Class 4 Flashcards

1
Q

Quantitative Design

  • what process
  • involves
  • vehicle for
  • what kind of analysis
A

Systematic scientific process of testing relationships, differences, and cause-and-effect interactions among and between variables

Involves a plan, a structure, and a strategy

Vehicle for hypothesis testing or answering research questions

Statistical analysis of numerical data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Variables in Quantitative Design

-Name the 3 variables and describe them

A

Dependent variable
-Outcome variable, observed but not manipulated

Independent variable
-Presumed effect variable manipulated in experimental studies

Extraneous variables
-Variables that may interfere with the results being studied
(age, gender, natural occurring event, researcher in the room)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Importance of Control 4

A

Hold conditions of the study constant

Avoid bias

Specific sampling and data collection criteria

E.g., Controlling extraneous variables

  • Homogeneous samples
  • Consistent data-collection procedures
  • Manipulation of IV
  • Randomization
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Types of Validity 2 and describe them

A

Internal Validity
-Researcher controls all extraneous variables and the only variable influencing the results of a study is the one being manipulated by the researcher

External Validity

  • The extent to which the results of a study can be generalized or extended to other populations or environmental conditions
  • How well did they control these things, how well can they apply it to others
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

6 Threats to Internal Validity and describe them

A

History
-Another specific event may affect the DV (dependent variable/outcome) [anything can happen]

Maturation
-Potential changes in an individual as a function of time (Threat to studies over a time)

Testing
-Repeated testing may influence participants’ responses (pre test / post test)

Instrumentation
Changes in how variables are measured or observed (biggest threat) [are you using the same tool, validity/reliability]

Mortality
loss or attrition of participants

Selection bias
The way in which participants are chosen and grouped. Do pretreatment differences exist?

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

3 Threats to External Validity

A

Selection Effects
Concerns about generalizability, when an ideal sample cannot be attained

Reactive Effects
Hawthorne effect; changes in participants’ behaviour as a response to being studied

Measurement Effects
Use of a pre-test allows participants to examine their attitudes and responses for follow-up testing

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Types of Quantitative Designs 3 and describe them

A

Experimental Designs
-manipulation of independent variables, randomization, control of extraneous variables, cause and effect

Quasi-Experimental Designs -manipulation, naturally occurring comparison groups, statistical control of extraneous variables

Non-Experimental Designs -Naturally occurring variation in independent variables, statistical grouping, statistical control of extraneous variables
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Experimental Design

cause and effect requires what three things (causation)

A

Causal variable and effect variable must be associated with each other

Cause must precede the effect

Relationship must not be explainable by another variable

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Randomized Clinical Trials (RCT) 4

drug studies!

A

Pre-test Post-test Control Group Design

Considered “gold standard” regarding cause-and-effect relationships

Minimal bias is introduced

Same results over and over?

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Quasi-Experimental Design

Main difference?

Pros 3

A

Main difference: They usually lack the element of randomization and/or may lack a control group
-natural groups, everybody is in experimental/ treatment group

  • Practical, feasible and the results are generalizable
  • More adaptable to real world settings than controlled experimental designs
  • May be the only way to evaluate the effect of the independent variable on the variable of interest
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Non-experimental Design 6

5 types

A
  • To examine events, people, situations as they naturally occur
  • Test relationships and differences among variables of interest
  • Requires clear, concise research problem or hypotheses based on theory
  • Elements of control are not possible
  • looking for natural change
  • no provided intervention

Survey research
-Descriptive, Exploratory, Comparative

Relationship/Difference Studies

  • Correlational
  • Developmental
    • Cross-Sectional
    • Longitudinal or Prospective
    • Retrospective or Ex Post Facto

psychometric Research

Secondary Analysis

Epidemiological Studies

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Survey research 5

2 advantages
4 disadvantages

A

Detailed descriptions of existing variables collected through a questionnaire or interview

