what are three advantages to the rank-size rule?

Rank–size distribution is the distribution of size by rank, in decreasing club of size. For example, if a data fix consists of items of sizes 5, 100, five, and viii, the rank–size distribution is 100, 8, 5, 5 (ranks 1 through 4). This is as well known as the rank–frequency distribution, when the source data are from a frequency distribution. These are particularly of involvement when the data vary significantly in scale, such as urban center size or give-and-take frequency. These distributions ofttimes follow a power law distribution, or less well-known ones such as a stretched exponential function or parabolic fractal distribution, at to the lowest degree approximately for sure ranges of ranks; see below.

A rank–size distribution is non a probability distribution or cumulative distribution part. Rather, information technology is a discrete form of a quantile office (changed cumulative distribution) in opposite order, giving the size of the chemical element at a given rank.

Unproblematic rank–size distributions [edit]

In the case of city populations, the resulting distribution in a country, a region, or the world will be characterized past its largest metropolis, with other cities decreasing in size corresponding to information technology, initially at a rapid rate and then more slowly. This results in a few large cities and a much larger number of cities orders of magnitude smaller. For example, a rank 3 city would accept one-3rd the population of a land's largest urban center, a rank 4 city would accept ane-fourth the population of the largest city, and and so on.^[2]

When whatsoever log-linear factor is ranked, the ranks follow the Lucas numbers, which consist of the sequentially additive numbers 1, three, 4, 7, 11, eighteen, 29, 47, 76, 123, 199, etc. Similar the more than famous Fibonacci sequence, each number is approximately 1.618 (the Golden ratio) times the preceding number. For example, the 3rd term in the sequence in a higher place, 4, is approximately ane.618³, or iv.236; the fourth term, 7, is approximately 1.618⁴, or half dozen.854; the eighth term, 47, is approximately i.618^viii, or 46.979. With higher values, the figures converge. An equiangular spiral is sometimes used to visualize such sequences.

Segmentation [edit]

Wikipedia word frequency plot, showing three segments with distinct beliefs.

A rank–size (or rank–frequency) distribution is often segmented into ranges. This is frequently done somewhat arbitrarily or due to external factors, particularly for market segmentation, only can likewise be due to distinct beliefs as rank varies.

Most but and unremarkably, a distribution may be split in ii pieces, termed the head and tail. If a distribution is broken into three pieces, the third (centre) piece has several terms, generically middle,^[iii] also belly,^[4] trunk,^[5] and body.^[6] These frequently accept some adjectives added, most significantly long tail, also fat belly,^[4] mesomorphic middle, etc. In more traditional terms, these may be chosen acme-tier, mid-tier, and bottom-tier.

The relative sizes and weights of these segments (how many ranks in each segment, and what proportion of the total population is in a given segment) qualitatively characterizes a distribution, analogously to the skewness or kurtosis of a probability distribution. Namely: is information technology dominated by a few top members (head-heavy, like profits in the recorded music industry), or is it dominated by many small members (tail-heavy, like internet search queries), or distributed in some other way? Practically, this determines strategy: where should attention exist focused?

These distinctions may exist made for various reasons. For example, they may arise from differing properties of the population, as in the 90–9–i principle, which posits that in an internet community, 90% of the participants of a community only view content, 9% of the participants edit content, and i% of the participants actively create new content. As some other case, in marketing, ane may pragmatically consider the head as all members that receive personalized attending, such as personal phone calls; while the tail is everything else, which does non receive personalized attention, for example receiving form letters; and the line is simply set at a indicate that resources allow, or where it makes business sense to stop.

Purely quantitatively, a conventional way of splitting a distribution into head and tail is to consider the head to be the showtime p portion of ranks, which business relationship for ${\displaystyle 1-p}$ of the overall population, as in the 80:xx Pareto principle, where the top xx% (head) comprises 80% of the overall population. The verbal cutoff depends on the distribution – each distribution has a single such cutoff point—and for power laws can be computed from the Pareto index.

Segments may arise naturally due to bodily changes in beliefs of the distribution every bit rank varies. Nigh common is the king effect, where behavior of the height scattering of items does not fit the pattern of the remainder, as illustrated at top for country populations, and higher up for most mutual words in English Wikipedia. For college ranks, behavior may alter at some betoken, and be well-modeled past different relations in unlike regions; on the whole by a piecewise role. For example, if two different power laws fit improve in different regions, one can use a broken power police force for the overall relation; the word frequency in English Wikipedia (in a higher place) also demonstrates this.

The Yule–Simon distribution that results from preferential attachment (intuitively, "the rich get richer" and "success breeds success") simulates a broken power police force and has been shown to "very well capture" word frequency versus rank distributions.^[7] It originated from trying to explicate the population versus rank in dissimilar species. It has also been shown to fit city population versus rank better.^[8]

Rank–size dominion [edit]

The rank–size rule (or police force) describes the remarkable regularity in many phenomena, including the distribution of city sizes, the sizes of businesses, the sizes of particles (such as sand), the lengths of rivers, the frequencies of word usage, and wealth among individuals.

All are real-world observations that follow power laws, such as Zipf's law, the Yule distribution, or the Pareto distribution. If one ranks the population size of cities in a given country or in the entire world and calculates the natural logarithm of the rank and of the metropolis population, the resulting graph volition testify a log-linear design. This is the rank–size distribution.^[9]

Theoretical rationale [edit]

One written report claims that the rank–size rule "works" because it is a "shadow" or casual mensurate of the true phenomenon.^[10] The truthful value of rank–size is thus not equally an accurate mathematical measure (since other power-law formulas are more than accurate, especially at ranks lower than 10) merely rather as a handy mensurate or "rule of pollex" to spot power laws. When presented with a ranking of data, is the tertiary-ranked variable approximately one-third the value of the highest-ranked one? Or, conversely, is the highest-ranked variable approximately ten times the value of the tenth-ranked one? If so, the rank–size rule has possibly helped spot another ability law human relationship.

Known exceptions to simple rank–size distributions [edit]

While Zipf's law works well in many cases, it tends to not fit the largest cities in many countries; 1 type of deviation is known as the King outcome. A 2002 study found that Zipf's law was rejected for 53 of 73 countries, far more than than would be expected based on random chance.^[eleven] The study also plant that variations of the Pareto exponent are better explained by political variables than by economical geography variables like proxies for economies of scale or transportation costs.^[12] A 2004 study showed that Zipf'southward law did non work well for the five largest cities in half-dozen countries.^[xiii] In the richer countries, the distribution was flatter than predicted. For example, in the United States, although its largest city, New York Urban center, has more than than twice the population of second-place Los Angeles, the 2 cities' metropolitan areas (too the 2 largest in the country) are much closer in population. In metropolitan-area population, New York City is only 1.3 times larger than Los Angeles. In other countries, the largest city would boss much more than expected. For example, in the Democratic Democracy of the Congo, the uppercase, Kinshasa, is more than eight times larger than the second-largest city, Lubumbashi. When considering the entire distribution of cities, including the smallest ones, the rank–size rule does not hold. Instead, the distribution is log-normal. This follows from Gibrat'due south law of proportionate growth.

Considering exceptions are so piece of cake to discover, the function of the rule for analyzing cities today is to compare the city-systems in different countries. The rank–size rule is a common standard by which urban primacy is established. A distribution such as that in the U.s. or Red china does not showroom a pattern of primacy, simply countries with a dominant "primate city" clearly vary from the rank–size rule in the opposite manner. Therefore, the rule helps to classify national (or regional) metropolis-systems according to the degree of dominance exhibited by the largest city. Countries with a primate city, for example, have typically had a colonial history that accounts for that city pattern. If a normal metropolis distribution pattern is expected to follow the rank–size rule (i.e. if the rank–size principle correlates with central place theory), then it suggests that those countries or regions with distributions that exercise not follow the rule take experienced some weather that accept altered the normal distribution design. For case, the presence of multiple regions inside large nations such equally Prc and the The states tends to favor a pattern in which more large cities appear than would be predicted by the rule. By contrast, small countries that had been continued (e.one thousand. colonially/economically) to much larger areas will exhibit a distribution in which the largest city is much larger than would fit the rule, compared with the other cities—the excessive size of the metropolis theoretically stems from its connection with a larger system rather than the natural hierarchy that central place theory would predict within that ane state or region lonely.

