Top Banner

of 59

271 33 Powerpoint Slides Chapter 6 Types Sources Data

Jun 02, 2018

Download

Documents

Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    1/59

    Chapter

    Types and Sources of Data

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    2/59

    Objectives

    To understand

    the primary and secondary types of data used in

    research

    the various methods of data collection, their

    applicability, and limitations

    how to anticipate and safeguard against the kind oferrors that infect data

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    3/59

    Data the quantification of tangible and intangible facts

    Data may be classified

    - By the purpose of collection:

    1. Primary Data : Data collected specifically for thepurpose of providing information on the decisionunder question

    2. Secondary Data: Data important for the decisionbeing examined, but not collected specifically forquestions related to it: socio-economic trends,industry trends, government policies or inc-

    company data including earlier researchreports

    Sources of Data

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    4/59

    cont.

    - By the nature of the var iables studied :

    1. Data related to past or future behaviour

    2. Data related to attitudes, perceptions, beliefs,

    etc.

    Both types of data required for understanding currentmarket-trends and for predicting future trends

    Sources of Data

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    5/59

    Methods of Data Collection All research requires secondary data. Most require primary

    data in addition.

    Data collection methods depend on the research approach:

    exploratory, descriptive or causal.

    Extensive studies require more than one research approach at

    different stages.

    Method of collecting primary data:* Observation

    * Surveys

    * Experiments

    * Qualitative methods

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    6/59

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    7/59

    ERRORS IN DATA

    SECONDARY DATA PRIMARY DATA

    Outdated Data Sampling Errors Missing-Response Response Errors

    Inappropriate Samples Errors

    Inaccuracy Ambiguity

    Guestimates Non-response Inaccuracy AmbiguityTwisting of Data Not-at-home

    Time Question

    Privacy Length

    Prestige Question

    Conflict Form

    with Question

    investigator wording

    Investigator

    Unwillingness Trans-lation

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    8/59

    Limitations of DataTypes of Data Methods of Data

    Collection

    Limitations

    Secondary Data Information may

    relate to adifferent periodand may not be

    relevant anylonger.

    Sample ,or database may bedifferent Rigour

    in collecting datacannot bevouchedfor.

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    9/59

    contd.

    Primary Data Observation

    Surveys

    Experiments

    Cannot answer thequestionwhy

    Scope forrationalizedresponses

    Quality of data willvary with the skill ofthe interviewer

    Cannot tap intoissues that are partof the subconscious

    mind. Can study only one

    dependent variableat a time.

    Limitations of Data

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    10/59

    Qualitative

    Make assumptionsthat are not alwayssustainable in reality

    Difficult to replicateand therefore togeneralize from.

    Results may bevitiated byenvironmentalvariables andcompetitive activity

    Difficult to generalize

    Quality of data highlydependent on the skillof the interviewer

    Limitations of Data

    TABLE 6.1: LIMITATION OF VARIOUS DATA COLLECTION METHODS

    contd.

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    11/59

    Benefits of secondary data

    Resource advantage

    Accessibility of data

    accuracy and stability of data

    Assessment of data

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    12/59

    Evaluation of secondary data

    Methodology check

    Sampling consideration

    Methodology of data

    Analytical tools used and subsequentreporting

    Accuracy check

    Topical check

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    13/59

    Classification of data

    Internal sources of data

    Company records

    Employee records

    Sales data (cash register receipt,salespersons call records ,sales invoices)

    Financial records

    External data sources

    Published data

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    14/59

    Published data sources

    Government sources (census data ,government publications)

    Other data sources

    Books and periodicals

    Guides

    Directories and indices

    Standard non-gov statistical data

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    15/59

    Computer stored data

    Reference database

    Syndicated data sources On-line database

    CD-ROM database

    Institutional syndicated data (Nielson,Prowess IMRB)

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    16/59

    Qualitative methods of data collection

    Direct (non-disguised)

    Observation

    Focus group

    Depth interviews Content analysis

    Indirect (disguised- only disadvantage is privacy issue)

    Projective

    Association ,completion ,construction, expressive,choice

    Sociometry

    new

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    17/59

    Qualitative vs quantitative data method

    Research objective

    Need to explore and describe

    Study is quantified and needed suitable analysis

    Research design Exploratory or descriptive ,loosely structured and

    open ended

    Structured and measurable set of variables

    Sampling plan Manageable small sample vs large representative

    sample

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    18/59

    Continued......

