Friday, 15 June 2012

Stages of conducting research


Formulating the research problem
One should try to gain knowledge of the various steps involved in conducting research, which have been suggested by different authors on the basis of their experiences. Every one, who is conducting research, will have to use his own skills in designing action oriented planning terms of various steps or stages essential in conducting social, economic or business research.
Steps / stages of Research:
In planning a research project/study, it is necessary to anticipate all activities, which must be undertaken. Research activities are classified and grouped in to various steps or stages. In business research they are generally called steps; while in social sciences these are referred to as stages. Boyd and Brown have used the word steps while Baily, the social scientist, has referred to the research process in terms of five stages. These research stages/steps are a part of research process, which cannot be mechanically contrived sequences of interdependent steps or stages. These consist of a number of interrelated, or overlapping activities. Each step of process is dependent to some extent on the other. The first step must be planned with the second, third, and so on, in mind.
The individual steps in the research process can be viewed, according to Boyd, Westfall and Starch, as consisting of the following seven steps:
                                                   I.      Formulating the study.
                                                 II.      Preparing a list of the needed information.
                                                III.      Designing the data collection project.
                                             IV.      Selecting a sample type.
                                               V.      Determining the sample size.
                                             VI.      Organizing the fieldwork.
                                            VII.      Analyzing the collected data and reporting the findings.
According to Boyd, the four steps, purpose of the study, information needed, data collection form, and tabulation are highly interrelated. The collection form is strongly related to information needed. Lyden O.Brown has divided the research procedure into the following eight basic steps:
                                       I.      The situation analysis.
                                     II.      The informal investigation.
                                    III.      The formal research.
                                 IV.      Collection of the data.
                                   V.      Tabulation and analysis.
                                 VI.      Interpretation of results.
                                VII.      Presentation of the results.
                              VIII.      Follow-up.

According to Clover and Balsley. The procedure of designing a research project consists of the following five steps;
                                         I.      Formulation of problems, Locating and defining problems.
                                       II.      Setting of hypothesis.
                                      III.      Collection of data.
                                   IV.      Analysis of data.
                                     V.      Preparing report.

Gilbert A. Churchill has listed the following “sequence of steps, called the research process, that can be followed when designing the research project”:

                                           I.      Problem formulation.
                                         II.      Research design.
                                        III.      Design of collection method and form.
                                     IV.      Sample design and data collection.
                                       V.      Analysis and interpretation of data.
                                     VI.      Research report.

Bailey has called the steps listed above as stages of research and pointed “although each research project is unique in some ways, all projects, regardless of the phenomenon being studied, involve the same basic stages”. These according to Bailey are as follows;

                                       I.      Choosing the research problem and stating the hypothesis.
                                     II.      Formulating the research designing.
                                    III.      Gathering the data.
                                 IV.      Coding and analyzing the data.
                                   V.      Interpreting the results so as test the hypothesis.

According to Tull and Hawkins, the process of designing a research project requires that a number of steps be taken, although not always conducted in the exact sequence shown, these steps are to;

                                       I.      Obtain agreement on statement of the management problem.
                                     II.      Obtain background information on the problem. Situation.
                                    III.       Get information on the manager problem’s situational model.
                                 IV.      Formulate own problem situation model.
                                   V.      Restate management problem as a research problem.
                                 VI.      Develop alternative ways of collecting and analyzing the data required.
                                VII.      Estimate the time and financial requirements of each design.
                              VIII.      Choosing among the conducting design.
                                 IX.      Prepare a research proposal.

