Atjaunināt sīkdatņu piekrišanu

E-grāmata: Design and Statistical Analysis of Animal Experiments

3.33/5 (5 ratings by Goodreads)
,
  • Formāts: EPUB+DRM
  • Izdošanas datums: 13-Mar-2014
  • Izdevniecība: Cambridge University Press
  • Valoda: eng
  • ISBN-13: 9781107779495
Citas grāmatas par šo tēmu:
  • Formāts - EPUB+DRM
  • Cena: 59,47 €*
  • * ši ir gala cena, t.i., netiek piemērotas nekādas papildus atlaides
  • Ielikt grozā
  • Pievienot vēlmju sarakstam
  • Šī e-grāmata paredzēta tikai personīgai lietošanai. E-grāmatas nav iespējams atgriezt un nauda par iegādātajām e-grāmatām netiek atmaksāta.
Design and Statistical Analysis of Animal ExperimentsPalielināt
  • Formāts: EPUB+DRM
  • Izdošanas datums: 13-Mar-2014
  • Izdevniecība: Cambridge University Press
  • Valoda: eng
  • ISBN-13: 9781107779495
Citas grāmatas par šo tēmu:

DRM restrictions

  • Kopēšana (kopēt/ievietot):

    nav atļauts

  • Drukāšana:

    nav atļauts

  • Lietošana:

    Digitālo tiesību pārvaldība (Digital Rights Management (DRM))
    Izdevējs ir piegādājis šo grāmatu šifrētā veidā, kas nozīmē, ka jums ir jāinstalē bezmaksas programmatūra, lai to atbloķētu un lasītu. Lai lasītu šo e-grāmatu, jums ir jāizveido Adobe ID. Vairāk informācijas šeit. E-grāmatu var lasīt un lejupielādēt līdz 6 ierīcēm (vienam lietotājam ar vienu un to pašu Adobe ID).

    Nepieciešamā programmatūra
    Lai lasītu šo e-grāmatu mobilajā ierīcē (tālrunī vai planšetdatorā), jums būs jāinstalē šī bezmaksas lietotne: PocketBook Reader (iOS / Android)

    Lai lejupielādētu un lasītu šo e-grāmatu datorā vai Mac datorā, jums ir nepieciešamid Adobe Digital Editions (šī ir bezmaksas lietotne, kas īpaši izstrādāta e-grāmatām. Tā nav tas pats, kas Adobe Reader, kas, iespējams, jau ir jūsu datorā.)

    Jūs nevarat lasīt šo e-grāmatu, izmantojot Amazon Kindle.

"Written for animal researchers, this book provides a comprehensive guide to the design and statistical analysis of animal experiments. It has long been recognised that the proper implementation of these techniques helps reduce the number of animals needed. By using real-life examples to make them more accessible, this book explains the statistical tools employed by practitioners. A wide range of design types are considered, including block, factorial, nested, cross-over, dose-escalation and repeated measures and techniques are introduced to analyse the experimental data generated. Each analysis technique is described in non-mathematical terms, helping readers without a statistical background to understand key techniques such as t-tests, ANOVA, repeated measures, analysis of covariance, multiple comparison tests, non-parametric and survival analysis. This is also the first text to describe technical aspects of InVivoStat, a powerful open-source software package developed by the authors to enable animal researchers to analyse their data and obtain informative results"--