    Data collection

    Data collection in depth and collected through more

    interactive and unstructured approach Data collected is formatted and structured

    Data analysis

    Textual and usually non statistical

    Interpretation through statistical methods Research deliverables

    Intial and ultimate objective to explain findings

    Findings are conclusive and demonstrate clear

    indications

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    19/59

    ChapterDesigning Questionnairesand

    Interview Guides

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    20/59

    Objectives

    To Understand

    the importance of a well-designed questionnaire

    the funnel approach

    the categories of questions and how to choose between them

    mail, telephone, and Internet surveys

    how to collect data from in-depth interviews

    What to look out for when reproducing a questionnaire

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    21/59

    Introduction

    A questionnaire acts as the means of communication

    between the respondent and the researcher. Clear and

    concise definition of the goals of the study make it easier to

    design the questionnaire.

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    22/59

    contd.

    The extent to which the subject matter as well as thestructure of the questionnaire interests and involves therespondent. The funnel approach must be used for thispurpose.

    The length of a questionnaire

    The appropriateness of a question: the flow chart approachand similar methods minimize errors in data collection.

    The purpose of the study: this influences the format andstructure of the questionnaire.

    Factors Influencing Questionnaire

    Design

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    23/59

    23

    Questionnaires in ClinicalResearch

    Much of the data in clinical research isgathered using questionnaires orinterviews.

    The validity of the results depends on thequality of these instruments. Good questionnaires are difficult to construct;

    bad questionnaires are difficult to analyze.

    Difficult to design for several reasons: Each question must provide a valid and

    reliable measure.

    The questions must clearly communicate the

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    24/59

    24

    Quality aims in survey research

    Goal is to collect information that is:

    Valid: measures the quantity or conceptthat is supposed to be measured

    Reliable: measures the quantity orconcept in a consistent or reproduciblemanner

    Unbiased: measures the quantity orconcept in a way that does notsystematically under- or overestimate the

    true value

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    25/59

    25

    Steps to design a questionnaire:

    1. Write out the primary and secondaryaims of your study.

    2. Write out concepts/information to becollected that relates to these aims.

    3. Review the current literature to identifyalready validated questionnaires thatmeasure your specific area of interest.

    4. Compose a draft of your questionnaire.

    5. Revise the draft.

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    26/59

    26

    Step 1: Define the aims of thestudy

    Write out the problem and primary andsecondary aims using onesentence peraim. Formulate a plan for the statistical

    analysis of each aim.

    Make sure to define the target populationin your aim(s).

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    27/59

    27

    Step 2: Define the variables to becollected

    Write a detailed list of the information to be collected and theconcepts to be measured in the study. Are you trying toidentify:

    Attitudes

    Needs Behavior

    Demographics

    Some combination of these concepts

    Translate these concepts into variables that can bemeasured.

    Define the role of each variable in the statistical analysis:

    Predictor

    Confounder

    Outcome

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    28/59

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    29/59

    29

    Step 4: Compose a draft [1]:

    Determine the mode of surveyadministration: face-to-face interviews,telephone interviews, self-completed

    questionnaires, computer-assistedapproaches.

    Write more questions than will be includedin the final draft.

    Format the draft as if it were the finalversion with appropriate white space toget an accurate estimate as to its length

    longer questionnaires reduce the response

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    30/59

    30

    Compose a draft [2]:

    Question: How many cups of coffee ortea do you drink in a day?

    Principle: Ask for an answer in only onedimension.

    Solution: Separate the question into two

    (1) How many cups of coffee do you drinkduring a typical day?

    (2) How many cups of tea do you drink during

    a typical day?

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    31/59

    31

    Compose a draft [3]:

    Question: What brand of computer do you own? (A) IBM PC (B) Apple

    Principle: Avoid hidden assumptions. Make sure toaccommodate all possible answers.

    Solution: (1) Make each response a separate dichotomous item

    Do you own an IBM PC? (Circle: Yes or No) Do you own an Apple computer? (Circle: Yes or No)

    (2) Add necessary response categories and allow for multiple

    responses. What brand of computer do you own? (Circle all that apply)

    Do not own computer IBM PC Apple Other

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    32/59

    32

    Compose a draft [4]:

    Question: Have you had pain in the lastweek?

    [ ] Never [ ] Seldom [ ] Often [ ]

    Very often

    Principle: Make sure question and answeroptions match.

    Solution: Reword either question oranswer to match.

    How often have you had pain in the last

    week?

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    33/59

    33

    Compose a draft [5]:

    Question: Where did you grow up? Country

    Farm

    City Principle: Avoid questions having non-

    mutually exclusive answers.

    Solution: Design the question withmutually exclusive options. Where did you grow up?

    House in the country

    Farm in the country

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    34/59

    34

    Compose a draft [6]:

    Question: Are you against drug abuse?(Circle: Yes or No)

    Principle: Write questions that willproduce variability in the responses.

    Solution: Eliminate the question.

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    35/59

    35

    Compose a draft [7]:

    Question: Which one of the following do you think increasesa persons chance of having a heart attack the most? (Checkone.)

    [ ] Smoking [ ] Being overweight [ ] Stress

    Principle: Encourage the respondent to consider eachpossible response to avoid the uncertainty of whether amissing item may represent either an answer that does notapply or an overlooked item.

    Solution: Which of the following increases the chance ofhaving a heart attack?

    Smoking: [ ] Yes [ ] No [ ] Dont know

    Being overweight: [ ] Yes [ ] No [ ] Dont know

    Stress: [ ] Yes [ ] No [ ] Dont know

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    36/59

    36

    Compose a draft [8]:

    Question:

    (1) Do you currently have a life insurancepolicy? (Circle: Yes or No)

    If no, go to question 3.

    (2) How much is your annual life insurancepremium?

    Principle: Avoid branching as much aspossible to avoid confusing respondents.

    Solution: If possible, write as one

    question.

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    37/59

    37

    Step 5: Revise

    Shorten the set of questions for the study.If a question does not address one of youraims, discard it.

    Refine the questions included and theirwording by testing them with a variety ofrespondents.

    Ensure the flow is natural.

    Verify that terms and concepts are familiarand easy to understand for your target

    audience.

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    38/59

    38

    Step 6: Assemble the final questionnaire[1]:

    Decide whether you will format the questionnaire yourself oruse computer-based programs for assistance:

    SurveyMonkey.com

    Adobe Live Cycle Designer 7.0

    GCRC assistance At the top, clearly state:

    The purpose of the study

    How the data will be used

    Instructions on how to fill out the questionnaire Your policy on confidentiality

    Include identifying data on each page of a multi-page, paper-based questionnaire such as a respondent ID number in casethe pages separate.

    bl h f l

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    39/59

    39

    Assemble the final questionnaire[2]:

    Group questions concerning major subjectareas together and introduce them byheading or short descriptive statements.

    Order questions in order to stimulaterecall.

    Order and format questions to ensure

    unbiased and balanced results.

    bl h f l

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    40/59

    40

    Assemble the final questionnaire[3]:

    Include white space to make answersclear and to help increase response rate.

    Space response scales widely enough so

    that it is easy to circle or check the correctanswer without the mark accidentallyincluding the answer above or below. Open-ended questions: the space for the

    response should be big enough to allowrespondents with large handwriting to writecomfortably in the space.

    Closed-ended questions: line up answersvertically and precede them with boxes or

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    41/59

    41

    Enhance response rate

    When writing questions and assemblingthe final questionnaire, edit with a viewtowards saliency: apparent relevance,

    importance, and interest of the survey tothe respondent

    Consider either pre-notifying those in your

    sample or sending reminders to those whoreceived the survey (if self-administered).Studies have shown that making contact

    with the sampled individuals increases the

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    42/59

    42

    Non-responders

    Understanding the characteristics of thosewho did not respond to the survey isimportant to quantify what, if any, bias

    exists in the results.

    To quantify the characteristics of the non-responders to postal surveys, Moser and

    Kalton suggest tracking the length of timeit takes for surveys to be returned. Thosewho take the longest to return the survey

    are most like the non-responders. This

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    43/59

    43

    Conclusions

    You need plenty of time!

    Design your questionnaire from researchhypotheses that have been carefully studied

    and thought out. Discuss the research problem with colleagues

    and subject matter experts is critical todeveloping good questions.

    Review, revise and test the questions on aniterative basis.

    Examine the questionnaire as a whole for flow

    and presentation.

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    44/59

    44

    References

    Designing Clinical Research, Stephen B.Hulley, et. al.

    www.statpac.com/surveys

    Design and use of questionnaires: areview of best practice applicable tosurveys of health service staff and

    patients, Health Technology Assessment,2001. Vol.5, No. 31.

    Moser CA, Kalton G. Survey methods in

    social investigation. 2nded. Aldershot:

    http://www.statpac.com/surveyshttp://www.statpac.com/surveys
  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    45/59

    45

    Answer key [1]:

    Question: How many cups of coffee ortea do you drink in a day?

    Principle: Ask for an answer in only onedimension.

    Solution: Separate the question into two

    (1) How many cups of coffee do you drinkduring a typical day?

    (2) How many cups of tea do you drink during

    a typical day?

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    46/59

    46

    Answer key [2]:

    Question: What brand of computer do you own? (A) IBM PC (B) Apple

    Principle: Avoid hidden assumptions. Make sure toaccommodate all possible answers.

    Solution: (1) Make each response a separate dichotomous item

    Do you own an IBM PC? (Circle: Yes or No) Do you own an Apple computer? (Circle: Yes or No)

    (2) Add necessary response categories and allow for multiple

    responses. What brand of computer do you own? (Circle all that apply) Do not own computer IBM PC Apple Other

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    47/59

    47

    Answer key [3]:

    Question: Have you had pain in the lastweek?

    [ ] Never [ ] Seldom [ ] Often [ ]

    Very often

    Principle: Make sure question and answeroptions match.

