Introduction to Research Methods and Data Analysis in the Health Sciences by Hagger-Johnson, Gareth -- Read -- Imperial Library of Trantor

Index

Cover Half Title Title Page Copyright Page Dedication Table of Contents List of figures List of tables List of boxes Acknowledgements Part I Introduction

1 Evidence-based health research

Preliminary exercise and installing R How to install the R program Answers to the formative numeracy exercise using R Further reading

PART II Critical numbers

2 Descriptive statistics part 1: levels of measurement and measures of central tendency

Intended learning outcomes Introducing key terms Levels of measurement Why is determining the level of measurement important? Are levels of measurement potentially misleading?

3 Descriptive statistics part 2: measures of dispersion

Intended learning outcomes Mean Sample and population mean Median Mode Range The normal distribution Other kinds of distributions Measures of dispersion Transformations Summary

4 Measures of association for categorical outcomes

Introduction Intended learning outcomes Risk and odds Calculating absolute risk Number needed to treat (NNT) and number needed to harm (NNH) Odds ratios Summary

5 Measures of association for continuous outcomes

Intended learning outcomes Differences between two means Summary

6 Confounding, effect modification, mediation and causal inference

Intended learning outcomes Introducing key terms Confounding variables Effect modifying variables Mediating variables Antecedent variables Causal variables

PART III Critical appraisal of existing research

7 Literature reviewing and database searching

Intended learning outcomes Narrative reviews of the literature Systematic reviews of the literature Social networking approaches to searching the literature Bibliographic software Summary Web links

8 Randomised controlled trials

Intended learning outcomes Introducing key terms A cognitive behavioural intervention to reduce sexually transmitted infections among gay men: randomised trial Effect on smoking quit rate of telling patients their lung age: the Step2quit randomised controlled trial Effect of physical activity on cognitive function in older adults at risk for Alzheimer’s disease: a randomised trial Summary

9 Cohort studies

Intended learning outcomes What are the essential features of a cohort study? Environmental tobacco smoke and tobacco related mortality in a prospective study of Californians, 1960–98 Joint effect of cigarette smoking and alcohol consumption on mortality Institutional risk factors for norovirus outbreaks in Hong Kong elderly homes: a retrospective cohort study Cohorts do not need to represent populations: a note about internal and external validity of cohort studies Summary

10 Case-control studies

Intended learning outcomes What are the essential features of a case-control study? Introducing key terms Pet birds and risk of lung cancer in Sweden: a case-control study Association between maternal sleep practices and risk of late stillbirth: a case-control study Mobile phone use and brain tumors in children and adolescents: a multicentre case-control study Summary

11 Research ethics and data management

Intended learning outcomes Introducing key terms Practical example of an IRAS application Questionnaires Data management Summary

PART IV Conducting new research

12 Dissemination and publication

Intended learning outcomes Types of published writing The structure of original research articles Choosing a journal

13 Linear regression for continuous outcomes

Intended learning outcomes Introducing key terms The linear regression equation The method of least squares Linear regression in R What do the regression coefficients mean? Interpreting the output The F-statistic and equivalence to ANOVA Standardising predictor variables Regression using centred age Multiple linear regression Running a multiple regression in R Hierarchical multiple regression Categorical predictor variables Adjusting for possible mediators to evaluate attenuation of an effect Adding interaction terms to evaluate effect modification R-squared Checking assumptions Transforming variables Outcome variables with a preponderance of zeros Non-normality in outcome variables Standardised regression coefficients Summary Further reading

14 Logistic regression for categorical outcomes

Intended learning outcomes Why linear regression is not suitable for dichotomous outcomes Introducing logistic regression Preparing for logistic regression The logistic regression equation Recap: log odds, odds, probability Getting started with logistic regression Results from a simple logistic regression model Comparing the goodness of fit of two logistic regression models: loglikelihood test Identifying whether a variable significantly improves fit of the model: Wald test Obtaining predicted probabilities Summary Further reading

Appendix 1: Critical values for the t-test Appendix 2: Critical values for the F-test Appendix 3: Table of z-values Appendix 4; T/U table for Mann Whitney U test Appendix 5: Critical values for the Wilcoxon test Appendix 6: Consent form Appendix 7: Statistical power Appendix 8: Validity and bias Glossary References Index

← Prev
Back
Next →

← Prev
Back
Next →