Recenzijas

'At last, a readable statistics book focusing solely on preclinical experimental designs, data and its analysis that should form part of an in-vivo scientist's personal library. The author's unique insight into the statistical needs of preclinical scientists has allowed them to compile a non-technical guide that can facilitate sound experimental design, meaningful data analysis and appropriate scientific conclusions. I would also encourage all readers to download and explore 'InVivoStat', a powerful software package that both my group and I use on a daily basis.' Darrel J. Pemberton, Janssen Research and Development 'This book provides an indispensable reference for any in-vivo scientist. It addresses common pitfalls in animal experiments and provides tangible advice to address sources of bias, thus increasing the robustness of the data. The text links experimental design and statistical analysis in a practical way, easily accessible without any prior statistical knowledge. The statistical concepts are described in plain English, avoiding overuse of mathematical formulas and illustrated with numerous examples relevant to biomedical scientists. This book will help scientists improve the design of animal experiments and give them the confidence to use more complex designs, enabling more efficient use of animals and reducing the number of experimental animals needed overall.' Nathalie Percie du Sert, National Centre for the Replacement, Refinement and Reduction of Animals in Research 'This book will transform the way biomedical scientists plan their work and interpret their results. Although the subject matter covers complex points, it is easy to read and packed with relevant examples. There are two particularly striking features. First, at no point do the authors resort to mathematical equations as a substitute for explaining the concepts. Secondly, they explain why the choice of experimental design is so important, why the design affects the statistical analysis and how to ensure the choice of the most appropriate statistical test. The final section describes how to use InvivoStat (a software package, assembled by the authors), which enables researchers to put into practice all the points covered in this book. This is an invaluable combination of resources that should be within easy reach of anyone carrying out experiments in the biomedical sciences, especially if their work involves using live animals.' Clare Stanford, University College London