Basic Steps for conducting Survey

The following are the basic steps for conducting a survey:
1.      Determine the objectives of the survey. Arrange meetings, discussions with senior executives for whom the survey is to be conducted.
2.      When the objectives of the survey were pre-determined and provided by the sponsoring agency, it is still necessary to hold meetings with the responsible officers in order to seek clarification.
3.      There should be mutual agreement between the chief executives of the sponsoring agency and the survey team prior to finalization for research methodology.
4.      Preparation of research methodology with sufficient details about each part, so that an action oriented to control the activities of researchers within given time and cost is possible.
5.      Preparation of Questionnaire: There are two basic goals in designing a questionnaire for any study, to collect information relevant to the determined objectives of the study and to collect this information with maximum reliability and validity.
6.      Pre-testing: Pre-testing is a technique of examining the workability or accuracy of the questionnaire, before starting to collect the data from the sample. This step is taken before the preparation of the final questionnaire/interview schedule to be used.
7.      Sampling: There are numerous methods and techniques of sampling. In case of homogenous population a smaller percentage of samples will suffice, whereas, a heterogeneous population may demand a stratified sampling. While drawing a stratified sample it is better to give higher representation to smaller strata as compared to larger stratum.
8.      Data collection: Selection of Field Assistants/Interviews: Personal characteristics: Keeping in view the characteristics of the population under study, age, education, ethnic background and personal appearance of the candidate be given top consideration.
9.      Training: As there is no universally standard survey or interview; there can be no standard training programme. The intensity and nature of training will depend on the size of the interviewers, past experience, type and size of the questionnaire and the time and money available. Thus, the time required for training may range from one day to four days.
10.  Problems: location of the sample unit: the location of the sample is very important task for the supervisors as well as interviewer. The wrong selection of the sample will not fulfill the objective of the survey. The validity and accuracy of the data will certainly depend upon the right approach to the sample as instructed by the supervisors and project incharge.
11.  Field problem: interviewers often face the following problems:-
12. Peoples’ suspicion
13. No proper place for interviewing, disturb the interviewers.
14. Contracting leader is difficult in case of clashes.
15. Lack of ability to know language of the respondents.
16. Non co-operation from the respondents.
17. Field Supervision: the role of field supervisor is also of great importance. It is therefore, necessary that the supervisor should be the full-time, experienced, and preferably the senior members of the research organization. In order to accomplish the cited task efficiently, the supervisors should be sober, experienced, polite and responsible type of person. They should be provided with all the necessary facilities.
18. Quality Control: a daily check of the completed questionnaire followed by a prompt discussion between the supervisor and the interviewers concerned will ensure better quality right from the beginning. In absence of a real foolproof method of checking for quality control, it is possible only to avoid such situations by a categorically making it clear to the interviewers during the training that various checks will be made on their work on various stages in order to maintain an acceptable standards.
19. Data processing: The following are the major steps which are normally followed while processing data manually:

Ø      Preparation of an editing plan for checking and verifying.
Ø      Coding and filling interview schedules.
Ø      Interview schedules are verified from sample unit.
Ø      The filled in interview schedules examined for legibility.
Ø      Prepare a coding key for all questions.
Ø      Each question is given a code number.
Ø      Due care to responses from the respondent.
Ø      Transfer whole data on the coding sheet.
Ø      Simple and contingency tables are prepared.
Ø      Group data by tally method will be presented.
Ø      In simple & cross tables data presented-characteristics/variable-wise.

20)                        Problems of Data Processing: There are some problems of data     processing, which need to be dealt  with due care.
21)                  Writing Research Report :
Ø      Prepare a comprehensive Outline.
Ø      Use tables, tables, charts, graph and pictures to show relationship.
Ø      Use simple language.
Ø      Be objective in presenting the research findings.
Ø      Effective communication of results.
Ø      Distinguish between technical and popular reporting.

Observational Method:
In survey research, it has been often complained that the interviewer has to contact respondents in every day activities and occupations. The respondent may, therefore, not co-operate whole-heartedly in spite of his good intentions because some other matters or obligations may bother him at the time of giving interview. In observational method, this disadvantage is not there. The observer is able to conduct his study without disturbing the respondent and is able to study the behavior of a particular respondent over even a long period of time. 
Importance of Observational Method:
According to Mr. Bailey, observation is decidedly superior to survey research as well as experimentation in collecting data on non-verbal behavior.
If we compare survey method with observational method, there are a few advantages of the observational method:
·        Observational method is superior to collect information about non-verbal behavior.
·        The researcher observes the behavior in its natural environment

Observational Method for Collecting Primary Data:
There are a number of situations where observational research method provides more relevant information. Observation technique has been used to collect such information where the overt human behavior can be observed by the trained researcher. The main quality of observation method is that the personal elements can be reduced to the minimum. While in personal interviews the personal elements of the interviewer as well as that of the respondent cannot be controlled to the same extent as in the case of observation techniques.
In observation method, even mechanical devices can be used to observe the behavior. It is a definite advantage that mechanical measuring and recording devices have greater degree of reliability. Human senses and judgments are used in observation and even in experimentation but the systematic procedures followed in these two techniques of data collection have a definite advantage. In a number of developing countries, business and social researchers are making use of observational and experimental techniques in primary data collection.

Certain advantages of the observation techniques may be listed; human error can be reduced; mechanical devices can secure more accurate data; observations may be made of actual, real conditions of occurrences; little effort and expense occurs in checking the results of observations.

In conducting research several steps are undertaken at any given time. It is not necessary that the first step be completed before the second is undertaken. Nor is it necessary that the informal investigation de completed before planning formal research work. Preliminary fieldwork can be started during the planning stage. Often tabulation and analysis of the field data are started as soon as the reports from the field are received. Similarly the report-writing expert can start work on interpretation before completing fieldwork.
 So interdependent are activities that the first step of the project can determine the nature of the last. If subsequent activities are not taken into account, serious difficulties may arise and prevent the completion of a study. At each step of the research process the requirements of subsequent step must be kept in mind.
Not all questions are researchable and all research questions are answerable. To be researchable, a question must be one for which observation or other data collection provides the answer. Many questions cannot be answered based on information alone.
Question of value and policy must often be weighed in management decisions. Management may be asking, “should we hold out for a liberalization of the seniority rules in our new labour negotiations?” while information can be brought to bear on this question, such additional considerations as “fairness to the workers” or “management’s right to manage” may be important in the decision. It may be possible for many of these questions of value to be transformed into questions of fact. Concerning,” fairness to the workers” one might first gather information from which to estimate the extent and degree to which workers  will be affected by a rule change; second, one could gather opinion statements of the workers about the fairness of seniority rules. Even so, substantial value elements remain. Left unanswered or such question as “should we argue for a policy that will adversely affect the security and well being of older workers who are least well equipped to cope with this adversity?” even if a question can be answered by facts alone, it might not be researchable because our procedures or techniques are in inadequate.

Exploration
An exploration typically begins with a search of published data. In addition, the researchers often seek out well informed people on the topic, especially those who have clearly stated positions on controversial aspects of the problem. Take the case of a company interested in enhancing its position in a given technology that appears to hold potential for future growth. This interest or need might quickly elicit a number of questions:
1.    How fast might this technology develop?
2.    What is the likely application of this technology?
3.    What companies now possess it and which ones are likely to make a major effort to get it?
4.    How much will it take in resources?
5.    What are the likely payoffs?
In the above investigation of opportunities, the researchers would probably begin with specific books and periodicals. They would be looking for only certain aspects in this literature, such as (1) recent developments, (2) predictions by informed figures about the prospects of the technology, (3) identification of those involved in the area, and (4) accounts of successful ventures and failures by others in the field.
After familiarization with the literature, they might seek interviews with scientists, engineers, and product developers who are well known in the field. They would give special attention to those who stand at the extremes of opinion about the prospects of the technology. If possible, they would talk with persons having information on particularly thorny problems in development and application. Of course, much of the information will be confidential and competitive. However, skilful investigation can uncover many useful indicators.
An unstructured exploration allows the researchers to revise the research problem and determine what is needed to secure answers to the proposed questions. With some problems, exploration may answer the question and terminate the project. If not, the problem chosen should be doable with in the constraints that have been imposed.

Designing the study
 The design of the study is the blueprint for fulfilling the objectives and answering questions. Selecting a design may be complicated by the availability of a large variety of methods, techniques, procedures, protocols and sampling plans. For example we may decide on a secondary data study, case study, survey, experiment, or simulation. If a survey is selected, should it be administrated by mail, computer, telephone, oral personal interview? Should all relevant data be collected at one time or at regular Intervals? What kind of structure will the questionnaire or interview guide possess? What question wording should be implied? Should the responses be scaled or open ended? How will reliability and validity be achieved? Will characteristics of the interviewer influence responses to the measurement questions? What kind of planning should the data collectors receive? Is a sample or census to be taken? What type of sampling should be considered? These questions re[present only a few of the decisions that have to be made when just one method is chosen.

