3. Contents
Basic Terms & Concepts
Probability Sampling
The Qualities of a Probability Sample
Non-Probability Sampling
Sample Size
Types of Error
4. Basic Terms &
Concepts
Population
Basically, the universe of unit
from which the sample is to be
selected.
Sample
The segment of the population
that is selected for
investigation.
9. Basic Terms &
Concepts
Probability Sample
A sample that has been
selected using random
selection model.
Non-Probability Sample
A sample that has not been
selected using random selection
model.
10.
11. Basic Terms &
Concepts
Sampling Error
The difference between a
sample and its population.
Non-Sampling Error
Difference between the
population and the sample that
arise either from deficiencies in
the sampling approach.
12. Basic Terms &
Concepts
Non Response
It occurs whenever some
members of the sample refuse
to cooperate.
Census
The enumeration of an entire
population.
14. Probality Sampling
Types of Probability Sampling
Simple
Random
Sampling
Systematic
Sampling
Stratified
Random
Sampling
Cluster
Random
Sampling
Multi-Stage
Cluster
Sampling
15. Simple Random Sampling
Here, a random sample is a subset of a statistical
population in which each member of the subset has an
equal probability of being chosen. A simple random
sample is meant to be an unbiased representation of a
group.
16. Systematic Sampling
where the elements are chosen from a target population
by selecting a random starting point and selecting other
members after a fixed ‘sampling interval’. Sampling
interval is calculated by dividing the entire population
size by the desired sample size.
18. Stratified Random Sampling
Sampling that involves the division of a population into
smaller groups known as strata. In stratified random
sampling or stratification, the strata are formed based on
members' shared attributes or characteristics
19. Cluster Sampling
where multiple clusters of people are created from a
population where they are indicative of homogeneous
characteristics and have an equal chance of being a part
of the sample. In this sampling method, a simple
random sample is created from the different clusters in
the population.
20. Multi Stage Cluster Sampling
Multistage sampling is the taking of samples in stages using smaller and smaller
sampling units at each stage. Multistage sampling can be a complex form of
cluster sampling because it is a type of sampling which involves dividing the
population into groups.
For example; Want to do a research on the sanitation of labor, participation of
female students in classroom etc.
23. The qualities of a probability sample
We can generalize findings derived
from a sample to the population. In
quantitative research to generalize
we can compare sample mean &
population mean.
The variation of the sample
means around the population
mean is the sampling error and is
measured using a statistic known
as the standard error of the mean.
We have to ensure equivalence in a
cross-cultural validation, a sample
that was representative of the
relevant target population.
24. Generalizing from a random sample to the
population
ABC company wants to measure the level of skill development, sample of 450 employees. As skill
development standard, number of training days completed in the previous 12 months is considered.
The mean number of trainings days undertaken by the sample (x) can be used to estimate the population
mean (𝜇). But with known margins of error.
Normal distribution technique.
Sample mean of ABC company is 6.7 days training per employee.
95% probability.
Standard deviation or standard error of the mean is 1.3.
25. The distribution of sample mean
-1.96 Population mean +1.96SE (Z value)
probability 0.4750
Numberofsample
Value of the mean
0.4750
Population mean will lie between:
• Sample mean+(1.96*standard error)
• Sample mean-(1.96*standard error)
So, 6.7+(1.96*1.3)=9.248
& 6.7-(1.96*1.3)=4.152
Between 9.248 and 4.152
26. Normal distribution in statistics
• What is the probability that a candidate selected at random will take between 500 and 650 hours
to complete training program? Here 𝜇 = 500, 𝛿=100
Z=
𝑥−𝜇
𝛿
=
650−500
100
= 1.5 [ And at z value of 1.5, probability is 0.4332. using normal
distribution table]
• If standard error is lower the range of the population mean would be narrower.
• In stratified sampling the standard error of the mean will be smaller, as the variation between
strata is eliminated.
• In cluster sample without stratification exhibits a larger standard error of the mean than a simple
random sample.
33. Sample size
Types of Sample size
Sample size for population
Sample size for statistical analysis
34. Sample size for population
To determine the sample size of population, a researcher need to know
population size
confidence interval or margin of error
confidence level (typically 95%).
Standard of deviation
35. Sample size for statistical analysis
Types of statistical analysis.
The effect size, alpha, and desired statistical power.
The effect size may be small, medium, and large.
And alpha is usually set at .05
36. Calculation of sample size
Sample size = (Z-score)2 * StdDev*(1-StdDev) / (margin of error)2
Confidence level corresponds to a Z-scores, this is a constant value needed for
this equation.
Example:
What is the sample size that a candidate assuming to choose a 95% confidence
level, .5 standard deviation, and a margin of error (confidence interval) of +/- 5%.
37. Calculation of sample size
sample size= ((1.96)2 x .5(.5)) / (.05)2
(3.8416 x .25) / .0025
.9604 / .0025
384.16
So, 385 respondents are needed.
If the sample size is too large, by decreasing confidence level or increasing
margin of error – this will increase the chance for error in sampling, but it can
greatly decrease the number of responses that need.
38. Other considerations
Time and cost
The sample size is profoundly affected by time and cost. The larger the sample
size the greater the uneconomic proposition.
39. Other considerations
Non response
The selecting sample may not participate in interview, in that case the researcher
can calculate response rate.
Response rate=( no. of usable questionnaires/ total sample – unsuitable
sample)*100
40. Other considerations
Heterogeneity of the population
When a sample is heterogeneous, like a population of whole country or city, the
population is highly varied. The larger the heterogeneous , the greater the
sample.
43. Sampling Error
Degree of Sampling error
Have performance
appraisal
Do not have performance
appraisal
Do not have performance
appraisal
Have performance
appraisal
44. Limits to Generalization
Representativeness
Time
Sample size
Lack of available and/or reliable data
Measure used to collect the data
Self-reported data