N

IO
T
A
IS
L
A
R
E

N
N
E
G

TI O Y
A
N
D

C
R
O

U
T
A
R

D
O
L
P

O
X
E

R
A
T

T
A
D

N
3

I
3
0
1
S
Q
Q
S
 DATA COLLECTION
A systematic process to obtain an adequate data set for
statistical analysis.

Before data collection is undertaken, a researcher must

determined:
 The target population.
 Whether sample is necessary.
 Variables to be obtained or measured.
 Scale of measurements involve.
DATA COLLECTION
The choice of data collection is strongly depending on
the types of statistical studies:

1. Descriptive: to describe about the population (i.e.

survey poll).
2. Comparative: to compare 2 or more populations.
3. Experimental: investigator intervenes to control
conditions to look at relationship between variables.
4. Observation: investigator collects data without
reaching to the objects.
DATA COLLECTION
Source of data can be summarized into two:

1. Primary source
Data which is collected by the researcher herself
using systematic process and has not previously
published.

2. Secondary source
Data which is obtained from existing trusted
resources either in raw form or compiled form.
 DATA COLLECTION

Primary Source Secondary Source

• Observation • Hardcopies: books, articles,

• Experiment directories, conference papers,
• Interview: face to face, focus newspapers, magazines,
group, panel, phone research reports and market
• Survey: questionnaire, mail reports
• Electronic resources: CD-ROM,
on-line databases, internet,
videos and broadcasts
 SECONDARY DATA VS. PRIMARY
DATA
Secondary data Primary data
May not match your need. Commonly match to your
need.
Access may be difficult or Original.
costly.
May save some costs and Sometimes involve some costs
time. and time.
Allow for longitudinal May be not appropriate for
studies. longitudinal studies.
Validity of some secondary Validity of the process in
data (e.g. internet sources) collecting the data.

6
 OBSERVATION

Observation is a design method to identify the problems that can arise

when people interact with products, services and environments.

For example, how people move around a shopping centre, or how people in
the street use their mobile phones.

Strategy: You may record your observation by

1. Jot down the event,
2. taking photos or video which let you to analyse the material after the
event.
 CONTROLLED EXPERIMENT ON SCURVY
In 1747, while serving as surgeon on HMS Salisbury, James Lind carried out a controlled experiment
to develop a cure for scurvy. Lind selected 12 men from the ship, all suffering from scurvy. Lind
limited his subjects to men who "were as similar as I could have them", that is he provided strict
entry requirements to reduce extraneous variation. He divided them into six pairs, giving each pair
different supplements to their basic diet for two weeks.

The treatments were all remedies that had been proposed:

A quart of cider every day
Twenty five gutts (drops) of elixir vitriol (sulphuric acid) three times a day upon an empty stomach,
One half-pint of seawater every day
A mixture of garlic, mustard, and horseradish in a lump the size of a nutmeg
Two spoonfuls of vinegar three times a day
Two oranges and one lemon every day.

The men who had been given citrus fruits recovered dramatically within a week. One of them
returned to duty after 6 days and the others cared for the rest. The others experienced some
improvement, but nothing was comparable to the citrus fruits, which were proved to be substantially
superior to the other treatments.
 INTERVIEW
Face to face – interview involves a trained interviewer going to the potential
respondent, asking questions and recording the responses.
Computer-Assisted Personal Interview - interviewer takes a laptop
computer to the interviewer and codes the data into the computer as it is
provided.
Postal/Mail survey – questionnaires are mailed out to respondents with a
return-paid envelope so that the respondent can mail back the completed
form.
Dropoff-Mailback and Dropoff-Pickup – The questionnaire is delivered to
respondents by an interviewer who explains the aims of the survey and
how to fill out the questionnaire. The questionnaire is left with the
respondent to be completed and either mailed back by the respondent or
picked up by the interviewer.
Telephone interview – involves potential respondents being telephoned and
asked by the survey questions over the phone.
SURVEY
RECAP: POPULATION AND SAMPLE
o Population includes all entities/objects in a defined
framework.

o Entities/objects in a sample are subset of the

population.
• Practical and useful when the size of population is either
unknown or huge.
• Cost for dealing with all entities is expansive.
• Duration time to complete the research is too short.
 PRINCIPAL OF SAMPLING
o Entities in a sample must be
• taken from the target population following some standard
precedures.
• be able to represent the actual population.
• adequate to be used in the analysis parts.
• adequate to supply necessary information to the research
questions.

