RE SEARCH ME THO DOLOG Y

MODULE 3 – PART B
MEAS URE MENT
 MEASUREMENT

 Selecting observable empirical events

 Usingnumbers or symbols to represent

aspects of the events

 Applyinga mapping rule to connect the

observation to the symbol.
Wh at is M easured?

 Objects:
• Things of ordinary experience
• Some things not concrete
 Properties:

• Characteristics of objects.
Characteristics of Data

 Classification

 Order

 Distance (interval between numbers)

 Origin of number series.
Data Types
Order Interval Origin
Nominal none none none

Ordinal yes unequal none

Interval yes equal or none

unequal
Ratio yes equal zero
Nom inal Dat a / S cal e * **
 Numbers identify &
 Basic Characteristics classify objects

 Examples  Store types, gender,

members in teams
 Descriptive
 Percentages, Mode
 Inferential
 Chi-square, Binomial
test
 Example - Nominal

Runner Runner Runner

7 11 3
 Ordina l D ata / S ca le * **

 Basic Characteristics  Numbers indicate relative

position of objects but not
magnitude of difference

 Quality rankings, market

 Examples position, social class

 Descriptive  Percentages, Median

 Rank-order Correlation,
 Inferential Friedman ANOVA
 Example - Ordinal

Third Second First

Place Place Place
 Basic Characteristics  Differences between objects
can be compared; zero point is
arbitrary

 Temperature, Attitudes,
 Examples
Opinions, Index numbers
 Descriptive  Range, Mean, Standard
Deviation

 Inferential  Correlation, t-test, ANOVA,

Regression, Factor Analysis

In te rva l D ata / Scale ** *

 Example - Interval

Rating Rating Rating

8.2 9.1 9.6
 Ratio D ata / S cale ** *

 Basic  Zero point is fixed;

Characteristics Ratios of scale values
can be computed

 Length, Weight, Age,

 Examples Income, Costs, Sales

 Geometric &
 Descriptive Harmonic Mean

 Coefficient of
 Inferential variation
 Example - Ratio

15.2 14.1 13.4

seconds seconds seconds
Sources of Meas ur ement
Diff erenc es

 Respondent

 Situationalfactors
 Measurer or researcher

 Data collection instrument.

 Characteristics of Sound
Measurement

 Validity – Extent to which a test

measures what we actually wish to
measure
 Reliability – Accuracy and Precision
of a measurement procedure
 Practicality – Wide range of factors of
economy, convenience and
interpretability.
Validity in Experimentation ***

 Internal Validity:
 Measure of accuracy in an
experiment
 Measures whether the
manipulation of the independent
variables, or treatments,
actually caused the effects on
the dependent variable (s).
 Validity in Experimentation ***

 External Validity:
 Determination of whether the
cause-and-effect
relationships found in the
experiment can be
generalised.
Validity
 Content Validity

 Criterion-Related Validity
•Predictive
•Concurrent
 Construct Validity.
Conte nt V alid ity
 Degree to which the content of items
adequately represent the universe of all
relevant items under study
 Sometimes called face-validity ***

 Methods:

• Judgemental
• Panel Evaluation.
Criterio n-R ela te d Va lid ity
 Degree to which predictor is adequate in
capturing the relevant aspects of the
criterion

 Method:

• Correlation.
Conc urre nt Va lid ity

Description of the present; Criterion

data are available at same time as
predictor scores.
Pred ic tiv e Va lid ity

Prediction of the future; criterion data

are measured after the passage of
time.
Cons tru ct Va lid ity

 What accounts for the variance

in the measure?
 Identifies the underlying
constructs being measured and
how well the test represents it

 Methods: Judgemental;
Correlation; Factor Analysis;
Multi-variate Analysis.
Relia bility

 Stability (Test-retest)
 Equivalence (Parallel forms)
 Internal Consistency (Split-half, KR20,
Cronbach’s alpha).
Tes t-R ete st (Sta bil ity )
 Same test is administered
twice to same subjects over
an interval of less than six
months

 Method: Correlation.
Stability means one can secure
consistent results with repeated
measurements with same
instrument.
Bias Caused By...
 Time delay between measurements
 Insufficient time between measurements
 Respondent thinks there is disguised
purpose
 Respondent forms new opinion before
retest (Topic sensitivity)
 Introduction of moderating variables
between measurements.
Parallel Forms
(Equivalence)
Test administered
simultaneously or with a
delay

Method: Correlation.
Equ iv ale nce
 Concerned with variations at one point in
time among observers and samples of
items

 Interrater Reliability

 Delayed equivalent forms

(to prevent “order of presentation”
effect).
Cr onb ach’s Alph a
(Int ernal Con sis ten cy )

 Degreeto which instrument items

are homogenous and reflect the
same underlying constructs

 Method:Specialised Correlation
formulae.
Improving Reliability

 Minimise External sources of

variation
 Standardise conditions under
which measurement occurs
 Improve investigator consistency

 Broaden measurement questions

 Add more observers or occasions

 Improve internal consistency.

 Practicality
 Economy

 Convenience

 Interpretability.