Statistics for Environmental Biology and Toxicology

ISBN-13: 9780412047312 / Angielski / Twarda / 1997 / 596 str.

John Bailer; Walter W. Piegorsch; W. Piegorsch

Opis

Statistics for Environmental Biology and Toxicology presents and illustrates statistical methods appropriate for the analysis of environmental data obtained in biological or toxicological experiments. Beginning with basic probability and statistical inferences, this text progresses through non-linear and generalized linear models, trend testing, time-to-event data and analysis of cross-classified tabular and categorical data. For the more complex analyses, extensive examples including SAS and S-PLUS programming code are provided to assist the reader when implementing the methods in practice.

Recenzje

"Teachers of statistics to students from other disciplines could will find this book useful, both for its condensed summaries of some of the more sophisticated techniques-in particular that for generalized linear models is helpful and also for the copious exercises and worked examples."
-Short Book Reviews of the ISI
"…I strongly recommend this text and believe it to be an excellent supplement for any biostatistics course or courses in related disciplines."
-Australian & New Zealand Journal of Statistics
"This book is an excellent source for information about the relevant statistical methods with a strong emphasis on applications. This is one of the best books that I have seen recently."
-Technometrics, Vol. 40, No.3



"The many examples are well selected and illustrate the use of the methods introduced on relevant data."… the book introduces many statistical concepts, it is concise but careful and it has many good examples…. could be used as a basic statistical textbook for researchers in environmental biology."
-Statistics in Medicine, Vol. 20: 1143-1152, 2001

Spis treści

Basic Probability and Statistical DistributionsIntroductory Concepts in ProbabilityFamilies of Discrete DistributionsFamilies of Continuous DistributionsThe Exponential ClassFamilies of Multivariate DistributionsSummaryExercisesFundamentals of Statistical InferenceIntroductory Concepts in Statistical EstimationNature and Properties of EstimatorsTechniques for Constructing Statistical EstimatorsStatistical Inference - Testing HypothesesStatistical Inference - Confidence IntervalsConfidence Intervals for Some Special DistributionsSemi-Parametric InferenceSummaryExercisesFundamental Issues in Experiment DesignBasic Terminology in Experiment DesignThe Experimental UnitRandom Sampling and RandomizationSample Sizes and Optimal Animal AllocationDose SelectionSummary Exercises Data Analysis of Treatment versus Control DifferencesTwo-Sample Comparisons - Testing HypothesesTwo-Sample Comparisons - Confidence IntervalsSummaryExercisesTreatment-versus-Control Multiple ComparisonsComparing More than Two PopulationsMultiple Comparisons via Bonferroni's InequalityMultiple Comparisons among a Control - Normal SamplingMultiple Comparisons among Binomial PopulationsMultiple Comparisons with a Control - Poisson SamlingAll-Pairwise Multiple ComparisonsSummary ExercisesTrend TestingSimple Linear Regression for Normal Data William's Test for Normal DataTrend Tests for ProportionsCochran-Armitage Trend Test for CountsOverdispersed Discrete DataDistribution-Free Trend TestingNonparametric Tests for Nonmonotone ("Umbrella") TrendsSummaryExercisesDose-Response Modeling and AnalysisDose-Response Models on a Continuous ScaleDose-Response Models on a Discrete ScalePotency Estimation for Dose-Response DataComparing Dose-Response CurvesSummaryExercisesIntroduction to Generalized Linear Models (GLiMs)Review of Classical Linear ModelsGeneralizing the Classical Linear ModelGeneralized Linear ModelsExamples and IllustrationsSummaryExercisesAnalysis of Cross-Classified Tabular/Categorical DataRxC Contingency TablesStatistical Distributions for Categorical DataStatistical Tests of Independence in RxC TablesLog-Linear Models and Relationships to GLiMsTables of ProportionsSummary ExercisesIncorporating Historical Control InformationGuidelines for Using Historical Control DataTwo-Sample Hypothesis Testing - Normal Distribution SamplingTwo-Sample Hypothesis Testing - Binomial SamplingTrend Testing with Historical ControlsSummaryExercisesSurvival Data AnalysisSurvival DataLifetime DistributionsEstimating the Survivor FunctionNonparametric Methods for Comparing Survival CurvesRegression Models for Survival DataSummaryExercisesAppendices References

O autorze

Walter W. Piegorsch is Professor of Statistics at the University of South Carolina, Columbia, SC, USA. A. John Bailer is Professor of Mathematics and Statistics and Co-director of the Center for Environmental Toxicology and Statistics at Miami University, Oxford, OH, USA.