RESEARCH METHODOLOGY LECTURE 11 DATA COLLECTION 1 Mazhar

RESEARCH METHODOLOGY LECTURE 11 DATA COLLECTION 1 Mazhar Hussain Dept of Computer Science ISP, Multan Mazhar. hussain@isp. edu. pk

ROAD MAP Introduction Chosing your research problem Chosing your research advisor Literature Review Plagiarism Variables in Research Construction of Hypothesis Research Design Writing Research Proposal Writing your Thesis Data Collection Data Representation Sampling and Distributions Paper Writing Ethics of Research 2

DATA COLLECTION METHODS Data Collection Primary Sources Observation Secondary Sources Interviews Questionnaire Records 3

METHODS OF DATA COLLECTION Primary Sources Secondary Sources 4

METHODS OF DATA COLLECTION Primary Sources � Information must be collected � First-hand information � Examples Attitudes of community towards health services Determining job satisfaction of employees 5

METHODS OF DATA COLLECTION Secondary Sources � Information required is already available and need only be extracted � Examples Use of census data to obtain information on the age-gender structure of a population Use of hospital records to find out mortality patterns in a community Use of an organization’s records to ascertain its activities 6

COLLECTING DATA USING PRIMARY SOURCES Observation Interviews Questionnaire 7

OBSERVATION Watching and listening to an interaction or phenomenon as it takes place Examples � Learning about the interaction in a group � Study the behaviour or personality trait of an individual � In situations where full or accurate information cannot be collected by questioning 8

OBSERVATION Two types � Participant observation � Non-participant observation Participant Observation � The researcher participates in the activities of the group being observed in the same manner as its members, with or without their knowing that they are being observered � Examples Study life of prisoners – pretend to be a prisoner Examine the reaction of general public towards people in wheel chair – observe by sitting in wheel chair 9

OBSERVATION Non-participant observation � The researcher does not get involved in the activities of the group but remains a passive observer, watching and listening to its activities and drawing conclusions � Examples Study the functions carried out by nurses in the hospital – Watch, follow and record their activities 10

PROBLEMS WITH OBSERVATION When individuals or groups become aware that they are being observed, they may change their behaviour. � Positive or negative – may increase or decrease productivity � Also known as Hawthorne Effect Possiblity of observer bias Interpretations drawn from observations may vary from observer 11

RECORDING THE OBSERVATION Narrative � Researcher records a description of the interaction in his own words � Brief notes while observing the interaction – makes detailed narrative notes soon after the interaction � Advantage – Deeper insight � Disadvantage Observer biased Different observers – Comparability is difficult 12

RECORDING THE OBSERVATION Scales � Observer develops a scale in order to rate various aspects of interaction or phenomenon -5 -4 Negative -3 -2 -1 0 1 2 Netural 3 4 5 Positive � Recording is done on the scale � Does not provide in-depth information 13

RECORDING THE OBSERVATION Error of central tendency � If the observer is not very confident, may tend to avoid extreme positions on the scale using mostly the central part Halo Effect � Error introduced when the way an observer rates an individual on one aspect influences the way he rates that individual on other aspects � Teaching – Performance in one subject may influence the impression on other subjects 14

RECORDING THE OBSERVATION Categorical Recording � Record observations using categories � Type and number depend on the problem � Examples Passive/Active Sometimes/Never/Always Strongly Agree / Uncertain / Disagree/ Strongly disagree � Same problems as with Scales 15

RECORDING THE OBSERVATION -TOOLS Paper and pencil � Cheap, Audio � Users limited to writing speed speak what they are thinking Video – accurate and realistic � Advantage: Play back many times before drawing conclusion � Users may not behave naturally in front of camera 16

RECORDING THE OBSERVATION -TOOLS Computer logging – automatically done � Large amounts of data difficult to analyze User notebooks – User takes notes himself � Coarse and subjective � Good for longitudinal studies Mixed use in practice � Audio/video transcription with paper record of significant events 17

OBSERVATION – PHYSIOLOGICAL METHODS Eye Tracking Physiological Measurements 18

EYE TRACKING Head or desk mounted equipment tracks the position of the eye Eye movement reflects the amount of cognitive processing required Measurements include � Fixations: Eye maintains stable position. Number and duration indicate level of difficulty with display � Saccades: Rapid eye movement from one point of interest to another 19

EYE TRACKING 20

PHYSIOLOGICAL MEASUREMENTS These may help determine a user’s reaction to an intervention Measurements include: � Heart activity, including blood pressure, pulse etc. � Activity of sweat glands � Activity in muscles � Activity in brain Difficulty in interpreting these physiological responses - more research needed 21

COLLECTING DATA USING PRIMARY SOURCES Observation Interviews Questionnaire 22

INTERVIEWS A person to person interaction between two or more individuals with a specific purpose in mind Can be: � Flexible Interviewer has the freedom to formulate questions as they come to mind around issue being investigated � Inflexible Strictly keep the questions decided before hand Interviews are classified according to the degree of flexibility 23

