Research Methods

1
Research Methods

• Jacob Godfrey Agea (PhD)
• Ethnobotany Applied Food Security
• Dept. Extension Innovation Studies, College of
  Agricultural Environmental Sciences, Makerere
  University, P.O. Box 7062, Kampala, Uganda.
  Mobile [phone]
• Email agea_at_forest.mak.ac.ug / jgagea_at_gmail.com
• Homepage http//ageajg.weebly.com/

2
Hypotheses

• A hypothesis - a possible solution or answer
  derived from a thought process using evidence
  provided in the established body of knowledge in
  the area of research.
• A research project often tests a hypothesis to
  refute or support it.

3
Four criteria to be satisfied by a good
hypothesis

• States an expected relationship among variables.
• Provides justification for the hypothesis from
  literature.
• Is testable under the constraints of the study
• Is clear and brief.
• Most hypotheses state the anticipated direction
  of the relationship of the variables revisit
  your statistics

4
Forms of hypotheses

• Null hypotheses Proposes that there is no
  relationship among the identified variables - if
  the study is an experiment, then a statistical
  test of significance will measure support for the
  null hypothesis. A null hypothesis is non
  directional since there is no relationship (Ho)
• Alternative hypotheses - remaining possible
  outcomes other than the null hypothesis.
  Alternative hypotheses usually have a direction
  stated in the relationship of variables (H,).

5
Research questions Vs hypotheses

• Common in social survey research.
• Simply a re-sating of the objectives of various
  aspects of the research in form of questions.
• Some examples.........

6
Literature Review

• Done at an early stage of research after
  identifying the topic.
• Learning what others have done in related area
  the knowledge gaps needing further investigation.
  
• Standing on the shoulders of others (giants).

7
Sources of Literature

• Text books Periodicals
• Technical reports Academic theses
• Websites
• Published papers (peer reviewed journals) -
  preferably better (current) than other literature
  sources normally referred to as grey
  literature.
• Pay attention on how to gather information from
  literature
• Take trouble to learn how to quote lit both in
  text and at the reference section examples --

8
Survey research

• A method of gathering data (can be qualitative or
  quantitative) to describe, compare, or explain
  knowledge, attitudes (general dispositions),
  systems of beliefs (core beliefs, general policy
  beliefs, specific beliefs), preferences (or, more
  disparagingly, opinions), trust, behaviours

8
9
Advantages of Undertaking Surveys

• Surveys have a number of advantages in terms of
  collecting, analyzing assessing information
  from the sampled population
• Quickness
• Inexpensiveness
• Flexibility
• Efficiency
• Accuracy
• Helpful in the decision-making process

• The advantages are only evident when surveys are
  properly conducted!

9
10
Weakness of survey research

• Poor design can easily lead to bias
• Weak on validity
• Subject to artificiality.

10
11
Types of Surveys

• Cross-Sectional Surveys
• Are used to gather information on a population at
  a single point in time. An example of a cross
  sectional survey would be a questionnaire that
  collects data on how parents feel about their
  adolescent boys.
• A different cross-sectional survey questionnaire
  might try to determine the relationship between
  two factors, like religiousness of parents and
  views on homosexuality.

11
12

• 2. Longitudinal Surveys
• Gathers data over a period of time. The
  researcher may then analyze changes in the
  population and attempt to describe /or explain
  them.

There are three main types of longitudinal
surveys

• trend studies,
• cohort studies,
• panel studies.

12
13

• Trend Studies
• Trend studies focus on a particular population,
  which is sampled scrutinized repeatedly.
• While samples are of the same population, they
  are typically not composed of the same people.
• Trend studies, since they may be conducted over a
  long period of time, do not have to be conducted
  by just one researcher or research project.
• A researcher may combine data from several
  studies of the same population in order to show a
  trend.

13
14

• b) Cohort Studies
• Cohort studies also focus on a particular
  population, sampled and studied more than once.
  But cohort studies have a different focus.
• For example, a sample of 2010 BCF graduates of
  MAK could be questioned regarding their attitudes
  toward the relevance of forestry education in
  their life.

14
15

• Five years later, the researcher could question
  another sample of 2010 BCF graduates of MAK, and
  study any changes in their attitude.
• A cohort study would sample the same class, every
  time. If the researcher studied the BCF. class of
  2010 five years later, it would be a trend study,
  not a cohort study.

15
16

• c) Panel Studies
• Panel studies allow the researcher to find out
  why changes in the population are occurring,
  since they use the same sample of people every
  time.
• That sample is called a panel. A researcher
  could, for example, select a sample of 2010 BCF
  graduate students, and ask them questions on
  their working experience.

16
17

• Every year thereafter, the researcher would
  contact the same people, and ask them similar
  questions, and ask them the reasons for any
  changes in their habits.
• Panel studies, while they can yield extremely
  specific and useful explanations, can be
  difficult to conduct.
• They tend to be expensive, they take a lot of
  time, and they suffer from high attrition rates.
  Attrition is what occurs when people drop out of
  the study.

17
18

• Potential Errors in Undertaking Surveys
• If we are to ensure reliability, validity
  representativeness of the survey findings, then
  we need to guard against all forms of survey
  errors.

18
19
19
20
Random Sampling Error

• A statistical fluctuation that occurs because of
  change variation in the elements selected for the
  sample (It cannot be eliminated but very large
  samples can minimize it gt400)

20
21
Systematic Error (bias)Systematic error results
from some imperfect aspect of the research design
or from a mistake in the execution of the research
Administrative error
Systematic error (bias)
Respondent error
21
22
Respondent Error

• A classification of sample bias resulting from
  some respondent action or inaction
• Non-response bias
• Response bias

22
23
Non-response Error

• Non-respondents - people who refuse to cooperate
• Not-at-homes
• Self-selection bias
• Over-represents extreme positions
• Under-represents indifference

23
24

• Response Bias
• A bias that occurs when respondents tend to
  answer questions with a certain slant that
  consciously or unconsciously misrepresents the
  truth. This includes
• Acquiescence bias
• Extremity bias
• Interviewer bias
• Auspices bias
• Social desirability bias

24
25
Acquiescence Bias

• A category of response bias that results because
  some individuals tend to agree with all questions
  or to concur with a particular position.

25
26
Extremity Bias

• A category of response bias that results because
  response styles vary from person to person some
  individuals tend to use extremes when responding
  to questions.
• Interviewer Bias
• A response bias that occurs because the presence
  of the interviewer influences answers.

26
27
Auspices Bias

• Bias in the responses of subjects caused by the
  respondents being influenced by the organization
  conducting the study.

27
28
Social Desirability Bias

• Bias in responses caused by respondents desire,
  either conscious or unconscious, to gain prestige
  or appear in a different social role.

28
29
Survey Error
Administrative error
Systematic error (bias)
Respondent error
29
30
Administrative Error

• Improper administration of the research task
• Blunders
• Confusion
• Neglect
• Omission

30
31
Types of administrative error

• Interviewer cheating - filling in fake answers or
  falsifying interviewers
• Data processing error - incorrect data entry,
  computer programming, or other procedural errors
  during the analysis stage.
• Sample selection error -improper sample design or
  sampling procedure execution.
• Interviewer error - field mistakes

31
32
Survey Research Tools

• Personal interviews
• Door-to-door
• Focus group interviews
• Telephone interviews
• Self-administered questionnaires

32
33

• Guidelines for Survey Interviewing
• Dress in a similar manner to the people who will
  be interviewed.
• Study and become familiar with the questionnaire.
• Follow question wording exactly.
• Record responses exactly.
• Probe for responses when necessary.

33
34

• Training for Interviewers
• Discussion of general guidelines and procedures.
• Specify how to handle difficult or confusing
  situations.
• Conduct demonstration interviews.
• Conduct real interviews.

