Small sample estimation for Taylor's power law Papers Received: 15 May 1994 Revised: 15 January 1995 DOI :
10.1007/BF00469426

Cite this article as: Clark, S.J. & Perry, J.N. Environ Ecol Stat (1994) 1: 287. doi:10.1007/BF00469426
Abstract An analysis of counts of sample size N =2 arising from a survey of the grass Bromus commutatus identified several factors which might seriously affect the estimation of parameters of Taylor's power law for such small sample sizes. The small sample estimation of Taylor's power law was studied by simulation. For each of five small sample sizes, N =2, 3, 5, 15 and 30, samples were simulated from populations for which the underlying known relationship between variance and mean was given by σ^{2} = c μ^{d} . One thousand samples generated from the negative binomial distribution were simulated for each of the six combinations of c =1,2 and 11, and d =1, 2, at each of four mean densities, μ=0.5, 1, 10 and 100, giving 4000 samples for each combination. Estimates of Taylor's power law parameters were obtained for each combination by regressing log_{10} s ^{2} on log_{10} m , where s ^{2} and m are the sample variance and mean, respectively. Bias in the parameter estimates, b and log_{10} a , reduced as N increased and increased with c for both values of d and these relationships were described well by quadratic response surfaces. The factors which affect small-sample estimation are: (i) exclusion of samples for which m = s ^{2} = 0; (ii) exclusion of samples for which s ^{2} = 0, but m > 0; (iii) correlation between log_{10} s ^{2} and log_{10} m ; (iv) restriction on the maximum variance expressible in a sample; (v) restriction on the minimum variance expressible in a sample; (vi) underestimation of log_{10} s ^{2} for skew distributions; and (vii) the limited set of possible values of m and s ^{2} . These factors and their effect on the parameter estimates are discussed in relation to the simulated samples. The effects of maximum variance restriction and underestimation of log_{10} s ^{2} were found to be the most severe. We conclude that Taylor's power law should be used with caution if the majority of samples from which s ^{2} and m are calculated have size, N , less than 15. An example is given of the estimated effect of bias when Taylor's power law is used to derive an efficient sampling scheme.

Keywords bias negative binomial distribution parameter estimation response surface sample scheme simulation small samples Taylor's power law variance-mean relationship

References Anderson, R.M., Gordon, D.M., Crawley, M.J. and Hassell, M.P. (1982) Variability in the abundance of animal and plant species.

Nature
296 , 245–8.

Google Scholar Binns, M.R. (1986) Behavioural dynamics and the negative binomial distribution.

Oikos
47 , 315–318.

Google Scholar Binns, M.R. and Nyrop, J.P. (1992) Sampling insect populations for the purpose of IPM decision making.

Annual Review of Entomology
37 , 427–53.

Google Scholar Blackshaw, R.P. and Perry, J.N. (1994) Predicting leatherjacket population frequencies in Northern Ireland. Annals of Applied Biology , (in press).

Bliss, C.I. (1941) Statistical problems in estimating populations of Japanese beetle larvae.

Journal of Economic Entomology
34 , 221–32.

Google Scholar Boag, B. and Topham, P.B. (1984) Aggregation of plant parasitic nematodes and Taylor's power law.

Nematologica
30 , 348–57.

Google Scholar Clark, S.J. and Perry, J.N. (1989) Estimation of the negative binomial parameter

k by maximum quasilikelihood.

Biometrics
45 , 309–16.

Google Scholar Downing, J.A. (1986) Spatial heterogeneity: evolved behaviour or mathematical artefact?

Nature
323 , 255–7.

Google Scholar Duchateau, L., Ross, G.J.S. and Perry, J.N. (1994) Parameter estimation and hypothesis testing for Adès distributions applied to tse-tse fly data. Biométrie Praximétrie , (in press).

Dye, C. (1983) Insect movement and fluctuations in insect population size.

Antenna
7 , 174–8.

Google Scholar Dye, C. (1984) Reply to Dr Taylor.

Antenna
8 , 65–6.

Google Scholar Finch, S., Skinner, G. and Freeman, G.H. (1975) The distribution and analysis of cabbage root fly egg populations.

Annals of Applied Biology
79 , 1–18.

Google Scholar Finch, S., Skinner, G. and Freeman, G.H. (1978) Distribution and analysis of cabbage root fly pupal populations.

Annals of Applied Biology
88 , 351–6.

Google Scholar Gaston, K.J. and McArdle, B.H. (1993) Measurement of variation in the size of populations in space and time: some points of clarification.

Oikos
68 , 357–60.

Google Scholar Hanski, I. (1987) Cross-correlation in population dynamics and the slope of spatial variance-mean regressions.

Oikos
50 , 148–51.

Google Scholar Holgate, P. (1988) Approximate moments of the Adès distribution.

Biometrical Journal
31 , 875–83.

Google Scholar Kemp, A.W. (1987) Families of discrete distributions satisfying Taylor's power law.

Biometrics
43 , 693–9.

Google Scholar Kemp, A.W. (1988) Response to Perry and Taylor.

Biometrics
44 , 888–9.

Google Scholar Lepš, J. (1993) Taylor's power law and the measurement of variation in the size of populations in space and time.

Oikos
68 , 349–56.

Google Scholar Marshall, E.J.P. (1985) Weed distributions associated with cereal field edges — some preliminary observations.

Aspects of Applied Biology
9 , 49–58.

Google Scholar Marshall, E.J.P. (1989) Distribution patterns of plants associated with arable field edges.

Journal of Applied Ecology
26 , 247–257.

Google Scholar May, R.M. and Southwood, T.R.E. (1990) Introduction. In Living in a Patchy Environment (B. Shorrocks and I.R. Swingland, eds), pp. 1–22. Oxford University Press.

