METHODS OF DATA COLLECTION
by Amin MarwatINTRODUCTION
The instruments that are employed to collect new facts or to explore new fields are called tools. It is of vital importance to select suitable instruments and tools. Different tools are used to collect different types of data. The use of a particular research tool depends upon the type of research proposal. The researcher may use one or more of the tools in combination for this purpose. Such tools or methods of data collection include tests, interviews, questionnaire, observation etc.
SIGNIFICANCE
The progress of any educational program very much depends upon well conduction research. It postulates sufficient, reliable and valid facts. Such facts are normally obtained through a systematic procedure which involves various devices. Each research tool is appropriate in a given situation to accomplish a specific purpose. These tools should be used together or in combination as they supplement the work of each other.
Jhon W. Best (1992, P.159) commented that like the tools in the carpenter box, each is appropriate in a given situation, to accomplish a particular purpose. Each data collecting device has both merits and limitations. However, for effective result each tool has its own significance. It must be used according to the required situation.
TYPES OF RESEARCH TOOLS
There are varieties of tools of research used in collecting data .These include:
Tests
Questionnaires
Opinionnaire or attitude scale
Quantitative interviews
Qualitative interviews
Focus groups
Observations
Quantitative observations
TESTS
As data gathering devices, tests are among the most useful tools of educational research, for they provide the data for most experimental and descriptive studies in education. The instruments have been designed to describe and measure sample of aspects of human behavior. These instruments assess variety of human abilities, potentials achievements and behavior tendencies. They possess different degrees of validity reliability and applicability.
TYPES OF TESTS
The following types of tests designed for different purposes are briefly described.
A. ACHIEVEMENT TEST
Achievement tests attempt to measure what an individual has learned his present level of performance. Most tests used in schools are achievement tests. They are particularly helpful in determining individual or group status in academic learning. Achievement test scores are used in placing, advancing or retaining students at particular grade revels.
B. APTITUDE TEST
Aptitude tests seek to assess the level of achievement that an individual can attain in some particular academic or vocational field. In other words, aptitude tests attempt to predict an individual capacity to require improved performance with additional training.
C. PERSONALITY TEST
It is concerned with the non-intellectual aspect of human behavior. Personality scales are usually self report instruments. The individual check responses to certain questions or statements. These instruments yield scores. Which are assumed or have been shown to measure certain personality traits or tendencies?
QUALITIES OF A GOOD TEST
The qualities of a good test are:
Validity; in general a test possesses validity to the extent that it measures what it claims to measure.
It is reliable A test is reliable to the extent that it measures accurately and consistently, from one time to another.
Objectivity: A test should yield a clear score value for each performance the score being independent of the personal judgment of the scorer.
QUESTIONNAIRE
Questionnaire is a self report data collection instrument that each research participant fills out as part of a research study. Researchers use questionnaire to obtain information about the thoughts, feelings, attitudes beliefs, values, perceptions, personality and behavioral intentions of research participants.
According to John W. Best (1992) a questionnaire is used when factual information is desired, when opinion rather than facts are desired, an opinionnaire or Attitude scale is used.
FORMS/KINDS OF QUESTIONNAIRE
The researcher can construct questions in the form of a closed, open pictorial and scale items.
1. Close form
Questionnaire that calls for short check responses as the, restricted or close form type. They provide for marking a Yes or No a short response or checking an item from a list of suggested responses.
Example
Whey did you choose your graduate work at this university? Kind indicate three reasons in order of importance, using number 1 for the most important, 2 for the 2nd most important, and 3 for the 3rd most important.
Convenience of transportation
Advice of a friend
Reputation of institution
Expense factor
Scholarship aid
Other
(Kindly specify)
Even when using the closed form, it is well to provide for unanticipated responses. Providing an “other” category permits the respondent to indicate what might be his most important reason, one that the questionnaire builder had not anticipated.
Advantages of the close form
It is easy to fill out.
It takes little time by respondents
It is relatively objective
Easy to tabulate and analyze
Answers are standardized.
Limitations of the close form
It fails to reveal the respondents’ motives and does not always get information of sufficient scope and in depth and may not discriminate between the finer shades of meaning.
The open form
The open form or unstructured type of questionnaire calls for a free response in respondents own words.
For example
Why did you intend to take admission in M.Phil programme in IER University of Peshawar?
In what respects IER programme needs improvement
Advantages of the open form questionnaire
Open end questions are flexible.
They can be used when all possible answer categories are not known.
They are preferable to complex issues that cannot be condensed.