Small or large samples of participants recruited from defined populations

Data used to justify and assess current conditions and practices or to improve health care practices

Descriptive, exploratory or comparative (terms used alone, interchangeably, or together to describe design)

Relationships and differences, NOT causation since u cant control all the elements so you cant says cause and effect

  • A great amount of information can be obtained from a large population in a more economical manner with very accurate information
  • if a sample is representative of population a relatively small number of participants can accurately represent the views of the population
  • Information may be superficial
  • Breadth rather than depth is emphasized
  • Great deal of research expertise is required
  • Large scale studies can be expensive and time consuming
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Relationship/Difference Studies:
Correlational Studies: what is it
advantages:
disadvantages

2 Correlational Studies may be:

A

Correlational Studies:
The investigator examines a relationship between two or more variables (correlation)

Advantages: Flexibility, Large amount of data about the relationship, Potential for clinical application, Foundation for future studies, Explore relationship between variables that cannot be manipulated

Disadvantages Correlational:
Inability to manipulate variables of interest
No randomization in the sampling procedures (deals with pre-existing groups)
Researcher cannot determine a casual relationship between the variables

  • Descriptive correlational where the goal is to describe the relationship between variables
  • Predictive correlational where several variables are examined to see which are related and if the presence or absence of particular variables predicts a certain outcome
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Relationship/Difference Studies
Developmental Studies:
Cross-Sectional 3

A
  • Cross-sectional studies examine data at one point in time, from a number of subjects
  • Cohort studies can be cross-sectional if data is gathered from different cohort groups at about the same time
  • Cross-sectional studies can explore relationships and correlations, differences and comparisons or both
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q
Relationship/Difference Studies
Developmental Studies: 
	Longitudinal2
3 advantages
3 disadvantages
A
  • AKA prospective or repeated-measures study
  • Collect data from the same sample at different points in time

Advantages:

  • Each participant acts as his/her own control
  • Increased depth of responses
  • Early trends can be analyzed

Disadvantages:
-Data collection may take a long time, increasing costs in time, effort, and money

Testing effects may be a threat

mortality is a significant threat owing to the increased potential for attrition

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q
Relationship/Difference Studies 4
Developmental Studies: 
Retrospective
advantages 2
disadvantage 3

used when looking at harmful things because you cant make people do harmful things

A
  • AKA ex post facto “from after the fact”
  • Researcher attempts to link current events to past events
  • DV has already been affected by the IV
  • E.g., Hypothesis variable X (cigarette smoking) is related to and a determinant of variable Y (lung cancer)

Advantages:

  • Similar to the advantages of the correlational design
  • Offers a higher level of control

Disadvantages:

  • Unable to draw a causal link between two variables
  • Alternate hypothesis may be the reason for the documented relationship
  • Difficulty finding similar group members
17
Q

Psychometric research 3

Involves 4 things in this exact order

A
  • Development and evaluation of data collection instruments, scales and techniques
  • Psychometric concerned with measurement of a concept with reliable and valid tools
  • Researcher interested in identifying intangible concepts (constructs) and making them tangible by developing an accurate measurement tool

Involves the following in the order of:

  1. Defining the construct or concept to be measured
  2. Formulating the tool’s items
  3. Developing instructions for users and respondents
  4. Testing tool’s reliability and validity
18
Q

Secondary Analysis3

A

Previously collected data from one study are reanalyzed for a secondary purpose

May involve a subset of a specific group of people or geographical setting

Exploring specific variables in greater detail through statistical analyses

19
Q

Epidemiological Studies 3

What are the two types conducted

A

Examine factors affecting the health and illness of populations

Often in relation to the environment

Distribution, determinants, and dynamics of health and disease

Prevalence- number of people affected
reduced by cured, die
-meds that prevent death increase prevalence (not necessarily bad)
-Prev is Incidence multiplied by duration of disease

Incidence- number of cases occurring in a particular period of time