Transcript Lecture 27

Research Tools and Techniques
The Research Process: Step 6
(Sampling Design Part C)
Lecture 27
Lecture Topics Covered Previously in the
Last Lecture
• Probability Sampling Techniques
What we are going to Cover in this
Lecture
• Non-Probability Sampling Techniques
• What Should be an Ideal Sample Size
• Introduction to Data Analysis Process
THE RESEARCH PROCESS
(1).
Observation
The Broad
Problem Area
(3).
(4).
Theoretical
Framework
Problem
Definition
Variables
Identification
(5)
(6).
Scientific
Research
Design
Generation
of
Hypothesis
(2).
Preliminary
Data
Gathering
Interviews
and Library
Search
(7).
Data
Collection
and
Analysis
(8)
Deduction
(9).
(10).
(11).
Report
Writing
Report
Presentation
Managerial
Decision
Making
THE ELEMENTS OF RESEARCH DESIGN
1. Purpose of
Study
•Exploratory
•Descriptive
•Hypothesis
Testing
•Case Study
2. Type of
Investigation
Establishing:
Causal
Relationship
or
Co-relational
3. Extent of
Researcher
Interference
•Minimal
•Moderate
•Excessive
4. Study Setting
•Contrived
•Non-Contrived
5.
Measurement
& Measures
•Operational
Definition
• Scaling
•Categorizing
•Coding
10. Test
Application
Feel for
Data
Goodness
of Data
6.Unit of Analysis
(Population to be
studied)
Individuals
Dyads
Groups
Organizations
Machines
etc.
8. Time Horizon
7. Sampling
Design
Probability
Non-probability
Sample Size (n)
One-Shot
(Cross-Sectional)
or
Longitudinal
9. Data
Collection
Methods
Observation
Interviews
Questionnaire
Physical
Measurement
Hypotheses
Testing
4). Double Sampling:
• A sub-sample of the primary sample is made to study
phenomena in more detail.
• Sample from a sample.
• We selected 100 individuals to fill out the questionnaire
and from these 100 individuals we selected 25 individuals
for the interviews and further clarification.
NON-PROBABILITY SAMPLING
TECHNIQUES
Elements of population do not have any probability
for being chosen in a sample. Generalizability is
low.
I). Convenience Sampling:
The members of population who
are conveniently available are
asked questions or interviewed
i.e. whom so ever likes to answer
questions at a marketing fair etc.
II). Purposive Sampling:
Data gathered from specific target groups.
1). Judgment Sampling:
IT company heads in Islamabad, Women senior
managers at Bank Al-Falah, Housewives surveyed in a
locality.
2). Quota Sampling:
Type of stratified random sampling done on convenience
basis.
50
Senior Managers
100
Middle Managers
210
First Line Managers
• From the group of managers who so ever is
conveniently available is selected as a
respondent to fill the questionnaire or to take
interview from.
• Non-Probability sampling techniques are ideal for
data gathering at the preliminary stages of
research.
Choice Points in Sampling Design
WHAT SHOULD BE AN IDEAL SAMPLE
SIZE?
The sample size depends on
1). The variability in the population
2). Precision and accuracy desired
Precision refers to how close our estimate is to the true
population.
3). Confidence level desired i.e. how certain we are that our
estimates hold true for the population.
4). Type of sampling used
5). Sample size >30 and <500 is appropriate for most
research
6). We can use the following formula
Sx bar = S/under root n
where Sx bar is the standard error or precision offered
by the sample, S is the standard deviation of sample
and n is the sample size.
U = X bar + K Sx bar
where U = Population Mean
X bar
= Sample Mean
K
= t-statistic for the level of confidence desired
(Constant having values already known i.e.
For 90% confidence level, the K value is 1.645
For 95% confidence level, the K value is 1.96
For 99% confidence level, the K value is 2.576)
Krejcie and Morgan Table for Determining
Sample Size
Introduction to Data Analysis Process
Data Analysis Process
Interpretation of Results
Data Collection
Data Analysis
Discussion
Getting Data
Ready for
Analysis
Feel for
Data
1. Mean
Editing Data
2. Median
1. Incompleteness
/omissions
3. Mode
2. Inconsistencies
5. Frequency
Distribution
3. Legibility
4. Coding Data
5. Categorizing
6. Creating a Data
File
4. Variance
Recommendations
Hypotheses
Testing
Appropriate
Statistical
Manipulation
(Inferential
Statistics)
Goodness
of Data
1. Reliability
2. Validity
Summary
• Non-Probability Sampling Techniques
• What Should be an Ideal Sample Size
• Introduction to Data Analysis Process