Vous êtes sur la page 1sur 5

CHAPTER 3

Alternatives to Experimentation: Non-Experimental Design

Internal validity
 If changes in variable A (independent) causes changes in variable B (dependent)

External validity
 Generability (if it’s applicable to real world settings)

Describing Research Activities

1.) Degree of manipulation of antecedent conditions (Should be high in experimental


designs, low in non-experimental designs)
2.) Degree of imposition of units
 Extent of which research limits the responses a subject way contribute to the data

5 Common Non-experimental Approaches


1.) Phenomenology
 Description of an individual’s immediate experiences
 Instead of behaviors and events, personal experiences are the source of data
 William James
o One of the most famous early psychologists
o Resistance of getting up inhibits our movement
o Warm sheets > cold floor
2.) Case Studies
 Descriptive records of a single individual’s experience or behaviors or both, kept by an
outside observer
o Sources, inferences, hypotheses, theories
o Source for developing therapy techniques
o Allow the study of rare phenomena
o Provide exceptions or counter inferences to accepted ideas, theories, or practices
o They have persuasive and motivational value
 An Example of the Role of Traumatic Experiences in the Development of Obsessive-
Compulsive Disorder
 Limitations
o Limited Participants
o Cannot observe an individual all the time
o Neglect to mention important information
 Retrospective Data
o Data collected in the present that are based on recollections of past events
3.) Field Studies
 Used in field or real-life settings
 Researchers combine various types of data gathering

Naturalistic Observation Studies


 Observe data as it occurs naturally (e.g. animal observation studies)

Participant Observation Studies


 Researcher actually becomes part of the group being studied

Systematic Observation
 Pre-arranged strategy for recording observations in which each observations are
recorded using specific guidelines or rules so that the observation are more specific

4.) Archival Studies


 Already existing records are reexamined for a new purpose (e.g. death penalty, martial law)
5.) Qualitative Research
 Relies on words rather than numbers

Paradigm – set of attitudes, values, beliefs, methods, and procedure that are generally
accepted within a particular discipline of a certain point in time

Empirical Phenomenology
Sources of Data
1.) Resources self-reflection on experiences relevant to the phenomena

CHAPTER 4
Alternatives to Experimentation: Surveys and Reviews

Survey Research
- Useful way of obtaining information about people’s opinions, attitudes, etc.
Constructing Surveys
- Map out your objectives
o Statement of the Problem – Qualitative
o Objectives – Quantitative
- Design survey items
o Closed Questions
 Questions that are answerable with a yes or no
 Researchers cannot discover or obtain more data
 Easily quantifiable
 Has a very high degree of imposition of units
o Open-ended Questions
 Questions that are answerable with more than a yes or no, or 1-10 rating
 Difficult to quantify
Measuring Responses
(Scales – to measure a construct using numbers)
- Nominal Scales (descriptive)
- Ordinal Scales (measures rank)
- Interval Scales
- Ratio Scales

1. Magnitude – moreness
2. Equal Interval
3. Absolute Zero

Magnitude Equal Interval Absolute Zero


Qualitative Nominal
Data Ordinal
Quantitative Interval
Data Ratio

Response Styles
- Tendencies to response to questions or test items in specific ways, regardless of context
- Willingness to answer to answer
- Position preferences
- Yea-saying
- Nay-saying
Collecting Survey Data
- Self-administered questionnaires
- Mail surveys (no longer practical)
- Computer and internet surveys (gaining popularity)
- Telephone surveys
- Interviews
- Focus groups (gathering people of same nature or with the same concerns)
Avoid these types of questions when constructing surveys
1.) Double-barreled questions
- Two questions at a time
2.) Loading questions
- Questions that give away the answer
3.) Double-negation
- Do you not believe in non-committal relationships?
- Which is not an example if non-compliant behavior?
4.) Jargon
- Use layman terms
SAMPLING
- Including who the subjects will be and then selecting them

POPULATION
SAMPLE OF SUBJECTS
Representativeness
- The extent to which the sample responses we observe and reflect those who would
obtain if we could sample the entire population
2 GENERAL SAMPLING APPROACHES
- Probability Sampling
o Everyone has an equal chance of being included in the research
o representativeness
- Non-probability Sampling
TYPES OF PROBABILITY SAMPLING
1.) Simple Random Sampling
- Most basic form of probability sampling whereby a portion of the whole population
is selected in an unbiased way
2.) Systematic Random Sampling
- Researcher selects every nth person from the population
3.) Stratified Random Sampling
4.) Cluster Sampling
TYPES OF NON-PROBABILITY SAMPLING
1.) Quota Sampling
2.) Convenience Sampling
3.) Purposive Sampling
4.) Snowball Sampling

CHAPTER 5
Correlational & Quasi-Experimental Designs

“Quasi” – “it seems” / “parang”


Correlation: The degree of relationship between the two traits, behaviors, or events
represented by r
Correlation Design
- Neither manipulated nor controlled by the researcher
- Non-experimental studies
Once the correlation is known, it can be used to make predictions

Higher correlation  more accurate predictions


Product Moment Correlation Coefficient

0.00 No correlation
0.10 Negligible  correlation
0.20 Low  correlation
0.40 Moderate  correlation
0.70 High  correlation
0.90 Very high  correlation
1.00 Perfect correlation