3.2 Disease causation
3.3 Host determinants
3.3.1 Age
3.3.2 Sex
3.3.3 Species and breed
3.3.4 Size and conformation
3.3.5 Immunity
3.4 Agent determinants
3.5 Environmental determinants of disease
3.6 Transmission of infection
3.6.1 Sources of infection
3.6.2 Shedding of agent
3.6.3 Mode of transmission
3.6.4 Invasion of the host
3.7 Animal performance
3.8 Types of variables and scales
3.9 Variation in observations
3.10 Descriptive analysis of qualitative and quantitative variables
3.11 Data levels

4 Observational Studies
4.1 Introduction
4.2 Design of epidemiological studies
4.3 Cross-sectional study
4.4 Cohort study
4.5 Case–control study
4.6 Other observational study designs

4.6.1 Cross-sectional study with follow-up
4.6.2 Nested case–control study
4.6.3 Repeated cross-sectional study
4.7 Further reading

5 Experimental Studies
5.1 Introduction
5.2 Design of experimental studies
5.3 Full factorial designs
5.3.1 Parallel group design
5.3.2 Factorial design
5.4 Fractional factorial designs
5.4.1 Latin and Graeco-Latin square design
5.5 Split-plot and strip-plot designs
5.6 Cross-over design
5.7 Clinical trials, laboratory experiments and ﬁeld trials
5.7.1 Laboratory experiments
5.7.2 Clinical trials
5.7.3 Field trials
5.8 Further reading

6 Measures of Disease Frequency
6.1 Introduction
6.2 Proportions and rates
6.3 Prevalence
6.4 Incidence
6.4.1   Incidence risk
6.4.2   Incidence rate
6.4.3   The relationship between incidence rate and incidence risk
6.4.4   Extending the time period
6.4.5   Dynamic populations
6.4.6   Incidence rate or incidence risk?
6.4.7   Prevalence and incidence
6.5 Other measures
6.6 Further reading

7 Measures of Association and Effect
7.1 Introduction
7.2 The 2 × 2 table

7.3 Measures of association
7.3.1   Risk and relative risk
7.3.2   Odds and odds ratio
7.4 Measures of effect
7.5 Summary of measures

8 Sample Size and Sampling Methods
8.1 Introduction
8.2 Sampling for a survey
8.2.1   Sample size to estimate a mean
8.2.2   Sample size to estimate a proportion
8.3 Sampling to detect disease
8.4 Sampling to detect a difference between groups
8.4.1   The power of a hypothesis test
8.4.2   Sample size to test a difference between means
8.4.3   Sample size to test a relative risk
8.4.4   Sample sizes in case–control studies
8.5 Sampling and allocation methods
8.5.1   Simple random sampling
8.5.2   Systematic random sampling
8.5.3   Stratiﬁed random sampling
8.5.4   Cluster sampling
8.5.5   Multistage sampling
8.5.6   Non-probability sampling
8.5.7   Combinations of sampling methods
8.5.8   Block randomisation

8.6 Further reading

9 Evaluating Diagnostic Tests
9.1 Introduction
9.2 Types of tests
9.3 Performance measures: Sensitivity, speciﬁcity and predicitive values

9.4 True and apparent prevalences
9.5 Performance measures for tests with continuous outcome
9.5.1   Cut-off values
9.5.2   Differential positive rate
9.5.3   ROC analysis
9.6 Multiple testing
9.7 Sensitivity and speciﬁcity at the herd level
9.8 Further reading

