摘要:

After making a case for the prevalence of nonnormality, this paper attempts to introduce some distribution—free and robust techniques to ecologists and to offer a critical appraisal of the potential advantages and drawbacks of these methods. The techniques presented fall into two distinct categories, methods based on ranks and "computer—intensive" techniques. Distribution—free rank tests have features that can be recommended. They free the practitioner from concern about the underlying distribution and are very robust to outliers. If the distribution underlying the observations is other than normal, rank tests tend to be more efficient than their parametric counterparts. The absence, in computing packages, or rank procedures for complex designs may, however, severely limit their use for ecological data. An entire body of novel distribution—free methods has been developed in parallel with the increasing capacities of today's computers to process large quantities of data. These techniques either reshuffle or resample a data set (i.e., sample with replacement) in order to perform their analyses. The former we shall refer to as "permutation" or "randomization" methods and the latter as "bootstrap" techniques. These computer—intensive methods provide new alternatives for the problem of a small and/or unbalanced data set, and they may be the solution for parameter estimation when the sampling distribution cannot be derived analytically. Caution must be exercised in the interpretation of these estimates because confidence limits may be too small.

ISSN:0012-9658    

DOI:10.2307/1939920

出版商:Ecological Society of America    

年代:1993

数据来源: WILEY

摘要:

Least—squares linear regression and multiple regression are among the most commonly used analytical techniques of ecologists. However, these techniques only address a portion of the possible applications of regression methods. We discuss two less commonly used regression analyses that could find wide application in ecology, logistic regression and LOWESS regression. Logistic regression is appropriate in cases where the dependent variable is categorical, dichotomous, or polychotomus. It can be used with continuous and/or discrete independent variables. Logistic regression is motivated by the underlying binomial or multinomial distribution of dichotomous and polychotomous dependent variables and transforms the data to explicitly model these distributions. Locally weighted regression scatterplot smoothing or LOWESS regression is used to model the relationship between a dependent variable and independent variable when no single functional form will do. LOWESS regression is motivated by the assumption that neighboring values of the independent variable are the best indicators of the dependent variable in that range of independent values.

ISSN:0012-9658    

DOI:10.2307/1939921

出版商:Ecological Society of America    

年代:1993

数据来源: WILEY

摘要:

Ecological studies typically involve comparison of biological responses among a variety of environmental conditions. When the response variables have continuous distributions and the conditions are discrete, whether inherently or by design, then it is appropriate to analyze the data using analysis of variance (ANOVA). When data conform to a complete, balanced design (equal numbers of observations in each experimental treatment), it is straightforward to conduct an ANOVA, particularly with the aid of the numerous statistical computing packages that are available. Interpretation of an ANOVA of balanced data is also unambiguous. Unfortunately, for a variety of reasons, it is rare that a practicing ecologist embarks on an analysis of data that are completely balanced. Regardless of its cause, lack of balance necessitates care in the analysis and interpretation. In this paper, our aims is to provide an overview of the consequences of lack of balance and to give some guidelines to analyzing unbalanced data for models involving fixed effects. Our treatment is necessarily cursory and will not substitute for training available from a sequence of courses in mathematical statistics and linear models. It is intended to introduce the reader to the main issues and to the extensive statistical literature that deals with them.

ISSN:0012-9658    

DOI:10.2307/1939922

出版商:Ecological Society of America    

年代:1993

数据来源: WILEY

摘要:

Experimental design should be accommodated to spatial heterogeneity in nature as well as indoors, whether it is a nuisance or a characteristic of interest, combined or not with assessment of treatment effects. The following analysis—of—variance approach to quantification of spatial heterogeneity is based on the adequate design of ecological field experiments, according to the type and the scale of heterogeneity of concern (at small scale, patches, one— or two—dimensional gradients). There are no recipes for doing so and judgment must be exercised every time: the experimenter's knowledge about the experimental material, combined with premanipulation or control, then, provides a useful prerequisite. For patches and environmental gradients, in the presence of treatment assignment, recommended designs require the blocking principle of grouping similar experimental units, which allows avoidance of spurious treatment effects and inflated error mean square. Completely randomized designs should only be used in the very particular case of spatial homogeneity at large scale. Illustrations in ecological field experimentation are given and discussed.