Papildus informācija

This book will provide scientists with a better understanding of statistics, improving their decision-making and reducing animal use.
Preface xiii
Acknowledgments xv
1 Introduction
1(17)
1.1 Structure of this book
3(2)
1.1.1 Introductory sections
4(1)
1.1.2 Approaches to consider when setting up a new animal model
4(1)
1.1.3 Approaches to consider when generating hypotheses
5(1)
1.1.4 Approaches to consider when testing hypotheses
5(1)
1.2 Statistical problems faced by animal researchers
5(1)
1.3 Pitfalls encountered when applying statistics in practice
6(9)
1.3.1 Pitfalls with experimental design
6(3)
1.3.2 Pitfalls with randomisation
9(1)
1.3.3 Pitfalls with statistical analysis
10(3)
1.3.4 Pitfalls when reporting animal experiments
13(2)
1.4 So where does statistics fit in?
15(1)
1.5 The ARRIVE guidelines
15(3)
2 Statistical concepts
18(12)
2.1 Decision-making: the signal-to-noise ratio
18(1)
2.2 Probability distributions
19(4)
2.2.1 The frequency distribution
20(1)
2.2.2 The density distribution
20(1)
2.2.3 The probability distribution
21(1)
2.2.4 The normal distribution
21(1)
2.2.5 The chi-squared distribution
22(1)
2.2.6 The t-distribution
22(1)
2.2.7 The F-distribution
23(1)
2.3 The hypothesis testing procedure
23(5)
2.3.1 The null and alternative hypotheses
23(2)
2.3.2 The p-value
25(1)
2.3.3 The significance level
25(1)
2.3.4 Significant stars
26(1)
2.3.5 Type I and Type II errors
26(2)
2.4 Exploratory vs. confirmatory experiments
28(1)
2.5 The estimation process
29(1)
3 Experimental design
30(92)
3.1 Why design experiments?
30(2)
3.1.1 Practical reasons
30(1)
3.1.2 Statistical reasons: variability, the signal and bias
31(1)
3.2 What does an experimental design involve?
32(14)
3.2.1 Variables to be recorded
32(1)
3.2.1.1 Types of response
32(2)
3.2.1.2 Reporting responses
34(1)
3.2.1.3 Baseline responses
34(1)
3.2.1.4 Recording conditions during the experiment
35(1)
3.2.2 Set of treatments
35(1)
3.2.3 The experimental unit and the observational unit
36(1)
3.2.4 Effects and factors
37(2)
3.2.4.1 Defining factor level labels
39(1)
3.2.4.2 Defining the factors in an experimental design
39(1)
3.2.5 Fixed and random factors
39(1)
3.2.5.1 Fixed factors
40(1)
3.2.5.2 Random factors
40(1)
3.2.5.3 Random or fixed?
41(1)
3.2.6 Categorical factors and continuous factors
42(1)
3.2.7 Crossed factors and nested factors
42(1)
3.2.7.1 Nested factors
42(1)
3.2.7.2 Crossed factors
43(2)
3.2.7.3 Partially crossed factors
45(1)
3.2.7.4 Designs containing nested and crossed factors
45(1)
3.2.8 Repeatedly measuring the animal
45(1)
3.3 Summary of design types
46(3)
3.3.1 Block designs
46(1)
3.3.2 Factorial designs
47(1)
3.3.3 Dose-response designs
47(1)
3.3.4 Nested designs
47(1)
3.3.5 Split-plot designs
48(1)
3.3.6 Repeated measures and dose-escalation designs
48(1)
3.3.7 Designs applied in practice
48(1)
3.4 Block designs
49(14)
3.4.1 Practical reasons to block
49(1)
3.4.2 Statistical reasons to block
49(1)
3.4.2.1 Variance reduction
49(2)
3.4.2.2 Bias reduction
51(1)
3.4.3 How to block
51(2)
3.4.4 Complete block designs
53(1)
3.4.4.1 Efficiency
53(1)
3.4.4.2 Randomisation
53(1)
3.4.4.3 Statistical analysis of block designs
54(1)
3.4.5 Incomplete block designs
54(1)
3.4.6 Balanced incomplete block design
55(1)
3.4.6.1 Efficiency
55(1)
3.4.6.2 Randomisation
55(1)
3.4.6.3 Statistical analysis
55(1)
3.4.7 More than one block: the row-column block design
56(1)
3.4.7.1 Efficiency
56(1)
3.4.7.2 Randomisation
56(1)
3.4.7.3 Statistical analysis
56(1)
3.4.8 Row-column block designs based on Latin squares
57(1)
3.4.8.1 Efficiency