Sampling
Another step in planning the design is to identify the target population and select the sample we must determine how many people to interview and how they will be ; hat event s to observe and how many there will be; or how many records to inspect and which ones.  A sample is a part of whole population selected to represent that population. When researchers undertake sampling studies, they are interested in estimating one or more population’s values and / or testing one or more statistical hypotheses.

Resource allocation and Budgets
General notions about research budgets have a tendency to single out data collection as a most costly activity. Data collection requires substantial resources perhaps
not as big as part of the budget as clients would expect. Without budgetary approval, many research efforts are terminated for lake of resources. A budget may require significant development and documentation as in grant contract the search or may require less attention as in some in-house projects or investigations funded out of the researcher’s own resources. The researcher who seeks funding must be able not only to persuasively justify he costs of the project but also to identify the sources and the methods of funding.
There is a great deal of inter-play between budgeting and value assessment in any management decision to conduct research. While this is more prevalent in applied research, even low cost academic studies should be able to demonstrate value to there intended consumers 

Valuing research information
Conceptually the value of applied research is not difficult to determine. In a business situation, the research should produce added revenues or reduce expenses in much the same way as any other investment of resources. One source suggests that the value of research information may be judged in terms of “the difference between the result of decisions made with the information and the result that would be made without it.” While such a criterion is simple to state its actual use presents difficult measurement problems.

Research proposal
The research proposal is an activity that develops concurrently with the project planning phases of the study. The proposal thus incorporates the choices the investigator has made in the preliminary steps.
A written proposal is often required when a study is be suggested. It assures that the parties understand the projects propose and proposed methods of investigation. Time and budgets are often spelled out, as are other responsibilities and obligations. Depending upon the needs and desires of the client, there may also be substantial background detail and elaboration of propose techniques.
Every proposal, regardless of length, should include two basic sections. First is the problem statement. In the brief memo type of proposal, the problem statement may be a paragraph setting out the situation and stating the specific task the research will undertake.
A second section includes a statement of what will be done. Often proposals are much more detailed and include specific measurement devices that will be used, time and cost budgets, sampling plans, and many other details.

Pilot testing
A pilot test is conducted to detect weaknesses in design and instrumentation and provide proxy data for selection of a probability sample. It should therefore draw subjects form the target population and simulate procedures and protocols that have been designed for data collection. If the study is a survey to be executed by mail, the pilot questionnaire should also be mailed. If the design calls for observation by an unobtrusive researcher this behavior should be practiced.

Data collection
The gathering of data may range from relatively simple observation at one location to a grandiose survey of multinational corporations at sites in different parts of the world. The method selected will largely determine who the data are collected. Questionnaires standardized test, observational forms, laboratory notes, and instrument calibration logs are among the devices used to record raw data.

Analyses and interpretation
After collecting the data, we still need to analyze it. Data analyzes usually involves reducing accumulated data to a manageable size, developing summaries, looking for patrons, and applying statistical technique. Scaled responses on questionnaires and experimental instruments often require the analyst to drive various functions, and relationships among variables are frequently explored after that. Further, we must interpret these findings in light of the clients question or, with theory building research, determine if the result are consistent with other hypothesis and theory.

Reporting the result
Finally, it is necessary to prepare a report and transmit the findings and recommendations to the client for the intended purpose of decision making. The style and organization of the report will differ according to the target audience, the occasion and the purpose of the research. In applied research, communication of the results may cover a range of actions from a conference call, a letter, a written report, or an oral presentation and some times all of them. Reports should be developed form the client’s perspective. Thus the sophistication of the design and sampling plan or the esoteric software used to analyze the data may have helped to establish the researcher’s credibility, but in the end, solving the problem is for most on the manager’s mind. Thus, the researcher must accurately assesses the managers needs throughout the research process and incorporate this understanding into the final product.

1 comment: