RESEARCHING THE REAL WORLD



MAIN MENU

Basics

Orientation Observation In-depth interviews Document analysis and semiology Conversation and discourse analysis Secondary Data Surveys Experiments Ethics Research outcomes
Conclusion

References

Activities

Social Research Glossary

About Researching the Real World

Search

Contact

© Lee Harvey 2012–2024

Page updated 8 January, 2024

Citation reference: Harvey, L., 2012–2024, Researching the Real World, available at qualityresearchinternational.com/methodology
All rights belong to author.


 

A Guide to Methodology

8. Surveys

8.1 Introduction to surveys
8.2 Methodological approaches
8.3 Doing survey research
8.4 Statistical Analysis

8.4.1 Descriptive statistics
8.4.2 Exploring relationships
8.4.3 Analysing samples

8.4.3.1 Generalising from samples
8.4.3.2 Dealing with sampling error
8.4.3.3 Confidence limits
8.4.3.4 Statistical significance
8.4.3.5 Hypothesis testing
8.4.3.6 Significance tests
8.4.3.7 Summary of significance testing and association: an example

8.4.4 Report writing

8.5 Summary and conclusion

8.4.3.1 Generalising from samples
The analysis of survey data undertaken so far has not attempted to make generalisations to wider populations from which the samples were taken. It is important to be aware that the data is for a sample, not a population, and analysis so far is about the sample.

One cannot simply transfer results for a sample onto the population from which it is drawn. Even representative samples are not identical replicas of the population but are liable to variation due to sampling error. The bigger the sampling error the less accurate your sample will be in estimating values for the population.

If the sample is not a representative sample (see Section 8.3.9) then it will be biased as well.

So making statements about wider populations must be done with care. It is important to be aware of both bias and sampling error when generalising about populations from samples.

There are a set of statistical procedures that enable accurate estimates of the impact of sampling error on random samples. These are called confidence limits and significance tests and are discussed in Section 8.4.3.3 and Section 8.4.3.4.

The other thing that to be aware of at this stage of the analysis is that although a relationship between two variables might have been identified, it is not possible to say how strong that relationship is on the basis of the analysis so far. Measuring the degree or extent of a relationship or an association can be done statistically (see Section 8.4.2.1).

 

Next 8.4.3.2 Dealing with sampling error

Top