58(1)
3.4.8.2 Randomisation
58(1)
3.4.8.3 Statistical analysis
58(1)
3.4.9 Crossover designs
59(1)
3.4.9.1 Complete crossover designs
59(1)
3.4.9.2 Incomplete crossover designs
60(1)
3.4.9.3 The benefits of crossover designs
61(1)
3.4.9.4 The issues with crossover designs
62(1)
3.4.9.5 Treatment carry-over effects
62(1)
3.5 Factorial design
63(21)
3.5.1 Randomisation
64(1)
3.5.2 Categorical factors and interactions
64(2)
3.5.3 Small factorial designs
66(2)
3.5.4 Large factorial designs
68(1)
3.5.4.1 Strategies when setting up a new animal model
68(2)
3.5.4.2 Graphical representation of large factorial designs
70(1)
3.5.4.3 Hidden replication
70(2)
3.5.4.4 Fractional factorial designs to reduce animal use
72(3)
3.5.4.5 Two-stage procedure to reduce animal use
75(2)
3.5.5 Factorial designs with continuous factors
77(1)
3.5.5.1 Strategies for setting up a new animal model
78(3)
3.5.5.2 Drug combination studies
81(2)
3.5.5.3 Continuous vs. categorical factors
83(1)
3.5.6 Final thoughts on factorial designs
83(1)
3.6 Dose-response designs
84(6)
3.6.1 The four- and five-parameter logistic curves
84(1)
3.6.2 Experimental design considerations
85(1)
3.6.2.1 Increasing the number of doses
86(1)
3.6.2.2 Decreasing the number of animals
86(1)
3.6.3 Including the control group
87(1)
3.6.3.1 Analysing a change from the control response
87(1)
3.6.3.2 Using a dual statistical model
88(1)
3.6.3.3 Adding an offset to the dose
88(2)
3.7 Nested designs
90(20)
3.7.1 Types of nested design
91(1)
3.7.1.1 Single-order nested design
91(1)
3.7.1.2 Higher-order nested design
91(2)
3.7.2 Sample size and power
93(1)
3.7.2.1 Factors that influence sample size
93(2)
3.7.2.2 Calculating sample sizes
95(2)
3.7.2.3 When not to calculate the statistical power
97(2)
3.7.3 Higher-order nested designs
99(1)
3.7.3.1 Identifying nested factors
99(2)
3.7.3.2 Investigating the sources of variability in higher-order nested designs
101(1)
3.7.3.3 Variance components: estimating the observational unit variability
102(1)
3.7.3.4 Predicting the experimental unit variability
103(2)
3.7.3.5 Investigating alternative nested designs
105(1)
3.7.3.6 Pseudo-replication
106(4)
3.8 Repeated measures and dose-escalation designs
110(7)
3.8.1 Repeated measures designs
110(1)
3.8.1.1 The repeated factor
110(2)
3.8.1.2 The core experimental design
112(1)
3.8.1.3 Nested repeated measures designs
112(2)
3.8.1.4 More complex repeated measures designs
114(2)
3.8.2 Dose-escalation designs
116(1)
3.8.2.1 More complex dose-escalation designs
117(1)
3.9 Split-plot designs
117(2)
3.9.1 Animals as whole plots
117(1)
3.9.2 Animals as subplots
118(1)
3.10 Experimental designs in practice
119(1)
3.11 A good design should result in...
120(2)
4 Randomisation
122(10)
4.1 Practical reasons to randomise
122(2)
4.1.1 Bias reduction
122(1)
4.1.1.1 Removing unforeseen trends
123(1)
4.1.1.2 Humans are systematic
123(1)
4.1.2 Blinding
124(1)
4.2 Statistical reasons to randomise
124(5)
4.2.1 Estimating the variability
125(1)
4.2.2 Deciding upon the statistical analysis strategy
125(1)
4.2.2.1 Including interactions in the statistical model
126(1)
4.2.2.2 Including blocking factors
127(1)
4.2.3 Repeatedly measured responses
127(1)
4.2.3.1 Repeated factors and randomised factors
127(1)
4.2.3.2 Block and dose-escalation designs
127(1)
4.2.3.3 Crossover and dose-escalation designs
128(1)
4.2.3.4 Including interactions involving the repeated factor
129(1)
4.3 What to randomise
129(1)
4.4 How to randomise
130(2)
5 Statistical analysis
132(106)
5.1 Introduction
132(3)
5.1.1 InVivoStat
133(1)
