sciences -- Social Sciences Interdisciplinary (hsv//eng)

NATURVETENSKAP  -- Matematik -- Sannolikhetsteori och statistik (hsv//swe)

NATURAL SCIENCES  -- Mathematics -- Probability Theory and Statistics (hsv//eng)

Keyword

Gravity model

Neural network

Poisson distribution

OLS

NLS

Infrastructure

nationalekonomi

Economics

ekonometri

Econometrics

Social and Economic Geography

kulturgeografi

Publication and Content Type

ref (subject category)

kap (subject category)