You are on page 1of 17

Sampling

• Sample definition
• Purpose of sampling
• Sampling Size
• Stages in the selection of a sample
• Types of sampling in quantitative researches
What is and Why Sampling?

❑ The process of selecting a number of individuals for a study in such a


way that the individuals represent the larger group from which they
were selected
❑ The population is dynamic, i.e. the component of the population could
change over time. Thus, it is practically impossible to check all items in
the population.
❑ The cost of studying the entire population could be very high. A sample
study is usually less expensive than a census study.
❑ Contacting the whole population would often be time-consuming.
Sampling can save time as the results can be produced at a relatively
faster speed.

Business Research Methods All Rights Reserved


© Oxford Fajar Sdn. Bhd. (008974-T), 2012 9– 3
Taking sample and using the results to make generalisation or
make inferences to samples of the population from which the
sample is taken from.
Determining the Sample Size

Level of Confidence
❑ The level of confidence denotes how certain we are
that our estimates will really hold true for the
population.
Sample Data, Precision and Confidence in
Estimation
❑ Precision and confidence play a vital role in
sampling as we use sample data to draw inferences
about the entire population.

Business Research Methods All Rights Reserved


© Oxford Fajar Sdn. Bhd. (008974-T), 2012 9– 5
Sample Size

❑ Implications if sample size too small? Too large?


❑ Some GRoT Recommendations form Literature
– Roscoe (1975): 30 to 500
– Roscoe (1975): Several times more (al least 10x) than variables
– Hair et al (1998): 15x to 20x number of IVs
❑ Krejcie and Morgan (1970): Refer Table (95% Level of Confidence)
❑ Gpower Analysis (Faul & Erdfelfer, 1992)
– Scientific approach based on Type I and II errors analysis

Business Research Methods All Rights Reserved


© Oxford Fajar Sdn. Bhd. (008974-T), 2012 9– 6
Gpower (Paper)

❑ Input Parameters (Example)


– Test Family = f-test
– Type of power analysis = Priori
– Effect size f-square =
– Alpha Criteria = 0.20
– Power Index = 0.80 (min. suggested)
– Number of predictor

Business Research Methods All Rights Reserved


© Oxford Fajar Sdn. Bhd. (008974-T), 2012 9– 7
Sampling Techniques

Sampling is the process of selecting a sufficient number of elements from


the population, so that a study of the sample and understanding of its
properties or characteristics would make it possible for us to generalize
such properties or characteristics to the population elements.

A sample is “a smaller (but hopefully representative) collection of units


from a population used to determine truths about that population” (Field,
2005)

Business Research Methods All Rights Reserved


© Oxford Fajar Sdn. Bhd. (008974-T), 2012 9– 9
Business Research Methods All Rights Reserved
© Oxford Fajar Sdn. Bhd. (008974-T), 2012 9– 10
Business Research Methods All Rights Reserved
© Oxford Fajar Sdn. Bhd. (008974-T), 2012 9– 11
Business Research Methods All Rights Reserved
© Oxford Fajar Sdn. Bhd. (008974-T), 2012 9– 12
The population is divided into two or more groups called strata,
according to some criterion,
Selected such as geographic
Probability Sampling location,
Method grade level,
age, or income, and subsamples are randomly selected from each strata.

Business Research Methods All Rights Reserved


© Oxford Fajar Sdn. Bhd. (008974-T), 2012 9– 13
Business Research Methods All Rights Reserved
© Oxford Fajar Sdn. Bhd. (008974-T), 2012 9– 14
Business Research Methods All Rights Reserved
© Oxford Fajar Sdn. Bhd. (008974-T), 2012 9– 15
Business Research Methods All Rights Reserved
© Oxford Fajar Sdn. Bhd. (008974-T), 2012 9– 16
You may refer to relevant text and
literature for all other methods.

Business Research Methods All Rights Reserved


© Oxford Fajar Sdn. Bhd. (008974-T), 2012 9– 17

You might also like