Circular data
Corresponding Author
Alan Lee
Department of Statistics, University of Auckland, Auckland, New Zealand
Department of Statistics, University of Auckland, Auckland, New Zealand.Search for more papers by this authorCorresponding Author
Alan Lee
Department of Statistics, University of Auckland, Auckland, New Zealand
Department of Statistics, University of Auckland, Auckland, New Zealand.Search for more papers by this authorAbstract
The special nature of circular data means that conventional methods suitable for the analysis of linear data do not apply. In this article, we survey a range of methods that have been developed over the last 50 years to handle the special characteristics of data consisting of angular measurements. We discuss summary statistics and graphical methods, methods for the analysis of single and multiple samples of circular data, circular correlation, regression methods, and time series. We discuss the standard probability models on which these analyses are based, and give several examples of the application of these methods. A reasonably comprehensive bibliography is provided. © 2010 John Wiley & Sons, Inc.
This article is categorized under:
- Data: Types and Structure > Traditional Statistical Data
REFERENCES
- 1Fisher NI. Statistical Analysis of Circular Data. Cambridge: Cambridge University Press; 1993.
- 2Pewsey A. The large-sample joint distribution of key circular statistics. Metrika 2004; 60: 25–32.
- 3Mardia KV, Jupp PE. Directional Statistics. New York: John Wiley & Sons; 2000.
- 4Jammalamadaka SR, SenGupta A. Topics in Circular Statistics. Singapore: World Scientific; 2001.
- 5Hall P, Watson GS, Cabrera J. Kernel density estimation with spherical data. Biometrika 1987; 74: 751–762.
- 6Fisher NI. Smoothing a sample of circular data. J Struct Geol 1989; 11: 775–778.
- 7Klemela J. Estimation of densities and derivatives of densities with directional data. J Multivariate Anal 2000; 73: 18–40.
- 8Taylor CC. Automatic bandwidth selection for circular density estimation. Comput Stat Data Anal 2008; 52: 3493–3500.
- 9Fraser YS, Hsu MD, Walker JJ. Identifiability of finite mixtures of von Mises distributions. Ann Econ Stat 1981; 9: 1130–1131.
- 10Bartels R. Estimation in a bidirectional mixture of von Mises distributions. Biometrics 1994; 40: 777–784.
- 11Kim PT, Koo JY. Directional mixture models and optimal estimation of the mixing density. Can J Stat 2000; 28: 383–398.
- 12Grimshaw SD, Whiting DG, Morris TM. Likelihood ratio tests for a mixture of two von Mises distributions. Biometrics 2001; 57: 260–265.
- 13Holzmann A, Munk H, Startman B. Identifiability of finite mixtures - with applications to circular distributions. Sankhya 2004; 66: 440–450.
- 14Fu Y, Chen J, Li P. Modified likelihood ratio test for homogeneity in a mixture of von Mises distributions. J Stat Plan Inference 2008; 138: 667–681.
- 15Chen J, Li P, Fu Y. Testing homogeneity in a mixture of von Mises distributions with a structural parameter. Can J Stat 2008; 36: 129–142.
- 16McCullaugh P. Mobius transformations and Cauchy parameter estimation. Ann Econ Stat 1996; 24: 787–808.
10.1214/aos/1032894465 Google Scholar
- 17Pewsey A, Lewis T, Jones MC. The wrapped t family of circular distributions. Aust N Z J Stat 2007; 49: 79–91.
- 18Pewsey A. The wrapped skew-normal distribution on the circle. Commun Stat Theory Methods 2000; 29: 2459–2472.
- 19Pewsey A. Modelling asymmetrically distributed circular data using the wrapped skew-normal distribution. Environ Ecol Stat 2006; 13: 257–269.
- 20Pewsey A. The wrapped stable family of distributions as a flexible model for circular data. Comput Stat Data Anal 2008; 52: 1516–1523.
- 21Jones MC, Pewsey A. A family of symmetric distributions on the circle. J Am Stat Assoc 2005; 100: 1422–1428.
- 22Wehrly TE, Johnson RA. Bivariate models for independence of angular observations and a related Markov process. Biometrika 1980; 67: 255–256.
- 23Saw JG. Dependent unit vectors. Biometrika 1983; 70: 665–671.
- 24Johnson RA, Wehrly TE. Measures and models for angular correlation and angular-linear correlation. J R Stat Soc., Ser A 1977; 39: 222–229.