34
35

• Personal Interviews

A personal interview is a form of direct
communication in which an interviewer asks
respondents in a face-to-face conversational
situation. It can be door-to-door or in form of
group interviews/discussions.
35
36

• Advantages of Personal Interviews
• Opportunity for Feedback Interviewer can
  provide direct feedback to the respondent, give
  clarifications help alleviate any
  misconceptions or apprehensions over
  confidentiality that the respondent may have in
  answering the interviewers questions
• Probing Complex Answers Interviewers can probe
  if the respondents answer is too brief or
  unclear. This gives interviewers some flexibility
  in dealing with unstructured questions and is
  especially suited for handling complex questions

36
37

• Length of Interview If the questionnaire is
  often very lengthy, the personal interview is the
  best technique for getting respondents to
  cooperate, without overtaxing their patience.
• Complete Questionnaires Personal ensures ensure
  that the respondent will answer all questions
  asked, unlike in telephone interview where the
  respondent may hang up or in mail questionnaire
  where some questions may go unanswered.

37
38

• Props Visual Aids Interviewers have the
  opportunity of showing respondents items such as
  sample products, graphs ands sketches, which can
  aid in their answers
• High Participation Interviewing respondents
  personally can increase the likelihood of their
  participation, as many people prefer to
  communicate directly verbally sharing
  information and insights with interviewers

38
39
Disadvantages of Personal Interviews

• Cost Personal interviews are usually more
  expensive than mail, telephone or internet
  surveys.
• Factors influencing the cost of the interview
  include the respondents geographic proximity,
  the length complexity of the questionnaire,
  the number of non-respondents

39
40

• Lack of Anonymity Respondents are not anonymous
  in a personal (face-to-face) interview may be
  reluctant to disclose certain information to the
  interviewer.
• Hence, considerable must be expended by the
  interviewer when dealing with sensitive questions
  to avoid bias effects on the respondents part.
• Necessity for Callbacks When a person selected
  for interview cannot be reached the first time, a
  callback has to be scheduled which result in
  extra cost and time spent

40
41

• Dishonesty Interviewers cheat to make their
  life easier save time and effort.
• Personal Style The interviewers individual
  questioning style, techniques, approach
  demeanor may influence the respondents answers.
• Global Considerations Cultural aspects may
  influence peoples willingness to participate in
  an interview (e.g. repressive Middle Eastern
  cultures discourage females from being questioned
  face-to-face by male interviewers).

41
42
Telephone Surveys
42
43

• In telephone interviews, respondents are
  contacted by telephone in order to collect data
  for surveys
• Telephone interviewing has been used for decades
  , in some ways, has advantages over other
  methods of undertaking surveys
• With improvements in the IT-field, computers can
  be used to assist in telephone interviewing,
  answers given by respondents can be entered by
  interviewers directly into the computer, saving
  effort, time cost

43
44

• Speed This is a major advantage of telephone
  interviewing, enabling data to be collected on
  very short notice.
• Cost Telephone interviews are comparatively
  cheaper to conduct than personal interviews. No
  travel time and travel cost is involved.
• No Face-to-Face Contact Bse telephone
  interviews lack the direct element of
  interaction, respondents may be more willing to
  provide certain information that they would be
  reluctant to disclose in a personal
  (face-to-face) interview.

44
45

• Cooperation People may be reluctant to allow
  interviewers into their homes, but they may be
  willing to cooperate by letting themselves be
  interviewed over the telephone.
• Callbacks Telephone callbacks are easier to
  perform than personal interview callbacks.

45
46

• Disadvantages of Telephone Interviews
• No Face-to-Face Contact Interviewer may not be
  able to record the respondents data fast enough
  and the respondent, who cannot see this, may
  continue to add data.
• Also, due to the visual communication gap, there
  is a greater tendency for interviewers to record
  no-answers and incomplete answers than in a
  personal interview.

46
47

• Cooperation Research shows that response rates
  in telephone interviews are declining with the
  passage of time the availability of respondents
  has also declined for various reasons.
• Also, reaching executives in workplaces can be
  very difficult due to tight schedules and the
  work load.
• Lack of Visual Mediums Visual aids cannot be
  used by interviewers in telephone interviews,
  hence, surveys which need visual aids to help
  respondents cannot be undertaken with this survey
  method.

