Addenda to “Are the log-growth rates of city sizes distributed normally? Empirical evidence for the USA [Empir. Econ. (2017) 53:1109-1123]”

Ramos, Arturo (2019): Addenda to “Are the log-growth rates of city sizes distributed normally? Empirical evidence for the USA [Empir. Econ. (2017) 53:1109-1123]”.

Abstract

We update the recently published paper [A. Ramos, Empir. Econ. (2017) 53:1109-1123] on the basis of another important paper [H. S. Kwong and S. Nadarajah, Physica A (2019) 513:55-62]. Specifically, we introduce the 3-normal (3N) and 3-logistic (3L) distributions and compare them with the best of our distributions in the firstly mentioned paper, namely the "double mixture exponential Generalized Beta of the second kind (dmeGB2)". The main result is that the dmeGB2 remains to be the best model when studying log-growth rates of USA city populations to date. However, if one does not want to achieve such a high precision when describing the data, the 3L emerges to be a very good model for the same purposes.

• Item Type: MPRA Paper
• Language: English
• Keywords: log-growth rates; normal distribution; logistic distribution; GB2 distribution; USA population log-growth rates
• Subjects: C - Mathematical and Quantitative Methods > C4 - Econometric and Statistical Methods: Special Topics > C46 - Specific Distributions ; Specific Statistics; R - Urban, Rural, Regional, Real Estate, and Transportation Economics > R1 - General Regional Economics > R11 - Regional Economic Activity: Growth, Development, Environmental Issues, and Changes; R - Urban, Rural, Regional, Real Estate, and Transportation Economics > R1 - General Regional Economics > R12 - Size and Spatial Distributions of Regional Economic Activity

References

Burnham,K. P. and Anderson,D. R. (2002).Model selection andmultimodel inference: A practical information-theoretic approach. New York: Springer-Verlag.

Burnham, K. P. and Anderson, D. R. (2004). Multimodel inference: Understanding AIC and BIC in model selection. Sociological Methods and Research, 33:261–304.

Duranton, G. (2007). Urban evolutions: The fast, the slow, and the still. American Economic Review, 97(1):197–221.

Efron, B. and Hinkley,D. V. (1978). Assessing the accuracy of themaximumlikelihood estimator: Observed versus expected Fisher information. Biometrika, 65(3):457–482.

Kwong, H. S. and Nadarajah, S. (2019). A note on “Pareto tails and lognormal body of US cities size distribution”. Physica A: Statistical Mechanics and its Applications, 513:55–62.

Luckstead, J. and Devadoss, S. (2017). Pareto tails and lognormal body of US cities size distribution. Physica A: Statistical Mechanics and its Applications, 465:573–578.

Luckstead, J., Devadoss, S., and Danforth, D. (2017). The size distribution of all Indian cities. Physica A: Statistical Mechanics and its Applications, 474:237–249.

McCullough, B. D. and Vinod, H. D. (2003). Verifying the solution from a nonlinear solver: A case study. American Economic Review, 93(3):873–892.

McDonald, J. B. (1984). Generalized functions for the size distribution of income. Econometrica, 52(3):647–665.

McDonald, J. B. and Xu, Y. J. (1995). A generalization of the beta distribution with applications. Journal of Econometrics, 66:133–152.

Ramos, A. (2017). Are the log-growth rates of city sizes distributed normally? Empirical evidence for the USA. Empirical Economics, 53:1109–1123.

Rozenfeld, H. D., Rybski, D., Gabaix, X., and Makse, H. A. (2011). The area and population of cities: new insights from a different perspective on cities. American Economic Review, 101:2205–2225.

S´anchez-Vidal, M., Gonz´alez-Val, R., and Viladecans-Marsal, E. (2014). Sequential city growth in the US: Does age matter? Regional Science and Urban Economics,44:29–37.

Vuong, Q. H. (1989). Likelihood ratio tests for model selection and non-nested hypotheses. Econometrica, 57(2):307–333.