- 25Rivest L-P. A distribution for dependent unit vectors. Commun Stat Theory Methods 1988; 17: 661–483.
- 26Singh H, Hnizdo V, Demchuk E. Probabilistic model for two dependent circular variables. Biometrika 2002; 89: 719–723.
- 27Kuiper NH. Tests concerning random points on the circle. Proc K Ned Akad Wet C 1960; 63: 38–47.
- 28Watson GS. Goodness-of-fit tests on the circle. Biometrika 1961; 48: 109–114.
- 29Ajne B. A simple test for uniformity of a circular distribution. Biometrika 1968; 55: 343–354.
- 30Sethuraman J, Rao JS. Pitman efficiencies of tests based on spacings. Nonparametric Techniques in Statistical Inference. Cambridge: Cambridge University Press; 1970; 405–415.
- 31Rao JS. Some tests based on arc lengths for the circle. Sankhya 1976; 38: 329–338.
- 32Bogdan K, Bogdan M, Futschik S. A data driven smooth test for circular uniformity. Ann Inst Stat Math 2002; 54: 29–43.
- 33Fisher NI, Lewis T. Estimating the mean direction of several circular or spherical distributions with differing dispersions. Biometrika 1983; 70: 333–341.
- 34Fisher NI, Hall P. Bootstrap confidence regions for directional data. J Am Stat Assoc, 1989, 84 996–1002 (correction 1990), 85: 608.
- 35Fisher NI, Hall P, Jing B-Y, Wood ATA. Improved pivotal methods for constructing confidence intervals with directional data. J Am Stat Assoc 1996; 91: 1062–1070.
10.2307/2291725 Google Scholar
- 36Upton GTG. Approximate confidence intervals for the mean direction of the von Mises distribution. Biometrika 1986; 73: 525–527.
- 37Lund U, Jammalamadaka SR. An entropy-based test for goodness of fit of the von Mises distribution. J Stat Comput Simul 2000; 67: 319–332.
- 38Watson GS, Williams E. On the construction of significance tests on the circle and the sphere. Biometrika 1956; 43: 344–352.
- 39Stephens MA. Tests for the von Mises distribution. Biometrika 1969; 56: 149–160.
- 40Watson GS. Large sample theory of the Langevin distribution. J Stat Plan Inference 1983; 8: 245–256.
- 41Anderson CFJ, Wu CM. Measuring location effects from factorial experiments with a directional response. Int Stat Rev 1995; 63: 345–363.
- 42Amaral GJA, Dryden IL, Wood ATA. Pivotal bootstrap methods for k-sample problems in directional statistics and shape analysis. J Am Stat Assoc 2007; 102: 695–707.
- 43Underwood AJ, Chapman MG. Multifactorial analyses of directions of movement of animals. J Exp Mar Biol Ecol 1985; 91: 17–43.
- 44Underwood AJ, Chapman MG. Experimental analyses of the influences of topography and of the substratum on the movements and density of an intertidal snail, Littorina unifasciata. J Exp Mar Biol Ecol 1989; 134: 175–196.
- 45Mardia KV. Linear-circular correlation coefficients and rythmometry. Biometrika 1976; 63: 403–405.
- 46Fisher NI, Lee AJ. Nonparametric measures of angular-linear association. Biometrika 1981; 68: 629–636.
- 47Fisher NI, Lee AJ. Regression models for an angular response. Biometrics 1992; 48: 665–677.
- 48Fisher NI, Lee AJ. Nonparametric measures of angular-angular association. Biometrika 1982; 69: 315–321.
- 49Jupp PE. A nonparametric correlation coefficient and a two-sample test for random vectors or directions. Biometrika 1987; 74: 887–890.
- 50Fisher NI, Lee AJ. A correlation coefficient for circular data. Biometrika 1983; 70: 327–332.
- 51Mardia KV, Jupp PE. A general correlation coefficient for directional data and related regression problems. Biometrika 1980; 67: 163–173.
- 52Rothman ED. Tests of coordinate independence for a bivariate sample on a torus. Ann Math Stat 1971; 42: 1962–1969.
- 53Rao JS, Puri ML. Problems of association for bivariate circular data and a new test of independence. In: PR Krishnaiah, ed. Multivariate Analysis, vol. 4. Amsterdam: North Holland; 1977; 515–223.
- 54Shieh GS, Johnson RA, Frees EW. Testing independence of bivariate circular data and weighted degenerate u-statistics. Stat Sin 1994; 4: 729–747.