47
48

• Limited Duration Length of interview time in a
  telephone interview is limited. Too long
  interview times may result in exasperated
  respondents hanging up the telephone or refusing
  to answer questions.
• Representative Samples Using the telephone
  directory as the basis for sampling can be
  problematic in the sense that many persons are
  unlisted or do not have telephones, but whose
  opinions are nevertheless important.
• Global Considerations In many countries, people
  are reluctant to divulge information over the
  telephone.

48
49
Self-Administered Questionnaires
49
50

• Self-administered questionnaires are those
  questionnaires that are filled in by the
  respondent independently, i.e. without the direct
  interaction with an interviewer
• There are many ways for distributing
  self-administered questionnaires, for example, by
  mailing or faxing questionnaires to pple, by
  posting them on websites, by distributing them at
  certain locations places, by including them as
  inserts in magazines so forth
• Researchers who have to interpret
  self-administered questionnaires have to be
  skillful at trying to understand what is being
  conveyed to them in written or electronic -
  rather than verbal - form

50
51
Mail Questionnaire Surveys
A mail questionnaire survey is a
self-administered questionnaire dispatched to
respondents thru' the mail. Mail questionnaires
surveys have several advantages disadvantages
Advantages Cost They are comparatively cheaper
to conduct than personal interviews telephone
surveys, but can still be quite costly bse of the
costs of printing mailing questionnaires,
possible follow-up actions
51
52

• Disadvantages
• Interviewer Absence Respondents may attach a
  different subjective meaning to questionnaires,
  which are outside the control or influence of the
  interviewer who cannot be consulted or queried.
  Respondents may thus misunderstand certain
  questions or aspects of the survey
• Standardized Questions Misunderstanding of
  questions on the part of the respondent can
  create problems since no interviewer is present
  to answer queries or clarify misunderstandings or
  overcome comprehension problems.
• Wrong Respondents Questionnaires may not be
  answered by target respondents, instead, the task
  of filling up the questionnaire is delegated to
  other pple.

52
53

• Time Factor Mail questionnaire surveys may be
  inappropriate if time is very limited
  information is needed quickly. Usually, it can
  take a few weeks before completed mail
  questionnaires are received, follow-up action
  initiated the information analyzed
• Length of Mail Questionnaire If the
  questionnaire is quite long (usually gt 6 pages),
  respondents must give considerable effort may
  not be willing to invest the effort. Sometimes,
  this reluctance can be overcome by using
  incentives.
• Social Factors The response rate is dependent
  on socio-econ. factors such as education level of
  respondent his/her econ. status. More educated
  well-to-do respondents, those with more
  interest in the subject of the survey, tend to
  reply more to questionnaires than respondents
  with less education.

53
54

• Geographic Flexibility Mail questionnaires can
  be distributed over a geographically wide area
  simultaneously quickly, including to
  respondents who may live in remote or not so
  cheaply accessible areas, respondents who may
  not be easy to reach.
• Responent Convenience Questionnaires can be
  filled out at the respondents convenience. The
  respondent has time to think about his or her
  answer which may provide more accurate data
  information to the interviewer than would be
  possible in the case of personal interviews or
  telephone surveys.
• Interviewer Absence Respondents may be willing
  to disclose sensitive information in a mail
  survey which they may not be willing to do if
  being interviewed personally.

54
55
How to Increase Response Rates for Mail Surveys

• Write a cover letter
• Money helps
• - As a token of appreciation
• Advanced notification
• Stimulate respondents interest with interesting
  questions
• Follow Up
• - Keying questionnaires with codes
• Sponsorship by a well-known prestigious
  institution

55
56
Fax Questionnaire Surveys
A survey in which questionnaires are distributed
and/or returned through fax machines

• Advantages
• Reduction in printing postage costs for the
  researcher and faster distribution and return
  than through mail surveys
• Disadvantages
• Not all respondents have fax machines some
  respondents may not want to return the fax if
  transmission cost is high due to geographical
  distance. Other disadvantages are the as with
  mail questionnaire surveys.

