Statistics in Toxicology Using R 1st edition by Ludwig Hothorn – Ebook PDF Instant Download/Delivery: 0367241421 , 9780367241421
Full download Statistics in Toxicology Using R 1st edition after payment
Product details:
ISBN 10: 0367241421
ISBN 13: 9780367241421
Author: Ludwig Hothorn
The apparent contradiction between statistical significance and biological relevance has diminished the value of statistical methods as a whole in toxicology. Moreover, recommendations for statistical analysis are imprecise in most toxicological guidelines. Addressing these dilemmas, Statistics in Toxicology Using R explains the statistical analysi
Statistics in Toxicology Using R 1st Table of contents:
Chapter 1 Principles
1.1 Evaluation of short-term repeated toxicity studies
1.2 Selected statistical problems
1.2.1 Data visualization by barcharts or boxplots?
1.2.2 How to present tests’ outcomes: Stars, letters, p-values, or confidence intervals?
1.2.3 Proof of hazard or proof of safety?
1.2.3.1 Decision making in toxicology
1.2.3.2 Be confident in negative results
1.2.3.3 Several two-sample comparisons or multiple comparisons versus control?
1.2.4 Sample size matters
1.2.5 Multiplicity occurs
1.2.6 Several types of endpoints occur
1.2.7 Directional decisions
1.2.8 Specific designs
1.2.9 Mixing distribution and outliers
1.2.10 The phenomenon of conflicting decisions
1.2.11 Decision tree approaches
1.2.12 The special importance of control groups
1.2.13 Statistical significance and biological relevance
1.3 Proof of hazard using two-sample comparisons
1.3.1 Normal distributed continuous endpoints
1.3.2 Log-normal distributed continuous endpoints
1.3.3 Non-normal distributed continuous endpoints
1.3.4 Proportions
1.3.5 Counts
1.3.6 Further endpoint types
Chapter 2 Simultaneous comparisons versus a negative control
2.1 Proof of hazard using simultaneous comparisons versus a negative control
2.1.1 Normally distributed continuous endpoints: The Dunnett procedure
2.1.1.1 The Dunnett procedure
2.1.1.1.1 Robustness
2.1.1.1.2 F-test and Dunnett procedure
2.1.2 Normally distributed continuous endpoints: The Williams procedure
2.1.2.1 Dunnett or Williams procedure?
2.1.2.2 A test when downturn effects at high doses seem possible
2.1.3 Normally distributed continuous endpoints: Ratio-to-control procedures
2.1.3.1 Procedures when variance heterogeneity occurs
2.1.4 Nonparametric approaches for comparisons versus a negative control
2.1.5 Simultaneous comparisons versus a negative control for proportions
2.1.5.1 Analysis of 2-by-k table data using the generalized linear model (GLM)
2.1.5.1.1 Dunnett-type test using a profile likelihood approach
2.1.5.2 Analysis of 2-by-k table data using exact procedures
2.1.5.3 Analysis of 2-by-k table data using adjusted cell estimates
2.1.5.4 Analysis of overdispersed proportions
2.1.5.4.1 Generalized mixed effect model
2.1.5.4.2 Generalized linear model with overdispersion
2.1.5.4.3 Arcsine square root transformation approaches
2.1.5.5 Analysis of multiple binary data
2.1.6 Trend tests for proportions
2.1.6.1 Cochran–Armitage trend test
2.1.6.2 Trend test with optimal dose scores
2.1.6.3 Williams-type test using GLM
2.1.6.4 Williams-type test using adjusted cell estimates
2.1.6.5 Williams-type test using a profile likelihood approach
2.1.6.6 Trend tests for proportions with possible overdispersion
2.1.7 Multinomial endpoints: Evaluation of differential blood count
2.1.8 Analysis of graded histopathological findings
2.1.8.1 Ordered categorical data trend test
2.1.9 Comparisons versus a negative control for transformed endpoints
2.1.10 Testing mixed responder/non-responder data
2.1.11 Testing non-inferiority: The evaluation of recovery period data
2.2 Trend tests
2.2.1 Aims and limitations
2.2.1.0.1 Trend test or non-linear model?
2.2.2 Closed testing procedure and order restriction
2.2.3 Trend tests for different endpoint types and different designs
2.3 Reference values
2.4 Analysis of complex designs
2.4.1 Analysis of interactions: Evaluation of sex by treatment interaction
2.4.2 Analysis of designs between one- and two-way layouts
2.4.3 Analysis of block designs
2.4.4 Analysis of covariance: Evaluation of organ weights
2.4.5 Repeated measures: Evaluation of body weights
2.4.5.1 Repeated measures: Inference for both treatment and time effects
2.5 Proof of safety
2.5.1 One-sided hypotheses: Test on non-inferiority
2.5.1.1 Test of significant toxicity
2.5.1.2 Proof of non-inferiority of poly-k estimates
2.5.2 Two-sided hypotheses: Test on equivalence
Chapter 3 Evaluation of long-term carcinogenicity assays
3.1 Principles
3.2 Analysis of mortality
3.2.1 Common NTP-style
3.2.2 A Williams-type trend test for the comparison of survival functions
3.3 Analysis of crude tumor rates
3.3.1 Analysis of crude tumor rates using a Williams-type test
3.3.2 Analysis of crude tumor rates using historical control data
3.4 Mortality-adjusted tumor rates with cause-of-death information
3.4.1 Analysis of incidental tumors
3.4.1.1 Further trend tests for stratified designs
3.4.2 Analysis of fatal tumors
3.5 Mortality-adjusted tumor rates without cause-of-death information
3.6 More complex analyzes
3.6.1 Multiple tumors
3.6.2 Multivariate response
3.6.3 The combined analysis over sex
3.6.4 Time-to-event data with litter structure
Chapter 4 Evaluation of mutagenicity assays
4.1 What is specific in the analysis of mutagenicity assays?
4.2 Evaluation of the Ames assay as an example for dose-response shapes with possible downturn effects
4.3 Evaluation of the micronucleus assay as an example for nonparametric tests in small sample size design
4.4 Evaluation of the SHE assay using trend tests on proportions
4.4.1 The Cochran–Armitage trend test for proportions
4.4.2 Trend tests followed by pairwise tests
4.4.3 Evaluation using Dunnett-type procedure for proportions
4.5 Evaluation of the in vivo micronucleus assay as an example of the analysis of proportions taking overdispersion into account
4.6 Evaluation of the in vivo micronucleus assay as an example of the analysis of counts taking overdispersion into account
4.7 Evaluation of HET-MN assay for an example of transformed count data
4.8 Evaluation of cell transformation assay for an example of near-to-zero counts in the control
4.8.1 Profile likelihood
4.8.2 FT-transformation
4.8.3 Zero-inflated Poisson model
4.9 Evaluation of the LLNA as an example for k-fold rule
4.10 Evaluation of the HET-MN assay using historical control data
4.11 Evaluation of a micronucleus assay taking the positive control into account
4.12 Evaluation of the Comet assay as an example for mixing distribution
4.13 Evaluation of the in vitro micronucleus assay as an example for comparing cell distributions
Chapter 5 Evaluation of reproductive toxicity assays
5.1 The statistical problems
5.2 Evaluation of the continuous endpoint pup weight
5.2.1 Possible simplification?
5.3 Evaluation of proportions
5.3.1 Possible simplification?
5.3.2 Analysis of multiple binary findings
5.4 Analysis of different-scaled multiple endpoints
5.5 Analysis of female-specific endpoints
5.6 Behavioral tests
5.6.1 Behavioral tests on selected pups
5.6.2 Behavioral tests with time-to-event data
5.6.3 Morris water maze test using juvenile rats
Chapter 6 Ecotoxicology: Test on significant toxicity
6.1 Proof of safety
6.2 Two-sample ratio-to-control tests
6.2.1 Two-sample ratio-to-control tests for non-inferiority for normal distributed endpoints, allowing heteroscedasticity
6.2.2 Two-sample ratio-to-control tests for proportions
6.3 Ratio-to-control tests for several concentrations
Chapter 7 Modeling of dose–response relationships
7.1 Models to estimate the EDxx
7.2 Benchmark dose estimation
7.2.0.1 BMD for continuous data
7.3 Is model selection toward LOAEL an alternative?
Chapter 8 Further methods
8.1 Toxicokinetics
8.2 Toxicogenomics
8.3 Evaluation of interlaboratory studies
Chapter 9 Conclusions
Appendix R Details
A.1 Selected packages containing specific statistical approaches
A.2 Packages containing toxicological data
A.3 Packages containing specific graphics and data manipulation
References
People also search for Statistics in Toxicology Using R 1st:
statistics in toxicology
how does toxicology use chemistry
how toxicology is used in forensics
a toxicology report
statistics for toxicology
Tags: Ludwig Hothorn, Toxicology Using, Statistics