McArdle, B.H., Gaston, K.J. and Lawton, J.H. (1990) Variation in the size of animal populations: patterns, problems and artefacts.

Journal of Animal Ecology
59 , 439–54.

Google Scholar Perry, J.N. (1981) Taylor's power law for dependence of variance on mean in animal populations.

Applied Statistics
30 , 254–63.

Google Scholar Perry, J.N. (1984) Negative binomial model for mosquitos.

Biometrics
40 , 863–4.

Google Scholar Perry, J.N. (1987) Iterative improvement of a power transformation to stabilise variance.

Applied Statistics
36 , 15–21.

Google Scholar Perry, J.N. (1988) Some models for spatial variability of animal species.

Oikos
51 , 124–30.

Google Scholar Perry, J.N. (1994a) Sampling and applied statistics for pests and diseases.

Aspects of Applied Biology 37 , 1–14.

Google Scholar Perry, J.N. (1994b) Chaotic dynamics can generate Taylor's power law.

Proceedings of the Royal Society of London Series B

257 , 221–6.

Google Scholar Perry, J.N. and Taylor, L.R. (1985) Adès: new ecological families of species-specific frequency distributions that describe repeated spatial samples with an intrinsic power-law variance-mean property.

Journal of Animal Ecology
54 , 931–53.

Google Scholar Perry, J.N. and Taylor, L.R. (1986) Stability of real interacting populations in space and time: implications, alternatives and the negative binomial

k
_{c} .

Journal of Animal Ecology
55 , 1053–68.

Google Scholar Perry, J.N. and Taylor, L.R. (1988) Families of distributions for repeated samples of animal counts.

Biometrics
44 , 881–90.

Google Scholar Perry, J.N. and Woiwod, I.P. (1992) Fitting Taylor's power law.

Oikos
65 , 538–42.

Google Scholar Ross, G.J.S. (1990) Incomplete variance functions.

Journal of Applied Statistics
17 , 3–8.

Google Scholar Routledge, R.D. and Swartz, T.B. (1991) Taylor's power law re-examined.

Oikos
60 , 107–12.

Google Scholar Southwood, T.R.E. (1966)

Ecological Methods . Methuen, London.

Google Scholar Southwood, T.R.E. (1984) Insects as models.

Antenna
8 , 3–14.

Google Scholar Taylor, L.R. (1961) Aggregation, variation and the mean.

Nature
189 , 732–5.

Google Scholar Taylor, L.R. (1965) A natural law for the spatial disposition of insects. Proceedings of the 12th International Congress of Entomology, London , 1964, pp. 396-7.

Taylor, L.R. (1970) Aggregation and the transformation of counts of

Aphis fabae (Scop.) on beans.

Annals of Applied Biology
65 , 181–9.

Google Scholar Taylor, L.R. (1971) Aggregation as a species characteristic. In

Spatial Patterns and Statistical Distributions (G.P. Patil, E.C. Pielou and W.E. Waters, eds.), Pennsylvania State University Press, Pennsylvania, pp. 357–77.

Google Scholar Taylor, L.R. (1984a) Assessing and interpreting the spatial distributions of insect populations.

Annual Review of Entomology
29 , 321–57.

Google Scholar Taylor, L.R. (1984b) Anscombe's hypothesis and the changing distribution of insect populations.

Antenna
8 , 62–7.

Google Scholar Taylor, L.R. (1986) Synoptic dynamics, migration and the Rothamsted Insect Survey.

Journal of Animal Ecology
55 , 1–38.

Google Scholar Taylor, L. R. and Taylor, R.A.J. (1977) Aggregation, migration and population mechanics.

Nature
265 , 415–21.

Google Scholar Taylor, L.R. and Woiwod, I.P. (1980) Temporal stability as a density-dependent species characteristic.

Journal of Animal Ecology
49 , 209–24.

Google Scholar Taylor, L.R. and Woiwod, I.P. (1982) Comparative synoptic dynamics. I. Relationships between inter- and intra-specific spatial and temporal variance/mean parameters.

Journal of Animal Ecology
51 , 879–906.

Google Scholar Taylor, L.R., Woiwod, I.P. and Perry, J.N. (1978) The density dependence of spatial behaviour and the rarity of randomness.

Journal of Animal Ecology
47 , 383–406.

Google Scholar Taylor, L.R., Woiwod, I.P. and Perry, J.N. (1979) The negative binomial as a dynamic ecological model for aggregation and the density-dependence of

k .

Journal of Animal Ecology
48 , 289–304.

Google Scholar Taylor, L.R., Woiwod, I.P. and Perry, J.N. (1980) Variance and the large-scale spatial stability of aphids, moths and birds.

Journal of Animal Ecology
49 , 831–54.

Google Scholar Taylor, L.R., Taylor, R.A.J., Woiwod, I.P. and Perry, J.N. (1983) Behavioral dynamics. Nature

303 , 801–4.

Google Scholar Taylor, L.R., Perry, I.N., Woiwod, I.P. and Taylor, R.A.J. (1988) Specificity of the spatial power-law exponent in ecology and agriculture.

Nature
332 , 721–2.

Google Scholar Thórarinsson, K. (1986) Population density and movement: a critique of Δ-models.

Oikos
46 , 70–81.

Google Scholar Woiwod, I.P. and Perry, J.N. (1989) Data reduction and analysis. Boletin de Sanidad Vegetal No. 17, Proceedings of PARASITIS 88 , pp. 159-74.

Yamamura, K. (1990) Sampling scale dependence of Taylor's power law.

Oikos
59 , 121–5.

Google Scholar Authors and Affiliations 1. IACR, Statistics Departments Rothamsted Experimental Station Harpenden UK 2. Entomology and Nematology Departments Rothamsted Experimental Station Harpenden UK