5.1.2 A recommended five-stage parametric analysis procedure
133(2)
5.2 Summary statistics
135(5)
5.2.1 Parametric measures of location
135(1)
5.2.1.1 The true mean and the sample mean
135(1)
5.2.1.2 The observed mean
136(1)
5.2.1.3 The predicted mean
137(1)
5.2.1.4 The geometric mean
137(1)
5.2.2 Parametric measures of spread
138(1)
5.2.2.1 Variance
138(1)
5.2.2.2 Standard deviation
138(1)
5.2.2.3 Standard error of the mean
138(1)
5.2.2.4 Confidence intervals
139(1)
5.2.2.5 Coefficient of variation
139(1)
5.2.3 Non-parametric measures of location
139(1)
5.2.4 Non-parametric measures of spread
140(1)
5.3 Graphical tools
140(11)
5.3.1 Scatterplots
140(2)
5.3.2 Box-plots
142(1)
5.3.3 Histograms
143(1)
5.3.4 Categorised case profiles plot
144(1)
5.3.5 Means with SEMs plot
145(1)
5.3.5.1 Problems with the means with SEMs plot
145(6)
5.3.5.2 Benefits of the means with SEMs plot
151(1)
5.4 Parametric analysis
151(77)
5.4.1 Parametric assumptions
152(1)
5.4.1.1 Numeric and continuous responses
152(1)
5.4.1.2 Normally distributed residuals
153(2)
5.4.1.3 Homogeneity of variance
155(3)
5.4.1.4 Independence of the responses
158(1)
5.4.1.5 Removal of outliers
159(3)
5.4.1.6 Additivity
162(1)
5.4.2 The t-test
163(1)
5.4.2.1 The unpaired t-test
163(2)
5.4.2.2 When not to use an unpaired t-test
165(2)
5.4.2.3 The paired t-test
167(1)
5.4.2.4 Randomisation and the paired t-test
168(1)
5.4.3 Analysis of variance (ANOVA)
168(1)
5.4.3.1 One-way ANOVA
169(4)
5.4.3.2 Including the positive control
173(1)
5.4.3.3 Two-way ANOVA
174(2)
5.4.3.4 Two-way vs. one-way ANOVA
176(1)
5.4.3.5 Dealing with missing factor combinations
177(2)
5.4.4 Repeated measures analysis
179(2)
5.4.4.1 Categorised case profiles plot
181(1)
5.4.4.2 Analysis of summary measures
181(8)
5.4.4.3 Repeated measures analysis
189(2)
5.4.4.4 The mixed-model approach vs. the ANOVA-based approach
191(4)
5.4.4.5 Advantages and disadvantages of the repeated measures analysis
195(1)
5.4.5 Predicted means from the parametric analysis
196(1)
5.4.5.1 Least square (predicted) means
196(1)
5.4.5.2 Variability of the least square (predicted) means
197(1)
5.4.5.3 Geometric means and confidence intervals
197(1)
5.4.5.4 Reliability of the predicted means
198(1)
5.4.6 Analysis of covariance (ANCOVA)
199(1)
5.4.6.1 What is a covariate?
200(1)
5.4.6.2 Best-fit lines and predicted lines
201(1)
5.4.6.3 Categorised scatterplot
201(1)
5.4.6.4 Predictions from ANCOVA
202(1)
5.4.6.5 Predicted group means
203(1)
5.4.6.6 Assumptions for ANCOVA
204(3)
5.4.6.7 Strategy for when the independence assumption does not hold
207(1)
5.4.6.8 ANCOVA and stratified randomisation
208(1)
5.4.6.9 Change from baseline responses
208(3)
5.4.7 Regression analysis
211(1)
5.4.8 Multiple comparison procedures
212(1)
5.4.8.1 The risk of finding false positives and false negatives
212(2)
5.4.8.2 Choosing the family of tests
214(1)
5.4.8.3 Unadjusted tests
215(3)
5.4.8.4 Stepwise multiple comparison procedures that control the FDR
218(1)
5.4.8.5 Simultaneous multiple comparison procedures that control the FWE
218(4)
5.4.8.6 Stepwise multiple comparison procedures based on group differences that control the FWE
222(1)
5.4.8.7 Stepwise-based multiple comparison procedures based on p-values that control the FWE
223(1)
5.4.8.8 The gateway ANOVA approach
224(3)
5.4.8.9 Multiple comparison procedures in statistical software packages
227(1)
5.4.8.10 Recommendations
228(1)
5.5 Other useful analyses
228(10)
5.5.1 Non-parametric analyses
228(1)
5.5.1.1 When to use a non-parametric test
229(1)
5.5.1.2 Non-parametric tests
230(1)
5.5.2 Testing the difference between proportions
