Data Collection Instruments

Transcription

1 Data Collection Instruments After the researcher has defined his problem and purpose of the study, stated his hypotheses or research questions and has determined his sample, the next logical steps in the research process involve the choice of the method for collecting data and for selecting and developing a tool which he will use to collect the data. Data collection refers to the ways and means by which a researcher obtains relevant information regarding the major ideas of the hypothesis of the study so that he can demonstrate whether or not the hypothesis could be verified. (Alreck and Seatle,1985; Descombe, 1989). What the researcher uses to collect data is known as instrument. Literature on research methods identify a variety of methods or instruments for collecting data. The most commonly used in scholarly research in the social sciences are the Questionnaire, the Interview, and Observation. All researchers use at least one and sometimes two or more of these methods in a particular piece of research. Before I discuss these one after the other, it is important to emphasise that researchers do not collect data just for collection sake. Research data must have a direct relationship to the hypotheses and/or research questions which are derived from the problem of the study. This means that data which are not related to the study should not be collected no matter how interesting or how easily available they may be. 1. The Questionnaire The questionnaire is by far the most common method of data collection for research in the social sciences (Aina,2000). I must point out, however, that the questionnaire is not useful for research purposes only. We have all at one time or the other, been asked to fill a form, for example when attending a hospital, or when we apply for a job, or seeking admission to a University. All these forms are examples of a questionnaire because by definition they consist of a list of questions for which we must provide answers. The hospital form for example seeks such information as name, date of birth, next of kin, and previous attendance to the hospital, family medical history, and previous Illness. This preliminary information gathered by questioning, together with the physician s examination provide the basis for subsequent diagnosis and treatment. The application forms you completed at the time you were seeking admission to this programme requested information about your name, date of birth, next of kin, hometown, postal address, educational qualification, subject preferences and so on. This is another example of a questionnaire. The researcher also uses a questionnaire to collect the relevant information which will help him verify his hypotheses, or find answers to his research questions, and draw conclusions accordingly. The questionnaire is described as a pencil-and-paper approach to the collection of data (Descombe,1999). It consists of a list of questions which relate to the aims and objectives of the study, and the hypothesis to be verified. The respondent (that is the one answering the questions) is required to answer the questions by filling in his responses. Respondents read the questions, interpret what they mean and then write down the answers. This is why the questionnaire is described as the paper-and-pencil approach to data collection. In the view of Descombe (1999), any formally organised list of questions which are presented in a uniform manner to a number of persons is a questionnaire, adding that in certain circumstances this is the most effective method of collecting information. P a g e 1 13

2 Types of Questionnaires Questionnaires can be classified in terms of: (1) the nature of information being sought and (2) the nature or format of questions which are used. I shall examine these one after the other. (1)The nature of information sought Information from questionnaires tends to fall in two main categories, namely facts and opinions. (i) Factual information does not require much in the way of judgement or personal attitudes on the part of the respondent. It just requires respondents to reveal information honestly and accurately. The most common factual data collected by questionnaire are demographic ones such as age, gender, social class, education qualification, level of income. Questionnaires may also seek information on past or present events for which written records have been made and which could be used to check the information given by the respondent; for example, the information you give your parents or friends on your academic performance (grade point average or grades received in examinations) could be checked by referring to your examinations records held by the Academic Affairs Directorate. Questionnaires might also request information on past events which most respondents would have kept no written records. For instance, you may be asked to recall some of the experiences you encountered in your first year at high school or University. (ii) Opinions: In addition to factual data, information about opinions, interest, attitudes, perceptions, behaviours, knowledge, beliefs, expectations, views, experiences and so on can be investigated using questionnaires. In this case, though, respondents are required to reveal information about feelings to express views, to weigh up alternatives etc in a way that calls for judgement about things rather than mere reporting of facts. It is very difficult to check such information by reference to any other source. In practice, questionnaires are very likely to include questions on facts and opinions (Alreck and Seattle (1985) For instance, a survey on library use by students might include factual questions about how many students visited the library each day during the academic year, their ages and gender, as well as questions about their perceptions of the attitudes of library staff towards students. Market researchers might want to know factual information about the age, gender, social class etc. of people whose opinions, attitudes and preferences they are investigating. (2) The nature of questions used or question format Another way in which questionnaire may be classified is in terms of the nature of the questions which are used, that is, the format of the question. The choice of the question format depends mainly on the type of data that researchers want to collect. There are two main types of question format: open-ended questions and closed-ended questions. Let s have a look at these one after the other. Closed-Ended Questions: In a closed-ended question the researcher provides possible answers in the questionnaire and the respondent takes the category that best describes his answer. Closed-ended questions come in various forms. (a). (b). (c). (d). two way questions checklist multiple-choice questions ranking scales P a g e 2 13

3 (a).two-way questions, as the term suggests offer a choice between two responses as shown below Please tick which is applicable i) Male (ii) Female A true/false or an agree /disagree as well as yes/no option can also be offered as in the following example: Question 1. You depend only on lecture notes. You don t read reference material prescribed by your lecturer. 2. There are too many commercials on television 3. Did you tape the president s speech? True Agree Yes Please tick one box False Disagree No (b).checklists provide respondents with a list of responses from which to select. They can tick as many items or statements as they think are applicable. Below is an example of a checklist. Please compare the applicant with others you have known during your professional career. For each of the categories below, check the appropriate box. Excellent Above Average Below Inadequate average average opportunity to observe Analytical ability [ ] [ ] [ ] [ ] [ ] Quantitative ability [ ] [ ] [ ] [ ] [ ] Command of field [ ] [ ] [ ] [ ] [ ] of study. Written English [ ] [ ] [ ] [ ] [ ] Oral English [ ] [ ] [ ] [ ] [ ] Interpersonal skills [ ] [ ] [ ] [ ] [ ] P a g e 3 13

4 Maturity [ ] [ ] [ ] [ ] [ ] Motivation [ ] [ ] [ ] [ ] [ ] Initiative [ ] [ ] [ ] [ ] [ ] Leadership [ ] [ ] [ ] [ ] [ ] potential. Results orientation [ ] [ ] [ ] [ ] [ ] Assertiveness [ ] [ ] [ ] [ ] [ ] Professional [ ] [ ] [ ] [ ] [ ] knowledge. Overall Impression of Candidate. Please tick as appropriate. [ ] Enthusiastically recommended [ ] Recommended [ ] Recommended with some reservations [ ] Do not recommend (c). Multiple choices is another format used in questionnaires. This offers respondents a list of responses, normally in the form of statements from which they can select the most applicable to them. The following is an example: Circle the letter of the correct answer to the question. Which of the following Level 200 courses were your favourites? A. Information Management B. Introduction to Information Technology C. Principles of Management D. Introduction to Computing (d). Rank-Order Responses: Another format of questioning is the ranking question in which respondents must arrange all the given alternatives in an order corresponding to some specified criteria: Here is an example: Please rank the following courses according to your degree of liking for each. Assign 1 to your most preferred course and 6 to your least preferred course. Information Management Introduction to Information Technology Principles of Management Introduction to Computing P a g e 4 13

5 Closed-ended questions have certain strengths and weakness. They are difficult to construct but easy to administer and analyse. With closed-ended questions, the researcher needs only to tabulate the number of responses to each alternative in order to gain some understanding about what the sample as a whole thinks about an issue. Closed-ended questions are generally more efficient than open-ended questions because a respondent is normally able to complete more closed-ended than open-ended questions in a given amount of time. Respondents may be less willing to compose a written response than to simply check off or circle the appropriate alternative. Open-Ended Questions: The Open form of questionnaire contains questions to which the subjects can reply as he likes and where he is not limited to a single alternative. Open-ended questions are not followed by any kind of choice and the answers have to be supplied and written by the respondent when researchers do not have all the answers to a question. Further when the researcher, wants to obtain respondents views, they can formulate an open-ended question as in the examples below: (a). Please indicate below the main factors that contribute to your job satisfaction... b. What do you like most about your lecturer?.... c. What is your favourite television programme? Explain why it is your favourite programme..... An open-ended question must be clear and unambiguous or else different respondents will interpret it differently. The major advantage of this type of question is the freedom that is given to the respondent to reveal his attitudes and motives, and to qualify or clarify his answers. The open-ended question provides a richer and fuller response and probably probes more deeply than the closed question. Respondents are allowed space to express themselves in their own way unlike in the case of closed-ended questions. Open-ended questions are often easier to phrase than closed questions but they may be more difficult to answer. Respondents may find it difficult to reply without the help of clues to guide their thinking, or if the questionnaire is designed to seek information about a subject with which they are unfamiliar, or seek their opinions on an issue on which they have no views. P a g e 5 13

6 Conversely some subjects find little difficulty in providing a wealth of information, but the tabulation and interpretation of this may be both difficult and time consuming. Administration of a questionnaire There are several ways by which questionnaires can be administered to respondents. (1). Postal / mailed questionnaire One of the ways to obtain research information by questionnaire is to mail the questions to the respondents. Mailed questionnaires can be sent to a large sample scattered over a wide geographical area quickly and relatively cheaply. Some respondents prefer the lack of physical contact with an interviewer or prefer to complete the questionnaire at a time which is convenient for them. This way of administering questionnaires come with some disadvantages. Postal questionnaires normally attract low response rate. The smaller the percentage of response, the less the degree of confidence which can be placed in the adequacy of the data which has been collected. There is also some likelihood that those who replied are different in some way from those who did not. It is possible that they may be less well educated or less interested in the topic than those who responded, and this may introduce a bias that will render the data useless. This form of administration demands a personal effort on the part of the respondents.the longer the time interval, the greater is the chance that the respondent will be influenced by events which occur during the interval. He may attempt to acquire knowledge by consulting books, or he may change his original views as a result of discussing the questions with his friends. In either case his answers are likely to be different from those he would have made had he completed the questionnaire as soon as he received it. (2). Group questionnaire A questionnaire may also be administered to groups in a face-to-face situation. This approach has the advantage of maximising the return rate and allowing the researcher to clarify any possible misunderstandings about the questionnaire. Group administration of questionnaires is often possible where participants are grouped at a particular place such as attending a function, a church service etc. Personal presentation of questionnaire to individual respondents Questionnaires can be presented to individuals at public places such as shopping centres, hospitals, health centres, schools etc. depending on the type of study population the researcher is targeting and where it is likely to be found. Usually the purpose of the study is explained to potential respondents as they approach and their participation in the study is requested. Advantages of the questionnaire Questionnaires are very cost effective when compared to face-to-face interviews. This is especially true for studies involving large sample sizes and large geographic areas. Questionnaires are easy to analyse. Data entry and tabulation for nearly all surveys can be easily done with many computer software packages. Questionnaires are familiar to most people. Nearly everyone has had some experience completing questionnaires and they generally do not make people apprehensive. P a g e 6 13

7 Questionnaires reduce bias. There is uniform questions presentation and no middle-man bias. The researcher s own opinions will not influence the respondent to answer questions in a certain manner. There are no verbal or visual clues to influence the respondent. Disadvantages of the questionnaire One major disadvantage of questionnaires is the possibility of low response rates. Low response can lower our confidence in the results. Another disadvantage of questionnaires is the inability to probe responses. Questionnaires are structured instruments. They allow little flexibility to the respondent with respect to response format. This problem is overcome by allowing frequent space for comments. Comments are among the most helpful of all the information on the questionnaire, and they usually provide useful information that would have otherwise been lost. Gestures and other visual cues are not available with questionnaires. The lack of personal contact will have different effects depending on the type of information being requested. A questionnaire requesting factual information will probably not be affected by the lack of personal contact. A questionnaire probing sensitive issues or attitudes may be severely affected. When returned questionnaires arrive in the mail, it is natural to assume that the respondent is the same person you sent the questionnaire to. This may not actually be the case. Authorities have noted that many times business questionnaires get handed to other employees for completion. Housewives sometimes respond for their husbands. For a variety of reasons, the respondents may not be who you think it is. Questionnaires are simply not suited for some people. For example, a questionnaire to a group of poorly educated people might not work because of reading skills problems. The Interview / Interviewing As you may have noticed, in our everyday life we engage in interactions that involve asking, and being asked questions. We can, therefore, say that we are all interviewers and interviewees, because interviewing requires interaction between people. Descombe (1999) refers to interview as verbal questioning of people to find out from them those things we cannot directly observe. Some of us have experienced job interviews or watched television interviews. You may yourselves have undergone an interview to gain a place in a job or in a school. These interviews are different from the casual conversations we engage in daily, in that, they have or should have a clear agenda, often prepared in advance for a specific purpose and limited in duration. An example is the interviews researchers carry out for the purpose of obtaining information from respondents. Like the questionnaire, interviews are effective in obtaining information about opinions, perceptions, beliefs, feelings, motivations, private behaviour, past behaviour and anticipated behaviour. (Alreck & Seattle 1985; Busha & Harter, 1980). What is interviewing? Interviewing is another method used by researchers to collect data. It is a very useful means of obtaining qualitative data. The purpose of interviewing people is to find out what is on their mind; what they think or how they feel about something. Citing Patton, Fraenkel and Wallen (2000:509) sum up the importance of interviewing in the following terms: P a g e 7 13

8 We interview people to find out from them those things we cannot directly observe. The issue is not whether observational data is more desirable, valid, or meaningful than selfreport data. The fact of the matter is that we cannot observe everything. We cannot observe feelings, thoughts, and intentions. We cannot observe behaviour that took place at some previous point in time. We cannot observe situations that preclude the presence of the observer. We cannot observe how people have organised the world and the meanings they attach to what goes on in the world. We have to ask people questions about those things. Interviewing can be used in combination with the questionnaire and other means of data collection. Types of interview Interviews vary in design or the way they are structured. Some are highly structured, others are unstructured. (1). Structured interview The structured interviews in their simplest form are sometimes just like the questionnaire. A structured interview is one in which the researcher determines in advance of the interview the procedure he would like to follow. The same questions are presented in the same manner and order to each respondent, and the wording of the instructions to the respondent specified. The interviewer must adhere strictly to the procedure and he has no freedom to rephrase questions, add extra ones or change the order in which they are presented. Structured interviews make the relationship between the interviewer and the respondent formal; they do not permit the interviewer to establish the kind of relationship between himself and the respondent which is necessary if the interview is to be conducted at any depth. The orderly manner in which questions are presented to respondents alike introduces controls which allow generalisations to be made from the information which is collected; the information gained from each respondent is the same and errors due to differences in interviewer technique are minimised. The list of questions used by an interviewer is known as the interview schedule or interview guide. The questions are either closed-ended or open-ended or a combination of both. (Busha and Harter, 1980;Alreck and Seattle, 1985; Descombe,1999; Fraenkel and Wallen; 2000). (2). Unstructured interviews At the opposite extreme are interview designs which are completely unstructured conversations between interviewer and respondent. The respondent has as much influence over the course of the interview as the interviewer. ( Alreck & Seattle, 1985; Fraenkel & Wallen, 2000). Thus the unstructured interview technique is more flexible. The interviewer develops a framework called the interview guide within which to conduct the interview. The series of questions to be asked and the procedure to be followed may be decided upon beforehand, but the interviewer is permitted to deviate from these if the situation appears to demand it. He can thus change the wording of the questions and the orders in which they are presented, follow up unexpected clues, and even alter the direction of the conversation. Authorities recommend this form of approach for studies which are to be carried out at some depth. The chief disadvantage of the unstructured approach is that the data gained in this way cannot be easily compared, and generalisations may not be possible. P a g e 8 13

