Ch. 2 - Quantitative, Qualitative And Mixed Research Flashcards
3 Research Methodology Paradigms
- Qualitative - popular during 1980’s as an alternative to quantitative
- Quantitative - relies primarily on quantitative data, based on variables, dominant during most of the 20th century
- Mixed - uses the best of both quantitative and qualitative approaches, has become increasingly popular during 21st century
Variables
Definition - A condition or characteristic that can take on different values or categories
Types:
- Independent Variable - Treatment variable presumed to cause changes to occur in another variable; a causal variable (time spent studying)
- Dependent Variable - Effect or Outcome variable that is changed because of another variable (test grades)
- Mediating Variable - Intervening variable that comes between other variables (long term memory)
- Moderator Variable - Can be adjusted to be intensified or reduced (Ritalin)
- Extraneous Variable - Confounding variables that confuse results, may compete with IV in explaining an outcome, part of the studies limitations (life event, distraction)
Constant
A single value or category of variable that is not going to change (eg, male or female gender)
Types of Measurement Variables
- Quantitative Variables - Vary in degree or amount (eg, income)
- Categorical Variables - Vary by type or kind (eg, gender)
Roles Taken By Variables
- Independent Variables “IV” - Presumed cause of outcome
- Dependent Variables “DV” - Presumed outcome or effect
- Mediator / Intervening Variables - Occur between two other variables in a causal chain. Eg, therapy (A) causes coping mechanism (B) causes reduced depression (C)
- Moderator Variables - Show how some relationships change across the levels of additional variables. Eg, Behavioral therapy works better for males and CBT for females (gender is a moderator)
- Extraneous Variables - Must be ruled out or controlled for to make a cause and effect claim
Example of an Experiment
Pretest Treatment Post test
O1 XE O2
O1 XC O2
Where:
E stands for experiment group (eg, teaching approach)
C stands for control group (eg, old teaching approach)
O stands for measurement of dependent variable
The best way to make the two groups similar at the beginning is to randomly assign participants to groups.
Paradigm
A perspective based on a set of assumptions, concepts, and values that are held and practiced by a community of researchers.
Logic of Experiment
- Form similar groups at start (random assignment if possible)
- Pretest participants on Dependent Variable
- Manipulate Independent Variable
- Post test participants on a Dependent Variable
Eg, give pill to experiment group and placebo to control group, see who improves
Types of Quantitative Research
- Experimental
2. Nonexperimental
Experimental Quantitative Research
Purpose - To determine and demonstrate cause and effect relationship.
Defining Characteristic - Active manipulation of an Independent Variable and random assignment to groups.
Strongest experimental designs have random assignment, producing equivalent groups.
Nonexperimental Quantitative Research
Purpose - To identify relationships in variables
Defining Characteristic - No manipulation of IV and no random assignment to groups.
Not as good for studying cause and effect, cannot conclude causation from relationship between one IV and one DV.
Sometimes categorized as causal-comparative (IV is categorical and DV is quantitative) or correlational (IV and DV quantitative)
Causal Comparative Nonexperimental Research
IV is categorical and DV is quantitative Eg, gender (IV) and class performance (DV)
Look for relationship by comparing male and female participants average performance levels
Correlational Nonexperimental Research
IV is quantitative and DV is quantitative Eg, self esteem (IV) and class performance (DV)
Look at relationship by calculating the correlation coefficient
Correlation Coefficient
A numerical index that indicates the strength and direction of the relationship between two variables.
- Varies between -1 and +1
- 0 stands for no relationship
- Two characteristics - strength and direction
- Strength - farther from 0 stronger relationship (+1 and -1 strongest)
- Direction:
- if positive sign then positive correlation (two variables move in the same direction, eg, GPA and SAT)
- if negative sign then negative correlation (eg, cholesterol consumption and life expectancy)
How to get strongest evidence of causality?
Experimental Research - Better shows cause and effect compared to Nonexperimental research
