3. NOMINAL DATA-- The observations on
qualitative variables may also be assigned
numbers. The categorical data can be made
into numerical data .
Ex: recording yes or no answers to a question
as ‘0’ and ‘1’.
This data do not share the properties of
numbers, like greater or less or difference.
4. In situations when we can not do any thing
except set up inequalities ,it is referred as
ordinal data.
Ex: the hardness of minerals can be referred
as 1 to 10 like talc-1, gypsum-2 , calcite-3
,fluorite-4, apatite-5, feldspar-6, quartz-7, topa-
8, sapphir-9 and diamond-10.we can write 5>2
or 6<9 as apatite is harder than gypsum and
feldspar is softer than sapphire.
5. In addition to setting up inequalities ,if we can
form differences it is known as interval data.
Ex: temperature readings
58˚,63˚,70˚,95˚,110˚, 126˚. We can write
100˚>70˚, or 95˚>135˚
also95˚--70˚=135˚--110˚.
Also 126˚does not mean that it is twice as hot
as 63˚.
6. In addition to setting up inequalities and
forming differences we can also form quotients,
which includes all the usual measurement of
length , height, money etc.
7.
8.
9. The process of assigning numbers to objects
or observations, the level of measurement
being a function of the rules under which the
numbers are assigned is known as
measurement.
10. The scales of measurement can be
considered in terms of their mathematical
properties.
11.
12. This is simply a system of scales assigning
number symbols to events in order to label
them.
This scale provides convenient ways of
keeping track of people , objects and events .
Ex: answers to certain questions like yes or
no can be recorded as 0 or 1.
13.
14. Nominal scale is the least powerful level of
measurement.
It indicates no order or distance relationship and has
no arithmetic origin.
This is very useful and are widely used in surveys.
This scale is restricted to use mode as the measures of
central tendency.
The most common test of statistical significance that
can be utilized is the Chi-square test.
The measures of correlation that can be worked out is
the contingency coefficient.
There is no generally used measure of dispersion for
nominal scales.
15. This scale places events in order, but there is
no attempt to make the intervals of the scale
equal in terms of some rule.
Ex: Role numbers of 5 students in class is as
follows,Anu—1, Binu—2, Dinu—3, Hema—4,
Rinu—5, in this Rinu’s number is 5 but it
doesn’t mean that she is superior to Anu , Binu,
Dinu or Hema.
16.
17. Ordinal scales are frequently used in research relating to
qualitative phenomena.
This scales only permits the ranking of items from highest
to lowest.
These have no absolute values.
The real differences between adjacent ranks may not be
equal.
The appropriate measure of central tendency is median.
The measures of correlations are restricted to various rank
order method.
The measures of statistical significance are restricted to
non-parametric methods.
The measures of dispersion used is percentile or quartile.
18.
In this intervals are adjusted in terms of some
rule that have been established as a basis for
making the units equal.
Ex: An increase in temperature from 30˚to
40˚involves the same increase in temperature
60˚ to 70˚, but one cannot say that the
temperture of 60˚ is twice as warm as the
temperture of 30˚.
19.
20. Interval scales provide more powerful
measurement than ordinal scales.
These scales have an arbitrary zero, but not
possible to determine the unique origin or absolute
zero.
The appropriate measure of central tendency is
the Mean.
The correlation techniques used is product
moment correlation.
The generally used statistical significance are the
t—test and F—test .
The mostly used measure of dispersion is standard
deviation.
21. This scales represents the actual amount
of variables.
Ex: weight , height, distance etc.
22.
23. All statistical techniques are usable with ratio
scales.
This scales have an absolute or true zero of
measurement.
The measures of central tendencies are geometric
and harmonic means.
The measures of dispersion can be calculated
using coefficients of variation.
The ratio involved does have significance and
facilities , a kind of comparison which is not
possible in case of an interval scale.
Ex: Jyothi’s typing performance was twice as
good as that of Reetu.
