UNIT 13 TOOLS AND TECHNIQUES OF

DATA COLLECTION
Structure
1 3.1 Introduction
13.2 Objectives
13.3 Tools of Data Collection
13.3.1 Questionnaire
13.3.2 Rating Scale
13.3.3 Attitude Scales
13.3.4 Check List
13.3.5 Tests
13.3.6 Inventory
13.4 Techniques of Data Collection
13.4.1 Interview
13.4.2 Observation
13.5 Documents
13.6 Characteristics and Criteria for Selection of a Good Tool
13.6.1 Validity
13.6.2 Reliability
13.6.3 Objectivity
13.6.4 Adequacy
13.65 Usability
13.6.6 Discriminating Power
13.6.7 Interest
13.7 Let Us Sum Up
13.8 Unit-end Activities
13.9 Point for Discussion
13.10 Suggested Readings
13.1 1 Answers to Check Your Progress
13.1 2 Glossary

13.1 INTRODUCTION
In order to get relevant and adequate data it is necessary to use appropriate data
collection device(s). The data-gathering devices that have proven useful in educational
research include tools e.g. psychological tests and inventories, questionnaires,
opinionnaires, checklists, rating scales and techniques, namely, observation, interview,
sociogram, content analysis and guess-who techn.+e. A researcher dspending upon
the nature of the research may select one of these devices or may e~hploya number
of them in combination. But before selecting the devices, it is also necessary for a
researcher to develop skill in constructing the required devices and using them
effectively.
In this Unit we have made an effort to familiarize you with some of the datacollection
devices.
43
Research Design

On the completion of the study of this Unit, it is expected that you will be able to:
state the meaning of a Questionnaire;
describe the types of a Questionnaire;
explain the characteristics of a good questionnaire;
identify the advantages and limitations of a questionnaire;
state the meaning of a Rating Scale;
describe the types of a rating scale;
explain the requirements of a good rating scale;
identify the advantages and limitations of a rating scale;
define an Attitude scale;
describe the types of attitude scale;
explain the characteristics of a good attitude scale;
identify uses and limitations of an attitude scale;
, state the meaning of a Check List;
describe types of check list;
identify uses and limitations of a check list;
define a test;
describe various types of a test;
explain basic characteristics of a standardized test;
state the meaning of Interview technique;
explain the types of interview;
describe the process of interview;
identify the advantages and limitations of interview;
state the meaning of Observation technique;
explain the types of observation;
describe the process of observation;
identify the advantages and limitations of observation; and
decide the criteria for selection of a good tool of data collection.

133 TOOLS OF DATA COLLECTION

For acquisition of the Fequireddata ~nanypmmhes have been developed to construct
difkr&t types of tools. Depending upon the nature of the required data the researcher
has to decide which tool will be appropriateunder the circtumtams. Some tools help
in getting descriptivdqualitative data and some in getting quantitative data. Let us get
i n f o d o n about some of the tools one by one.

133.1 Questionnaire
A questionnaire is an important instrmnent in normative-sorvey research, being used
to gather information from widely scattered sources and also used when factual
i n f o d m is desired,
 Meaning -1s mnd Techniques
of Data Collection
Barr, et.al(1953), define questionnaire as "a systematic compilation of questions that
are submitted to a sampling of population from which information is desired". Its
scope is very vast. It has been used for studying a wide range of problems.

Qpes or Forms of Questionnaire

1. Structured Vs. Non-structured Questionnaire
A structured questionnaire contains definite, concrete and directed questions, whereas
non-structured one may consist of partially completed questions or statements. A
non-structured questionnaire is often used as the interview guide, which is nondirective.
2. Closed fonn Vs. Open form
The questions that call for short check responses are known as restricted or closed
form type. They provide for marking a ' yes or no' short response. It restricts the
choice of response for the respondent.
The open form including open end or unrestricted type of questions calls for a free
b
response in the respondent's own words. No clues areprovided. It probably provides
for greater depth of response.

- Example of Open-ended Questionnaire.

Question : What should be the role of Open and Learning System to promote
access of the people to educational opportunities?
Example of Close-ended Questionnaire.
I Question : Should performance of the teachers be evaluated by their students?
i Answer: a) Yes b) No c ) Undecided.

Characteristics of a Good Questionnaire

1. A good questionnaire deals with a significant topic so that it enthuses respondent
to give response. Its significance is carefully stated on the questionnaire itself or
on its covering letter.
2. It seeks only that data which cannot be obtained from the resources like books,
reports and records.
3. It is as short as possible, though comprehensiveand clear enough for securing all
the essential information.
4. It is attractive in appearance, neatly arranged and clearly duplicated or printed.
5. It contains directions which are clear and complete. Important terms are clarified
and each question deals with a single idea in unambiguous terms, so that it is valid
and reliable.
6. Items are arranged in categories to ensure easy and accurate responses.
7. The questions are objective, with no clues, hints as to the responses desired.
Heading questions are carefully avoided.
8. Questions are presented in good psychological order proceeding from general to
more specific responses.
9. Double negatives and putting two questions in one question are also avoided.
10. The questions carry adequate number of alternatives.
11. It is easy to tabulate and interpret, based on a preconstructed tabulation sheet
and a visualized final analysis of data.
Research Dcsipn Advantages
1. As an instrument of data collection the questionnaire has great potentialities when
it is properly used.
2. It is economical both for the sender and for the respondent in time, effort and
cost.
3. It is easy to plan, construct and administer.
4. When the subjects of the study are scattered far and wide, it will be a better tool
as compared to the tools like interview. It permits nationwide or even international
coverage.
5. It permits group administration and is adaptable to any objectives.
6. It is generally regarded as dependable when used to obtain statement of fact.
7. Information of a personal nature often may be obtained more readily by means
of questionnaires.
8. It places less pressure on the subject for immediate response.
9. It helps in focusing the respondent's attention on all the significant items. It does
not permit much of variation.
10. It may be used as a preliminary tool for conducting indepth study later on by any
other method.
11. The responses given by the subjects are available in their own language and
version.

Limitations
1. Its reliability and validity is low. It seeks secondary information concerning facts
when primary evidence is not at hand.
2. Frequently questionnaireresearch constitutes simply a pooling of ignorance. It is
compilation of the opinions of many persons who may not know the answer.
3. It gives a biased sample. The matter of non-response is always a big question
mark.
4. The respondents who return the questionnaires may not constitute a representative
section of the entire group.
5. If the subject misinterprets a question or gives an incomplete or indefinite response,
nothing can be done.
6. A questionnaire is more or less rigid in its structure about complex emotional
subjects.
7. Some respondents may not like to put their views on controversial issues in writing.
8. The behaviours, gestures, reactions, emotions of the respondent remain unnoticed.
9. Some of the research areas are so delicate, sensitive and confidential in nature
that it becomes difficult to frame questions on them.
10. The questionnaire cannot be used with illiterate subjects and children.

