Method of data collection

Islamic University Nursing College

Introduction
The data collection methods used by researchers
need to be objective and systematic.
Objective:
The data must not be influenced by
anyone who collects the information.
Systematic:
The data must be collected in the same
way by everyone who is involved in the
collection procedure.

Operationlization:
Is the process of translating the concepts of
interest into a researcher to observable and
measurable phenomena.
N.B: There may be a number of ways to collect
the same information.
Example:
Measuring anxiety by measuring sweat gland
activity or by administering an anxiety scale.

Measuring Variables of Interest

The success of the study depends to a large extent

on the quality of the data collection methods chosen
and employed.

There are many types of methods for collecting

information.

Determining what measurement to use in a

particular investigation may be the most difficult and
time consuming period in study design.

The method of data collection must be appropriate

to the problem, the hypothesis the setting, and the
population.

Selection of the data collection method begin during

the literature review . The researcher begins to
explore how pervious investigators defined and
operationalized variables similar to those of interest
in the current study.

Operational definition translates the conceptual

definition in to behaviors or verbalizations that
can be measured for the study.

The construction of new instruments for data

collection that have reasonable reliability and
validity is the most difficult task.

Consistency means that the data are collected

from each subject in the study in exactly the
same way or as close to the same way as
possible. It can minimize the bias introduced
when more than one person collects the data.

 Inter-rater reliability is the consistency of

observations between two or more observers,

it often is expressed as a percentage of
agreement among raters or observers or a
coefficient of agreement that considers the
element of chance (coefficient Kappa).

Data Collection Methods

Physiological.
Observational.
Interviews.
Questionnaires.
Records or available data.

Physiological data collection

Physiological and biological

measurements involve the use of
specialized equipment to determine
physical and biological status of subjects.
Such measures require specialized
training.
Such measures can be :
1. Physical such as weight or temperature.
2. Chemical such as blood glucose level.
3. Microbiological as with cultures.
4. Anatomical as in radiological examinations.

These measurements require special equipment to

make the observation.
Example: Measuring temperature by a thermometer.

These measurements needs careful standardization of

the procedures so that the instruments were all used in
the same way.

It is important for determining the effectiveness of

certain nursing action.

Advantages of using physiological

:data collection methods include
1.
2.
3.

Objectivity.
Precision. (accuracy)
Sensitivity.

Disadvantages of using physiological

:data collection methods include
1.
2.
3.
4.

Some instruments may be quite expensive

to obtained.
Often require specialized knowledge and
training to be used accurately.
Just by using them, the variable of interest
may be changed.
The presence of some types of devices
might change the measurement.
Example: the presence of a heart rate monitoring device might
make some patients anxious and increase their heart rate.

5.

Nearly all types of measuring devices

are affected in some way by the
environment.

6.

There may not be a physiological way to

measure the variable of interest.

7.

If the device does not really measure

the phenomenon of interest, the validity
of its use is suspect.

Observational Methods
Sometime nurse researchers are interested

in determining how subjects behave under

certain conditions.
Observation is not merely looking at what is

happening, but rather is watching with a

trained eye for certain specific events.

Observational must fulfill the

:following
1.
2.

3.
4.

Consistent with the studies specific

objectives.
There is a standardized and systematic
plan for the observation and the
recording of data.
All of the observation are checked and
controlled.
The observations are related to scientific
concepts and theories.

Observation is suitable when

:dealing with

Nursing process.

Parent-child interaction.

Verbal & nonverbal communication behaviors.

Activities and skill attainment.

Environmental characteristics

Description of sleep.etc.

:Types of observational roles in research

1.

Concealment without intervention.

2.

Concealment with intervention.

3.

No concealment without intervention.

4.

No concealment with intervention.

Concealment
Yes

No

Intervention

Yes

Researcher
hidden some
intervention

Researcher
open
Some
intervention

No

Researcher
hidden no
intervention

Researcher
open no
intervention

Types of observational roles in research.

1- Concealment without
intervention:

It is used when a researcher is concerned that

the subjects behavior will change as a result of
being observed. The researcher watches the
subjects without their knowledge of the
observation but he does not provoke them into
action. (Example: hidden television cameras).

It usually used in observational studies of

children ( developmental research).

Concealment with- 2
:intervention
It is used when the researcher
believed that by being open to
the subjects, the subjects
behavior would change.

3- No Concealment without
intervention:

It this case the researcher obtains informed consent

from the subjects to be observed and then simply
observes their behavior.

The observer makes no attempt to change the

subjects. The problem with this type of observation is
reactivity, Hawthorne effect occur when the subject
know that he observed and change his behavior.

4- No Concealment with
intervention:
The researchers were not concealed
in their observations but they did
intervene with the subjects.
It is employed when the researcher
is observing the effects of some
intervention introduced for scientific
purposes.

Debriefing
when observing subjects without their knowledge
you may violate assumption of informed consent.
The problem is often handled by informing subjects
after the observations and allowing them
opportunity to refuse to have their data included in
the study and to discuss any question they might
have.

Structured and unstructured

observations:
Observation may be:
1.
2.

Structured
Unstructured

Structured Observations

Involve specifying in advance what behaviors or events are to

be observed.

Preparing forms for record keeping such as categorization

system, checklists, and rating scale.

The observer watches the subject and then marks on the

recording form what was seen.

The observations must be similar among the observers.

It is important that observers be trained to be consistent in

their observations and ratings of behavior.

Unstructured Observations

Unstructured observational methods:

Are not characterized by a total absence of structure but
usually involve collecting descriptive information about the
topic of interest. such as participant observation and use of
anecdotes).

:Advantages of scientific observation

1.

It may be the only way to study the variable of interest

(such as studying human behavior).

2.

It may be the only way to ensure the validity of the findings.

3.

No other data collection method can match the depth and

variety of information that can be collected when using
these techniques.

4.

It is quit flexible in that it may be used in both experimental

and nonexperimental designs and in laboratory and field
studies.

:Disadvantages of scientific observation

1.
2.
3.

The problem of reactivity and ethical concerns.

Data obtained by observational techniques are
vulnerable to the bias of the observer.
Emotions, prejudices, and values all can influence
the way that behaviors and events are observed.

NB:

The more the observer needs to make inference and judgment about
what is being observed the more likely it is that distortions will occur.
It is important to consider how observational tools were constructed
and how observers were trained and evaluated when judging the
adequacy of observational methods.

Interview
Interviewand
and Questionnaires
Questionnaires
Interviews:
Are a method of data collection where a data
collector questions a subject verbally.
It may be face to face or performed over the
telephone.
It may consist of open ended or closed ended
questions.
Questionnaires:

Are paper & pencil instruments designed to

gather data from individuals about knowledge,
attitudes, beliefs and feelings.

When evaluating an interview or questionnaire

:the reader should consider
1.
2.

The content of the schedule.

The individual items which should be:
A. Clearly written so that the intent of the question
and nature of the information sought are clear to
the respondent (through pilot test).
B. Items must ask only one questions.
C. Be free of suggestions.
D. Use correct grammar.
E. Items may be open ended or closed ended.

3.

Order of items.

Likert Scales

When items of indirect interest are combined to obtain an

overall score, the measurement tool is called a scale.
Likert scales are lists of statements on which
respondents indicate, for example whether they strongly
agree, agree, disagree or strongly disagree there
may be a neutral category which sometimes creates
problems because it often is the most frequent response
and this response is difficult to interpret.
Fixed response items can be used for questions requiring
yes or No responses.

Fixed response items have the advantage of

simplifying the respondents task and the
researchers analysis, but they may miss some
important information about the subject
Interview and questionnaires commonly are used
in nursing research.
Interview and questionnaires have the ability to
obtain certain kinds of information, such as the
subjects, attitudes and beliefs, that would be
difficult to obtain without asking the subject
directly.
All methods that involve verbal reports, however
share a problem with accuracy.

Unstructured response format allow such information

to be included, but require a special technique to
analyze the responses (content analysis).

Because people are known to respond to questions

in a way that makes a favorable impression (social
desirability), so the researcher usually is forced to
assume that the respondent is telling the truth.

Advantages of interviews and

:questionnaires
1.

2.
3.
4.
5.

Questionnaires paper and pencil tests

are most useful when there is a definite
set of question to be asked.
They are desirable tools when the
purpose is to collect information
Less expensive than interviews
Allow for complete anonymity.
No interviewers bias such as nod of the
head of the researcher may affect the
respondents responds.

Disadvantages of interviews and

:questionnaires

If questionnaires are too long , they

are not likely to be completed.

Face to face techniques or interviews

Advantages

Are best used when the researcher may need to

clarify the task for the respondent or is interested
in obtaining more personal information from the
respondent.

Always higher response rate and this helps to

eliminate bias.

Telephone interviews allow the researcher to

reach more respondents than face to face
interviews, and they allow for more clarity than
questionnaires.

 It is suitable for children, blind and the

illiterate.
It can clarify misunderstood questions.
It has strict control over the order of

questions.
It allow for richer and more complex data

to be collected.

Using a combination of interview of

questionnaires to study a problem (multiple
measures) gives a more complete picture
that the use of just one measure.

Choices between interview and

questionnaires usually depends on what
instruments are available and their relative
costs and benefits.

Records and available data

Records and available data are used

when researchers are interested in
examining information in a new way to
study a problem.

Records or available data

Records or available data are forms of

information that are collected from
existing materials, such as hospital
records, historical documents, or
videotapes and are used to answer
research questions in a new manner.

Advantages of Records or available

:data
1.

Saving time.

2.

Allows examination of trends over time.

3.

Decreases problems of reactivity and

response set bias.

4.

The researcher does not have to ask

individuals to participate in the study
(consent ).

Disadvantages of Records or
:available data
1.

Institution are sometimes refuse to allow researchers to have

access to their records.

2.

Individuals may be identified by records.

3.

The researcher has access only to those records that have

survived.

4.

If the records available are not representative of the possible

records, the researcher may have a problem with bias.

5.

Records could be biased such as when studying

socioeconomic factors associated with the suicide rate.
These data are frequently underreported because of the
stigma attached to suicide.

Critiquing criteria
1.

2.
3.

4.

5.

Are all of the data collection instruments

clearly identified and described?
Is the rationale for their selection given?
Is the method used appropriate to the
problem being studied?
Is the method used appropriate to the
clinical situation?
Are the data collection procedures similar for
all subject?

Physiological measurement
1.

2.

3.

Is the instrument used appropriate to the

research problem and not forced to fit it?
Is a rationale given for why a particular
instrument was selected?
Is there a provision for evaluating the
accuracy of the instrument and those who
use it?

Observational Methods
1.
2.

3.
4.

5.

6.

Who did the observing ?

Were the observers trained to minimize any
bias?
Was there an observational guide?
Were the observers required to make inference
about what they saw?
Is there any reason to believe that the
presence of the observers affected the
behavior of the subject?
Were the observations performed using the
principles of informed consent?

Interviews
1.

2.

3.

4.

Is the interview schedule described

adequately enough to know whether it
covers the subject?
Is there clear indication that the subjects
understood the task and the question?
Who were the interviewers, and how were
they trained?
Is there evidence of any interviewer bias?

Questionnaires
1.

2.

3.

4.

Is the questionnaire described well enough

to know whether it covers the subject?
is there evidence that subjects were able to
perform the task?
Is there clear indication that the subjects
understood the questionnaire?
Are the majority of the items appropriately
close- or open-ended?

Available data and

:records
1.
2.

3.
4.

Are the records that were used appropriate to

the problem being studied?
Are the data examined in such a way as to
provide new information and not summarize
the records?
Has the author addressed questions of internal
and external criticism?
Is there any indication of selection bias in the
available records?