56
57
E-Mail Questionnaire Surveys
A survey in which questionnaires are distributed
and returned via email. Surveys conducted with
email are especially suited for time-sensitive
issues

• Advantages- Speed of distribution, lower
  distribution processing costs, faster
  turnaround time, more flexibility.
• Disadvantages- Not all respondents have emails.
  There may be concerns on the part of respondents
  about confidentiality the format of emails can
  differ considerably depending on the prog. used
  the settings of respondents computer (spam mgt).
  Moreover, respondents have different skill levels
  in handling emails, especially complicated
  survey-related ones.

57
58
Internet questionnaire Surveys

• A self-administered questionnaire posted on a
  Website. Respondents provide answers to questions
  displayed online by highlighting a phrase,
  clicking an icon, or keying in an answer.
• Advantages
• access to a large (possibly global) audience on
  24-hour basis
• Real-time data entry analysis
• More accurate data capture if properly programmed
• obtaining confidential, anonymous answers quickly
  cost-effectively

58
59

• No costs for paper, postage, data entry
  administrative costs.
• Large samples can be larger than with interviews
  other types of self-administered
  questionnaires.
• Questionnaires can include use of appealing
  multimedia aids including photographs or drawings
  of prototypes.
• Callbacks are automated (if response incomplete
  or not given).
• email can be used to invite respondents to visit
  the website, for e.g. to participate in panels.
• Flexible personalized questioning of
  respondents.

59
60
60
61
Disadvantages- internet questionnaire surveys

• Many people in the general population do not have
  access to the internet.
• Different levels of technology may be prevalent
  (broadband or dial-up connectivity) which may
  result in some users not being able to access
  information as quick as others.
• Hardware deficiencies /or software
  incompatability
• Different computer skill levels.
• Physical incentives (e.g. inclusion of money) is
  not possible, only the promise of a future
  reward.
• Research on internet surveys is small so are
  ideas for improving response rates.

61
62

• You can read about other Types of
• self-administered questionnaire surveys.

62
63
Questionnaire Design

• Before starting to design a questionnaire, write
  a study protocol!

63
64
Basic Rules

• On first page
• Return address
• Study title
• On all pages
• Identifier
• Page numbers
• Numbered questions
• Instructions (in bold or italic)

64
65
Structure of a questionnaire

• Introductory cover letter
• Identification
• Instructions on how to answer
• Questions
• Conclusion

65
66
1. Example of an introductory cover letter

• Good morning,
• My name is ..... , I work for ..
• You may have been already informed that a survey
  on risk factors for being stung by a jellyfish
  will be done this week in Kabakas Lake, Mengo.
  This study has been approved by the national
  ethical committee. Only anonymous data will be
  analysed. You have been randomly selected to
  participate in this study. Your participation is
  voluntary. The interview is about 15 minutes
  long.
• I will start with the first question .....

66
67
2. Identification

• Each questionnaire/interviewed person must be
  identified
• Example I_I I_I_I I_I_I
• interviewer N district N person
  N
• Demographic data age, sex
• Identifiers kept separately from names
  (anonymous)

67
68
3. Instructions on how to answer

• Give clear instructions about how to answer the
  questions
• Use different fonts (e.g. italics)
• Give instruction which questions can be skipped
  where to jump to.

Example I will ask you a few questions about
your relationship with jellyfish. You will answer
by yes or no If no, go to question 27
68
69
4. Questions

1. Content
2. Order
3. Format
4. Problems pitfalls
5. Coding

69
70
A. Content of questions

• Clear focus on research questions
• avoid sidetracking
• avoid unnecessary information

70
71
B. Question order

• Decide on the order of items/questions
• easy ? difficult
• general ? particular
• factual ? abstract
• Group questions by topic
• Be aware of ordering effects
• Dont put the most important items last
• Where to place sensitive questions?

71
72
C. Format of questions
73

• Read about advantages disadvantages of closed
  open-ended question formats.

74
Dichotomous Questions

• When a question has two possible responses, we
  consider it dichotomous. Surveys often use
  dichotomous questions that ask for a Yes/No,
  True/False or Agree/Disagree response.
• E.g.
• Do you believe that death penalty is ever
  justified?
• ? Yes ? No
• Please indicate your sex
• ? Male ? Female

75
Questions Based on Level of Measurement

• Rank order question
• You might ask respondents to rank order their
  preferences for presidential candidates using an
  ordinal question Rank the candidates in order of
  your preference from best to worst.
• ? Besigye Kizza Kifefe Ipc Forum For
  Democratic Change
• ? Abed Bwanika Peoples Development Party
• ? Beti Olive Namisango Kamya Uganda Federal
  Alliance
• ? Samuel Lubega Walter Mukaaku Independent
• ? Mao Norbert Democratic Party
• ? Yoweri Kaguta Museveni National Resistance
  Movement
• ? Olara Otunnu Uganda Peoples Congress
• ? Bidandi-Ssali Jaberi Peoples Progressive
  Party
• We want the respondent to put a 1, 2, 3, 4 up to
  8 next to the candidate, where 1 is the
  respondent's first choice.

76
Interval level questions - Likert response scale

• We can also construct survey questions that
  attempt to measure on an interval level. One of
  the most common of these types is the traditional
  1-to-5 rating (or 1-to-7, or 1-to-9, etc.). This
  is sometimes referred to as a Likert response
  scale.
• Here, we see how we might ask an opinion question
  on a 1-to-5 bipolar scale (it's called bipolar
  because there is a neutral point the two ends
  of the scale are at opposite positions of the
  opinion).

77

• 18. Death penalty is justifiable under some
  circumstances.

• 1? I strongly disagree
• 2? I disagree
• 3? I neither agree or disagree
• 4? I agree
• 5? I strongly agree

19. Capital punishment in the form castration is
the best way to deal with male rapist

• 1? I strongly disagree
• 2? I disagree
• 3? I neither agree or disagree
• 4? I agree
• 5? I strongly agree

78

• Interval level questions - semantic differential
  scale
• Another interval question uses an approach call
  the semantic differential.
• Here, an object is assessed by the respondent on
  a set of bipolar adjective pairs (using 5-point
  rating scale).
• E.g.

79
Example of semantic differential scaling
80
Interval level questions - Cumulative or Guttman
scale
Finally, we can also get at interval measures by
using what is called a cumulative or Guttman
scale. Here, the respondent checks each item
with which they agree. The items themselves are
constructed so that they are cumulative -- if you
agree to one, you probably agree to all of the
ones above it in the list.
81
Example of Cumulative or Guttman scale

• Please tick each statement that you agree with
• Are you willing to permit immigrants to live in
  your country?
• Are you willing to permit immigrants to live in
  your community?
• Are you willing to permit immigrants to live in
  your neighbourhood?
• Would you be willing to have an immigrant live
  next door to you?
• ? Would you let your child marry and immigrant?

82
Filter or Contingency Questions

• Sometimes you have to ask the respondent one
  question in order to determine if they are
  qualified or experienced enough to answer a
  subsequent one.
• This requires using a filter or contingency
  question.
• For instance, you may want to ask one question if
  the respondent has ever smoked marijuana a
  different question if they have not.
• In this case, you would have to construct a
  filter question to determine whether they've ever
  smoked marijuana. E.g.

83
Example of Filter or Contingency Questions
84

• The example above shows how you can make
  effective use of an arrow and box to help direct
  the respondent to the correct subsequent
  question.
• If you can't fit the response to a filter on a
  single page, it's probably best to be able to say
  something like "If YES, please turn to page 4"
  rather that "If YES, please go to Question 38"
  ..
• Because the respondent will generally have an
  easier time finding a page than a specific
  question.

85
D. Problems pitfalls
86
(No Transcript)
87
(No Transcript)
88
And finally,

• Dont forget to thank the interviewed persons.
• Tell them when the results will be available
  where.