231(1)
5.5.2.1 Analysis procedure
232(1)
5.5.2.2 Chi-squared test
232(1)
5.5.2.3 Fisher's exact test
233(1)
5.5.3 Survival analysis
234(1)
5.5.3.1 The survival function
235(1)
5.5.3.2 Comparing groups
236(2)
6 Analysis using InVivoStat
238(55)
6.1 Getting started
238(3)
6.1.1 Data import
238(1)
6.1.1.1 Single measure format
238(1)
6.1.1.2 Repeated measures format
239(1)
6.1.2 Importing a dataset into InVivoStat: Excel import
240(1)
6.1.3 Importing a dataset into InVivoStat: text file import
240(1)
6.1.4 Data management
240(1)
6.1.5 Running an analysis
240(1)
6.1.6 Warning and error messages
241(1)
6.1.7 Log file
241(1)
6.1.8 Exporting results
241(1)
6.2 Summary Statistics module
241(2)
6.2.1 Analysis procedure
242(1)
6.2.2 Worked example
243(1)
6.3 Single Measure Parametric Analysis module
243(9)
6.3.1 Analysis procedure
243(2)
6.3.2 Worked example
245(3)
6.3.3 Technical details
248(1)
6.3.3.1 Analysis of large factorial experiments
248(1)
6.3.3.2 Analysis of small factorial experiments
248(1)
6.3.3.3 Analysis of experiments involving blocking factors
249(2)
6.3.3.4 Analysis of crossover trials
251(1)
6.3.3.5 Analysis of designs with missing factor combinations
252(1)
6.4 Repeated Measures Parametric Analysis module
252(6)
6.4.1 Analysis procedure
252(3)
6.4.2 Worked example
255(1)
6.4.3 Technical details
255(3)
6.5 P-Value Adjustment module
258(2)
6.5.1 Analysis procedure
259(1)
6.5.2 Worked example
259(1)
6.6 Non-Parametric Analysis module
260(2)
6.6.1 Analysis procedure
260(2)
6.6.2 Worked example
262(1)
6.7 Graphics module
262(1)
6.7.1 Analysis procedure
262(1)
6.7.2 Example plots
263(1)
6.8 Power Analysis module
263(4)
6.8.1 Analysis procedure
263(2)
6.8.2 Worked example
265(2)
6.9 Unpaired t-test Analysis module
267(5)
6.9.1 Analysis procedure
267(4)
6.9.2 Worked example
271(1)
6.10 Paired t-test/within-subject Analysis module
272(5)
6.10.1 Analysis procedure
272(4)
6.10.2 Worked example
276(1)
6.11 Dose-Response Analysis module
277(5)
6.11.1 Technical details on curve fitting
277(1)
6.11.2 Fitting logistic curves to data
278(1)
6.11.3 Analysis of quantitative assays
278(1)
6.11.4 Analysis procedure
279(2)
6.11.5 Worked example: a biological assay
281(1)
6.11.6 User-defined equation option
282(1)
6.12 Chi-squared Test and Fisher's Exact Test module
282(3)
6.12.1 Analysis procedure
283(1)
6.12.2 Worked example
284(1)
6.13 R-Runner module
285(1)
6.14 Nested Design Analysis module
285(4)
6.14.1 Analysis procedure
286(3)
6.14.2 Worked example
289(1)
6.15 Survival Analysis module
289(4)
6.15.1 Analysis procedure
289(2)
6.15.2 Worked example
291(2)
7 Conclusion
293(2)
Glossary 295(2)
References 297(6)
Index 303
Simon T. Bate is a Principal Statistician at GlaxoSmithKline, supporting pre-clinical research. He has spent over 12 years supporting the design and statistical analysis of animal experiments, including drug discovery research, toxicology studies and safety assessment. He presents many statistics courses around Europe, including the statistics module of the British Association for Psychopharmacology's Pre-Clinical Certificate. Robin A. Clark is a Senior Analyst Programmer at Huntingdon Life Sciences, Alconbury. Originally qualified as a marine ecologist, he is now a software architect producing data collection and statistical applications for the pharmaceutical industry. Robin produced the WindowsTM GUI and designed the system architecture for InVivoStat.
Biežāk uzdotie jautājumi par e-grāmatām Biežāk uzdotie jautājumi par e-grāmatām
Permanent link: https://www.kriso.lv/db/97811077794956e.html
Keywords: