METHODS OF DATA COLLECTION ABHISHEK KUMAR CHARU SHARMA KALPANA SINGH MEGHA GUPTA RISHIKA MAHESHWARI RITESH SAXENA SWATI GUPTA TAMANNA GHOSH VIBHOR GOEL : METHODS OF DATA COLLECTION ABHISHEK KUMAR CHARU SHARMA KALPANA SINGH MEGHA GUPTA RISHIKA MAHESHWARI RITESH SAXENA SWATI GUPTA TAMANNA GHOSH VIBHOR GOEL INTRODUCTION : 2 INTRODUCTION THE TASK OF DATA COLLECTION BEGINS :
After the research problem has been identified and,
Research design/plan chalked out. TWO TYPES OF DATA : 3 TWO TYPES OF DATA PRIMARY DATA : which are collected afresh and for the the first time, and thus happens to be original in character.
SECONDARY DATA : which have already been collected by someone else and which have already been passed through the statistical process. METHOD OF COLLECTING PRIMARY DATA : 4 METHOD OF COLLECTING PRIMARY DATA Observation method
Through questionnaires OBSERVATION METHOD : 5 OBSERVATION METHOD Most commonly used.
Method in which the researcher relies on his or her powers of observation rather than communicating with a person in order to obtain information
E.g.wrist watch ADVANTAGES : 6 ADVANTAGES Subjective bias is eliminated.
The information obtained under this method relates to what is currently happening.
This method is independent of respondent’s willingness to respond. LIMITATIONS : 7 LIMITATIONS Expensive method
Information provided is limited
Sometimes, unforeseen factors may interfere with the observational task. IMPORTANT POINTS TO BE KEPT IN MIND BY THE RESEARCHER : 8 IMPORTANT POINTS TO BE KEPT IN MIND BY THE RESEARCHER What should be observed?
How the observations should be recorded?
How the accuracy of observations can be ensured? Observation Techniques : 9 Observation Techniques Types of observation:
Structured versus unstructured
Disguised versus undisguised
Controlled versus uncontrolled
Human versus mechanical Observation TechniquesStructured versus Unstructured : 10 Observation TechniquesStructured versus Unstructured Structured observation: researcher identifies beforehand which behaviors are to be observed and recorded
Unstructured observation: no restriction is placed on what the observer would note: all behavior in the episode under study is monitored Observation TechniquesDisguised versus Undisguised : 11 Observation TechniquesDisguised versus Undisguised Disguised observation: subject is unaware that he or she is being observed
Undisguised observation: respondent is aware of observation Observation TechniquesControlled versus Uncontrolled : 12 Observation TechniquesControlled versus Uncontrolled Controlled observation: when observation takes place according to definite pre-arranged plans, involving experimental procedures.
Uncontrolled observation: the major aim is to get a spontaneous picture of persons and no attempt is made to use precision arrangements. Observation TechniquesHuman versus Mechanical : 13 Observation TechniquesHuman versus Mechanical Human observation: observer is a person hired by the researcher, or, perhaps the observer is the researcher
Mechanical observation: human observer is replaced with some form of static observing device INTERVIEW METHOD : 14 INTERVIEW METHOD MEANING OF INTERVIEW : 15 MEANING OF INTERVIEW An interview is a specialized type of communication, usually verbal, between two or more people and is carried out for a specific purpose. TYPES OF INTERVIEW : 16 TYPES OF INTERVIEW Personal interview
Telephone interview PERSONAL INTERVIEW : 17 PERSONAL INTERVIEW Requires the interviewer to ask questions face to face.
It can be of two types: direct and indirect.
In direct personal investigation the interviewer has to collect the information personally from the sources concerned. Cont…. : 18 Cont…. In indirect oral examination the interviewer has to cross examine other persons who are supposed to have knowledge about the problem under investigation. STRUCTURED INTERVIEW : 19 STRUCTURED INTERVIEW This means planning the format of the interview and the questions to be asked in advance and limiting the degree of discretion an interviewer is allowed to take in deviating from the predetermined plan. CONTD…. : 20 CONTD…. Standardization of all questions can give quantifiable data.
Data is more reliable as the issue is being investigated in a consistent way.
Allows generalization of results/conclusions to the population from which the sample was drawn. UNSTRUCTURED INTERVIEW : 21 UNSTRUCTURED INTERVIEW Characterised by a flexibility approach to questioning.
Does not follow a system of predetermined questions and standardised techniques of recording information.
Interviewer has greater freedom to ask questions. ADVANTAGES : 22 ADVANTAGES Flexible, responsive and sensitive to the participants.
Highly detailed and valid qualitative data. DISADVANTAGES : 23 DISADVANTAGES Demand deep knowledge and greater skill on the part of the interviewer.
Possible interviewer bias in 'selective' use of leading, and spontaneous questions. FOCUSSED INTERVIEW : 24 FOCUSSED INTERVIEW Is meant to focus attention on the given experience of the respondents and its effects.
Interviewer has the freedom to decide the manner and sequence of question.
He has freedom to explore reasons and motives. Cont…. : 25 Cont…. Interviewer may interpret the answers in his own way.
The interpretation of the interviews by the researcher is also very difficult and gives an opportunity for personal bias to distort the findings.
There is a high proportion of irrelevant information in the data. CLINICAL INTERVIEW : 26 CLINICAL INTERVIEW Is concerned with broad underlying feelings or motivations or with the courses of individual’s life experience.
The method of eliciting information is left at interviewer’s discretion. ADVANTAGES : 27 ADVANTAGES Flexible, responsive and sensitive to participants.
Preparation of core questions should ensure validity. DISADVANTAGES : 28 DISADVANTAGES Generalization of the findings is difficult in case of large population.
Interviewer biasness is possible. TELEPHONE INTERVIEW : 29 TELEPHONE INTERVIEW It involves contacting a sample of respondents on phone and asking them series of questions.
The interviewer uses a paper questionnaire and records the responses with a pencil. ADVANTAGES : 30 ADVANTAGES It is a quick method for conducting a number of interviews within a short time.
The interviewers can be supervised easily.
The sampling can be spread over the country and traveling is eliminated.
People who might otherwise be inaccessible, can be interviewed, since the interview can be very brief and arranged for a time that is convenient to the respondent. DISADVANTAGES : 31 DISADVANTAGES Only a short questionnaire can be used.
Observation is not possible, so that the interviewers have to rely totally on what the respondent tells them.
The times during the day when respondents can be called are limited .
Little time for the respondent to answer. Questionnaire : 32 Questionnaire QUESTIONNAIRESA questionnaire is a formalized schedule for collecting data from respondents. The issue involved in questionnaire design directly relate to developing and administering these attitude measurement techniques. The function of questionnaire is MEASUREMENT Questionnaire can be used to measure Past behavior Attitudes Respondent characteristics : 33 QUESTIONNAIRESA questionnaire is a formalized schedule for collecting data from respondents. The issue involved in questionnaire design directly relate to developing and administering these attitude measurement techniques. The function of questionnaire is MEASUREMENT Questionnaire can be used to measure Past behavior Attitudes Respondent characteristics PROBLEM IN QUESTIONNAIRE CONSTRUCTION : 34 PROBLEM IN QUESTIONNAIRE CONSTRUCTION One of the serious problem is MEASUREMENT ERROR
For example,the survey conducted by research center at the university of Michigan. QUESTIONNAIRE COMPONENTS : 35 QUESTIONNAIRE COMPONENTS Consists of five main sections
Request for cooperation
Classification data QUESTIONNAIRE DESIGN : 36 QUESTIONNAIRE DESIGN It is a skill that the researcher learns through experience rather than by reading a series of guidelines.It is an art form than an scientific undertaking.
Way to begin :-
Write a questionnaire
Use it in a series of interview
Analyze its weaknesses
Revise it STEPS IN QUSTIONNAIRE DESIGN : 37 STEPS IN QUSTIONNAIRE DESIGN Review preliminary considerations Decide on question content Design on response format Deside on question wording Deside on question sequence Design on physical characteristics Pretest,revise, and make final draft LINK BETWEEN INFORMATION NEEDS AND DATA TO BE COLLECTED : 38 LINK BETWEEN INFORMATION NEEDS AND DATA TO BE COLLECTED Questionnaire
Needs DECIDE ON QUESTION CONTENT : 39 DECIDE ON QUESTION CONTENT The content of the questions is influenced by the respondent’s ability and/or willingness to respond accurately
ABILITY TO ANSWER ACCURATELY
Respondent is uniformed :- We are frequently asked questions to which we do not have the answers.
Respondent is forgetful :- Research studies have shown that we forget mopst events fairly rapidly after we learn about them. The rate of forgetting is very rapid over the first few days and continues with the passage of time. WILLINGNESS TO RESPOND ACCURATELY : 40 WILLINGNESS TO RESPOND ACCURATELY Unwillingness to respond accurately can be reflected in
Refusal to respond to a question or a series of questions,that is,items no response error.
Deliberate provision of an incorrect or distorted response to a question,that is,measurement error. Respondents may be unwilling to respond accurately for any of the following three reasons : 41 Respondents may be unwilling to respond accurately for any of the following three reasons They may consider the situation inappropriate for disclosing the data
Disclosure of the data would be embarrassing
Disclosure would be a potential threat to the respondents prestige or normative views. Approaches that have been developed to deal with the bias resulting from respondent unwillingness to respond accurately : 42 Approaches that have been developed to deal with the bias resulting from respondent unwillingness to respond accurately Counter biasing statement
Labeled response categories
Randomized response technique. Decide to response format : 43 Decide to response format The three types of questions,which range from unstructured to structured response formats
Dichotomous questions. Advantage of open-ended questions : 44 Advantage of open-ended questions An open-ended questions can serve as an excellent first question on a topic
Open –ended questions influence responses less than multiple-choice or dichotomous questions.
Open-ended questions can provide the researcher with insights,side components and explanations that are useful in developing a feel for the research findings. Disadvantages of Open-ended questions : 45 Disadvantages of Open-ended questions High potential for interviewer bias.
Lies in the time and cost associated with coding the responses.
Implicit extra weight given to respondents
Less suited for self-administered questionnaires.
3-5 times more costly because of the complexity associated with the data processing. Multiple –Choice questions : 46 Multiple –Choice questions Respondent choose an answer from a list provided.
Advantages of Multiple-Choice questions
They reduce interview bias and the cost and time associated with data processing
Comparatively easy and fast to administer
Cooperation by respondents is difficult to maintain unless the bulk of the questions have a structured –response format Issues in Multiple-choice question design : 47 Issues in Multiple-choice question design The number of alternatives
Position bias. Dichotomous Questions : 48 Dichotomous Questions An extreme form of the multiple-choice question which allows the respondent a choice of only two responses “Yes or No” “Did or Did not” Agree or Disagree” Advantages of dichotomous questions : 49 Advantages of dichotomous questions The interviewers find the questions quick and easy to administer
Little chance of interviewer bias
The responses are easy to code,process,and analyze. Disadvantages of Dichotomous questions : 50 Disadvantages of Dichotomous questions There is a risk of assuming that the respondent group approaches the topic of interest
Forcing respondents to express their views in a dicthomous manner when they are not thus polarized can produce results that contain substantial measurement error.
Issues in Dichotomous Question design Decide on question wording : 51 Decide on question wording The heart of the questionnaire consists of the questions-the link between the data and the information needs of the study. General guidelines that should be considered in designing the wording of a question. : 52 General guidelines that should be considered in designing the wording of a question. Use simple words.
Use clear words.
Avoid leading questions.
Avoid biasing questions.
Avoid implict alternatives.
Avoid implict assumptions.
Avoid double-barreled questions
Consider the frame of reference. Decide on question sequence : 53 Decide on question sequence Once the wording of the question has been determined, the next step is to establish their sequence.
This can influence the nature of the respondents answers.
Some of the guidelines are as follows:
Use a simple and interesting opening question.
Ask General Questions First.
Place uninteresting and difficult Questions late in the sequence.
Arrange Questions in logical order. Decide On Physical Characteristics : 54 Decide On Physical Characteristics Influencing in securing the cooperation of the respondents.
Mainly with mail surveys: Quality of paper and printing & presentation determines the respondents 1st reaction to the questionnaire.
Name of the organization should be written on the 1st page.
With personal and telephone interviews, questionnaire should be numbered serially. Carry Out Pretesting and revision, and make the final draft : 55 Carry Out Pretesting and revision, and make the final draft Consider the following as :
In terms of physical appearance:
Will the questionnaire appeal to respondents?
Does questionnaire include brief instructions?
Is the format conducing to the chosen method of data entry?
In terms of context:
Does each ques ask for only one bit of information?
Does the question wording bias response?
Are any of the ques words emotionally loaded, overly defined? Contd……… : 56 Contd……… 4. Do any of the question have double meaning which may confuse respondents?
5. Are the questions responses mutually exclusive and sufficient to cover each conceivable answer?
It is important that only best interviewers be used for pretest work. He detect areas for confusion, and probe the nature of this confusion. The interviewer should be sensitive to words that are not understood by all respondents, should test question sequence. The number of people interviewed in a pretest can range from 15 to 30.
Whenever significant changes are made in the questionnaire, another pretest should be conducted. Pretests result suggest minor changes go for the final draft. Observational Forms : 57 Observational Forms Observational forms are easier to design than questionnaires.
This is useful to characterize the information needs as who, what, when, where.
Who is to be observed?
What is to be observed?
When is observation to be made?
Where should observations be made?
These must be simple to use.Physical layout follow the above 4 ques.
Need some degree of revision and Pretesting. SECONDARY DATA SOURCES : 58 SECONDARY DATA SOURCES MEANING OF SECONDARY DATA : 59 MEANING OF SECONDARY DATA Secondary data means data that are already available that they refer to the data which have already been collected and analyzed by someone else. Two types : 60 Two types PUBLISHED NON PUBLISHED Diaries
Research works (not published )
Etc. Publications of central and state government.
Publications of foreign government, international bodies and their subsidiaries organization.
Books, newspapers and magazines.
Etc. CHARACTERSTICKS OF SECONDARY DATA : 61 CHARACTERSTICKS OF SECONDARY DATA RELIABLE ADEQUATE SUITABLE RELIABILITY OF DATA : 62 RELIABILITY OF DATA Data reliability can be tested by finding out the following things about the said data –
Who collected it ?
What were the sources of data ?
At what time were they collected ?
What level of accuracy was desired ? SUITABILITY OF DATA : 63 SUITABILITY OF DATA Data that are suitable for one enquiry may not necessarily be found suitable in another enquiry. Hence if the available data are found to be unsuitable, they should not be used by the researcher. Therefore researcher must be careful in using secondary data. ADEQUACY OF DATA : 64 ADEQUACY OF DATA If the level of accuracy achieved in data is found inadequate for the purpose of the present enquiry, then it should not be used by the researcher. An inadequate data is one if it is related to an area which may be either narrower or wider than the area of the present enquiry. ADVANTAGES OF SECONDARY DATA : 65 ADVANTAGES OF SECONDARY DATA It saves time in comparison with primary data.
It is economical as compared to that of primary data source.
Act as an aid in the formulation of the decision problem.
Suggest methods and types of data for meeting the information needs. Contd.. : 66 Contd.. Serve as a source of comparative data by which primary data can be interpreted and evaluated.
They may be so wide ranging that collecting them would be beyond the means of the typical organization. Eg :- Census DISADVANTAGES OF SECONDARY DATA : 67 DISADVANTAGES OF SECONDARY DATA The extent that the data fit the information needs of the project.
The accuracy of the data.
The timeliness of data. DATA FIT PROBLEM : 68 DATA FIT PROBLEM As we know that secondary are collected for the purpose other than those of the research project at hand, they will rarely completely serve the information needs of the project. The degree of fit is influenced by two factors :-
Units of measurement.
Definition of classes. DATA FIT PROBLEM : 69 DATA FIT PROBLEM It may be possible that the secondary data are expressed in units different from those required by the project.
Eg:- a project may require data regarding household income, the researcher may find that income is measured by individual , family rather than by household. UNITS OF MEASURMENT DATA FIT PROBLEM : 70 DATA FIT PROBLEM Another problem relates to class boundaries used to summarize the data. A researcher could find that data on household income are cited with certain boundaries which is required by projects needs. DEFINITION OF CLASSES ACCURACY PROBLEM : 71 ACCURACY PROBLEM While collecting secondary data there are a number of sources of error in the sampling, data collection, analysis etc which influences the accuracy of the data. The source of data is very is very important in evaluating the accuracy of data. It can be secured from an original or an acquired source. ACCURACY PROBLEM : 72 ACCURACY PROBLEM It is the source that originated the data. ORIGINAL SOURCE Acquired source It is the source that procured the data from the original source. ORIGINAL SOURCE IS THE MOST ACCRATE AND RELIABLE SOURCE Eg :- The statistical abstract of the United states is an acquired source. TIMELINESS PROBLEM : 73 TIMELINESS PROBLEM Data which is collected today keeping in mind the accuracy, reliability may not be of any use tomorrow. Slide 74: 74 VARIOUS SOURCES OF DATA International secondary data source Library sources CENSUS
DATA GOV. DATA SOURCE LIBRARY SOURCES : 75 LIBRARY SOURCES It included an array of publicly circulated material.
E.g.:- Gov documents, periodicals, research reports etc. GOVERNMENT DATA SOURCE : 76 GOVERNMENT DATA SOURCE For years marketing researchers have relied on this source of data for developing market potential and sales forecast, sales territories, sales quotas etc. INTERNATIONAL DATA SOURCES : 77 INTERNATIONAL DATA SOURCES International organizations such as the United Nations and the world banks have secondary data available, but great care must be taken in utilizing international secondary data as they often not comparable across countries.