Transcript 09. choosing tool for data collection.ppt

By:
Awatif Ali Alam
Professor
[email protected]
What?
•Concepts
•Variables
•Measures
HOW?
Overall
Method
•Survey
•Experiment
•Case Study
•Secondary Data
Data Gathering
Analysis
Application
Who?
•Population
•Sampling
STEPS IN A SURVEY
1. Define study objectives
2. Identify information needs & study population(s)
3. Determine basic design/approach:
- a self-administered survey
- could be mailed or on-site survey
4. Questionnaire design
5. Choose sample (frame, size, sampling design)
6. Estimate time, costs, manpower needs, etc.
Questionnaire Design
1. Preliminary Info
 Information needed
 Who are subjects
 Method of communication
2. Question Content
3. Question Wording
4. Response Format
5. Question Sequencing/Layout
Wording
1. Will words be uniformly understood? Simple
language. Avoid technical phrases, jargon and
abbreviations.
2. Does question adequately express the alternatives?
3. Is the question misleading due to unstated assumption
or unseen implications.
4. Is wording biased, emotional, or unfair?
5. Will wording be offensive to respondents?
6. Should you use more or less personalized wording?
7. Ask in a more direct or more indirect way?
What Information?
Demographic, Socioeconomic, Physical
•e.g. income, age, weight, hometown,…
Cognitive - Knowledge & beliefs
• e.g. Aware of a program, believe in global warming
Affective - attitudes, feelings, preferences
• Like or dislike program, satisfied, prefer this or
that
Behaviors
•Swimming last year, repeat experience, stay longer
in program?
1. Simple fill in the blank.
Obtaining a straightforward number or other easily understood
response.
How old are you?
(years).
In what county is your permanent residence?
( county)
How much money did you spend on this trip?
2. Open ended:
To avoid leading subject,
 to obtain wide range of responses in subject’s own
words,
 or when you don’t know kinds of responses to expect.
What is your primary reason for visiting the park today?
_______________________________________.
3. Partially closed ended.
 List major response categories while leaving room for
others.
Which of the following community recreation facilities do
you most frequently use? (check one).






neighborhood parks/playgrounds
swimming pools
community centers
natural areas
tennis courts
other (please specify)
_________________
4. Checklists:
 Allow subjects to check multiple responses.
 Categories exhaustive & mutually exclusive
Which of the following winter recreation activities have
you participated in during the past month?
(check all that apply)





Cross-country skiing
Downhill skiing
Snowmobiling
Ice Skating
Sledding
5. Likert Scales:
Versatile format for measuring attitudes.
Please check the box that best represents your level of agreement
or disagreement with each of the following statements about
downhill skiing:
Strongly
Agree
Downhill skiing is...
exciting
dangerous
expensive



Agree



Strongly
Neutral Disagree Disagree









Can replace “agree” with “importance” “satisfaction”,
“interest” “preference” and other descriptors to fit the attitude
you wish to measure.
6. Rank Ordering:
 To measure preferences or priorities. Limit to short
lists.
 Rank the following states in terms of your interest as
possible travel destinations for a summer vacation trip.
(Place a 1 beside the city you would most like to visit,
place a 2 besides your second choice, and a 3 beside
your third choice.)
______
______
______
Taief
Abha
Jeddah
7. Filter Question.
To screen for eligibility or knowledge prior to asking other questions.
Did you stay overnight on your most recent trip?
 NO
 YES
If Yes, How many nights did you spend away
from home?
To next question
Sequencing & layout
1. Will this question influence responses to
others?
2. Is question led up to in a natural way?
3. Placement to create interest, improve
response rate.
4. Branching, skipping, and transitions on
questionnaires.
Question Content
1. Is this question necessary? useful?
2. Are several questions needed on this subject? Avoid double
barreled questions.
3. Do respondents have information to answer the question? Use
filter questions to screen.
4. Does question need to be more concrete, specific and related to
subject's personal experience? Is a time referent provided?
5. Is question sufficiently general? Do you want recent behavior
or "typical behavior"?
6. Do replies express general attitudes or specific ones?
7. Is content loaded or biased
8. Are subjects willing to answer?
9. Can responses be compared with existing information?
1.Observations:
 simple visual observation
 clinical examination,
 x ray,
 biochemical, etc..
2.Interviews & self administered questionnaires:
3.The use of documentary sources:
 clinical records,
 death certificates,
(SECONDARY DATA)
 mortality statistics
 census,
 publications, etc.
1. Accuracy and relevance of information.
2. The need for personnel, skill, equipment, etc. in
relation to what is available, and the urgency with
which results are needed.
3. The probability that the method will provide a good coverage,
ie will supply the information about target subjects.
4.The investigator’s familiarity with a study procedure.
1.Attributes:
 refer to personal or demographic characteristics.
 Some of the most frequently requested attributes
are age, sex, marital status, income, education,
occupation,, etc.
2.Attitudes:
 questions are evaluative and reflect respondent’s
views about the desirability of something done in
the past,
 what they are currently doing, or
 what they plan to do in the future.
3.Beliefs:
are assessments of what a person thinks is true or
false.
 These questions are designed to elicit people’s
perceptions of past, present, or future reality.
4.Behavior:
 questions elicit people’s beliefs about their
behavior, and may be concerned with what they
have.

1.Enables researcher to maintain uniformity in
information collected during health surveys .
2.Ensures completeness of health records from each
respondent .
3.Guarantees proper homework on the type of
information required for a meaningful research.
4.Tests “K” of the investigator about the research.
5.Allows the investigator to prepare “dummy” tables for
collected data.
1. The number of questions should be determined in
relevance to the proposed objectives.
2. Avoid irrelevant questions.
3. The questions must be simple, short, contain one
idea.
4. Avoid sensitive questions or leave them to the
end.
5. Avoid leading questions.
6. Arrange questions in an orderly manner .
7. Questions relating to the same issue must be
in close proximity.
put
8. Avoid technical terms.
9. Use local language of comm.
The questionnaire contains 2 main parts:
 The first part :

contains information for identifying the
respondent’s house no., address, record no.,etc
 The

second part :
contains the relevant questions to the study
objectives which may be subdivided such that
questions in any section deal with specific themes.
1.CLOSE-ENDED with ordered choices: Answers

Choices are provided for these questions.

The respondent’s task is to find the most
appropriate place on an implied continuum for
his/her response.
e.g. Subject may be asked to indicate the degree of
agreement with choices
1.STRONGLY AGREE 2.AGREE 3.UNDECIDED
4. DISAGREE 5.Strongly Disagree
2.CLOSE-ENDED with unordered response choices :

Answer choices are provided

Respondents must choose from among discrete,
unordered categories by independently
evaluating each choice and selecting the one that
best reflects his/her situation.
e.g. Marital Status: 1. Single 2. Married
3. Widowed 4. Divorced
3. PARTIALLY CLOSE-ENDED:

These questions provide a compromise.

Although answer choices are provided,
respondents have the option of creating their
own responses. e.g. provide the option
“ OTHER (SPECIFY)”.
4.OPEN-ENDED QUESTIONS:

These questions have no answer choices from
which respondents select their response.

Respondents must “create” their own answers and
state them in their own words.
e.g. Why did you stop smoking?
1.
2.
Must have face validity.
Respondents can be expected to know the
answers.
3.
Must be clear and unambiguous.
4.
Must not be offensive.
5.
Must be fair.

Close-ended questions:
- Provide greater interrater reliability.
- May be scored quickly.
- Provide greater uniformity and simplify the analysis.
“ HOWEVER”
-They may be open to interpretive error due to guessing & they limit
the variety and detail of responses.

Open-ended questions:
- May be constructed more quickly.
- Provide fewer stimulus cues for guessing.
- Play an imp. role in exploratory surveys.
- Provide interesting information which may be
used to brighten up a dull report.
“HOWEVER”
-They may produce difficulty in interpreting and
categorizing responses.
- They may be more difficult to score accurately.

Closed ended or Open ended questions?
Which one to use?
It is sometimes advisable to use an openended question first, in a pretest, in order to
collect free responses which can be used as a
basis for constructing “closed” categories.




Describe the population
◦ Demographics, knowledge, attitudes, behavior
Test for differences between subgroups
◦ Are men different than women in sports participation?
(gender related to partic.)
Test for relationships between variables
◦ Does boat ownership vary with income?
Evaluate a program (specify criteria as part of objective)
◦ How satisfied are customers? What do they like or
dislike about program?
◦ Estimate benefits (costs, impacts) of a program