24. Thus proceeding from the least precise type of
scale, the nominal scale to the most precise type of
scale, the ratio scale relevant information is
obtained increasingly.
A researcher should use the scale that provides
the most precise description if the nature of the
variables permits.
Ex: Physical science researchers are generally
limited to describe variables in ratio scale form
while Behavioral science researchers are
generally limited to describe variables in interval
scale form.
25.
26. This is the most critical criterion and
indicates the degree to which an instrument
measures what it is supposed to measure.
It can also be thought of as utility.
There are three types of validity
Content validity, criterion—related validity,
construct validity, Accuracy.
27. This is the extent to which a measuring
instrument provides adequate coverage of the
topic under study.
If the instrument contains a representative
sample of the universe , the content validity is
good.
It can also be determined by using a panel of
persons who shall judge how well the
measuring instruments meets the standards,
but there is no numerical way to express it.
28. This relates our ability to predict some outcome or
estimate the existence of some current condition.
This form of validity reflects the success of measures
used for some empirical estimating purpose.
This must possess the qualities like Relevance(proper
measure), Freedom from bias(when criterion gives
each subject an equal opportunity to score well),
Reliability (stable or reproducible), Availability
(Information must be available).
This validity is a broad term which refers
a) Predictive validity ( the usefulness of a test in
predicting some future performance)
b) Concurrent validity (the usefulness of a test in
closely relating to other measures of known validity)
29. This is the most complex and abstract validity. It
is the degree to which scores on a test can be
accounted for by the explanatory constructs of a
sound theory.
For determining construct validity associate a set
of other propositions with the results received
from using our measurement instrument.
If measurements in our devised scale correlate in a
predicted way with these other propositions ,we
can conclude that there is some construct validity.
30. A measuring instrument is reliable if it provides
consistent results.
A valid instrument is always reliable.
Two aspects of reliability are stability and
equivalence.
stability is concerned with securing consistent
results with repeated measurements of the same
person and with the same instruments.
Equivalence considers how much error may get
introduced by different investigators or different
samples of the items being studied.
31. This characteristic of a measuring instrument can
be judged in terms of economy, convenience and
interpretability.
Economy consideration suggests some trade—off
is needed between the ideal research project and
that which the budget can afford.
Ex: the length of measuring instrument is an
important area where economic pressures are
quickly felt. More items may give reliability but in
order to limit the observation time or interview
time we have to take only a few items.
Similarly data collection methods to be used are
also dependent at times upon this factor.
32. Convenience test suggests that the measuring
instrument should be easy to administer.
Ex: a questionnaire with clear
instructions(illustrated by examples) is
certainly more effective and easier to complete.
33. Interpretability consideration is specially
important when persons other than the designers
of the test are to interpret the results.
In order to be interpretable, the measuring
instruments must be supplemented by
a) detailed instructions for administering the tests
b)scoring keys
c) evidence about the reliability and
d) guides for using the test and for interpreting
results.
34. The characteristic of accuracy of a
measurement scale means it should be a true
representative of the observation underlying
characteristic.
Ex: measuring with an inch scale will provide
accurate value only up to one—eighth of an
inch, while measuring with centimeter scale
provide more accurate value.
35. Measurement should be precise and
unambiguous in an ideal research
study. Following are the possible
sources of error in measurement.
36. At times the respondent may be reluctant to
express strong negative feelings , so it is likely
to result in an interview of guesses.
Transient factors like fatigue, boredom,
anxiety, etc may limit the ability of the
respondent to respond accurately and fully.
37. Any condition which places a strain on
interview can have serious effects on the
interview respondent rapport.
Ex: if someone else present the respondent is
not sure about the anonymity ,he may reluctant
to express certain feelings.
38. The interviewer can distort responses by
rewording or reordering questions.
His behavior style and looks may encourage or
discourage certain replies from respondents.
Errors may also creep in because of incorrect
coding, faulty tabulation or statistical
calculations, particularly in the data analysis
stage.