- 55Presnell B, Morrison SP, Littell RC. Projected multivariate linear models for directional data. J Am Stat Assoc 1998; 93: 1068–1077.
- 56Mardia KV, Downs TD. Circular regression. Biometrika 2002; 89: 683–697.
- 57Kato K, Shimizu S, Shieh G. A circular-circular regression model. Stat Sin 2008; 18: 633–645.
- 58Lund UJ. Tree-based regression for a circular response. Commun Stat Theory Methods 2002; 31: 1549–1560.
- 59Breckling J. The Analysis of Directional Time Series: Application to Wind Speed and Direction. New York: Springer Verlag; 1989.
10.1007/978-1-4612-3688-7 Google Scholar
- 60Fisher NI, Lee AJ. Time series analysis of circular data. J R Stat Soc., Ser A 1994; 56: 327–339.
- 61Artes R, Paula GA, Ranvaud R. Analysis of circular longitudinal data based on generalised estimating equations. Aust N Z J Stat 2000; 42: 347–358.
- 62Holzmann H, Munk A, Suster M, Zucchini W. Hidden Markov models for circular and linear-circular time series. Environ Ecol Stat 2006; 13: 325–347.
- 63Bowers ID, Morton JA, Mould GI. Directional statistics of the wind and waves. Appl Ocean Res 2000; 22: 13–30.
- 64Martin LV, Cremades A, Santabarbara JM. Analysis and modelling of time series of surface wind speed and direction. Int J Climatol 1999; 19: 197–209.
- 65Carta C, Bueno JA, Ramirez P. Statistical modelling of directional wind speeds using mixtures of von Mises distributions. Energy Conserv Manage 2008; 49: 897–907.
- 66Somerville MC, Mukerjee S, Fox DL, Stevens RK. Statistical approaches to wind sector analyses for assessing local source impacts. Atmos Environ 1994; 28: 3483–3493.
- 67Marchetti GM, Scapini F. Use of multiple regression models in the study of sandhopper orientation under natural conditions. Estuar Coast Shelf Sci 2003; 58S: 207–215.
- 68D'Elia A, Borgioli C, Scapini F. Orientation of sandhoppers under natural conditions in repeated trials: an analysis using longitudinal directional data. Estuar Coast Shelf Sci 2001; 53: 839–847.
- 69Preisler HK, Akers RP. Autoregressive-type models for the analysis of bark beetle tracks. Biometrics 1995; 51: 259–267.
- 70Tracey JA, Zu J, Crooks K. A set of nonlinear regression models for animal movement in response to a single landscape feature. J Agric Biol Environ Stat 2005; 10: 1–18.
- 71Brunsdon C, Corcoran J. Using circular statistics to analyse time patterns of crime incidence. Comput Environ Urban Syst 2006; 30: 300–319.
- 72Gao K-S, Chia F, Krantz I, Nordin P, Machin D. On the application of the von Mises distribution and angular regression methods to investigate the seasonality of disease onset. Stat Med 2006; 25: 1593–1618.
- 73Mooney JA, Helms PJ, Joliffe IT. Fitting mixtures of von Mises distributions: a case study involving sudden infant death syndrome. Comput Stat Data Anal 2003; 41: 505–513.
- 74Nunez-Antonio G, Gutierrez-Pena E. A Bayesian analysis of directional data using the von Mises-Fisher distribution. Commun Stat Simul Comp 2005; 34: 989–999.
- 75Rodrigues J, Leite JG, Milan LA. An empirical Bayes inference for the von Mises distribution. Aust N Z J Stat 2000; 42: 433–440.
- 76Ghosh SR, Jammalamadaka K, Tiwari RC. Semiparametric Bayesian techniques for problems in circular data. J Appl Stat 2003; 30: 145–161.
- 77George BJ, Ghosh K. A semiparametric Bayesian model for circular-linear regression. Commun Stat Simul Comp 2006; 35: 911–923.
- 78Barnett V, Lewis T. Outliers in Statistical Data, 2nd ed. London: John Wiley & Sons; 1984.
- 79Collett D. Outliers in circular data. Appl Stat 1980; 29: 50–57.
10.2307/2346410 Google Scholar
- 80SenGupta A, Laha AK. The slippage problem for the circular normal distribution. Aust N Z J Stat 2001; 43: 461–471.
- 81Mardia KV. Statistics of Directional Data. New York: Academic Press; 1972.
- 82Batschelet E. Circular Statistics in Biology. London: Academic Press; 1981.