| |
| |
Preface | |
| |
| |
| |
Basic Principles of Experimentation | |
| |
| |
| |
Introduction | |
| |
| |
| |
Field and glasshouse experiments | |
| |
| |
| |
Choice of site | |
| |
| |
| |
Soil testing | |
| |
| |
| |
Satellite mapping | |
| |
| |
| |
Sampling | |
| |
| |
| |
Basic Statistical Calculations | |
| |
| |
| |
Introduction | |
| |
| |
| |
Measurements and type of variable | |
| |
| |
| |
Samples and populations | |
| |
| |
| |
Basic Data Summary | |
| |
| |
| |
Introduction | |
| |
| |
| |
Frequency distributions (discrete data) | |
| |
| |
| |
Frequency distributions (continuous data) | |
| |
| |
| |
Descriptive statistics | |
| |
| |
| |
The Normal Distribution, the t-Distribution and Confidence Intervals | |
| |
| |
| |
Introduction to the normal distribution | |
| |
| |
| |
The standard normal distribution | |
| |
| |
| |
Further use of the normal tables | |
| |
| |
| |
Use of the percentage points table (Appendix 2) | |
| |
| |
| |
The normal distribution in practice | |
| |
| |
| |
Introduction to confidence intervals | |
| |
| |
| |
Estimation of the population mean, [mu] | |
| |
| |
| |
The sampling distribution of the mean | |
| |
| |
| |
Confidence limits for [mu] when [sigma] is known | |
| |
| |
| |
Confidence limits for [mu] when [sigma] is unknown--use of the t-distribution | |
| |
| |
| |
Determination of sample size | |
| |
| |
| |
Estimation of total crop yield | |
| |
| |
| |
Introduction to Hypothesis Testing | |
| |
| |
| |
The standard normal distribution and the t-distribution | |
| |
| |
| |
The single sample t-test | |
| |
| |
| |
The P-value | |
| |
| |
| |
Type I and Type II errors | |
| |
| |
| |
Choice of level of significance | |
| |
| |
| |
The usefulness of a test | |
| |
| |
| |
Estimation versus hypothesis testing | |
| |
| |
| |
The paired samples t-test | |
| |
| |
| |
Comparison of Two Independent Sample Means | |
| |
| |
| |
Introduction | |
| |
| |
| |
The Independent Samples t-test | |
| |
| |
| |
Confidence intervals | |
| |
| |
| |
The theory behind the t-test | |
| |
| |
| |
The F-test | |
| |
| |
| |
Unequal sample variances | |
| |
| |
| |
Determination of sample size for a given precision | |
| |
| |
| |
Linear Regression and Correlation | |
| |
| |
| |
Basic principles of Simple Linear Regression (SLR) | |
| |
| |
| |
Experimental versus observational studies | |
| |
| |
| |
The correlation coefficient | |
| |
| |
| |
The least squares regression line and its estimation | |
| |
| |
| |
Calculation of residuals | |
| |
| |
| |
The goodness of fit | |
| |
| |
| |
Calculation of the correlation coefficient | |
| |
| |
| |
Assumptions, hypothesis tests and confidence intervals for simple linear regression | |
| |
| |
| |
Testing the significance of a correlation coefficient | |
| |
| |
| |
Curve Fitting | |
| |
| |
| |
Introduction | |
| |
| |
| |
Polynomial fitting | |
| |
| |
| |
Quadratic regression | |
| |
| |
| |
Other types of curve | |
| |
| |
| |
Multiple linear regression | |
| |
| |
| |
The Completely Randomised Design | |
| |
| |
| |
Introduction | |
| |
| |
| |
Design construction | |
| |
| |
| |
Preliminary analysis | |
| |
| |
| |
The one-way analysis of variance model | |
| |
| |
| |
Analysis of variance | |
| |
| |
| |
After ANOVA | |
| |
| |
| |
Reporting results | |
| |
| |
| |
The completely randomised design--unequal replication | |
| |
| |
| |
Determination of number of replicates per treatment | |
| |
| |
| |
The Randomised Block Design | |
| |
| |
| |
Introduction | |
| |
| |
| |
The analysis ignoring blocks | |
| |
| |
| |
The analysis including blocks | |
| |
| |
| |
Using the computer | |
| |
| |
| |
The effect of blocking | |
| |
| |
| |
The randomised blocks model | |
| |
| |
| |
Using a hand calculator to find the sums of squares | |
| |
| |
| |
Comparison of treatment means | |
| |
| |
| |
Reporting the results | |
| |
| |
| |
Deciding how many blocks to use | |
| |
| |
| |
Plot sampling | |
| |
| |
| |
The Latin Square Design | |
| |
| |
| |
Introduction | |
| |
| |
| |
Randomisation | |
| |
| |
| |
Interpretation of computer output | |
| |
| |
| |
The Latin square model | |
| |
| |
| |
Using your calculator | |
| |
| |
| |
Factorial Experiments | |
| |
| |
| |
Introduction | |
| |
| |
| |
Advantages of factorial experiments | |
| |
| |
| |
Main effects and interactions | |
| |
| |
| |
Varieties as factors | |
| |
| |
| |
Analysis of a randomised blocks factorial experiment with two factors | |
| |
| |
| |
General advice on presentation | |
| |
| |
| |
Experiments with more than two factors | |
| |
| |
| |
Confounding | |
| |
| |
| |
Fractional replication | |
| |
| |
| |
Comparison of Treatment Means | |
| |
| |
| |
Introduction | |
| |
| |
| |
Treatments with no structure | |
| |
| |
| |
Treatments with structure (factorial structure) | |
| |
| |
| |
Treatments with structure (levels of a quantitative factor) | |
| |
| |
| |
Treatments with structure (contrasts) | |
| |
| |
| |
Checking the Assumptions and Transformation of Data | |
| |
| |
| |
The assumptions | |
| |
| |
| |
Transformations | |
| |
| |
| |
Missing Values and Incomplete Blocks | |
| |
| |
| |
Introduction | |
| |
| |
| |
Missing values in a completely randomised design | |
| |
| |
| |
Missing values in a randomised block design | |
| |
| |
| |
Other types of experiment | |
| |
| |
| |
Incomplete block designs | |
| |
| |
| |
Split Plot Designs | |
| |
| |
| |
Introduction | |
| |
| |
| |
Uses of this design | |
| |
| |
| |
The skeleton analysis of variance tables | |
| |
| |
| |
An example with interpretation of computer output | |
| |
| |
| |
The growth cabinet problem | |
| |
| |
| |
Other types of split plot experiment | |
| |
| |
| |
Repeated measures | |
| |
| |
| |
Comparison of Regression Lines and Analysis of Covariance | |
| |
| |
| |
Introduction | |
| |
| |
| |
Comparison of two regression lines | |
| |
| |
| |
Analysis of covariance | |
| |
| |
| |
Analysis of covariance applied to a completely randomised design | |
| |
| |
| |
Comparing several regression lines | |
| |
| |
| |
Conclusion | |
| |
| |
| |
Analysis of Counts | |
| |
| |
| |
Introduction | |
| |
| |
| |
The binomial distribution | |
| |
| |
| |
Confidence intervals for a proportion | |
| |
| |
| |
Hypothesis test of a proportion | |
| |
| |
| |
Comparing two proportions | |
| |
| |
| |
The chi-square goodness of fit test | |
| |
| |
| |
r [times] c contingency tables | |
| |
| |
| |
2 [times] c contingency tables: comparison of several proportions | |
| |
| |
| |
2 [times] 2 contingency tables: comparison of two proportions | |
| |
| |
| |
Association of plant species | |
| |
| |
| |
Heterogeneity chi-square | |
| |
| |
| |
Some Non-parametric Methods | |
| |
| |
| |
Introduction | |
| |
| |
| |
The Sign test | |
| |
| |
| |
The Wilcoxon single-sample test | |
| |
| |
| |
The Wilcoxon matched pairs test | |
| |
| |
| |
The Mann-Whitney U test | |
| |
| |
| |
The Kruskal-Wallis test | |
| |
| |
| |
Friedman's test | |
| |
| |
| |
The normal distribution function | |
| |
| |
| |
Percentage points of the normal distribution | |
| |
| |
| |
Percentage points of the t-distribution | |
| |
| |
| |
5 per cent points of the F-distribution | |
| |
| |
| |
2.5 per cent points of the F-distribution | |
| |
| |
| |
1 per cent points of the F-distribution | |
| |
| |
| |
0.1 per cent points of the F-distribution | |
| |
| |
| |
Percentage points of the sample correlation coefficient (r) when the population correlation coefficient is 0 and n is the number of X, Y pairs | |
| |
| |
| |
5 per cent points of the Studentised range, for use in Tukey and SNK tests | |
| |
| |
| |
Percentage points of the chi-square distribution | |
| |
| |
| |
Probabilities of S or fewer successes in the binomial distribution with n 'trials' and p = 0.5 | |
| |
| |
| |
Critical values of T in the Wilcoxon signed rank or matched pairs test | |
| |
| |
| |
Critical values of U in the Mann-Whitney test | |
| |
| |
References | |
| |
| |
Further reading | |
| |
| |
Index | |