They allow more opportunity for creativity, thinking and self expression.
Limitation
There is possibility of collection of worthless or irrelevant information.
Data collected through open end questionnaire are not often standardized from person to person.
Coding is difficult and subjective.
Pictorial form
Some questionnaires present respondents with drawings and photographs rather than written statement from which to choose answers. This form of questionnaire is particularly suitable tool for collecting data from children and adults who had not developed reading ability. Pictures often capture the attention of respondents more readily than printed words, lessen subjects’ resistance and stimulate the interest in questions.
“To get better answers, ask better questions”
IMPROVING QUESTIONNAIRE ITEMS
There are no certain ways of producing foolproof questions; certain principles can be employed to make items more precise. A few are suggested here.
Define or qualify terms that could easily be misinterpreted.
What is the value of your house?
The meaning of the term value is not clear. It could mean the assessed value for tax purposes, what it would sell for on the present market, what you would be willing to sell it for, what it would cost to replace, or what you paid for it. These values may differ considerably. It is essential to frame specific questions such as, “What is the present market value of your house?”
Be careful in using descriptive adjectives and adverbs that have no agreed upon meaning. This fault is frequently found in rating scales as well in questionnaires. Frequently, occasionally and rarely do not have the same meanings to different persons. One respondent occasionally may be another’s rarely. Perhaps a stated frequency times per week, times per month would make this classification more precise.
Beware of double negatives. Underline negatives for clarity.
Are you opposed to not requiring students to take showers after gym class?
Be careful of inadequate alternatives.
Married € Yes € No
Does this question refer to present or former marital status? How would the person answer who is widowed, separated or divorced?
Avoid the double barreled question
Do you believe that gifted students should be placed in separate groups for instructional purposes and assigned to special schools?
Underline a word if you wish to indicate special emphasis.
A parent should not be told this child’s IQ score.
When asking for rating or comparisons a point of reference is necessary.
How would you rate this student teachers classroom teaching?
Superior Average Below average
Avoid unwarranted assumptions.
Are you satisfied with the salary raise that you received last year? A “no” answer might mean that I did not get a raise, or that I did get a raise, but I am not satisfied.
Phrase questions so that they are appropriate for all respondents.
What is your monthly teaching salary?
Some teachers are paid on a nine month basis, some ten, some eleven and some twelve. Three questions would be needed.
Your salary per month
Number of months in school term
Number of salary payments per month
Design questions that will give a complete response.
Do you read the Indianapolis star? Yes No.
A yes or no answer would not reveal much information about the reading habits of the respondents.
Provide for the systemic quantification of responses.
What are your favorite television programs? Rank in order of preference your first, second, third, fourth, and fifth choices.
The items can they be tabulated by inverse weightings?
1st choice 5 points
2nd choice 4 points
3rd choice 3 points
4th choice 2 points
5th choice 1 point
Consider the possibility of classifying the responses yourself, rather than having the respondent choose categories.
If a student were asked to classify his father’s occupation in one of the following categories, the results might be quite unsatisfactory.
Unskilled labor
Skilled labor
Clerical work
Managerial work
Profession
It is likely that by asking the child one or two short questions about his father’s work, it could be classified more accurately.
At what place does your father work?
What kind of work does he do?
The opinionnaire or attitude scale: The information form that attempts to measure the attitude or belief of an individual is known as an opinionnaire or attitude scale.
How an individual feels or what he believes, is his attitude. But it is difficult, if not impossible, to describe and measure attitude. The researcher must depend upon what the individual says are his beliefs and feelings. This is the area of opinion. Through the use of questions or by getting an individual’s expressed reaction to statements a sample of his opinion is obtained. From this statement of opinion may be inferred or estimated his attitude what he really believes.
Two procedures have been used extensively in opinion research.
Thurstone techniques
The first method of attitude assessment is known as the Thurston technique of scaled values. A number of statements, usually 20 or more, that express various points of view towards a group, institution, idea or practice are gathered. They are then submitted to a panel of a number of judges, who each arranges them in 11 groups, ranging form one extreme to another in position. This sorting by each judge yields a composite position for each of the items. When there has been marked disagreement between the judges in assigning a position to an item, that item is discarded. For items that are retained, each is given its median scale value, between one and eleven as established by the panel.
The list of statements is then given to the subjects, who are asked to check the statements with which they are in agreement. The median value of the statements that they check establishes their score, or quantifies their opinion.