13.3.2 Rating Scale

Meaning
"Rating is a term applied to expression of opinion or judgement regarding some situation,
object or character. Opinions are usually expressed on a scale of values. Rating
techniques are devices by which such judgements may be quantified - Barr, et. al
(1953), Rating scale is a device for obtaining judgements of the degree to which an
individual posseses certain behaviour traits and attributes not readily detectable by
46
objective tests. A rating scale consists of a set of characteristics or qualities to be Tools and Techniques
of Data Collection
judged and some type of scale for indicating the degree to which each attribute is
present. Descriptions of different degrees of quality are arranged along a line from
high to low and this line is the scale.

mpes of Rating Scale

1. Numerical Rating Scale
One of the simplest type of rating scales is that where the rater checks a number to
indicate the degree to which a characteristic is present. Typically, each of a series of
numbers is given a verbal description which remains constant from one characteristic
to another. This type of scale is useful when the characteristic to rate can be classified
into a limited number of categories.
2. Descriptive Rating Scale
This rating form uses descriptive phrases to identify the points on a graphic scale. The
descriptions convey in behavioural terms what the individualsare like at different step
along the scale. It is also called 'Behavioural Statement Scale'.
3. Graphic Rating Scale
The distinguishing feature of the graphic rating scale is that each characteristic is
followed by a horizontal line. The rater's evaluation is indicated by placing a check or
cross on a line to indicate presence or absence of a given trait.
4. Ranking Methods
Some rating procedures do not require a printed scale. Probably the most applicable
and best known of these is the simple rank order method. With this approach, the
pupils (or products) being rated are merely ranked in the order in which the rater
estimates they possess the characteristics being judged.
5. Standard Scales
In standard scales a set of standards is presented to the rater. The standards are
usually objects of the same kind to be rated with pre-established scale values. For
example, in case of rating the drawing skill in science, a set specimen can be provided
for comparison.
a) The percentage of group scale
Here the rater is asked to give the percentage of the group that possesses the
trait on which the individual is rated.
b) Man to Man scale
The rater is asked to rate the ratee by comparing him to the person mentioned on
the scale and assign the ratee his position.
6. Forced Choice Scales
In forced choice rating method the rater is asked to only mention whether the ratee
has one or more traits. Instead of deciding whether particular quality of a person1
object is above average, average, or below average certain observable characteristics
are stated for rating. These statements differ in the degree of that quality, e.g.
- the student is very much regular in attending the fitness programme.
- the student is not regular in attending the fitness programme.
- the student rarely attends the fitness programme.
* Requirements of a good rating Scale
1. Traits must be clearly defined. The specific mode of behaviour must be defined

47
Researcl~Design 2. Number of divisions on the scale should be neither too numerous nor too few.
Optimum number of divisions is perhaps five to seven.
3. The rater may be asked to quote instances in support of his judgement.
4. Rater should be instructed to omit ratings of characteristics, if he had no
opportunity to observe the traits.
5. The rater should be instructed to avoid the generosity and the logical error and
the error due to halo effect.
6. Rating from several observers should be combined wherever possible.
7. The directions should be clear and comprehensive.
8. Items may be arranged in ascending or descending order from left to right.
9. Well informed and experienced persons should be selected for rating.
10. The number of characteristics to be rated should be limited.
I 1. In the rating scale card, some space may be provided for the rater to write some
supplementary material.

Advantages of Rating Scale

1. A simple form of rating scale is commonly employed in judging contests of various
kinds such as speaking and music competitions.
2. Rating Scales have been put to extensive uses in the field of rating teaching and
teachers. This process extends to the selection of teachers and the prediction of
teaching success.
3. Rating Scales are also used for testing the validity of many objective instruments
like paper-pencil inventories of personality.
4. These scales are also employed for school appraisal including appraisal of courses,
practices and programmes.
5. The rating scales are advantageous in several other ways. They are -
i) helpful in writing reports to parents.
ii) helpful in filling out admission blanks for colleges.
iii) helpful in filling out student needs.
iv) helpful in recommendations to employers.
v) helpful in supplementing other sources of ~nderstanding~about
the child.
vi) helpful in their stimulating effect upon the individuals who are rated.

Limitations of Rating Scale

1. People differ markedly in their ability to make ratings.
2. People differ in their reliability as subjects for ratings.
3. Immediate emotional reactions affect ratings.
4. Self-ratings tend to be too high on desirable traits and too low on undesirable
traits.
5. Raters are frequently unable to justify ratings or are apt to give absurd
rationalizations.
6. Generosity Error -The raters would not like to run down their own people by
giving them low ratings. The result is that high ratings are given in almost all
cases. The raters are also inclined to be unduly generous in rating aspects which
they have had no opportunity to observe.
7. The Halo Error -It is difficult for rater to get rid of the halo effect which causes
him to carry qualitativejudgement from one aspect to another. Halo effect appears
48
 frequently when the rater has to rate a number of factors on some of which he Tools and Techniques
of Data Collection
has no evidence for judgement.
8. The Error of Central Tendency -There is a tendency in some observers to rate
most of the ratees near the mid points of the scale.
9. Stringency Error -The opposite of generosity error may be called stringency
error. Some raters are so cautions and hesitant that they have a tendency to rate
r all individuals low.
10. The Logical Error -It is difficult to convey to the rater just what quality one
i wishes him to evaluate. An adjective or adverb may have no universal meaning.

An example of a rating scale

Dissection of Rate to expose Arterial System

Stcps ~ o l l o w e din the Dissection Weightage Rating Weighted

a) Keeping the animal ventrally in the 03% 5 0.15
dissection tray filled with 113 level of water
b) Fixing the pins on the arms and 05% 4 0.20
legs of the rat
C) Giving deep incision from the center 07% 3 0.21
of thoracic region thereby removing the
fat bodies and exposing the internal organs
d) Puncturing the veins 15% 3 0.45
e ) Exposing the arteries 35% 4 1.40
(Note: Here it is important to see the number
of arteries, e.g., internal and external carotid)
f) Display of arterial system by putting 25 % 3 0.75
blackpaper-strips or photographic film strips
g) Diagram of arterial system 10% 3 0.30
3.46

Source: IGNOU (2004): Evaluation Perspectives in Higher Education, Instruction

in Higher Education. New Delhi: School of Education, IGNOU.

Validity and Reliability of a Rating Scale

Rating for intelligence and for special aptitudes can be validated against objective test
scores, but rating of personality traits cannot be so validated, since no objective test
scores are available for personality traits. In general reliability and validity increase
with the number of agreements when ratings are made independently.

Check Your Progress

Notes: a ) Space is given below for writing your answers.
b) Compare your answers with those given at the end of the unit.
1. Write the definition of a questionnaire and a rating scale.
................................................................................................................
................................................................................................................
................................................................................................................

49
Hesearch Design
2. State different types of a questionnaire and a rating scale.
................................................................................................................
................................................................................................................
................................................................................................................
3. In case of a questionnaire and a rating scale mention one major advantage and
one limitation.
................................................................................................................
................................................................................................................
................................................................................................................

13.3.3 Attitude Scales

Attitude scales have been designed to measure attitudes of a subject or group of
subject towards issues, institutions and group of people.
Allport referred to attitude as 'the most distinctive and indispensable concept in
contemporary American Social Psychology'. Thurstone boldly asserted that 'attitude
can be measured'. In view of these two quotes it is no surprise that attitude has
become an important concept in the field of education.

