SOWK 6003 Social Work Research Week 4 Research process, variables, hypothesis, and research designs

1
SOWK 6003 Social Work ResearchWeek 4Research
process, variables, hypothesis, and research
designs

• By Dr. Paul Wong

2
Research Process?

1. Problem formulation
2. Designing the study
3. Data collection
4. Data processing
5. Data analysis
6. Interpreting the findings
7. Writing the report

3
Purposes of Research

1. Exploration
2. Description
3. Explanation
4. Evaluation
5. Multiple purposes

4
This week we will focus on the first 2 steps in a
research process

• Formulating a problem and Designing a study

5
Operationalization of Concepts

• Concept as a mental image that symbolizes an
  idea, an object, an event, a behavior, a person
  and so onword that people agree upon to
  symbolize something.
• Attributes are concepts that can be grouped
  together to form a broader concept.
• Variable is
• - something of interest to us that can take on
  different values
• an element in a research project that, when
  measured, can take on more than one value
• A variable is a characteristic that has two or
  more values.

6
Relationships between Variables

• Correlations
• Correlational relationship simply says that two
  things perform in a synchronized manner.

7
(No Transcript)
8
(No Transcript)
9
Think about this relationship!

• Weather and fashion, how are they relate to each
  other?

10
Types of Variables

• Independent Variables (IVs) vs. Dependent
  Variables (DVs)
• IV is a variable that explains or causes
  something, and is not depending on the other
  variables. It is what the researcher (or nature)
  manipulates.
• DV is the variable which is the effect, being
  explained or caused.

11
Extraneous Variables vs Mediating Variables

• Extraneous variables represent alternative
  explanations for the relationships that are
  observed between the independent variable and
  dependent variables

12

• Mediating Variable is the mechanism by which an
  independent variable affects a dependent
  variable. Sometimes it is also referred as
  intervening variables.

13

• How do Extraneous Variables come in to the
  picture between weather and fashion?

14
Continuous, Discrete, and Dichotomous Variables

• Continuous variable has an infinite number of
  different values between the highest and lowest
  score. E.g., ?
• Discrete variable has a limited and countable
  number of distinct steps between the highest and
  lowest score. E.g.,?
• Dichotomous variable has only two levels. E.g.,?

15
What is research design?

• http//www.csulb.edu/msaintg/ppa696/696preex.htm

16
When we talk about study design, we need to
consider the following aspects

1. Nature
2. Setting
3. Time
4. Participants

17
Nature

• Experimental Design - investigation that
  involves manipulation and control of an
  independent or treatment variable with the intent
  of assessing whether the independent variables
  causes a change in the level of a dependent
  variable. Note Randomization random assignment
  to the control and experimental group, which is
  not equal to random sampling. It is about the
  reduction of systematic error such as selection
  bias.
• Quasi-Experimental Design - research study set up
  to resemble a true experiment but that does not
  involve random assignment of the participants to
  a group or manipulation and control of a true
  independent variable, instead relying on
  measuring groups based on pre-existing
  characteristics. (Beins, 2009)
• Pre-Experimental Design - the features of
  experimental design and quasi-experimental design
  are not present.

18
Setting

• Applied Research take place in a natural
  environment where people are acting as they
  normally do. It usually attempts to address
  practical questions rather than theoretical
  questions
• Basic Research is more likely to occur in a
  laboratory or other controlled setting. It tests
  or expands on theory, with no direct application
  intended. (Beins, 2009)

19
Time

• One time Cross-sectional/One shot/Posttest only
• Two time pretest posttest design
• More than two times Longitudinal
• Many many times Time Series

20
Participant/Subject

• One person Case study
• One group A cohort
• More than one person
• More than one group Comparison study

21
Treatment/intervention
22
(No Transcript)
23
(No Transcript)
24
(No Transcript)
25
(No Transcript)
26
(No Transcript)
27
(No Transcript)
28
(No Transcript)
29
(No Transcript)
30
(No Transcript)
31
Data Source

• Qualitative
• Observations
• Journal/Diary/Self report
• Indepth Interview
• Focus Group
• Art work
• Archives
• Documents
• Quantitative
• Measurements through self-administered
  questionnaires (by hand, by mail, or online)
• Interview survey (telephone, home visit)
• Health indicators (BP, skin temperature, saliva
  cortisol etc.)

32
Research rigor (means good standard)

• Ethical Rigor - concerns about ethical
  consideration
• Methodology Rigor
• 1. The matching of research questions with the
  research methods
• 2. The appropriateness and reliability of the
  data collection method
• 3. The representativeness of the samples
• 4. The generalizability of the data

33
Rigor of Data Collection Method (we will talk
more about them next week)

• Reliability
• consistency of measurement over-time (test-retest
  reliability)
• consistency of measurement by different rater
  (interrater reliability)
• consistency of measurement on different subgroup
  (split-half reliability)
• consistency of measurement on items of the
  measurement tools (internal consistency
  reliability. Cronbachs alpha)
• Validity
• - refers to the extent to which an empirical
  measure adequately reflects the real meaning of
  the concept under consideration.
• Face validity
• Content validity
• Criterion-related validity
• Construct validity convergent and discriminant
  validity
• Factorial validity

34
In class activity 1

• Discussions on last weeks homework

35
In class activity 2

• How to write a research proposal?