Likert Method
The second method, the likert method of Summated Ratings, which can be carried out without the panel judges has yielded scores very similar to those obtained by the Thurston method. The coefficient of correlation between the scales was reported as high as +.92 in one study. Since the likert type scale takes much less time to construct, it offers an interesting possibility for the student of opinion research.
Likert Scale
The likert scaling technique assigns a scale value to each of the five responses.
Scale Value
a. Strongly agree 5
b. Agree 4
c. Undecided 3
d. Disagree 2
e. Strongly disagree 1
For statements opposing this point of view, the items are scored in this opposite order.
Scale Value
a. Strongly agree 1
b. Agree 2
c. Undecided 3
d. Disagree 4
e. Strongly disagree 5
INTERVIEW
The interview is in a sense, an oral questionnaire. Instead of writing the response, the subject or interviewee gives the needed information verbally in a face to face relationship.
Interview that are done face to face are called in person interviews; interviews conducted over the telephone are called telephone interviews.
The four types of interviews are:
The closed quantitative interview
The standardized open ended interview
The interview guide approach
The informal conversational interview
These four types can be grouped into quantitative interviews (which include the closed quantitative interview) and qualitative interviews (which include the standardized open ended interview, the interview guide approach and the informal conversational interview)
Quantitative interviews
When carrying out quantitative interviews, one must carefully read the words as they are provided in the interview protocol. The interview protocol is the data collection instrument that includes the items, the response categories, the instructions and so forth. The interview protocol in a quantitative interview basically a script written by the researcher and read by the interviewer to the interviewees. The interview protocol is usually written on paper for in person interviews and shown on a computer screen for telephone interviews.
The goal of the quantitative interview is to standardize what is presented to the interviewees. Standardization has been achieved when what is said to all interviewees is the same or as similar as possible.
The key idea here is that here quantitative researchers want to expose each participants to the same stimulus so that the result will be comparable. Not surprisingly, quantitative interview result in mostly quantitative data that are later analyzed using quantitative statistical procedure. The reason we say mostly because quantitative interview protocols often included a few open ended items. If an open ended question is asked in a quantitative interview however it is asked in exactly the same way for each participant in the study.
Qualitative interviews
Qualitative interviews consist of open -ended questions and provide qualitative data. Qualitative interviews are also called depth interviews because they can be used to obtain in depth information about a participant’s thoughts, beliefs, knowledge, reasoning, motivations and feelings about a topic. Qualitative interviewing allows a researcher to enter into the inner world of another person and to gain an understanding of that person’s perspective.
The three types of qualitative interview:
The informal conversational interview:
This is the most spontaneous and loosely structured of the three types of qualitative interviews. The interviewer discusses the topics of interest and follows all leads that emerge during the discussion. Because there is no interview protocol in the informal conversational interview, it is a good idea to tape record the interview so that no important information will be lost.
The interview guide approach.
In the next approach to qualitative interviewing, the interview guide approach, the interviewer enters the interview session with a plan to explore specific topics and to ask specific open ended questions of the interview. These topics and questions are provided on an interview protocol written by the researcher before the interview session. The interviewer, however, does not have to follow these topics and questions during the interview in any particular order. The interviewer can also change the wording of any questions listed in the interview protocol
The standardized open-ended interview:
In the third approach to qualitative interviewing, the standardized open ended interview, the interview enters the interview session with a standardized interview protocol similar to the interview protocol used in quantitative interviewing. The key difference is that the interview protocol in the quantitative interview includes primarily closed ended items but the interview protocol in the standardized open ended interview includes primarily open ended items. In the standardized open ended interview, the questions are all written out, and the interviewer reds the questions exactly as written and in the same order to all interviewees. Some techniques for establishing trust and rapport are to explain who the sponsoring organization is to explain why you are conducting the research and to point out to the participant that this or her responses are either anonymous (no name or identification will be attached to the respondents data) or confidential the respondents name or identification will be attached to the respondents data, but the researcher will never divulge the respondents name to any one. A list of tips that you should find helpful if you ever need to conduct an interview.
Tips for conducting an effective interview
Make sure all interviewers are well trained.
Do background homework on the interviewees so that you will know a little about the people you will be interviewing.
Establish rapport and trust with your interviewee.
Be empathetic and remain neutral toward the content of what the interviewee says.
Use gentle nonverbal head nods and verbal “Um-hms” to show your interest in what the interviewee says.
Be reflexive (i.e. monitor yourself).
Make sure the interviewee is doing most of the talking not you.
Be sensitive to gender, age and cultural differences between you and the interviewee.
Make sure the interviewee understands exactly what you are asking.
Provide sufficient time for the interviewee to answer each question.
