Statistics in geography and environmental science / Richard Harris, Claire Jarvis.

Includes bibliographical references and index.

Machine generated contents note: 1.Data, statistics and geography
Chapter overview
Learning objectives
1.1.Statistics: a brief introduction
1.2.Why you should study statistics
1.3.Types of statistic
1.4.Analysis and error
1.5.Geographical data and analysis
1.6.Some problems when analysing geographical data
Key points
References
2.Descriptive statistics
2.1.Data and variables
2.2.Simple ways to make sense of and present data
2.3.Some useful notation
2.4.A second data set
2.5.Measures of central tendency
2.6.Some measures of spread and variation
2.7.Presenting the centre and spread of data
2.8.Types of numeric data
2.9.Conclusion
3.The normal curve
3.1.Introducing the normal curve
3.2.Models, error and uncertainty
3.3.Why are the data [approximately] normal?
Contents note continued: 3.4.Important properties of a normal curve
3.5.An experiment
3.6.Probability and the normal curve
3.7.Worked examples
3.8.z values and the standard normal curve
3.9.Signs of non-normality
3.10.Moments of a distribution
3.11.The quantile plot
3.12.Conclusion
4.Sampling
4.1.Introduction
4.2.The process of sampling, phase 1: scope and scale
4.3.The process of sampling, phase 1: issues
4.4.The process of sampling, phase 2: sampling method
4.5.Sampling methods: issues and practicalities
5.From description to inference
5.1.About inference
5.2.A measure of unreliability
5.3.What is a population?
5.4.A geographical example
5.5.A thought experiment
5.6.Why the thought experiment is useful
5.7.Calculating the standard error
5.8.Confidence intervals
Contents note continued: 5.9.Consolidation and worked examples
5.10.Finding a 99.9% or any other confidence interval
5.11.Calculating a confidence interval for a small sample
5.12.Conclusion
6.Hypothesis testing
6.1.Detecting difference
6.2.Hypothesis testing and the one-sample t test
6.3.One-tailed tests of difference
6.4.Power, error and research design
6.5.The two-sample t test and the F test
6.6.Additional notes about the t test
6.7.Analysis of variance
6.8.Non-parametric tests
6.9.Conclusion: from detection to explanation
7.Relationships and explanations
7.1.Looking for relationships
7.2.Using scatter plots
7.3.Independent and dependent variables
7.4.Correlation
7.5.Complications with the correlation coefficient
7.6.Bivariate [two-variable] regression
Contents note continued: 7.7.Interpreting regression analysis
7.8.Assumptions of regression analysis
7.9.Checking the residuals
7.10.What to do if the residuals do not meet the regression assumptions
7.11.Multiple regression
7.12.Interpreting multiple regression
7.13.Assumptions of multiple regression
7.14.Partial regression plots
7.15.A strategy for multiple regression
7.16.The strength of the effects and the problem of `too much power'
7.17.Using the F test to compare regression models
7.18.Uses of regression
7.19.Other types of regression model
8.Detecting and managing spatial dependency
8.1.Introduction
8.2.Why does spatial dependency matter in the context of quantitative geographical analyses?
8.3.Looking for spatial autocorrelation
8.4.Global measures of spatial autocorrelation
8.5.Other measures of global autocorrelation
8.6.Conclusion
Contents note continued: Key points
9.Exploring spatial relationships
9.1.Introduction
9.2.Mapping with cartograms
9.3.Spatial analysis and spatial autocorrelation
9.4.Who's my neighbour? Defining a weights matrix
9.5.Spatial error model
9.6.Spatial lagged y model
9.7.Geographically weighted regression [GWR]
9.8.Local indicator of spatial association [LISA]
9.9.Modelling at multiple scales
9.10.Geography, computation and statistics
References.