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

CASE STUDY Illustration that the sample variance is a biased estimate of the population variance

Consider the population which consists of four counters marked zero, one, two, and three.

The mean score of the counters is equal to 0+1+2+3 divided by four because 6/4 = 1.5. The population mean therefore equals 1.5.

The variance of the population equals the sum total of all the deviations of population members from the population mean, squared and then divided by n. The population variance is the 1.25.

Consider all the samples of size 2 can be taken from this population the variances of all these samples of size two are shown in the table below.

Table 1: Variances of all the samples of size two from the population of 4 items numbered 0–3, using n as denominator of the computation

First counter 0 1 2 3
0 0 0.25 1 2.25
1 0.25 0 0.25 1
2 1 0.25 0 0.25
3 2.25 1 0.25 0

The mean variance of all the samples equals ∑(variances)/number of samples = 10/16 0.625.

This is not the same as the population variance therefore any sample variance will give us a biased estimate of the population variance. However this bias can be rectified if, instead of dividing by n when calculating the sample variances, we divide by n–1 (see Table 2).

Table 2: Variances of all the samples of size two from the population of 4 items numbered 0–3, using n-1 as denominator of the computation

First counter 0 1 2 3
0 0 0.5 2 4.5
1 0.5 0 0.5 2
2 2 0.5 0 0.5
3 4.5 2 0.5 0

The mean variance of all the samples equals ∑(variances)/number of samples = 20/16 = 1.25

Top

Return to Hypothesis testing (Section 8.3.13)