Maintain control of the interview and keep the interview focused.
Typically you should tape record the interview session.
After an interview is completed, check your notes and recording for quality and completeness.
FOCUS GROUPS
A focus group is a type of group interview in which a moderator (working for the researcher) leads a discussion with a small group of individuals (e.g., students, teachers, teenagers) to examine, in detail, how the group members think and feel about a topic. It is called a ‘focus” group because the moderator keeps the individuals in the group focused on the topic being discussed. The moderator generates group discussion through the use of open ended questions, and he or she acts as a facilitator of group process. Focus groups are used to collect qualitative data that are in the words of the group participants. A focus group is composed of 6 to 12 participants who are purposively selected because they can provide the kind of information of interest to the researcher. A focus group is usually homogeneous, (composed of similar kinds of people) because the use of a homogeneous group promotes discussion.
The group moderator (The person leading the focus group discussion) must have good interpersonal skills and he or she must know how to facilitate group discussion. He or she needs to get everyone involved in discussing the researcher’s questions and not allow one or two people to dominate the discussion.
OBSERVATION
The next method of data collection involves something that we do most of our waking hours: observe things. Researchers are also observers of things in the world. In research, observation is defined as the watching of behavioral patterns of people in certain situations to obtain information about the phenomenon of interest. Observation is an important way of collecting information about people because people do not always do what they say they do. It is a maxim in the social and behavioral sciences that attitudes and behavior are not always congruent.
Observational data are collected in two different types of environments.
Laboratory observation is carried out in settings that are set up by the researcher and inside the confines of a research lab. An example would be a researcher observing the behaviour of children through a one way window in the researcher’s laboratory.
Naturalistic observation is carried out in the real world. Observing the behaviour of children in their classrooms is example of natural lactic observation. We now contrast how quantitative and qualitative researchers collect observational data.
Quantitative observation
Quantitative (or structured) observation involves the standardization of all observational procedures in order to obtain reliable research data. It often involves the standardization of each of the following. Who is observed (what kinds of people are to be studied, such as teachers or students), what is observed (what variables are to be observed by the researcher, such as time on tasks or out of seat behavior), when the observation are to take place (during the morning hour, during break time), where the observation are to be carried out (in the laboratory in the classroom, in the lunchroom, in the library, on the playground) and how the observations are to be done. Quantitative observation usually results in quantitative data, such a counts or frequencies and percentages.
Quantitative observation might also involve observational sampling techniques. One technique is called time interval sampling, which involves checking for events during time interval specified in advance of the actual data collection. An example of time interval sampling is a researcher observing student behavior for the first then minutes of every hour.
Another technique is called event sampling, which involves making observations only after a specific event has occurred. An example of event sampling is observing the behavior of students in a classroom after a teacher sends a student to the principal’s office.
Researchers conducting quantitative observation usually use checklists or other types of data collection instruments, such as a laptop computer to record the research data or a video-tape recorder for later coding.
Qualitative observation
Qualitative observation involves observing all relevant phenomena and taking extensive field notes without specifying in advance exactly what is to be observed. In other words, qualitative observation is usually done for exploratory purposes. It is also usually done in natural settings. In fact, the terms qualitative observation and naturalistic observation are frequently treated as synonyms in the research literature. Not surprisingly, qualitative observation is usually carried out by qualitative researchers.
The four main roles that a researcher can take during qualitative observation.
The complete participant takes on the role of an insider, essentially becoming a member of the group being studied and spending a great deal of time with the group and does not tell members they are being studied.
Participant- as -observer
Researcher spends extended time with the group as an insider and tells members they are being studied.
Observer as participant
Researcher spends limited amount of time observing group members and tells members they are being studied.
Complete observer
Researcher observes as an outsider and does not tell the people they are being observed.
SUMMARY
The instruments that provide for the collection of data upon which hypotheses may be tested are tools of research. From the great variety of these tools the research chooses those that are most appropriate to the sources of data that are most relevant and useful. The quantification of these data makes possible more precise analysis and interpretation.
Biblography
Akhtar, S.M.(1987) Educational Research, Rawalpindi, Sigma Press(p.93)
Best,J.W.(1970).Research in education(2nded) Printice . Hall,INC.,Englewood Cliffs, New Jersey(p,163)
Ghaffar, S.A.(2005), Research in Education and Social Sciences. The printman ,Peshawar(p.133)
Jonson, B. & Christensen (2008).(3rd ed) Quantitative, Qualitative and mixed Research Approach Los Angeles: SAGE Publications. (p.203)