39. Error may arise because of the defective
measuring instrument. The use of ambiguous
meanings, poor printing, inadequate space for
replies, response choice omissions etc., are a
few things that make the measuring instrument
defective.
40.
41. In this stage researcher should arrive at an
understanding of the major concepts pertaining
to his study.
This is more apparent in the theoretical studies
than in pragmatic research, where the
fundamental concepts are often already
established.
42. This step accomplished by deduction, ie, by
adopting a more or less intuitive approach or
by empirical correlation of the individual
dimensions with the total concept or the other
concepts.
Ex: when one is thinking about the image of a
certain company, he may think about the
dimensions such as product reputation,
customer treatment ,etc. of that company.
43. Once the dimensions of a concept have been
specified, the researcher must develop
indicators for measuring each concept element.
Ex: indicators—scales, questions etc by which
respondent’s knowledge, opinion etc are
measured.
The use of more than one indicator gives
stability to the scores and it also improves their
validity.
44. When we have several dimensions of a concept
or different measurements of a dimension, we
may need to combine them into a single index.
One simple way for getting an overall index is
to provide scale values to the responses and
then sum up the corresponding scores. Such an
overall index would provide a better
measurement tool than a single indicator
because of the fact that an individual indicator
has only a probability relation to what we really
want to know.
45. Procedure for the assignment of numbers
to a property of objects in order to impart
some of the characteristics of numbers to
the properties in question
46. This describes the procedures of assigning
numbers to various degrees of opinion,
attitude and other concepts.
A scale is a continuum , consisting of the
highest point and the lowest point along with
several intermediate points between these two
extreme points.
Scaling has been defined as a procedure for the
assignment of numbers to a property of objects
in order to impart some of the characteristics of
numbers to the properties in question.
47. 1. Making a judgment about some
characteristics of an individual and then
placing him directly on a scale that has been
defined in terms of that characteristics.
2.Constructing questionnaires on such a way
that the score of individual’s responses assigns
him a place on a scale.
48.
49. Scale may designed to measure the
characteristics of the respondent who
completes it or judge the stimulus object
which is presented to the respondent.
50. Under this two types of scales
1.Cateogorical scales—(Rating scales)
This is used when a respondent scores some
object without direct reference to other objects.
2. Comparative scales—(Ranking scales)
In this the respondent is asked to compare
two or more objects.
Ex: the respondent may rank different brand
pens as 1, 2 and 3.
51. With this the scale data may be based on
whether we measure subjective personal
preferences or simply make non—preferences
judgements.
In subjective personal preferences the
respondent is asked to choose which person
he favours or which solution he would like to
see employed.
In non—preferences judgements, the
respondent is simply asked to judge which
person is more effective in some aspect.
52. Considering scale properties we may classify
the scales as nominal, ordinal , interval and
ratio scales.
53. With respect to this scales, can be classified as
uni—dimensional and multi—dimensional.
In uni—dimensional measure only one
attribute of the respondent or object.
In multi—dimensional the respondent or object
is measured by an attribute space of “n”
dimensions rather than a single dimension
continuum.
54. Following are the Five main techniques by
which scales can be ddeveloped.
1.Arbitrary approach—is an approach where
scale is developed on adhoc basis.
2.Consensus approach– a panel of judges
evaluate the items chosen for inclusion in the
instrument in terms of whether they are
relevant to the topic area and unambiguous in
implication.
55. 3.Item analysis approach—a number of
individual items are developed into a test which
is given to a group of respondents
After administering the test, the total scores
are calculated for every one.
Individual items are then analysed to
determine which items discriminate between
persons or objects with high total scores and
those with low scores.
56. 4. Cumulative scales– are chosen on the
basis of their confirming to some ranking of
items with ascending and descending
discriminating power.
5.Factor scales—may constructed on the basis
of inter correlations of items which indicate
that a common factor accounts for the
relationship between items. This is measured
through factor analysis method.
57. This is broadly classified into comparative
scaling techniques and non—comparative
scaling techniques.