Book contents
- Frontmatter
- Contents
- List of figures
- List of tables
- List of panels
- Preface
- Part I Elementary statistical analysis
- Chapter 1 Introduction
- Chapter 2 Descriptive statistics
- Chapter 3 Correlation
- Chapter 4 Simple linear regression
- Part II Samples and inductive statistics
- Part III Multiple linear regression
- Part IV Further topics in regression analysis
- Part V Specifying and interpreting models: four case studies
- Appendix A The four data sets
- Appendix B Index numbers
- Bibliography
- Index of subjects
- Index of names
Chapter 2 - Descriptive statistics
Published online by Cambridge University Press: 05 June 2012
- Frontmatter
- Contents
- List of figures
- List of tables
- List of panels
- Preface
- Part I Elementary statistical analysis
- Chapter 1 Introduction
- Chapter 2 Descriptive statistics
- Chapter 3 Correlation
- Chapter 4 Simple linear regression
- Part II Samples and inductive statistics
- Part III Multiple linear regression
- Part IV Further topics in regression analysis
- Part V Specifying and interpreting models: four case studies
- Appendix A The four data sets
- Appendix B Index numbers
- Bibliography
- Index of subjects
- Index of names
Summary
This chapter presents an introduction to the key elements of descriptive statistics: the ways in which quantitative information can be presented and described. The first step in the analysis of quantitative data is its organization and presentation in tables and graphs. The basic features of the data – such as its central or most common values and the way the observations are distributed around these central values – can then be summarized in various ways.
Presentation of numerical data
Frequency distributions
Quantitative data in their raw form consist of a series of numbers or categories. For example, the Poor Law data on per capita relief expenditure in 1831 by the 24 parishes in Kent could be set out in its original sequence as in table 2.1, with the data rounded to one decimal place.
Even with 24 observations it is difficult to get much sense of the data in this form. It would help a little if the values were arranged in ascending or descending order of magnitude (known as an array). This would immediately show the highest and lowest values and give some indication of the most common level of payment, but with a large number of observations it would still be hard to interpret the information in this form.
- Type
- Chapter
- Information
- Making History CountA Primer in Quantitative Methods for Historians, pp. 33 - 70Publisher: Cambridge University PressPrint publication year: 2002