Scribd
Upload
6 views2 pages

Systematic Sampling Notes

Systematic sampling is a probability method where a random start is selected, and every a-th element is chosen from a population list. The efficiency of this method depends on the ordering of the population, with variance influenced by the homogeneity of the samples. It can be more or less efficient than simple random sampling, and the measure of homogeneity (δ) is crucial for comparison.

Uploaded by

rastifaizurrehman
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
6 views2 pages

Systematic Sampling Notes

Systematic sampling is a probability method where a random start is selected, and every a-th element is chosen from a population list. The efficiency of this method depends on the ordering of the population, with variance influenced by the homogeneity of the samples. It can be more or less efficient than simple random sampling, and the measure of homogeneity (δ) is crucial for comparison.

Uploaded by

rastifaizurrehman
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

SYSTEMATIC SAMPLING – EXAM REVISION NOTES

1. Definition of Systematic Sampling


Systematic sampling is a probability sampling method in which only one random start is
selected, and then every a-th element is chosen from the population list. The number a is
called the sampling interval.

Procedure
1 Arrange the population units in some order.
2 Choose the sampling interval a = N / n.
3 Select a random start r from {1, 2, …, a}.
4 Select units: r, r+a, r+2a, … until the sample is complete.

2. Estimator under Systematic Sampling


Let y■ be the value of the study variable for unit k. The population total is t = Σ y■. Under
systematic sampling, the unbiased estimator of the population total is:
t■ = a · t■, where t■ is the total of the selected systematic sample.

3. Variance of the Estimator


The variance of the estimator depends on how similar or dissimilar the values are within each
systematic sample.
Variance expression:
VSY(t■) = (N² / n) S²yU [ (1 − f) + (n − 1) δ ]
where:
f = n / N (sampling fraction)
S²yU = population variance
δ = measure of homogeneity within systematic samples

4. Comparison with Simple Random Sampling (SRS)


Variance under simple random sampling (SI):
VSI(t■) = N² (1 − f) S²yU / n
Design Effect:
deff(SY) = VSY / VSI = 1 + [(n − 1) / (1 − f)] δ
• If δ < 0 → Systematic sampling is more efficient than SRS.
• If δ > 0 → SRS is more efficient.

5. Controlling the Sample Size


Let N = n a + c, where 0 ≤ c < a.
• If c = 0 → sample size is exactly n.
• If c > 0 → sample size can be either n or n + 1.
Thus, systematic sampling may not always give a fixed sample size unless N is a multiple of n.

6. Efficiency of Systematic Sampling


The efficiency of systematic sampling depends on the ordering of the population.
• If neighboring units have similar values → samples are homogeneous → variance is large →
low efficiency.
• If neighboring units are very different → samples are heterogeneous → variance is small →
high efficiency.
Systematic sampling works best when the population is ordered randomly or cyclically.

7. Homogeneity Measure (δ)


δ measures how similar elements are within the same systematic sample.
Range of δ:
δmin = −(a − 1)/(N − a) (maximum heterogeneity)
δmax = 1 (complete homogeneity)

8. Key Exam Points


1 Only one random start is required.
2 Estimator of total is t■ = a t■.
3 Efficiency depends on population ordering.
4 Systematic sampling can be better or worse than SRS.
5 Always mention δ when comparing efficiencies.

You might also like