week 1 Flashcards
(60 cards)
1
Q
types of questions
A
Behaviour questions: ask about what people do
Belief questions: ask about what people believe to be true or false about topics
Attitude questions: seek to establish what respondents think is desirable
Knowledge questions: determine what people know about particular topics
Attribute questions: seek information about more objective characteristics
2
Q
narrative research
A
- exploring the life of an individual
- needing to tell stories of individuals experiences
3
Q
phenomenology
A
- understanding the essence of the experience
- needing to describe the essence fo a lived phenomenon
4
Q
grounded theory
A
- developing a theory grounded data from the feild
- grounding a theory of the views of participants
5
Q
ethnography
A
- describing and interpreting a culture sharing group
- describing and interpreting the shared patterns of culture of a group
6
Q
case study
A
- developing an in depth description and analysis of a case
- providing an in depth understanding a case or cases
- explores a real-life, contemporary bounded system (case) or multiple bounded systems (cases) over time (Creswell, 2013)
7
Q
why do a survey
A
- Interested in individuals
- Interested in aggregation of views
- Interested in big groups
- To measure change
- To measure specific traits, attitudes or opinions
- To inform planning and use of resources (e.g. government, private industry, marketing)
- To assess the impact of introducing a new program, service or product
8
Q
types of information you can obtain from a survey
A
- Factual Knowledge
- Cognitive Beliefs or Perceptions
- Affective Feelings or Emotional Responses
- Reports on Behaviours
- Trait or State Orientations or Dispositions
- Networks of Communication
- Demographic Features age gender, socio-economic status, mariagital status
9
Q
different types of survey question formats
A
format: open and closed questions
Survey Questions in Context:
• Identify the questionnaire’s specific purpose(s)
• Clarify the terms used to state the questionnaire’s purpose(s)
• Be sure to have the specific objectives of the questionnaire
• Know the respondents
Questions Context :
• Standardise the response format
• Ask questions in a social, cultural, and economic context
• Keep confidentiality and voluntary participation
• Include a letter of introduction or presentation
10
Q
how to obtain valid information
A
- Ask purposeful questions
- Ask concrete questions
- Use time periods based on importance of the questions
- Use conventional language
- Use complete sentences
- Avoid abbreviations
- Review questions with experts and potential respondents
- Use shorter questions
- Avoid two-edged questions
- Avoid negative questions
- Adopt/adapt questions used successfully in other questionnaires
11
Q
Outline the steps in conducting a survey
A
- Research Design
- Construct Questions & Field Test Items
- Select Sample
- Ask Questions
- Analyse Data eg calculating percentage responses or mean
- Report Results eg tables, graphs
- Interpret & discuss findings eg main trends, summary of findings
12
Q
whats response rate
A
is the percentage of surveys that are returned
13
Q
whats a high vs low response rate
A
- A high response rate indicates there is a less chance of significant response bias than a low response rate.
- A low response rate is a danger signal, because the non respondents are likely to differ from the respondents in ways other than just their willingness to participate in the survey.
14
Q
acceptable response rates
A
- a response rate of 50% is adequate for analysis and reporting
- a response rate of 60% is good
- a response rate of 70% is very good
15
Q
designing survey questions and items you should
A
avoid confusing phrasing
minimise the risk of bias
avoid making either disagreement or agreement disagreeable
minimise fence sitting and floating
16
Q
whats a double barrelled question
A
- So-called double-barreled questions are also guaranteed to produce uninterpretable results because they actually ask two questions but allow only one answer.
17
Q
whats dense sitting and floating
A
- Two related problems in question writing also stem from people’s desire to choose an acceptable answer.
- There is no uniformly correct solution to these problems
- Fence-sitters, people who see themselves as being neutral, may skew the results if you force them to choose between opposites.
18
Q
strengths of survey research
A
- Only Way to Probe Opinion of a Very Large Group
- A Very Flexible Tool: • Medical, Educational, Political, Business, etc.
- Facilitates Hypothesis Testing
- Encourages Standardisation and Systematic Comparison
- Is relatively inexpensive compared to other research
- Facilitates use of both quant and qual methods to obtain fuller picture of phenomenon being investigated
19
Q
weaknesses of survey research
A
- Standardisation comes at a price
- Surveys often do not get at the “why” of an issue or topic
- Respondents might not have an opinion
- Respondents may not actively engage with survey topic
- Respondents may not be truthful
- Challenging to get reasonable response rate
20
Q
data analysis for grounded theory
A
- Open/initial coding
- Code interview transcript – phrase or word summarizing key idea for each sentence.