    Solution: Reword either question oranswer to match.

    How often have you had pain in the last

    week?

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    48/59

    48

    Answer key [4]:

    Question: Where did you grow up? Country

    Farm

    City Principle: Avoid questions having non-

    mutually exclusive answers.

    Solution: Design the question withmutually exclusive options. Where did you grow up?

    House in the country

    Farm in the country

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    49/59

    49

    Answer key [5]:

    Question: Are you against drug abuse?(Circle: Yes or No)

    Principle: Write questions that willproduce variability in the responses.

    Solution: Eliminate the question.

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    50/59

    50

    Answer key [6]:

    Question: Which one of the following do you think increasesa persons chance of having a heart attack the most? (Checkone.)

    [ ] Smoking [ ] Being overweight [ ] Stress

    Principle: Encourage the respondent to consider eachpossible response to avoid the uncertainty of whether amissing item may represent either an answer that does notapply or an overlooked item.

    Solution: Which of the following increases the chance ofhaving a heart attack?

    Smoking: [ ] Yes [ ] No [ ] Dont know

    Being overweight: [ ] Yes [ ] No [ ] Dont know

    Stress: [ ] Yes [ ] No [ ] Dont know

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    51/59

    51

    Answer key [7]:

    Question:

    (1) Do you currently have a life insurancepolicy? (Circle: Yes or No)

    If no, go to question 3.

    (2) How much is your annual life insurancepremium?

    Principle: Avoid branching as much aspossible to avoid confusing respondents.

    Solution: If possible, write as one

    question.

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    52/59

    Designing the Questionnaire

    The process of questionnaire design depends on

    The management dilemma

    Definition of the marketing research problem

    The research design: the sample, the specific interview

    approach and the medium of data collection including type of

    questions to be asked

    The process of questionnaire design:

    Contd.

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    53/59

    Designing the QuestionnaireThe process of questionnaire design:

    Definition of MR Problem

    Hypotheses

    Objectives / Areas of Enquiry

    Definition of Sample

    Decision about Data-Collection Approach

    Flow -Chart for Questions

    Identification Questions

    Research Questions

    Classificatory Questions

    Errors in Questionnaire Design and

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    54/59

    Errors in Questionnaire Design and

    the Flow Chart

    Questionnaire design must consider:

    Type of questions : structured vs. unstructured; closed- vs.open-ended; scales

    Order of questions: the funnel approach from general tospecific

    The use of a flow-chart helpful for ensuring the order ofquestions

    Content of questions: governed by

    a) the purpose of the question,b) the extent to which it needs to be disguised,c) the scope of the questiond) the wording of the question -- respondents ability and

    willingness to answer it.

    .contd.

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    55/59

    Errors in Questionnaire Design andthe Flow Chart

    Pre-testing the questionnaire: - administration of thequestionnaire to a

    small sample prior toits finalisation

    - purpose: to check forsuitability of the type ofquestions, their order,content, and length

    - sample: 15 for a simplequestionnaire; 25 for a

    complex questionnaire

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    56/59

    Questionnaires for Telephone and

    Internet Surveys Factors to be taken into consideration:

    i. use structured questions as far as possible

    ii. frequent use of graphics, specially for attitudinal/

    perception related questions

    iii. extensive use of multiple-choice or dichotomousquestions

    iv. short questions

    v. limited use of whyquestionsvi. brief questionnaire

    .contd.

    Q ti i f T l h d

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    57/59

    Questionnaires for Telephone andInternet Surveys

    Advantages of non-personal survey methods:

    i. Anonymity that provides privacy

    ii. The ability to answer at leisureiii. Lower per unit cost than personal interviews

    Disadvantages of non-personal survey methods:

    i. Low response rates in the absence of controlii. Biased sample because of non-response from those not

    interested

    P j ti T h i d I t i

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    58/59

    Projective Techniques and InterviewGuides

    Projective techniques useful when respondent unwilling or unableto share information.

    In-depth interviews require interview guidelines that do notinclude formal, structured, complete questions, but only a list ofthe areas of enquiry.

    The interview guideline used in projective techniques and in-depth interviews aims at obtaining information on all relevantissues, without being restricted to a predetermined order orstructure of questions.

    The interview may at times require going back and forth on oneissue, thus repeating inquiry through differently wordedquestions each time.

    Projective techniques particularly useful for interviewing children: retain their interest and encourage spontaneity.

  • 8/11/2019 271 33 Powerpoint Slides Chapter 6 Types Sources Data

    59/59

    Physical quality and visual appeal secondary but impact

    making characteristic of the interviewing instrument .

    Good production and paper quality important.

    Errorfree typing and design essential.

    Accurate and easy-to-understand translation crucial in mult

    lingual countries like India.

    Reproduction of the Questionnaire