PILOT STUDY 341

Wbere r=thecorrelation coefficient computed on the split-halves with

'= the estimated reliability of the entire test Formnula 9.2.

The split-half technique is frequently used to estimate the internalconsistency; however, a

more preferred method is Cronbachs alpha or coefficient alpha may be calculated by using
the following formula (Formula 9.4):
Formula 9.4

K-1| oy'
Where r = the estimated reliability
k= the total number of items in the test.
o;= the variance of each individual itenm.
o = the variance of the total test scores
S=the sum of
Equivalence: This aspect of reliability is estimated when a researcher is testing the reli
ability of atool, which is used by twodifferent observers to observe a single phenomenon
simultaneously and indeperndently or twopresumably parallel instruments are admiis
tered to an individual at about the same time. For example, a rating scale is developed to
assess cleanliness of the bone marrow transplantation unit; this rating scale may be admin
istered to observe the cleanliness of the bone marrow transplantation unit by two different
observers simultaneously but independently.
This is also known as interrater or interobserver reliability, which is estimated by the adminis
tration of tool to observe a single event simultaneously and independently by two or more
trained observers. This reliability may be computed by using following equation:

Number of agreements
r=
Number of agreements+ Number of disagreements

PILOT STUDY
In nursing science research, the term pilot study is utilized in twodifferent ways. It refers
Lto the sO-called feasibility studies that are trial run or small-scaleversions, which are done
in preparation for the major study. However, a pilot study can also be the 'trying out' or
pretesting of a specific research instrument.
A pilot study is referred to a small-scale preliminary tryout of the method to be used in an
actually large study, which acquaints the researcher with problems that can be corrected
in proportion for the large research study or is done to provide the researcher with an op
portunity to try out the procedure, methods, and tools of data collection.
In other words, the pilot study is miniature trial run of the methodoogy planned for the
major research study, which facilitates to improve the methodology of thestudy, can as
Sess the feasibility of the study, and may iderntify the problems that may be faced by the
researcherin actual large research project.

I. FUNDAMENTALS OF NURSING RESEARCH

 342 9. TOOLS AND METHODS OF DATA COLLECTION

A small-sçale test of the methods and procedures to be used on a larger scale is called
pilot [Link] main intention of conducting a pilotstudy is to ascertain the feasibility of a
method tht is required toultimately be used in a large-scale study. This includes all types
of research studies.
" A fundamental phase of the research process is represented by a pilot study. The intention
of conducting apilot study is to check the feasibility of a method intended to be utilized in
a large-scale study.
Apilot study is the required initial step in exploring a unique intervention or an innovative
application of an intervention. Pilot results can depict feasibility and check modifications
required in the design of a larger, ensuing hypothesis testing study.
" Apilot study can also be utilized to measure the feasibility of assessment procedures, re
cruitment, randomization, retention,new methods, and implementation of the novel inter
vention.
One of the merits of conducting a pilot study is that it might provide advance warning
aboutwhere research protocols may not be followed, where the main research project
could not work, or whether proposed methods or instruments are inappropriate or too
complicated.

Definitions
Pilot study is a trial study carried out beforearesearch design is finalized to assist in defining the
Tesearch question or to test the feasibility, reliability, and validity of the proposed study design.
Pilot study is asmaller version of a study carried out before the actual investigation is done. Re
searchers use information gathered in pilot studies to refine or modify the research methodology
for a study and to develop large-scale studies.
Pilot study is asmall-scale study conducted to test the plan and method of a research study.
Pilot study is a small study often carried out to help in preparing a larger and more comprehen
sive investigation.
Pilot study is a trial run or a small preliminary test of an intervention of an evaluation activity
(viz. an instrumnent or sampling procedure). The results of the pilot are utilized to facilitate the
programme or evaluation procedure being piloted before it is used on a larger scale.

Purposes of Pilot Study

There are several reasons or purposes to undertake a pilot study; but there are some mnore
reasons, for example, convincing funding bodies that their research proposal for the main
study is worth funding. Thus, pilot studies are employed for a range of different purposes o
reasoOns:

Assessing study feasibility and practicability of research study.

Assessing the availability of study subjects.
Establishing validity and reliability of the research tools.
Ensuring the appropriateness of methods and procedures of data collection.
" Understanding the study variables and other confounding variables.

I. FUNDAMENTALS OF NURSING RESEARCH

 PILOT STUDY 343

Estimating the actual time and potential problems researcher may encounter during the
actual large research study.
Refining the study methodology.
Planning for the data analysis and interpretation of the final larger research.
Developing and testing sufficiency of research instruments.
Assessing the practicality of a full-scale study/survey.
Assessing whether the research protocol is practicable and workable.
. Establishing if the technique and sampling frame are effective.
. Assessing the probable success of proposed study subject recruitment approaches.
. Logistical problems identification by using proposed methods.
Estimating variability in outcomes to help in determining sample size.
Preliminary data collection.
. Determining the resources (e.g. finance, staff) required for a planned study.
Assessing the proposed data analysis techniques for potential problems.
Developing a research plan and research question.
Training aresearcher in various elements of the research process.
Convincing funding bodies that the research team is knowledgeable and competent.
Convincing funding bodies that the main study is worth funding and feasible.
Convincing other institutes and stakeholders that the main study is worth supporting
Pilot study resultscan guide in the desigrning and implementation of larger scale efficacy stud
ies. There are several aspects of randomized control trial (RCT) feasibility that are informed by
conducting a pilot study. A pilot study can be used to evaluate the feasibility of recruitment,
randomization, retention,assessmernt procedures, and implementation of the novel interven
tion; and each of these can be quantified. Study components that are deemed infeasible or
unsatisfactory should be modified in the subsequent trial or are removed altogether.

Problems and Issues of Pilot Study

It should be recognized that the pilot studies may also have a number of problems, issues,
and limitations. Following are some of the significant problems or issues of pilot study, which
a researcher may consider while carrying out the pilot study:
" It may be a possibility that the researcher may make inaccurate predictions or assumptions
on thebasis of pilot data, specifically when the data of pilot study is used for estimating
the sample size. Thus it isalways suggested that it is better to use the findings of previous
full-scale similar study conducted for estimating a sample size rather than using the data
from a pilot study for sample size estimation.
Contamination is another concern. This may arise in twoways: (1)where pilot participants
are included in the main study, but new data are collected from these people and (2) where
contamina
data from the pilot study are included in the main results. To avoid the risk of
tion,the following is considered:
main study data.
The data collected during pilot study are not included in analysis ofstudy
The other reason that the pilot study data is not included in main data analy
study
Sis is that after the pilot study there are changes in data collection tool(s) and
methodology. However, if there is no change in study methodology and data collection
results.
methods and tools), the pilot study data may be included in main study

I. FUNDAMENTALSOF NURSING RESEARCH

 344 9. TOOLS AND METHODS OF DATA COLLECTION

The main study is generally not conducted in the same area where pilot study was con
ducted to avoid the risk of contamination.
So to sum up, pilot study is the preresearch activity to refine research methodology and plan
for appropriate use of resources with sound beforehand information about the main shudy
parameters.

SUMMARY

" Data ane the observable and measurable facts that provide information about the phenom
enon under study. Data are primarily classified as primary and secondary data.
There are different methods of datacollection such as questionnaire, interview, observa
tion, bio-physiological methods, psychological methods (projective techniques, Q-sorts,
vignettes).
Selection of a method of data collection depends on several factors that are nature of phe
nomenon under study, type of research subjects, type of research study, purpose of study,
size of study sample, distribution of target population, time frame of study, literacy level
of study subjects,availability of resources and manpower and researcher's level of knowl
edge and competency.
The interview is a method of data collection, which involves communication or interaction
in which the subjects or interviewee gives the required information verbally, either face
to-face or telephonically. Interview could be classified as structured, unstructured, semi
structured, in-depth and focused group interview.
1Questionnaire is a structured instrument consisting of aseries of questions prepared by
researcher that a research subject is asked to complete, gather data from individuals about
knowledge, attitude, beliefs, feelings and so on.
" Likert scale is a composite measurement scale used to measure attitude, values and feel
ings of the people that involve summation of scores on the set of positive and negative
declarative statenments regarding measuring variables tó which respondents are asked to
indicate their degree of agreement or disagreement.
Semantic differential scale is a type of rating scale designed to measure the connotative
meaning of objects, events and concepts. These connotations are used to derive the re
spondents' attitude towards the objects, events and concepts.
Visual analogous scale is atool that is used to assist a person in rating the intensity of cer
tain feelingsand sensations (e.g. pain).
" Observation is a technique of data collection or acquiring information,which can be ob
served through senses with or without mechanical devices. Observation could be struc
tured, unstructured, participatory or non-participatory in nature. Observation can be as
sisted using some of tools such as rating scale, checklist, etc. Other methods of observation
could be field notes, anecdotes, event sampling, time sampling, observation technology
such as photographs and CCTV/audiotape/videography etc.
Rating scale refers to ascale with a set of opinions, which describes varying degrees of the
dimensions of an attitude being observed. Rating scale could beclassified as graphical,
descriptive, numericalor comparative rating scales.

I. FUNDAMENTALS OF NURSING RESEARCH

 REVIEW QUESTIONS 345
.Achecklist is a simple instrument consisting of aprepared list of expected items of
performance or attributes, which are checked by a researcher for their presence or
absence.

Bio-physiologic method involves the collection of bio-physiologic data from subjects by

using the specialized equipment to determine biological and physical status of subjects.
Bio-physiologic mnethods are either in-vivo (mneasuring direct on subject; e.g. ECG record
ing) or in-vitro (done on outside the subject; e.g. blood test).
Validity refers to the degree to which an instrument measures what it is supposed to be
measuring. Validity could be classified as face validity, content validity, eriterion validity
and construct,validity.
Reliability is the degree of consistency and accuracy with which an instrument measures
the attribute for which it is designed to measure. Reliability is estimated through test-retest
method,split-half method or inter-rater reliability method.
Pilot study is a small-scale study conducted to test the plan, tools and methods of a re
search study.

REVIEW QUESTIONS

Long Answer and Short Answer Questions

1. Criteria for assessing measuring tools.
2. Methods of data collection.
3. Interview method.
4. Characteristics of the research instrument.
5. Write in detail about the construction of questionnaires and interview schedules.
6. Observation method.
7. Differentiate between questionnaire and structured interview nethod of data collection
in nursing research.
8. Advantages and disadvantags of questionnaire.
9. Differentiate between questionnaire and structured interview mnethod of data collection.
10. Rorschach ink blot test (projective technique) as a method of data collection.
11. Explain in detail the sources of data collection in nursing research.
12. What is a questionnaire? Mention the characteristics of a good questionnaire.
13. Criteria in selecting an instrument.
14. Discuss the advantages and disadvantages of a questionnaire. Explain the different ques
tions with an example for each.
15. Pilot study.
16. Explain the steps of constructing Likert scales.
17. What do you understand by reliability of a tool? Describe the different methods of estab
lishing reliability.
18. Measurements of variables using scale methods and develop a Likert scale.
19. Questionnaire method of data collection:
20. Validity of a research tool.
21. Reliability of a research tool.

I. FUNDAMENTALS OF NURSING RESEARCH