ISSN:0012-9658    

DOI:10.2307/1939923

出版商:Ecological Society of America    

年代:1993

数据来源: WILEY

摘要:

Autocorrelation is a very general statistical property of ecological variables observed across geographic space; it most common forms are patches and gradients. Spatial autocorrelation, which comes either from the physical forcing of environmental variables or from community processes, presents a problem for statistical testing because autocorrelated data violate the assumption of independence of most standard statistical procedures. The paper discusses first how autocorrelation in ecological variables can be described and measured, with emphasis on mapping techniques. Then, proper statistical testing in the presence of autocorrelation is briefly discussed. Finally, ways are presented of explicitly introducing spatial structures into ecological models. Two approaches are proposed; in the raw—data approach, the spatial structure takes the form of a polynomial of the x and y geographic coordinates of the sampling stations; in the matrix approach, the spatial structure is introduced in the form of a geographic distance matrix among locations. These two approaches are compared in the concluding section. A table provides a list of computer programs available for spatial analysis.

ISSN:0012-9658    

DOI:10.2307/1939924

出版商:Ecological Society of America    

年代:1993

数据来源: WILEY

ISSN:0012-9658    

DOI:10.2307/1939925

出版商:Ecological Society of America    

年代:1993

数据来源: WILEY

摘要:

Biostatistics channels ecologists into thinking primarily about the mean and variance of a probability distribution. But many problems of biological interest concern the extremes in a variable (e.g., highest temperature, largest force, longest drought, maximum lifespan) rather than its central tendency. Such extremes are not adequately addressed by standard biostatistics. In these cases an alternative approach–the statistics of extremes–can be of value. In the limit of a large number of measurements, the probability structure of extreme values conforms to a generalized distribution described by three parameters. In practice these parameters are estimated using maximum likelihood techniques. Using this estimate of the probability distribution of extreme values, one can predict the expected time between the imposition of extremes of a given magnitude (a return time) and can place confidence limits on this prediction. Using data regarding sea—surface temperature, wave—induced hydrodynamic forces, wind speeds, and human life—spans we show that accurate long—term predictions can at times be made from a surprisingly small number of measurements if appropriate care is taken in the application of the statistics. For example, accurate long—term prediction of sea—surface temperatures can be derived from short—term data that are anomalous in that they contain the effects of an extreme EL Nino. In the cases of wave—induced forces and wind speeds, the probability distribution of extreme values is similar among years and diverse sites, indicating the possible existence of unifying principles governing these phenomena. Limitations and possible misuse of the method are discussed.

ISSN:0012-9658    

DOI:10.2307/1939926

出版商:Ecological Society of America    

年代:1993

数据来源: WILEY

摘要:

To evaluate the tendency of plant species to be arranged in hierarchies of competitive ability, Keddy and Shipley (1989) introduced a definition of competitive transitivity in multispecies competition matrices and developed an inferential statistic to test for such a pattern. Here, I introduce a more demanding definition of competitive transitivity ("complete transitivity") that defines a strict hierarchy of competitive relationships and that has more desirable properties for inferring competitive exclusion. A null model, and its accompanying Monte Carlo test, is developed that can be used in analyzing empirical competition matrices. Ten published competition matrices are analyzed; nine show clear evidence of complete transitivity.

ISSN:0012-9658    

DOI:10.2307/1939927

出版商:Ecological Society of America    

年代:1993

数据来源: WILEY

摘要:

I examined spatial patterns of two populations of the clonal herb Aralia nudicaulis for evidence of spatial inhibition among neighboring ramets. Second—order spatial analysis revealed that ramet patterns of both populations were regular at local spatial scales, a result consistent with the proposition that localized, inter—ramet interactions are important in reducing spatial overlap. Localized ramet interactions suggest Markovian dependence, which is defined when an event (e.g., occurrence of a ramet) at X is dependent solely on the existence or otherwise of an event within a distance ° of X. Evidence of Markovian dependence in the populations was tested by fitting Markov point—process models to the observed ramet patterns. The populations conformed well to the Markov model, the results indicating that both ramet spatial patterns were Markov of range ° = 18 cm. This inhibition distance corresponds closely to the mean horizontal radius of an A. nudicaulis ramet, indicating that interactions occur at the spatial scale of the individual. I suggest that a likely mechanism for the development of locally regular spatial patterns in these populations in inter—ramet competition for a limiting resource, probably light.

ISSN:0012-9658    

DOI:10.2307/1939928

出版商:Ecological Society of America    

年代:1993

数据来源: WILEY

摘要:

In simulations, the computational method chosen to implement a model can critically affect quantitative results. Here I show that two reasonable implementations of a neighborhood model of plant growth produce predictions that differ quantitatively in several important respects. I conclude that for modelling forest canopies, pixel—based implementations should prove superior to implementations that are based on indices of neighborhood crowding.

ISSN:0012-9658    

DOI:10.2307/1939929

出版商:Ecological Society of America    

年代:1993

数据来源: WILEY