Meaning
Allport attempted to glean from the various definitions and arrived at three common
features -
a) preparation or readiness for favourable or unfavourable responses.
b) which is activated in the presence of all objects and situations with which the
attitude is related.
As per Barr, et. a1 (1953) - "An attitude may be defined as a learned emotional
response set for or against something".
Thrustone (1929) defines attitude as the degree of positive or negative affect associated
with some psychological objects. By a psychological object, he means any
institution,ideal, symbol, phrase, slogan, job or idea towards which people can differ .
with respect to positive or negative affect. The attitude is a personal disposition which
impels an individual to react to an object, situation or proposition in favourable or
unfavourable ways. For an attitude, there is continuous extending from favourableness
through neutral to unfavourableness.

Qpes of Attitude Scales

The most prevalent means of measuring attitudes is providing individuals with a list of
sentences or adjectives and asking them to respond to each sentence or adjective in
accordance with their true feelings. These lists are called as 'Scales'. Various 'scaling
techniques' have led to the development of different types of attidues scales. The
most frequently used scales are Linkert scale, Guttman scale, Thrustone scale and
Semantic Differential scale.

1) Likert Scale
Likert scale consists of a series of statements all of which are related to a person's
attitude towards a single object (e.g. -attitude toward school). Two types of statements
appear on Likert scales.
50
 The first type of statements whose endorsement indicates a positive or favourable Tools and Techniques
I
i) of Data Collectiun
attitude toward the object under consideration (called as favourable statements).
ii) The second type includes statements whose endorsement indicates a negative or
unfavourable attitude toward the object (called as unfavourable statements).
Equal number of favourable and unfavourable statements are included in a Likert
scale.

Modifications of Likert Scale

i) Modification of the response options - the original Likert scale included five
response options. In the use of odd number of options the respondent tends to
choose the 'not sure' option to avoid making real choice. With an even number
of option the respondent is forced to choose between favourable and unfavourable
respolises to the attitude object.
ii) Modification of the statement format has also been made. Incomplete statements
rather than complete statements have been used.
ic
Advantages of Likert Scale
i) easy to construct.
ii) adaptability to a wide variety of attitude objects, situations, settings
iii) ability to assess both -directions and intensity of attitude

Disadvantages of Likert Scale

Different respolise patterns can produce the same total score, hence not as sensitive
as Guttnian and Thurstone scales.
Example of an Attitude Scale
Directions: Indicate how much you agree or disagree with each statement by circling
the appropriate letter(s).
Key SA - Strongly Agree
Agree
Undecided
Disagree
Strongly Disagree
1. Science classes are interesting.
SA A U D SD 2. Science laboratory is dull and boring.
c SA A U D SD 3. It is fun working on science problems.
SAAUDSD 4. Class activities are good.
SAAUDSD 5. Reading the textbook is a waste of time.
6. The laboratory experiments are interesting.
SAAUDSD 7. Most class activities are monotonous.
SAAUDSD 8. I enjoy reading the textbook.
SAAUDSD 9. The problems we are studying are unimportant.
SAAUDSD 10. I am not very enthuslm.,tW about science.
Figure 13.1: Likert-type attitude scale for measuring attitude towards a science
course.
Source: N.E. Gronlund (1 981): Measurement and Evaluation in Teaching. 4th 4.
New Delhi: MacMillan.
Research Design 2) Guttman Scale
Guttman scale includes a set of statements which relate to a person's attitude towards
a single object. Guttman scale possesses two characteristics -
i) the statements included on such a scale represent increasingly positive feelings
with respect to the attitude toward an object.
ii) the endorsement of any statement implies the endorsement of each less positive
statement.

3) Thurstone Scale
Thurstone's technique is also known as the technique of equal appearing intervals. If
attitude is accepted as a uni-dimensional linear continuum, then Thurstone's proposal
to measure it by statements scaled by the method of equal-appearing intervals would
apply.

4) Semantic Differential Scale

It is a method for measuring aspects of the meaning of various concepts. It is widely
used as an attitude measurement technique. It consists of a set of seven-point-bipolar
scales and a set of concepts. Each concept is rated on each scale.

Uses of Attitude Scale

1) Attitude scales are used in educational research, especially for finding the attitudes
of persons on issues like co-education, religious education,international cooperation
etc. depending upon the need of the situation.
2) To obtain the measure of the belief of an individual or a group of individuals
towards some phenomenon the inquiry form attitude scale is used.

Limitations of Attitude Scales

1. As already stated, an individual may express socially acceptable opinions and
conceal his real attitude.
2. An individual may not be a good judge of himself and may not be clearly aware
of his real attitude.
3. He may not have confronted with a real situation to discover what his real attitude
towards a specific phenomenon was.
4. There is no basis for believing that the five positions indicated in the Likert Scale
are equally spaced.
5. It is unlikely that the statements are of equal value in 'far' or 'against' a
proposition.
6. It is doubtful whether equal scores obtained by several individuals would indicate
equal favourableness towards a given position.
7. It is unlikely that a respondent can validly react to a short life-qualifying situation.
8. Inspite of anonymity of response, individuals tend to respond according to what
they should feel rather than what they really feel.

Characteristics of a Good Attitude Scale

1) It provides for quantitative measure on a uni-dimensional scale of continuum.
2) It uses statements from the extreme positive position to extreme negative position.
3) It generally uses a four point scalt-. I S Strongly Agree (SA), Agree (A), Disagree
(D), Strongly Disagree (SD). Tht .ndividual gets the score as the sum of items
credits.
4) It is usually standardized and norms are worked out. Tools and Techniques
of Data Collection
5) It disguises the attitude object rather than directly asking about the attitude on the
subject.
It may require the judges to pile up the given statements and compute the scale values
according to the per$entage of judges who place each statement in the score on the
basis of the median scale values of the statements he has endorsed.
Validity of Attitude Scales
The attitude as denoted by the test score is compared with observable behaviour in a
corresponding situation, and the extent to which they agree is taken as a measure of
the validity of the scale.
Reliability of Attitude Scale
Most attitude scales have quite high reliability often between +0.75 and +0.90. The
more varied the items included in a scale, the greater is likely to be its reliability,
because variations in opinions about individual items are more likely to cancel out in
this case than when the items are all very similar.
The reliability of a test also depends on the heterogeneity of opinions expressed by the
individuals being tested, for greater the range of scores obtained, the higher will be the
correlation between sets of scores obtained on different occasions.

13.3.4 Check List

The check lists consist of a list of items or behaviours with aplace to check or to mark
'yes or no'. The chief purpose of the check list is to call attention to various aspects of
an object or situation, to see that nothing of importance is overlooked. It is a simple
laundry-list type of device, consisting of a prepared list of items. It is a type of
questionnaire in the form of a set of categories for the respondent to check. It is used
to record the presence or absence of the phenomena under study.
Four Common Styles of Constructing Check Lists
Types of Check Lists -
1. In one of the arrangements, all items found in a situation are to be checked, for
example, a subject may be asked to check by putting (P) in the blank beside each
activity undertaken in a school e. g.
- Games and sports ( )
- Mass drill ( )
- Dramatics ( )
2. In the second form, the respondent is asked to check with a yes or no and is
asked to encircle or underline the response to the given item.
3. In the third form all the items are positive statements with checks (P) to be
marked in a column on the right.
4. In the fourth form, the items are presented in sentences and the appropriate
response out of the supplied responses is checked, underlined or encircled.

Hints on Constructing and using a Check List

1. The list of items in the check list may be continued or divided into groups of
related items.
2. These lists are fomulated on the basis of the judgement of experts and then
each item is evaluated in respect of the number of favourable and unfavourable
responses.
53
Research Design 3. The items are arranged in categories and the categories are in a logical or
psychological order. Related items are grouped together.
4. Terms used in the items are clearly defined.
5. An intensive survey of the literature is made to determine the type of check list
to be used in an investigation.
6. Items are arranged in such a way that they are discriminative in quality to secure
the required information and details.
7. Check lists have the quality of completeness and comprehensiveness. A pilot
study is quite helpful in this direction.
Uses of Check Lists
The check list is an important tool in gathering facts for educational surveys.
It may also be used as a form for recording in observational studies of behaviour.
When used as a sort of scale to yield a score, it is an instrument often used in
educational appraisal studies of - school buildings, property, plan, textbooks,
instrumental procedures etc.
There are check lists designed for possible economies in a school, in the purchase
of school supplies, appraising of the superintendent's report and the organization
of high schools.
Check lists are also applied to classroom instructional activities, the studying of
the working habits of students, the supervision of classroom instruction and teacher
-pupil relationships.
The check lists which were built up in the Commonwealth Teacher Training
Study may be used in a number of ways both for analysis and for evaluation.
Another use of the check list is the checking of textbooks which deal with
topics related to teaching.
Personality is also sometimes rated by means of a check lists.
Many have made use of check lists in the Character Education Inquiry.
Check list is used for knowing the interest of the subject also, Kuder's Interest
Inventory and Strong's Interest Blank are essentially Check Lists.

Example of a Check List

Measurement of 'Y' by the Method of Flexture
Check List
(Put a tick against those steps enumerated below, which the student performed
correctly).
1. a) Determine : The vernier constant of the calipers
b) Measure The breadth of the beam
2. a) Determine : The least count of the gauge
b) Measure : The depth of the beam
3. Set the beam properly between the knife-edges to have the desired length
under study.
4. Measure the vernier constant of the trowelling microscope(Tm).
5. Place the frame containing the indicator (pin) properly on the beam (i.e. it
should be at the center perpendicular to the beam).
6. Focus the pin at the TM.
a) Measure the height of the tip of the pins from the surface of the table
and bring the operating part of the TM at the same height.
 Tools and Techniques
b) Use the hand to place the paper (or anything easily identitifiable) a of Data Collection
little away from the outer end of the objective lens of the TM.See
through the microscope and use the other hand to rotate the knob till
the object is sharply focused. Now measure the approximate distance
of this object from the objective lens. Let this distance be 'X'
C) Adjust the knob of the microscope so that the front side of the operating
tube is approximately as a distance 'X' from the pin. The pin should
get focused by this arrangement. If not, then give slight movement to
the operating tube in the possible directions and you will get the
sharply focused image of the pin. Make sure that there is no parallax
between the tip pf the pin and the horizontal cross-wire.
7. Take load vs. depression data
8. Draw load vs. depression graph
9. Take any one point on the graph, other the experimental point to calculate 'Y'
10. Point out the source of errors.
Source: IGNOU (2004): Evaluation Perspectives in Higher Education,
Instruction: A Higher Education. New Delhi: School of Education, IGNOU.
The above check list is an example of assess a particular instructional process. It aims
to find out whether a particular itemlobject exists or not but not its extent/proportion or
quality.

13.3.5 Tests
With the help of tests we can collect quantitative data in research. There are different
type of tests. It was the English biologist, Sir Francis Galton, who was primarily
responsible for launching the testing movement. In an article written by Cattell in 1890
,the term 'mental test' was used for the f m t time. Psychologicaltesting is arelatively
young bfanch of one of the youngest of the sciences.
What is a Test ?
A Test is a systematic procedure for observing a per~on'sbehaviour and describing it
with aid of a numerical scale or a category system. A PsychologicalTest is essentially
an objective and standardized measure of a sample of behaviour.
'Qpes of Tests
Tests are classified in different ways.

Classificationof Tests

I I
By function By nature BY
Procedure of
Administration

i)
I
Group tests
(achievement & ii) Power tests ii) Individual tests
diagnostic) iii) Verbal tests
ii) Personality tests iv) Non-verbal tests
iii) Aptitude tests v) Performance tests
vi) Standardized tests
vii) Criterion-referenced tests
viii) Culture fair tests
ix) Adapted tests
55
Research Design Let us now understand the meaning of this classification. We will also get information
about various tests in details.
1. Classification of the Tests as per their Nature
Depending upon what a test aims to measure the tests are classified into one group.
(i) Educational Tests - Certain types of tests are developed for use in educational
context. They include achievement tests and diagnostic tests.
Achievement tests are designed to measure the effects of a specific programme
of instruction or training. An achievement test measures the effects of relatively
standardized sets of learning experiences. It generally represents a terminal
evaluation of the individual's status on the completion of an instructional programme
or training. An achievement test measures developed abilities/skills.
Diagnostic tests are designed to analyze individual specific strengths and
weaknesses in a subject and to suggest causes of hislher difficulties.
In connection with the use of all diagnostic tests , one point deserves special
emphasis . The diagnosis of the learning disabilities is the prerequisite for a
programme of remedial teaching.
(ii) Personality Tests -These most often refer to measures of affective aspects of
behaviours such as emotional states, interpersonal relations, motivation, interests
and attitudes. A personality test could be a self report inventory, a situational test
or the third approach could be the application of projective technique.
(iii) Aptitude Tests -These measure the effects of learning under relatively (in
comparison with achievement tests) uncontrolled and unknown conditions. They
include general intelligence tests, multiple aptitude batteries, special aptitude tests
(e.g. creativity tests) etc.
Intelligence tests are designed to measure the intelligence of an individual. Here, we
must bear in mind that intelligence is not a single, unitary ability but a composite of
several abilities. The term is commonly used to cover a combination of abilities required
for survival and advancement within a peculiar culture. (e.g. Stanford Binet test of
intelligence)
Multiple Aptitude batteries yield a profile of test scores in set of relatively independent
abilities identified through factor-analysis. One of the most widely used multiple Aptitude
batteries is Differential Aptitude Test. This DAT yields scores on eight abilities -
Verbal reasoning, Numerical ability, Abstract reasoning, Clerical speed and accuracy,
Mechanical Reasoning, Space relations, Spelling and language Usage.
Creative Aptitude Batteries have been produced at University of Southern California
by J.P. Guilford & his colleagues, and 'Tests of Creative Thinking' by Paul Torrance.
2. Classification of the Tests as per their Nature
(i) Speed Tests are those tests which contain such items which are of somewhat
equal difficulty value. To solve the tests the time limits are very much fixed. e.g.
our usual school/college tests.
(ii) Power tests are those tests which contain items of different difficulty value
arranged in increasing order of difficulty value . For such tests time limit is not
fixed, it is flexible.
(iu) Verbal Tests include question answer pattern in the form of 'words'. Such verbal
tests can be either paper pencil (written) tests or oral tests.
(iv) Non-verbal Tests necessarily contain items in the figural or symbolic form i.e.
other than 'words'. Raven's Progressive Matrices Test is a non-verbal test.
(v) Performance Tests require some action on part of the respondent as histher
response. Bhatia's Intelligence test is a performance test.
56
 Tools and Tkchniqucs
(vi) Standardized Tests imply uniformity of procedure in administering and scoring of Data Collection
the tests. Another important aspect of standardized tests is the establishment of
norms, reliability and the validity of the tests.
I (vii) Criterion referenced Tests have been contrasted with the usual norm-referenced
t tests in which an individual's score is interpreted by comparing it with the scores
I obtained by others in the group on the same test. Unlike in a norm-referenced
test, in a criterion referenced test an individual's score is interpreted by comparing
it with an external criterion e.g. '80x80 mastery level'.
(viii) Culture fair Tests presuppose only such experiences that are common to different
cultures. The terms 'culture-fair', 'culture-common', and 'cross-cultural' are
used synonymously and have replaced the term 'culture-free'.
(ix) Adapted Tests are the versions of the tests standardized in other countries in
dissimilar cultures and modified to suit the culture under consideration.

I ' 3. Classification of Tests as per the Procedure of Administration

(i) Group Tests are designed as mass testing instruments. They permit the
simultaneous testinglexamination of large groups. The instruction and
administration procedures are simplified so as to demand a minimum of training
on the part of the test administratorlexaminer .
(ii) Individual Tests are those which can be administered to one individual at a time.
In view of the testing situation including response in the form of actual
performance, the observer can record the entries in the performance sheet for
one candidate at a time.

4. Basic Characteristic of a Standardized Test

i) Norms - Norms represent the test performance of the standardization sample.
The norms are empirically established by determining what persons in a
representative group actually do on the test. The norms, by converting raw scores
into derived scores are expressed in one of the two major ways -
(a) developmental level attained and
(b) relative position within a specified group. Age Norms, Grade Norms are
the examples of developmental Norms , whereas Percentiles ,Standard-
scores are the examples of within Group Norms.
ii) Reliability of a Test - As used in psychometrics, the term reliability means
consistency. Test reliability is the consistency of scores obtained by the same
persons when retested with identical or equivalent form of the test.
(a) Test-retest Reliability - a test is administered to a sample at two different
occasions with some interval in between. The correlation between the two
sets of scores is the reliability coefficient. It is the extent to which scores
on a test can be generalized over different occasions.
(b) Split-half Reliability - The procedure to establish the split-half reliability
involves one-time administration of the test. The scores obtained by the
sample are grouped into two sets. This grouping is done mostly by separating
the even items in one group and odd items in another for every candidate.
Thus we get a pair of total scores fcr ,-.I one. Correiatioa !:.tween those
two scores is the reliability coefficient. It is the measure of internal
consistency of the test.
(c) Alternate Form Reliability - Pertaining to the objectives, two parallel
tests are constructed and they are administered to the sample with some
interval in between. The correlation between these two scores is the reliability
coefficient. It is the measure of both temporal stability and consistency of
response to different item samples. 57
Research Design Validity of a Test
The validity of a test concerns what the test measures and how well it does it.
All procedures for determining test validity are concerned with the relationship
between performance on the test and other independent observable facts about
the behaviour characteristics under consideration. The specific methods employed
for investigating these relationships are classified under three principal categories
- content, criterion-related and construct validity.
(a) Content Validity - Content validation involves essentially the systematic
examination of the test context to determine whether it covers a
representative sample of the behaviour domain to be measured. It is
commonly used in case of achievement tests.
(b) Criterion related Validity - It refers to two types of validity under different
time frames.
Predictive validity - If a test is designed to pickup good candidates for appointment
as teachers, and test scores show a high positive correlation with actual
performance on the job, the test has a high degree of predictive 'validity. Thus
predictive validity refers to the usefulness of a test in predicting some future
performance. It is important particularly for aptitude tests.
Concurrent validity - The coefficient of correlation between the test scores and
scores on another test or measure of known validity is the concurrent validity of
the test. If both the tests are similar (e.g. creativity tests) then in that case it is
known as convergent validity and contrasted with this if the tests are of different
type in that case it is known as discriminant validity.
Construct validity - It is the degree to which scores on a test can be accounted
for by the explanatory constructs of a sound theory. If one were to study such a
construct as 'originality' one would hypothesize that people who have this
characteristics will perform differently from those who do not. Theories can be
built describing how people with 'originality' behave in a distinctive way. If this is
done, such people can be identified by observation, rating them in terms of the
theory. A device could then be designed to have construct validity to the extent
that the scores on this device are systematically related to the judgement made
by observation of behaviour identified by the theory as possessing 'originality'.

Check Your Progress

Notes: a) Space is given below for writing your answers.
b) Compare your answers with those given at the end of the unit.
4. State the definition of the following -
Attitude Scale, Check List, Test.
..............................................................................................................
..............................................................................................................
..............................................................................................................
5. What are the different types of Attitude Scale?
..............................................................................................................
..............................................................................................................
..............................................................................................................
58
 Tools and Techniques
6. Elaborate the classification of tests, with one example each. af Data Collection

..............................................................................................................
..............................................................................................................
..............................................................................................................

13.3.6 Inventory
An inventory is a kind of self-report instrument. The individual checks responses to
certain questions or statements. Inventories yield scores which are assumed or have
been shown to measure certain tendencies or traits.
Interest inventories attempt to yield a measure of the types of activities that an individual
has a tendency to like and to choose. In 1907, Hall, a psychologist, standardized
Recreational Interest Inventory and in 1934, Kuder, another psychologist, standardized
Occupational Interest Inventory.
Q p e s of Interest Measurement
1. Direct Questioning - It presents questions like - 'Do you like to play cricket?'
2. Direct Observation - Behaviour of the individual is observed and it is found out
in which activities the individual is more interested.
3. Tested Interest - The individual is exposed to various experiences related to
different types of interests and it is observed in which area the individual is
showing more interest.
4. Interest Inventory - This is most preferred way of measuring interest. It consists
of various statements and the individual is asked to arrange them in order of
preference. Mostly interest inventories are of verbal type.
5. A Personality Inventory attempts to measure certain personality traits such as
individual need, adjustment, etc. It consists of questions of 'Yes /No' type.
Advantages
1) Interest inventories are useful in educational and vocational guidance.
2) They are helpful to the teachers to provide educational facilities to the students
as per their interests. ,-

3) Individual as well as group administration is possible.

4) Personality inventories have been proved valuable in diagnosisin clinical situations
for the psychiatrists.
5) An inventory is not very much time-bound.
6) For administering the inventory trained person is not required.
Limitations
1) Because of individuals' inability or unwillingness to report their own reactions
accurately or objectively these instruments may be of limited value.
Part of this limitation may be due to the inadequate theories of personality upon which
some of these inventories have been based.

13.4 TECHNIQUES OF DATA COLLECTION

We can collect the requisite data for the research in hand employing some techniques.
Following particular techniques, interview schedules and observation schedules can
be prepared for the purpose of data collection. Let us get information about these in
details.
59
Research Design
13.4.1 Interview
Interview is a two-way method which permits an exchange of ideas and information.
As a research technique, the interview is a conversation carried out with the definite
purpose of obtaining certain information by means of the spoken word.

Types of Interviews
1) In structured interviews the same questions are presented in the same manner
and order to each subject and the choice of alternative answers is restricted to a
predetermined list. These interviews are rigidly standardized and formal, but they
are more scientific in nature than unstructured ones.
2) unstructured interviews are flexible, few restrictions are placed in respondent's
answers. In this interview, one can penetrate behind initial answers, follow up
unexpected clues.

Procedure of Interview
As a technique of data collection good interview requires
i) Preparing for interview -
The following factors need to be determined in advance of the actual interview.
clear conception of the purpose and of what information is needed.
e kind of interview - individual or group.
A clear outline or schedule of the best sequence of questions.
A well thought plan for recording responses.
ii) Conduct of interview (execution) -
The initial task of securing the confidence and co-operation of the subject what
is called - rapport -requires an expertness and sensitivity almost amounting to
art.
securing desired information through asking questionsin the planned sequence
should be done in not too rigid a manner but with stimulatingand encouraging
comments and necessary explanations and recordings.
The recording device selected should be used without distracting the
interviewee.
Before an interview study is undertaken, the interviewer should undergo
rigorous training.
iii) Recording and Interpreting Responses -
it is best to employ, if possible, a device of recording which would retain the
actual wording of the responses. Tape-recording is convenient and not too
expensive if tape-recorder is available.
If the responses to questions in the interview have to be noted down, it can
be done either simultaneously with the interview or immediately after it.
Sometimes, instead of recording responses, the interviewers tend to record
their evaluations of them as the interview goes on.

Advantages of Interview
i) The interview, with skillful interviewers, is much superior to other data gathering
devices.
ii) It is specially appropriate when dealing with young children, illiterates and in an
abnormal state of mind.
60
iii) It is used for practical purposes rather than for gathering data for research. It is Tooh and TKbniques
of Data Collection
used for student counseling, selection of candidates for education etc.
iv) In interview the investigatorcan create a right type of friendly atmosphere which
is very conducive for obtaining desired data.
V) If necessary the interviewer can give assurance to the interviewee that the facts
wi 11 be properly used.
vi) It permits even exchange of ideas and information. It provides opportunity for
give and take.
i The respondent's difficultieslike bad handwriting, poor expression are also avoided
as every schedule is filled by the interviewer.
viii) The personal contact with the respondent enables the interviewer to probe more
deeply into the character of the respondent.
ix) The data gathefed through interviews have been found to be fairly reliable.
X) There is possibility of crossquestioning and putting supplementary questions.

Litations of Interview
i) This technique is time-consuming and one of the most difficult ones to employ
successfuIly.
ii) There is constant danger of interviewer bias.
iio The objectivity, sensitivity and insight of the interviewer is crucial. This pmcedum
requires a level of expertness not ordinarily possessed by an average research
worker.
iv) A busy person may prefer to fill out a questionnaireat leisure rather than submit
to a long interview.
V) The respondent suffers from four limitations-
a) his experience as an interviewee.
b) his judgement about himself.
C) his accessibility and readiness to divulge the information.
d) his ability to express himself clearly.
vi) The recording of data from an interview is full of dficulties.
vii) Tape recording of the entire interview is likely to be expensive of time and
money.
viii) It does not work well with infants, shy people, deaf people and mad people.
13.4.2 Observation
Observation is a more natural way of gathering data. It seeks to ascertain what people
think and do. By watching them in action as they express themselves in various situations
and activities.
'Qpes of Observation
1. Participant and Non-participant Observation - In participant observation; the
observer becomes more or less one of the group under observation. In such situations,
the observer will be in sight of the person being observed and may actually take part
in some activity with the individual or group. The observer may play as one of several
roles in observation, with varying degree of participation, as a visiting stranger, an
attentive listener, an eager learner, or a more complete role as participant observer.
In Non-participant observation, the observer remains aloof from the group. He keeps
his observation as inconspicuous as possible. It is used with such groups as those of
infants, children or abnormal persons. 61
Research Design 2. Structured and Non-structured Observation - In structured observation the
investigator must be ready to shift from his original plans to the study of aspects which
he sees as more significant.
The observation is wide and unstructured in the early stages, it gets restricted and
structured as the investigation proceeds.

Stages in the process of Observation

As a good data collection technique observation needs -

1. Planning for Observation

The factors one must consider in detail while planning to employ observation as a
research tool includes:
Definition of specific activities.
An appropriate group of subject to observe.
Scope of observation - individual or group.
Determination of length of each observation period.
Deciding about the instruments and the form of recording and physical position
of the observer.
Determining the special conditions required for subjects.
Preparation of proper tools for recording observation.
Gettirig oneself trained in terms of expertness of an observer.

2. Execution of Observation
An expert execution demands :
Proper arrangement of special conditions for the subjects.
Assuming the proper physical position for observing.
Focusing attention on the specificactivitiesor units of behaviour under observation.
a Observing directly, the length and number of periods and intervals decided upon. '

Handling well the recording instruments to be used.

Utilizing the training received in terms of expertness.

3. Recording and Interpreting Observations

The two common procedures for recording observation are -
Simultaneous- when the observer goes on recording his observations
simultaneously with the occurrence of the phenomena observed, as in time
sampling.
Soon after the observation - when the observer undertakes to record his
observations not simultaneously with his actual observation process, but
immediately after he has observed for a unit of time, while the details are still
fresh in his mind.

Advantages of Observ'ation
1. Observation as a research technique is being refined and made exact to an extent
that it is likely to make an important contribution in descriptive research.
2. Significant aspects of personality which express themselves in behaviour can be
best studied directly through observation rather than indirectly through
questionnaire and interview.
 3. Simple observation of physical aspects of school buildings or students and teachers, Tools and Techniques
of Data Collection
etc. is made through physical examination, measurement, assessment and
comparison with fixed standards.
4. Observation of physical activities as in games and in the workshop is made directly
very often for coaching purposes.
. 5. Observation in the classroom is made to analyse learning behaviour which is a
more complex phenomenon, and to improve classroom performance.

Limitations of Observation
1. Establishing the validity of observation is always difficult. Many of the items of
observation cannot be defined with sufficient precision.
2. 'The problem of subjectivity is also involved. A person tends to see what he
knows.
3. There is also the danger of concentrating in an observation on the aspects of
limited significance simply because they can be recorded objectively and
accurately.
4. There is the possibility of distortion of the phenomena through the very act of
observing.
5. Also the observer tends to see only those things which he wants to see.
6. Usually when an observer goes to the scene, the situation is new to him.
7. The incidents described may be samples of rarely occurring behaviour. The
observer fails to obtain an adequate sample of data on the basis of which
conclusions can be drawn.
8. The lack of competence of the'observer may hamper validity and reliability of
observation.
9. The people being observed become conscious and begin to behave in an unnatural
manner.
10. It is a slow and laborious process. A particular-situation which is desired to be
observed might not occur for a very long time.
11. The data may be unmanageable. It would be difficult to arrange the behaviours
along a continuum.
12. It is going to be a costly affair. It involves expenses on traveling, staying at the
place of phenomena.

13.5 DOCUMENTS
Documents are the ready-made records which provide data to the researcher in
. relation to the research problem under consideration .They contain the dataof remote
periods and places for scientific analysis. Since the content of the document is itself
the data, it does not depend upon a specific investigator. The system of recording the
data is already determined by the person(s) other than the researcher .
Types of Documents - Documents are categorized in three ways
1. Expressive Documents
These specify the process of social interaction and include personal letters ,diaries ,
biographies, autobiographies . Such types of documents are more used and useful for
data collection in historical researches and in case studies .
2. Official Records
These documents provide useful information about the time and frequency of the
occurrence of an event. Such data cover a wide range of events e.g. birthdate, 63
Research Design attendance and progress records of the students; data related to particular courses,
result sheet etc. They also include the records of the minutes of the school committee
meetings, minutes of various university meetings such as the meetings of academic
council, board of studies etc. The annual reports, budgets and the pictorial records
(e.g. photographs, videos) also comprise the official records.
The official records are useful in knowing and understanding past events and trends
so as to gain perspective on the present and the future. They are helpful in studying
the administrative pattern of the institution. They yield the data useful in historical and
survey type researches and also in case studies .

13.6 CHARACTERISTICS AND CRITERIA FOR

SELECTION OF A GOOD TOOL
13.6.1 Validity
A good research tool must actually measure what it is supposed to measure. A test is
valid, if it meets the purpose for which it was designed. Validity is basic, we may
consider validity in terms of categories such as high, moderate or low validity.
Furthermore validity is specific, a test may be valid for one purpose but not valid for
another. A data collection tool must be a valid one.

13.6.2 Reliability
The second important quality of a measuring instrument is its reliability or consistency.
A reliable test is one which measures accurately and consistently. If a reliable test is
given two or three times to the same group, each person in the group should ge't
approximately the same score on all occasions. Reliability is a statistical concept. To
determine the reliability of a test, it must be administered to a group of individuals
under appropriate circumstances. Reliability can be expressed by a correlation
coefficient.

13.6.3 Objectivity
A test is objective when the examiner's personal judgement does not affect the scoring.
An objective test is one for which the items can readily be scored as right or wrong.
Such item types as multiple choice, matching, true-false are objective. Objectivity is a
prerequisite to reliability in a test. Objective judgements are accurate and hence tend
to be reliable. Hence data collection tool must be objective.

13.6.4 Adequacy
The careful test maker never assumes that the instrument he has constructed is capable
of measuring all of the factual knowledge or skills that apupil has acquired in a school
course .Adequacy is a prerequisite to the reliability as well as to validity of a test.
Hence the data collection tool must be adequate.

13.6.5 Usability
The most valid test in the world will do nothing to improve the school programme if it
is not used. Usability or practicality is an important criterion for assessing the value of
a test. Usability of a test depends upon a number of factors.
i) Ease of Administration - Directions for administering the test should be simple
and clear, and the timing of the test should not be too difficult for adjustment.
ii) Ease of Scoring - If algebraic manipulations are required to get the scores or if
the original raw scores require to be converted into complicated derived scores,
teachers will avoid to use such a test.
 iii) Ease of Interpretation - In the final analysis, the success or failure of a testing Tobh and Techniques
of Data Coiieetion
programme is determined by the use made of test results.
iv) Economy - Economy is certainly one of the major criteria of a good test. Real
economy in testing will not be achieved by the indiscriminateuse of cheap tests,
but it is equally true that users will avoid buying costly instruments and tests.
Economy also refers to the time required for administering and scoring the test.
i
V) Availability of Equivalent Forms - Equivalent forms of a test measure the same
I aspects of behaviour by using test items which are alike in content, level of
difficulty and other characteristics. Thus one form of the test can substitute the
I other. Equivalent forms are especially valuable when these are used for research
purposes.
The data collection tool must be a usable one.

13.6.6 Discriminating Power

A test discriminates well when it is constructed in such a manner that it will detect or
measure small differences in achievement and when it picks out the good from the
poor. This quality of a test directly affects its validity, so this also becomes an essential
II criterion of selecting the data collection tool.

13.6.7 Interest
Tests that are interesting and enjoyable help to gain the cooperation of the subject.
Under unfavourable conditions, the test is not likely to yield useful results. Hence,
from amongst the available the one satisfying all other criteria, the interesting tool
should be selected for data collection.

Check Your Progress

Notes: a) Space is given below for writing your answers.
b) Compare your answers with those given at the end of the unit.
7. Define the terms - Interview and Observation.
................................................................................................................
................................................................................................................
8. State different types of Interview and Observation.
................................................................................................................
................................................................................................................
9. Give one major advantage and one limitation of interview and observation as
techniques of data collection.
................................................................................................................
................................................................................................................
10. List different criteria of selecting a good tool of data collection.
................................................................................................................
................................................................................................................
1 1 . State the importance of Document in data collection .
................................................................................................................
................................................................................................................
Research Design
13.7 LET US SUM UP
In this unit we have provided information about data gathering tools and techniques.
i
Questionnaire, rating scales, attitude scale, checklist, tests are the major tools and
interview and observation are the major data gathering techniques.
We discussed the meaning of questionnaire, rating scale, attitude scale, test, interview
and observation. Along with the meaning of each one of these, we also explained their
advantageduses and limitations.
Because each data-gathering device has its own particular limitations, it is advisable
to use multiple methods, supplementingone with others to counteract bias and generate
more adequate data.
Many wiiters have argued the superiority of the interview over the questionnaire, or
the use of the psychological test over the interview. The late Arvil S. Ban,University
of Wisconsin, a teacher and a researcher, resolved discussions of this sort by asking,
'Which is better, a hammer or a handsaw?' Like the tools in the carpenter's chest,
each is apl;roPriate in a given situation.

13.8 UNIT-ENDACTIVITIES
- --- - - - -

1. Refer to the dissertations/theses available in the local universities/post graduate 1

colleges. List the tools used for data collection, along with the objectives and
type of the tool.
i
2. Go through the various psychological tests and read the manuals as well.