12
INTRODUCTION TO POPULATION AND SAMPLE

Sample B

Sample A Sample C 13
 SOME IMPORTANT TERMS

Census
 A systematic procedure that collects and records data from all entities of a
population.

Survey
 Studies that are designed to obtain information from a large number of
respondents through written questionnaire, interview or similar procedure.

Randomisation
 A process by which experimental units are allocated to treatments by a
random process and not by any subjective to avoid biased approach.
SAMPLING TECHNIQUES
o Probability sampling
• All objects in the population will have equal chance to be chosen as
sampel.
• Less bias sampling procedure.

o Nonprobability sampling
• Objects in a sample are usually selected on the basis of accessibility.
• Bias sampling procedure.

15
 SAMPLING TECHNIQUES

Probability sampling Nonprobability

sampling

1. Simple random 5. Quota

2. Systematic random 6. Snow-ball
3. Stratified random 7. Convenience
4. Cluster random (and 8. Purposive
multi-stage) 9. Self-selection

16
PROBABILITY SAMPLING
o Researcher must ensure that every object has
equal opportunity for selection

o Randomisation is a must.

o The techniques are free of systematic and

sampling bias.

17
1. SIMPLE RANDOM

o Selecting a group of n objects in such a way that each

object
• has the same chance of being selected and
• is selected at random.

o Advantage:
• The easiest probability sampling technique.

18
2. STRATIFIED RANDOM
SAMPLING
o Objects are initially grouped into different classifications
(called strata), e.g. high-income and low-income.

o Researcher selects a simple random sample from each

strata.

o A good technique if there is an evidence that subgroups

occur within the population.

19
3. SYSTEMATIC SAMPLING
o A likely to an arithmetic choice of objects.

o Steps:
1. Prepare the population in a list.
2. Randomly chosen the initial object from the beginning
of the list.
3. Select every kth object thereafter.
4. Stop when the needed sample is obtained.

20
4. CLUSTER RANDOM SAMPLING
o Often confused by stratified sampling technique.

o Objects are grouped into different groups (called cluster), e.g. states in
Malaysia.

o Researcher selects a simple random sample of clusters then sample all

items within the selected clusters.

21
NON-PROBABILITY SAMPLING
o A good alternative because true random sampling
is difficult to achieve.

o Also practical if
• One is bounded by time, money and work force in
completing the research.
• Objects are difficult to access.

22
5. QUOTA SAMPLING
o Researcher chooses proportion representation of
objects depending on trait which is considered as the
quota.
o Example:
Gender Age (year) Quota

20 – 29 56
Male
30 - 44 104

20 – 29 50
Female
30 - 44 110
23
6. SNOWBALL SAMPLING
o This technique is commonly used when members of
the desired population are difficult to be identified.

o Strategy:
1. Identify the initial object from the population.
2. Ask the initial object to identify the next potential
object(s).
3. Ask the new objects to identify further new
objects.

24
OTHER SAMPLING TECHNIQUES
7. Convenience: Objects are chosen because they
are easy to get. It is considered the easiest and
least time consuming.

8. Purposive: Objects are chosen to meet the

research’s objectives. Also known as judmental
sampling.

9. Self-selection: Researcher allows an individual to

take part in the study.

25
MORE SAMPLING TECHNIQUES
o Line-intersect sampling
 Elements are chosen in a region whereby an element is
sampled in a chosen line segment.

o Panel sampling
 A sampling group is chosen (usually by random), and is
asked for the same information repeatedly over a period
of time.

o Event sampling
 Behaviour of interest is collected at the specified interval.

26
MORE SAMPLING TECHNIQUES
o Simulation
• A study that involves a creation of situations which
attempt to represent the actual phenomena.

• Suitable for a study that aims on

• creating a new method, function or system.
• modifying an existing method, function or
system for future used.

27
 GROUP ACTIVITY
Each group is required to get a published article in any journal (surf to
UUM’s library e-journal).

Read the article carefully and identify the following:

1. Objective of the study
2. Sampling process
3. Variables and measurement scale
4. Results

Include all the information in the given template

 Add the title here

Objectives

List of variables & measurement scale:

Sampling
a. Type:
b. Strategy:
1. Here

Results / Findings