INTERVIEWS Interviews Unstructured Flexible Different levels of flexibility Structured Rigid 24

UNSTRUCTURED INTERVIEWS Almost complete freedome in terms of content and structure Freedom in sequence, wording and explanation of questions Forumalate questions on the spur of the moment depending upon the context of the discussion 25

STRUCTURED INTERVIEWS Pre-determined set of questions Same wording and sequence of questions as specified in the interview schedule Written list of questions � Open ended � Closed ended 26

COLLECTING DATA USING PRIMARY SOURCES Observation Interviews Questionnaire 27

QUESTIONNAIRE Written list of questions – answers are recorded by respondents Respondents � Read the questions � Interpret what is expected � Write the answers Contrary to interview – No one to explain the questions � Questionnaire must be clear and understandable 28

INTERVIEW VS. QUESTIONNAIRE Nature of Investigation � An issue - respondents may feel reluctant to disucss with an investigator – Questionnaire ensures anonymity � Examples: Drug use, criminal activities, personal info Geographical Distribution of study population � Potential respondents – scattered over a wide area � Interviews – Too expensive Type of study population � Illiteraute, very young or very old, handicapped – Interviews are a good option 29

QUESTIONNAIRES Opening In order to gain an understanding of the situation of employment in the country, we would like to ask some questions about your work history …………. Example paras in your text book 30

ADMINISTRATING A QUESTIONNAIRE Mailed questionnaires � Send by mail – most common � Assumption – access to addresses of respondents � Also send a pre-paid self addressed envelope with the questionnaire � Accompanied by a covering letter � Problem – low response rate 31

ADMINISTRATING A QUESTIONNAIRE Collective Administration � Captive Audience – Students in a class, people in a function, participants in a conference � High response rate � Explain the purpose/questions 32

ADMINISTRATING A QUESTIONNAIRE Administration in a public place � Shopping centers, parks etc. � Slightly time consuming � Similar advantages as collective administrative 33

COVERING LETTER WITH QUESTIONNAIRE Introduce yourself and institution Objectives of study General Instructions Assure about anonymity of information Provide contact number Give a deadline/return address Thank them for participation 34

ADVANTAGES OF QUESTIONNAIRE Less expensive � Save time, finances and human resource � Convenient and inexpensive � Collective administration – least expensive Greater anonymity � No face to face interaction � Sensitive questions – likely to have more accurate responses 35

DISADVANTAGES OF QUESTIONNAIRES Limited application � Study population that can read and write Low response rate � People do not return questionnaires – 25 to 30% � Effective sample size will reduce Selection bias � Those who returned may have attributes different from those who did not return � Findings may not be representative of population Clarification of issues � Can not clarify the questions 36

DISADVANTAGES OF QUESTIONNAIRES Spontaneous responses � Inappropriate when spontaneous responses are required � Questionnaire gives time to reflect before answering Cosultation � Respondent may consult others – not own opinion Influence of other questions � Respondent can see all questions before answering � Knowledge of other questions may affect the response to a question 37

FORMS OF QUESTIONS Open Ended Questions � Possible responses are not given � Answer in words of respondents � Example: What is your average annual income? Closed Ended Questions � Possible answers in the questionnaire � Respondent ticks the appropriate choice � Example: What is your average annual income? Under 10, 000 – 19, 999 20, 000 – 39, 000 40, 000 + 38

OPEN ENDED QUESTIONS Provide in-depth information Analysis is difficult Respondent feel free – variety in information Respondents may not be able to express themselves 39

CLOSED ENDED QUESTIONS Information lacks depth and variety Researcher’s Bias – Only those choices are listed which researcher thinks are the possible answers Ease of answering – ready-made list of responses Ensure that required information is obtained Analysis is easy 40

CONSIDERATIONS IN FROMULATING QUESTIONS Use simple and everyday language � Avoid technical terms � Example: ‘Is anyone in your family dipsomaniac? ’ Do not ask ambiguous questions � Are you satisfied with your canteen? � Which aspect: Service, prices, quality of food? Do no ask questions based on presumptions � How many cigarettes do you smoke in a day? Do not ask leading questions � Unemployment is increasing, isn’t it? 41

CONSIDERATIONS IN FROMULATING QUESTIONS Do not ask double-barrelled questions � Question within a question � You do not know which particular question the user has answered � Some respondents may answer both the questions, others may answer only one � Example: How often and how much time do you spend on each visit? Does your department have a special recruitment policy of minorities and women? YES – for both categories? 42

COLLECTING SENSITIVE INFORMATION Direct Manner � May be offensive Indirect Manner � Showing cartoons � Asking to pick up cards � Asking to complete sentences etc. 43

COLLECTING DATA FROM SECONDARY SOURCES Government of semi-government publications � Census, surveys, economic reports Earlier Research Personal records � Historical and personal records Mass media � Newspapers, magazines etc. Ensure validity and reliability 44

The material in these slides is based on the following resources. REFERENCES Research Methodology, Ranjit Kumar, Chapter 9 45