10 Data Management

10.1 Introduction
10.2 Primary observation, measurement and data recording
10.3 Sources of data
10.3.1 Governmental veterinary institutions and organisations
10.3.2 Veterinary practices
10.3.3 Slaughterhouses – meat inspection
10.3.4 Agricultural organisations and farm records
10.4 Database structure
10.5 Data quality
10.5.1 Clinical data
10.5.2 Pathological data
10.5.3 Laboratory data
10.5.4 Medicine consumption
10.5.5 Production data
10.5.6 Demographic data
10.5.7 Risk factors
10.6 Data control
10.7 Data editing
10.8 Examples of databases with information on Danish farm animals
10.8.1 Central Farm Animal Register (in Danish: Centrale HusdyrbrugsRegister, CHR-register)
10.8.2 Vetstat
10.8.3 DANMAP – Danish Integrated Antimicrobial Resistance Monitoring and Research Program

10.8.4 Danish Cattle Database (in Danish: ‘Kvægdatabasen’)
10.8.5 Danish register on bovine virus diarrhoea virus
10.8.6 The Danish SPF Company Database (speciﬁc pathogen-free pigs)
10.8.7 The PRRS Database (porcine reproductive and respiratory syndrome)     (pigs)
10.8.8 The database for mandatory meat inspection recordings (pigs)
10.8.9 The Zoonosis Register (pigs)
10.8.10           The Efﬁciency Control (pigs)
10.8.11           The Ante Mortem Database (poultry)
10.8.12           The Post Mortem Database (poultry)
10.8.13           The Salmonella Database (poultry)
10.8.14           The Efﬁciency Control Database (poultry)
10.8.15           Project databases
10.9    Further reading
10.10 Acknowledgements

11 Bias and Interaction

11.1 Introduction
11.2 Bias
11.2.1 Selection bias
11.2.2 Information bias
11.2.3 Confounding bias
11.3 Interaction

12 Questionnaires
12.1    Introduction
12.2    Types of questionnaires and communication forms
12.2.1 Questionnaire types
12.2.2 Communication forms
12.3    Types of questions and scales of measurement
12.4    Constructing the questionnaire
12.4.1 Pre-coding of answers in structured questionnaires
12.4.2 Pre-testing
12.5    Obtaining the information
12.6    Bias related to questionnaires
12.6.1 Selection bias
12.6.2 Information bias
12.7    Validity of questionnaire data
12.8    Perspectives and applicability of questionnaires in the dialogue between farmers and advisors
12.9    Acknowledgement

13 Data Analysis
13.1    Introduction
13.2    Introduction to hypothesis testing
13.3    Selection of statistical test
13.4    Analysis of a continuous outcome
13.4.1 Comparison of a mean with a given value
13.4.2 Comparison of means for two independent groups: t-test
13.4.3 Comparison of means for two dependent groups: paired t-test
13.4.4 Comparison of means for more than two groups: analysis of variance (ANOVA)
13.4.5 Correlation
13.4.6 Linear regression
13.5    Analysis of a dichotomous outcome
13.5.1 Comparison of a proportion with a given value
13.5.2 Comparison of proportions for independent groups: Fisher exact test and χ ²-test
13.5.3 Comparison of paired proportions: McNemar test
13.5.4 Logistic regression
13.5.5 Logistic analysis
13.6    Model control
13.6.1 Model control of analyses of a continuous outcome
13.6.2 Model control of analyses of a dichotomous outcome
13.7    Model reduction
13.8 Confounding and interaction
13.8.1 Confounding
13.8.2 Interaction
13.8.3 The relationship between confounding and interaction
13.9 Measuring agreement
13.9.1 Agreement for qualitative variables: Cohen’s kappa (κ )
13.9.2 Agreement for quantitative variables: Bland–Altman plot
13.10 Overview of statistical analyses
13.11 Further reading

Appendix A: Exercises
Answers to Exercises

Appendix B: Biostatistics
B.1 Introduction

B.2 The normal distribution
B.3 The binomial distribution

Appendix C: Statistical Tables
C.1 The normal distribution
C.2 The t distribution

C.3 The χ ²-distribution
C.4 The F-distribution

Appendix D: Data Sets for the Examples in Chapter 13

Appendix E: SAS-code and Output for the Examples in Chapter 13

Appendix F: R-code and Output for the Examples in Chapter 13