9 Semi-structured Between the structured and unstructured interview is the semi-structured where the researcher designs set of key questions to be raised before the interview takes place. The researcher has the opportunity to include additional topics. This makes the semi-structured interview more flexible. It is important to point out that whether structured, semi-structured or unstructured, interviews are carried out to collect basically two type of information. There are those which seek information which are factual in nature, and those which collect information on attitudes, opinions and beliefs. In the first case the respondent is required to provide factual information which could be obtained from other sources, possibly from documents. In the second case the respondent is asked to provide information which is entirely subjective, namely his attitudes and opinions. ( Alreck and Seattle,!985; Descombe, 1999; Fraenkel and Wallen, 2000). Ways of conducting interviews (1). Personal interviews When personal interviews are used to collect data, respondents are usually contacted in their homes or offices or on the street or other public places and trained interviewers administer the questionnaire. Advantages The interview is more flexible than the questionnaire. It permits the researcher to pursue and probe more and ask for clarification of responses. The researcher also can clarify questions which the respondent has not been able to understand Disadvantages The interviewer controls the order of questions and can ensure that subjects responses to questions are recorded orderly. The percentage of responses is likely to be much higher than in the case of the questionnaire. The interview situation usually permits much greater depth. It permits the interviewer to establish a rapport and encourages the respondent to provide more complete and valid answers. The interview also allows the observation of the respondent s facial expression and other signs of non cooperation and irregularities. Personal interview is costly. The use of trained interviewers is expensive in terms of both money and time. There is potential for interviewer bias. The interviewer is expected to be neutral medium through which questions are asked and answers recorded. Interviewer bias occurs when the interview tries to adjust the wording of a question to fit the respondent, or record only selected portions of the respondent s answers. P a g e 9 13

10 A busy person may prefer to fill out a questionnaire at leisure rather than submit to a long interview. For adequate coverage a large number of field workers may have to be engaged and trained in the work of collecting data. All this involves a lot of expenditure. Tape recording of the entire interview is likely to be expensive of time and money. Moreover, the use of a tape recorder may make the interviewee cautious and scare him away from divulging any secrets. Interviewing does not work well with infants, shy people and the handicapped. (2). Focused group interview The focused group or focused interview is done in a group setting. The researcher questions a group of respondents at the same time. The interview takes the form of discussions in which the researcher learns from respondents more about the phenomenon being investigated. The goal is to obtain a qualitative description of the ideas that emerge from the group discussion. (3). Telephone interviews Interview can also be conducted by telephone. Advantages Telephone interviewing provides better access to dangerous neighbourhoods, locked buildings and respondents who are available only during evening hours. Interviews can be completed more quickly when contacts are made by phone. Disadvantages A possible selection bias exist when respondents are limited to only those who have telephones There is a limit to how long respondents are willing to stay on the phone Recording interview data Interview can be recorded by taking written notes of the responses, but this can be time consuming. However, it does have the advantage of being a complete and accurate record of the responses to which reference can be made after the interview, and it removes one source of bias, in that, what is recorded is not selected by the interviewer. To overcome the disadvantage associated with note taking during the interview, some interviewers prefer to make notes after the interview is finished. Alreck & Seattle (1985) have noted that this is an appropriate strategy to adopt in certain circumstances, but the danger is that the interviewer may remember only a small proportion of the points made by the respondent. The use of a tape recorder is recognised to be the most convenient way of recording the results of an interview. In this way the interviewer is freed from the necessity of writing out the subject s responses P a g e 10 13

11 during the interview, and can concentrate upon making notes of aspects of the subject s behaviour which he observes. The tape recording provides a complete and accurate record of the entire interview. It also preserves the emotional and vocal character of the replies, and the errors that are sometimes made in written records are avoided. Advantages of interview It is the most appropriate approach for studying complex and sensitive areas. The interviewer has the opportunity to prepare a respondent before asking sensitive questions. It is useful for collecting in-depth data by probing. Hence in a situation where in-depth data is required, interviewing is the preferred method of data collection. An interviewer is able to supplement information obtained from responses with those gained from observation and questionnaire. The interviewer has the opportunity to explain questions if need be. He does this by putting questions in a form that is understood by respondents. It can be used with almost any type of population: children, handicapped, illiterate or very old. In this sense it has a wider application than the questionnaire. Interview offers the possibility of high response rate. It is flexible in that it allows respondent to express themselves and interviewees to probe where necessary. Disadvantages Interviews are extremely expensive and time consuming, especially, in comparison with methods which do not require the presence of an interviewer, for example, questionnaire sent through the post. Interviewers also require a salary or a fee and their expenses must be paid. Observation as a means of data collection Observation is a fact of everyday life. We are constantly observing other people and events as a means of obtaining information about the world around us. Observation is also a tool of scientific research. When used for this purpose the observations are systematically planned and recorded so as to relate to the specific phenomenon of interest. What is observation? We have noted that analyses of questionnaire responses is concerned with what people think and do, as revealed by what they put on paper. The interview reveals what people think and do by what they express in conversation with the interviewer. Observation seeks to ascertain what people think and do by watching them in action as they express themselves in various actions and situations. Observation offers the social researcher a distinct way of collecting research data. It does not rely on what people say they do, or what they say they think instead it is based on the premise that, for certain purposes, it is best to observe what happens (Fraenkel and Wallen, 2000). P a g e 11 13

12 Observation is appropriate in situations where full and / or accurate information cannot be collected by questioning, because respondents either are not co-operative or are unaware of the answers. Observation is frequently used when researchers are more interested in the behaviour than in the perceptions of individuals, or when subjects are so involved in the interaction that they are unable to provide objective information about it. (Kumar,1996) Types of observation The researcher can play one of two roles while gathering observational data: non-participant observer or participant observer. Non-participant observer The researcher can collect the data in the role of a pure researcher without trying to become part of the situation being observed. This is non-participant observation. (Fraenkel & Wallen,2000). By merely observing the activities and recording them on paper, the researcher comes up with some findings. Observers must naturally be physically present at the research setting for extended periods of time. This makes observational studies time-consuming. Participant Observer Another observational role that the researcher can play is that of the participant observer. Here, the researcher enters the organisation or the research setting. He becomes a part of the situation under investigation. For instance, if a researcher wants to study group behaviour in an organisation, then he may enter the organisation in the role of, for instance, an employee, and observe the behaviours in groups while being a part of the institution and work groups. It is noted that most anthropological research is conducted in this manner, where the researcher becomes a part of the alien culture about which he is interested in knowing more. Structured and unstructured observational studies Observational studies could be of either the non-participant observer or the participant observer type. Both of these, again, could be either structured or unstructured. Where the observer has a predetermined set of categories of activities or phenomena that he plans to study, it is a structured observational study. (Fraenkel and Wallem, 2000). Observation forms for the purpose could be specially designed. If, however, the observer has no definite ideas of the particular aspects that he wants to focus on in the observation, but records practically everything that is observed, it is an unstructured observational study. Recording observational data Recording on mechanical devices The use of video tape and sound recorders and other mechanical devises allows behaviour to be recorded and to be reproduced so that the nature of behaviour may be more accurately analysed. Check lists A check list or a schedule consists of a list of items which are thought by the researcher to be relevant to the problem being investigated. After the name of each item, a space is provided for the observer to P a g e 12 13

13 indicate the presence or absence of the item. This check list draws the attention of the researcher to relevant factors and enables him to record the data quickly, and in a systematic way. Rating scales An observer may be asked to judge the behaviour he sees and to classify it into categories. This is essentially the task he performs when completing a schedule, but he can also be asked to give a numerical value or rating to his judgements. Measurement of behaviour in a standardised form is not easy. However to make this possible social scientists have developed a number of scaling techniques which enable them to assign numerical values or ratings to their judgments of behaviour. Advantages and disadvantages of observation Advantages Observation may provide access to groups that would otherwise be difficult to observe or examine. For example, a questionnaire sent to a group of prostitutes or gangsters is not likely to have a high return rate. An observer, however, may be able to establish enough mutual trust with such a group to persuade them to respond to sensitive questioning. Observation is usually inexpensive. In most cases, writing materials or a small tape recorder will suffice. Expenses increase if the problem under study requires a large number of observers, extensive travel, or special equipment such as video recording machines. Observation takes place in the natural setting of the activity being observed and can thus provide detailed data. Disadvantages When individuals or groups become aware that they are being observed, they may change their behaviour. Depending upon the situation, this change could be positive or negative it may increase or decrease, for example, their productivity and may occur for a number of reasons. When a change in the behaviour of persons or groups is attributed to their being observed it is known as the Hawthorne Effect. The use of observation in such a situation introduces distortion: what is observed does not represent their normal behaviour. There is always the possibility of observer bias. If an observer is biased, he can easily introduce bias and there is no easy way to verify the observations and the inferences drawn from them. The interpretations drawn from observations may vary from observer to observer. There is the possibility of incomplete observation, which varies with the method of recording. An observer may watch keenly but at the expense of detailed recording. The opposite problem may occur when the observer takes detailed notes but in doing so misses some of the interaction. P a g e 13 13