Probability density function and estimation for error of digitized map coordinates in GIS

Abstract

Traditionally, it is widely accepted that measurement error usually obeys the normal distribution. However, in this paper a new idea is proposed that the error in digitized data which is a major derived data source in GIS does not obey the normal distribution but the p-norm distribution with a determinate parameter. Assuming that the error is random and has the same statistical properties, the probability density function of the normal distribution, Laplace distribution and p-norm distribution are derived based on the arithmetic mean axiom, median axiom and p-median axiom, which means that the normal distribution is only one of these distributions but not the least one. Based on this idea, distribution fitness tests such as Skewness and Kurtosis coefficient test, Pearson chi-square x₂ test and Kolmogorov test for digitized data are conducted. The results show that the error in map digitization obeys the p-norm distribution whose parameter is close to 1.60. A least p-norm estimation and the least square estimation of digitized data are further analyzed, showing that the least p-norm adjustment is better than the least square adjustment for digitized data processing in GIS.

Keywords

probability density function / distribution fitness test / least p-norm estimation

References

[1] NCGIA. The research plan of the national center for geographic information and analysis [J]. International Journal of Geographical Informational System, 1989, 3(1): 117-136

[2] UCGIS. Research priorities for geographic information science [J]. Cartography and GIS, 1996, 23(3): 115-127

[3] ThapaK, BosslerJ. Accuracy of spatial data used in geographic information systems [J]. Photogrammetric Engineering and Remote Sensing, 1992, 58: 835-841

[4] BurroughP APrinciples of Geographic Information Systems for Land Resource Assessment [M], 1986, Oxford, Clarendon Press

[5] TongXiao-hua, ZhouDe-yi. Accuracy analysis of scanned topographic map image correction [J]. Journal of Tongji University, 2003, 31(1): 75-81(in Chinese)

[6] KeeferB J, SmithJ L, GregoireT GSimulating manual digitizing error with statistical models [A]. The American Congress on Surveying and Mapping: GIS/LIS’88 Proceedings Accessing the World[C], 1988, Texas, San Antonio: 475-483

[7] BolstadP V, GesslerP, LillesandT M. Positional uncertainty in manually digitized map data [J]. International Journal of Geographical Informational System, 1990, 4: 399-412

[8] CasparyW, ScheuringR. Positional accuracy in spatial databases [J]. Computer, Environment and Urban System, 1993, 17: 103-110

[9] ShiW ZModeling Positional and Thematic Uncertainties in Integration of Remote Sensing and Geographic Information Systems [D], 1994, Netherlands, ITC Publication

[10] MengXiao-lin, LiuDa-jie, ZhuZhao-hong. The NL distribution test for digitization data error [J]. Journal of Tongji University, 1996, 24(5): 525-529(in Chinese)

[11] FangKai-tai, XuJian-lunStatistical Analysis [M], 1987, Beijing, Science Press(in Chinese)

[12] MikhailE M, AckermannFObservations and Least Squares [M], 1976, New York, IEP-A Dun-Donnelley Publisher

[13] TongXiao-hua, LiuDa-jie, YangDong-yuan. The adjustment models of digitized data in GIS [J]. Journal of Tongji University, 1998, 26(6): 682-685(in Chinese)