3 - SAMPLING TECHNIQUES NON-PROBABILITY SAMPLING

 One cannot estimate beforehand the chance of each

element being included in the sample. It also does not
assure that every element has a chance of being
included
✓ convenience sampling
✓ purposive sampling
✓ quota sampling

PROBABILITY SAMPLING
Simple random sampling Cluster sampling
• each member of the population has an equal and known • a sampling technique in which clusters of participants that
chance of being selected. represent the population are identified and included in the
Population - a collection of elements about which we wish to sample
make an inference.
Sample - a subset of the population

Why sample?
❑ The population of interest is usually too large to attempt
to survey all of its members.
❑ A carefully chosen sample can be used to represent the
population
Stratified sampling
• the population is divided into different strata then samples
are selected from each stratum

Differences between stratified sampling and random

sampling

PROBABILITY SAMPLING
 Every unit of the population has an equal chance of
being selected for the sample.
✓ random sampling Systematic sampling
✓ stratified sampling • researchers select members of the population for their
✓ systematic sampling sample at a regular interval determined in advance.
✓ cluster sampling
✓ Multi-stage sampling
Multi-stage sampling Purposive sampling ⚫ Construction

⚫ Evaluation
• sample is selected in various stages but only last sample is • The selection of elements is based upon the judgement of
studied. the researcher

⚫ Validation
• is called judgement sample

⚫ Revision
PLANNING

⚫ Identify the purpose of the test

⚫ Specify the content area to be studied

⚫ Identify the target group

PLANNING

⚫ Review Related Literature

Quota sampling
• the researcher selects a specified number of persons from
each category ❖ To be certain that no instrument already exists for the
evaluation of the variables in the test
❖ To determine the operational definitions of the constructs
that are to be measured

CONSTRUCTION

⚫ Identify the objectives of the instrument

❖ What is the purpose of the test
❖ What is intended to measure
CONSTRUCTING AND EVALUATING RESEARCH INSTRUMENTS
When should we design research instrument?

⚫ When there is no available instrument that measures the

CONSTRUCTION

⚫ Develop table of specifications

NON-PROBABILITY SAMPLING
Convenience sampling
• the researcher selects any member of the population who construct of your interest

⚫ When the available instruments don’t measure what you

❖ The specifications should narrow the purpose and identify
are conveniently and readily available
the content areas
intend to measure
CONSTRUCTION
PHASES IN CONSTRUCTING AND EVALUATING RESEARCH ⚫ Write the items in the instrument
INSTRUMENTS

⚫ Planning
❖ Determine the format
❖ The format of the questions should be determined by the
type of data that need to be collected
CONSTRUCTION ⚫ Criterion-referenced validity – used when the researcher Interval Scale

⚫ Review the items

wants to determine if the scores from an instrument are a ▪ has ordered numbers with meaningful divisions.
good predictor of an expected outcome ▪ A scale that not only arranges objects into ranks, but also
❖ For clarity of the items distinguishes the ordered arrangements in units of equal
❖ Format QUANTITATIVE EVALUATION interval

⚫ Test the quantitative data for reliability and validity

❖ Acceptable response options ▪ Temperature is on the interval scale:
❖ Wording, etc. ❖ a difference of 10 degrees between 90 and 100 means the
⚫ Construct validity – established by determining if the
same as 10 degrees between 150 and 160.
EVALUATION ❖ Compare that to high school ranking (which is ordinal),

⚫ Submit the instrument for content validation (consult 2-3

scores recorded by an instrument are meaningful, where the difference between 1st and 2nd might be .01 and
significant, useful, and have purpose between 10th and 11th .5.
experts) ❖ If we have meaningful divisions, we have something on

⚫ Revise as needed
REVISION the interval scale.
⚫ Revise the instrument based from the results of the validity
Ratio Scale
and reliability tests
EVALUATION ▪ This scale is exactly the same as the interval scale with one

⚫ Have representative sample of the target group take the

major difference: zero is meaningful.
SCALING TECHNIQUES
▪ For example, a height of zero is meaningful (it means you
SCALING TECHNIQUE

⚫ assigning numbers to various degrees of opinions, attitude,

test don’t exist). Compare that to a temperature of zero, which
❖ The group who took the test may critique the quality of while it exists, it doesn’t mean anything in particular
the individual items and overall instrument for further (although admittedly, in the Celsius scale it’s the freezing
and other concepts

⚫ Scales of Measurement
refinement point for water).

QUANTITATIVE EVALUATION
❖ Nominal Scale
⚫ Test the quantitative data for reliability and validity ❖ Ordinal Scale

⚫ Reliability coefficient can range from 0.00 to 1.00 with

❖ Interval Scale
❖ Ratio Scale
values of 0.70 or higher indicating acceptable reliability
(George and Mallery, 2003); SCALING TECHNIQUE SCALES OF MEASUREMENT

⚫ However, values higher than 0.95 are not necessarily good,

Nominal Scale
▪ uses labels to classify cases (measurements) into classes.
since they might be an indication of redundance (Hulin, ▪ Example: What is your gender? What is your hair color?
Netemeyer, and Cudeck, 2001). Where do you live?

QUANTITATIVE EVALUATION Ordinal Scale

⚫ Test the quantitative data for reliability and validity

▪ This contains things that we can place in order (rank).
▪ For example, hottest to coldest, lightest to heaviest, richest
to poorest. Basically, if we can rank data by 1st, 2nd, 3rd
place (and so on), then we have data that’s on an ordinal
scale.
▪ Other examples: socioeconomic class, t-shirt size..)
 ⚫ There are many types of validity measures. One of the
PSYCHOMETRIC PROPERTIES OF RESEARCH INSTRUMENTS most commonly used is the construct validity. Thus, the

⚫ Reliability
construct or the independent variable must be accurately
defined.

⚫ Validity When is an instrument valid?

⚫ Reliability refers to the consistency while Validity refers to ⚫ The construct validity would determine if the items being
the test results’ accuracy. used in the instrument have good validity measures using
factor analysis and each sub-scale has a good inter-item
PSYCHOMETRIC PROPERTIES OF RESEARCH INSTRUMENTS correlation using Bivariate Correlation. The items are

⚫ An instrument should accurately and dependably measure

considered good if the pvalue is less than 0.05

what it ought to measure.

⚫ Its reliability can help to have a valid assessment; its

validity can make us confident in making a prediction.

When is an instrument reliable?

⚫ Although there are many types of reliability tests, what is

more usually looked at is the internal consistency of the
test.

⚫ Examiners might look for the results of the Cronbach’s

alpha or the Kuder-Richardson Formula 20 computations.

When is an instrument reliable?

⚫ But if we would like to determine the inter-correlations of

the items in the instrument and if these items measure the
same construct, Cronbach’s alpha is suggested.

When is an instrument reliable?

• Reliability coefficient can range from 0.00 to 1.00 with
values of 0.70 or higher indicating acceptable reliability
(George and Mallery, 2003);
• However, values higher than 0.95 are not necessarily good,
since they might be an indication of redundance (Hulin,
Netemeyer, and Cudeck, 2001).

When is an instrument valid?