- Generate a list of codes - Focused coding
- Compare codes within & across interview transcripts,
- Grouping together most common or significant codes that make analytic sense - Axial coding
- Grouping together focused codes to form categories & subcategories - Theoretical coding
- explore relationship between categories to develop coherent story e.g. themes & theory
21
Q
participatory action research
A
emerged from the need for oppressed populations to empower themselves and improve their lives by acting to address the contextual issues (e.g. social, political, economic, environment)
- Aims to gain an understanding of a particular context to develop actions a nd outcomes relevant to the community of interest.
- Involving participants’ as co-researchers can improve understanding of issues and potential solutions from participants perspective
22
Q
rigorous in quantitative vs trustworthiness qualitative
A
Quantitative research = validity and reliability
Qualitative research=trustworthiness
Rigorous research is important because:
- Trustworthiness of a study
- Clinicians & other researchers can rely on study findings
- Rules, procedures or techniques relevant to research design used
23
Q
four criteria of trustworthiness of qual research
A
credibility
transferability
dependabilty
confirmabilty
24
Q
whats credibility
A
determine if we can trust findings, have authors presented findings from the participants (strategy member checking)
25
whats transferability
: evaluates if findings can be applied to other people, groups, contexts. Described participants and setting of study eg type of spinal cord injury, where they still in rehab or in community
26
whats dependability
description of research process. What type of data analysis was used, how did they analyse data, why have they chosen to do one or two data collection, clear decisions around sampling process. Strategy: audit trail
27
whats confirmability
role of research in research process, have they stated values, beliefs, perspectives that caused them to lead the study.
28
strategies of trustworthiness in qual
```
audit trial
triangulation
member checking
peer review/debieging
thick description
reflexivity
prolong engagement
feild notes
```
29
whats audit trial
involves an external person that checks on research descions that have been made. Important to outline decisions made throughout research. Keep a methological log, discus why chosen techniques.
30
whats triangulation
multiple methods of data collect (interviews, observation), multiple data sources (multiple participants in different setting compare), researchers different backgrounds brings different perspectives
31
whats member checking
v: supports confirmability and credibility, checking interpretations of data with participants. Could transcribe interview and send to participants, or write a summary and send to participant
32
what reflexivity
: researcher reflecting on process gone through, interest of starting study, professional background, assumptions or concepts coming into study with. Supports credibility.
33
types of survey research
1. Self-completion questionnaire
2. Interviewer administered survey
3. Telephone interview survey
4. Mail / Postal survey
5. Group administered surveys
6. Web-based survey
34
whats a self completion questionnaire
Are completed in writing by the respondent.
- Most common mode of completion is delivery & return through the mail.
- Can also be completed in the presence of the researcher (who can provide assistance and check questionnaire for completeness).
- Offer low cost relative to other types of surveys (cost of postage & printing).
- Potential coverage of a widely dispersed population (e.g., throughout Melbourne).
- Avoids potential for interviewer bias.
- Has the potential for low response rates.
- Requires a certain literacy level for respondents to complete survey.
- Are well suited for less complex topics.
- Should be shorter than an interview and use more close-ended questions (e.g., true/false, yes/no, agree/disagree).
35
whats interviewer administers survey
- Each respondent is asked the same set of questions by the interviewer.
- Able to collect more detailed and complex data.
- Open ended questions can be used more readily.
- Are costly and resourceintensive.
- Are able to deal with more sensitive or personal topics.
- Are more suitable if you are trying to elicit the respondent’s story or personal narrative about a topic.
- Interviewers need to travel to respondents.
- Interviewers need to be trained to ensure consistency in how questionnaires are administered, scored and interpreted.
- Personal characteristics (such as age, gender, ethnicity) of interviewer can impact on the response rate & nature of the responses.
36
whats telephone interview survey
- Maximise the advantages of the self-report questionnaires and face-toface interviews using this approach.
- Since travel is not required, can cover a large population relatively quickly at a lower cost.
- Researcher can provide clarification on unclear questions if needed
- Response rates while not as high as face-to-face interviews, can be between 90 to 95% although this is dependent on the topic and level of interest of the respondents.
- Considered suitable for complex tasks.
- Can deal with more sensitive topics
37
disadvantages of telephone interview surveys
- Time consuming to complete
- Need access to telephone numbers (e.g. unlisted numbers & cell phone numbers)
- Need trained interviewers
- Have over-abundance of telemarketers
- Issues of sampling bias & generalisability of findings.
- May be not suitable for certain groups such as people with hearing impairment, older people, people with cognitive impairment, lower income who may not have a phone and recent migrants whose first language is not English
38
advantages of mail/postal survey
- Efficient for volume of information
- People are likely to provide frank, thoughtful, honest information that is tension free
- Gives people adequate time to respond to questions
- All respondents receive exactly the same questions in the same way…ensures some degree of consistent
- Allows for larger samples to be recruited
- Cheaper to conduct than interviews
- Respondent does survey on his/her own time
39
disadvantages of mail/postal survey
- Low response rate
- Must be simple and easy to understand
- Need accurate mailing lists with addresses
- Mailing / postage and copying costs
- Privacy, confidentiality, and anonymity must be assured
- Results may be misleading if do not follow-up with non respondents
- Generalisability may be limited if respondents are self selected
- Respondents’ handwritten responses may not be legible
40
advantages of group administered surveys
- High response rate
- Easy to clarify items for all respondents
- Provides greatest sense of respondent anonymity
- Inexpensive
41
disadvantages of group administered survey
- May require cooperation of others (e.g., to access groups)
- Reach only those in attendance
- Group dynamics may influence individual responses
- Opportunity for researcher to potentially influence participants’ responses or answering of items
42
web based survey advantages
- Nearly complete elimination of paper, postage, mail out and data entry costs
- Time for implementation of survey can be reduced
- Once electronic data collection system is developed, cost of surveying additional respondents is much less
- Display of response data can be simultaneous with completion of surveys
- Reminders and follow-ups for non-respondents is relatively easy
- There are currently several good quality online systems for developing, formatting and administering online surveys include Survey Monkey and Qualtrics
43
disadvantages of web based survey
- Not everyone is connected to the web
- Surveys may not be conducive to be completed on certain mobile devices
- Not all respondents are equally computer literate
- Sampling of email addresses can be difficult
- The decision not to respond is likely to be made more quickly
44
sampling methods
```
random smapling
convince smapling
snowball sampling
quota sampling
proportional sampling
```
45
whats random sampling
is the method of choice a precise selection method where all individuals in a defined population have an equal chance of being selected for inclusion in the study
46
whats convenience sampling
is based on these participants who are available when data gathering is scheduled to occur.
- This method of sampling is open to bias & subjectivity.
- Another method is volunteer sampling where individuals volunteer to take part and are therefore self-selected
47
whats snowball sampling
one member of the sample is asked to suggest other people who could be involved in the study.
48
whats quota sampling
different groups need to be represented in proportion to their size within the overall populations.
49
sample size
- Too small a sample is unlikely to give an accurate description of the issue being explored; results can be biased.
- As a rule, aim for as large a sample as time, availability of participants and funding permits.
50
different research designs quant
Types of research designs:
1. Experimental & Quasi-experimental
2. Single subject studies
3. Field studies & naturalistic observations
4. SURVEY STUDIES (focus of OCC3041)
5. Psychometric studies
51
experimental research
- Basic characteristic is that the investigator manipulates an independent variable that is expected to produce an effect on the dependent variable
- Design is meant to provide evidence that the independent variable is the cause of the changes or differences in the dependent variable
- Main aim is to control as much as possible the extraneous influences that might lead to an incorrect conclusion about the influence of the independent variable on the dependent variable.
52
quasi experimental
- Lacks the same degree of rigour found in true experiments (e.g., single group or whereby participants act as their own control group) or convience sampling
- Less costly, most common research design conducted by OT’s
53
single subject studies
- Examine the impact of interventions on single subjects who serve as their own controls.
- Often involves gathering baseline data and then gathering data during alternating periods in which the experimental condition is present or withdrawn (e.g., ABABA design).
- EXAMPLE: sensory processing presented with children with autism. Child assessed pre-test thorough out treatment and post-test. Childs performance is compared to their previous results.
54
field studies and naturalistic observations
- Takes place in actual, real-life settings.
- Researchers study events as they happen and persons in their natural environments.
- Largely used in qualitative research contexts
55
survey studies
- Are non-experimental designs undertaken to investigate the characteristics of a defined group or population.
- Often conducted with large samples. More than 100
- Will use mailed surveys, webbased questionnaires, face-toface interviews, phone interviews or group administered survey
56
research purposes types
1. basic: - Includes investigations undertaken for the purposes of generating evidence about some phenomena or testing theory about some phenomena.
2. applied: - Involves studies that seek to solve some practical problem or to generate information specifically to inform practice
3. transformative: - Studies designed to bring about change in some practical situation or specific context.
57
purpose of research
- Description.
- Analysis of relationships.
- Analysis of differences.
- Analysis of association / correlation.
- Predictiveness of variables.
58
timing of research
Retrospective: the researcher uses data collected before the research question was formulated.
Prospective: the researcher completes data collection after the research question was developed.
59
levels of manipulation
Experimental research: involves controlled manipulation of participants. • Non-experimental: does not involve the manipulation of participants
60
types of controls applied to variables
- Control of implementation of independent variable.
- Control of participant selection & assignment.
- Control of extraneous variables related to setting.
- Control of extraneous variables related to the participants.
- Control of measurement of the dependent variable.
- Control of information given to participants and research.