See also [edit]

• Pareto principle
• Long tail

References [edit]

1. ^ "Stretched exponential distributions in nature and economic system: "fat tails" with characteristic scales", J. Laherrère and D. Sornette
2. ^ "The 200 Largest Cities in the United States by Population 2021". worldpopulationreview.com . Retrieved 2021-03-28 .
3. ^ Illustrating the Long Tail, Rand Fishkin, November 24th, 2009
4. ^ ^{a b} Digg that Fat Belly!, Robert Immature, Sep. iv, 2006
5. ^ The Long Tail Keyword Optimization Guide - How to Profit from Long Tail Keywords, August 3, 2009, Tom Demers
6. ^ The Small Head, the Medium Body, and the Long Tail .. so, where's Microsoft? Archived 2015-xi-17 at the Wayback Motorcar, 12 Mar 2005, Lawrence Liu's Study from the Inside
7. ^ Lin, Ruokuang; Ma, Qianli D. Y.; Bian, Chunhua (2014). "Scaling laws in human speech, decreasing emergence of new words and a generalized model". arXiv:1412.4846. Bibcode:2014arXiv1412.4846L.
8. ^ Dacey, M F (1 April 1979). "A Growth Procedure for Zipf'southward and Yule's City-Size Laws". Environment and Planning A. xi (4): 361–372. doi:ten.1068/a110361. S2CID 122325866.
9. ^ Zipf'due south Police force, or the Rank–Size Distribution Archived 2007-02-13 at the Wayback Auto Steven Brakman, Harry Garretsen, and Charles van Marrewijk
10. ^ The Urban Rank–Size Hierarchy James W. Fonseca
11. ^ "Kwok Tong Soo (2002)" (PDF).
12. ^ Zipf's Law, or the Rank–Size Distribution Archived 2007-03-02 at the Wayback Automobile
13. ^ Cuberes, David, The Rising and Refuse of Cities, University of Chicago, September 29, 2004

Further reading [edit]

• Brakman, S.; Garretsen, H.; Van Marrewijk, C.; Van Den Berg, Thou. (1999). "The Return of Zipf: Towards a Further Agreement of the Rank–Size Distribution". Journal of Regional Science. 39 (i): 183–213. doi:10.1111/1467-9787.00129. S2CID 56011475.
• Guérin-Step, F. (1995). "Rank–Size Distribution and the Process of Urban Growth". Urban Studies. 32 (3): 551–562. doi:10.1080/00420989550012960. S2CID 154660734.
• Reed, W.J. (2001). "The Pareto, Zipf and other power laws". Economic science Letters. 74 (1): 15–19. doi:10.1016/S0165-1765(01)00524-9.
• Douglas R. White, Laurent Tambayong, and Nataša Kejžar. 2008. Oscillatory dynamics of city-size distributions in earth historical systems. Globalization as an Evolutionary Process: Modeling Global Alter. Ed. by George Modelski, Tessaleno Devezas, and William R. Thompson. London: Routledge. ISBN 978-0-415-77361-4
• The Use of Amanuensis-Based Models in Regional Science—an agent-based simulation report that explains rank–size distribution.

External links [edit]

• Media related to Rank-size distribution at Wikimedia Eatables

saxagiation.blogspot.com

Source: https://en.wikipedia.org/wiki/Rank%E2%80%93size_distribution

Share this post