13.9 POINTS FOR DISCUSSION

1. What are the different phases of standardizing a test?
2. How to frame a good question?

13.10 SUGGESTED READINGS

Ban; A.S., Robert, A. Davis and Plainer, 0.Johnson (1953): Mutational Research
and Appraisal. Chicago: J.B. Lippincott.
Best, John. W. and Kahn, James. V. (1995): Research in Education. 7"' edition,
New Delhi: Prentice Hall of India. '
Borg, Walter R. (1989): Applying Educational Research, A Practical Guide for
Teachers. 2" edition, New York: Longman.
Dandekar, W.N. (1986): Evaluation in Schools. Poona: Vidya Prakashan.
Kerlinger, Fred. N. (1993): Foundations of Behavioural Research. New York: Holt,
~ i i e h a rand
t Winston.
Sukhia, S.P., Mehrotra, P.V., Mehrora, R.N. (1996): Elements of ~ a z i oResearch.
~ l
2" edition, New Delhi: Allied Publishers Pvt. Ltd.
Keeves, John. P. (ed.) (1998): Educational Research. Methodology and
Measurement, An International Handbook. London: Pergarnon Press.
Evans, K. M. (1972): Attitudes and Interest in Education. London: Routledge and
Kegan Paul.
Edwards, Allen. A. (1969): Techniques of Attitude Scale Construction. New York:
Appleton Centrurt Crofts.
Groundlund, N.E. (1981): Measurement and Evaluation in Teaching. 4"'ed., New Tools and Tecbnlqucs
of Data Collection
Delhi: McMillan Publishing Co.
Koul, Lokesh (1997): Methodology of Educational Researrh. New Delhi: Vikas
Publishing House Pvt. Ltd.
Thrustone, L.L. & E.J. Chave (1 929): The Measurement of Attitude. Chicago: The
University of Chicago Press.
Tuckman, B .W. ( 1972): Conducting Educational Research. New York: Harcourt
Brace Jovanovich.

13.11 ANSWERS TO CHECK YOUR PROGRESS

I. Questionnaire - A set of questions prepared to obtain factual information with
regard to the topic under study.
Rating Scale - It is the qualitative description of some aspects of a thing or of
traits of a person, classified into five to seven categories.
2. Types,of Questionnaire
i) Structured Vs. Non-Structured - Where the former includes directed
questions and the latter non-directed.
ii) Closed form Vs. Open form - The first one calls for fixed responses and
the second one calls for free responses.
Types of Rating Scale
i) Numerical rating scale - where the ratee checks a number to indicate the
degree of presence of a characteristic.
ii) Descriptive - Graphic rating scale - uses descriptive phrases to identify the
points on a graphic scale.
iii) Graphic rating scale - the rater marks a cross or a check on a horizontal
line representing a characteristic, to indicate the presencdabsence of a
given chancteristicttrait.
iv) Ranking method - in terms of possessing the characteristic being judged,
the rater simply ranks in order.
V) Standad scale - against a standard provided to the rater, rating is done.
vi) Forced Choice scale - the rater is supposed to only mention whether or not
the rater has one or more traits.
3. Advimtage of
Questionnaire - Most preferred tool when the respondents are scattered far and
wide.
Rating Scale - Useful in the field of rating teaching and teachers.
Limitation of -
Questionnaire - Respondents who return the questionnaire may not constitute a
representative sample.
Rating Scale - Dominated by subjectivity.
4. Attitude scale - is a list of sentences or adJ:, ives to obtain responses from an
a

individual, to each sentence or adjective as per hisher true feelings.

Check list - is a list of items or behaviours to indicate the presence or absence of
that item behaviour.
5. Types of Attitude scale -
Likert scale, Guttman scale, Thurstone scale and Semantic Differential scale are
the four types of Attitude Scale.
Research Dcsign 6. Classification of Tests -
As per the Function-
i) Educational tests.
ii) Personality tests. (Allport - Vernon)
iu) Aptitude Tests (DAT)
As per the Nature -
i) Speed Tests (usual school/college tests)
ii) Power Tests (Raven's Progressive Matrices Test)
iii) Verbal Tests (usual school tests)
iv) Non-verbal Test (Raven's Progressive Matrices Test)
V) Performance Test (Koha's Blocks Tests)
vi) Standardized Test (Raven's Progressive Matrices Test)
vii) Criterion - referenced Tests.
viii) Culture fair Test (Raven's Progressive Matrices Test)
ix) Adapted Tests (Kulhman's Test of Intelligence adapted by Gnyan
Prabodhini, Pune)
As per the mode of Administration -
i) Group tests (Cattel's personality test)
ii) Individual test (A Performance Test)
7. Interview - is a technique of asking questions and getting responses orally and
face-to-face.
Observation - is a technique of collecting data directly by attending activities of
an individual in different settings.
8. Types of Interview -
i) Structured interview - same questions are asked in same order.
ii) Unstructured interview -has flexibility in framing and deciding the order
of the questions.
n p e s of Observation -
i) Participant Vs Non-participant Observation - In the first one, observer is
one of the members of the group being observed whereas in the other one
observer is outsider to the group.
ii) Structured Vs Non-Structured Observation - Observer plans as per the
significant aspects of situation in structured observation whereas in non-
structured one, initially it is wide.
9. Advantage of -
Interview - Useful in case of young children, illiterates and in an
abnormal state of mind.
Observation- Significant aspects of behaviour can be studied directly.
Limitation of -
Interview - lime consuming, very much dependent on the interviewer.
Observation - All the significant aspects can not be observed
simultaneously.
10. Criteria of selecting a good tool of data collection -
The tool to be selected should be -
 Tools and Techniques
i) reliable of Data CoIIectLon
ii) valid
iii) objective
iv) adequate
V) usable
vi) possessing satisfactory discriminatingpower and
vii) of interest to the respondents.
1 1. The documents are very important tools of data collection. Expressive documents
specify the process of social interaction. The official records provide information
regarding the time and frequency of occurrence of past events and trends. Hence
the documents are useful in historical and survey researches and in case studies.

13.12 GLOSSARY
Attitude A moderately intense emotion that prepares or
predisposes, an individual to respond consistently
in a favourable or unfavourable manner when
confronted with a particular psychological object.
Attitude Scale It is the most prevalent means of measuring attitude
which provides individuals with a list of statements
and asks them to respond to each statement in
accordance with their true feelings.
Observation A technique of collecting data by directly examining
the activities of an individual in different settings.
Qualitative Data Descriptive narrations, responses to open ended
questions, quotations, field notes etc are qualitative
data.
Quantitative Data Numerical figures or ratings are quantitative data.
Questionnaire A set of questions dealing with psychological, social,
educational or any other topic sent to an individual
or a group with the purpose of obtaining factual
information with regard to the topic under study.
Rating Scale It is the qualitative description of a limited number
of aspects of a thing or of traits of a person. The
classifications may be set up in five to seven
categories.
Reliability It is the extent to which a tool is consistent in
measuring whatever it may measure.
Test A psychological test is an instrument designed to
describe and measure a sample of certain aspects
of human behaviour.
Check List A Check List is a prepared list of behaviours or
items to indicate the presence or absence of the
bahaviours or the item.
Data All relevant materials, past and present, serving as
basis for research study and analysis is the data.
Interview It is a technique of asking questions and getting
responses orally in face-to-face situation.
Validity The extent to which adevice does the job for which
it is designed is its validity.
69
NOTES