PSY 105 Lecture Notes - Lecture 4: Naturalistic Observation, Dependent And Independent Variables, Descriptive Statistics
Week 3
What is a science?
- Two core tenets of science:
- The universe operates according to certain natural laws
- Such laws are discoverable and testable
How do we avoid biases and heuristics
- Test specific hypothesis derived from broader theories
- Theories are never “proven”, but hypotheses can be confirmed or disconfirmed
Research design matters
- Helps eliminate biases
- We want to avoid subjective impressions at all costs
Two basic types of research methods
- Descriptive
- Research method used to observe and describe behaviour
- Used to determine the existence of a relationship between the variables
- Experimental
- To demonstrate a cause and effect relationships between the variables
The scientific toolbox
- Experimental designs
- Naturalistic observation
- Case study
- Self report measures and surveys
- Correlational designs
Scientific theory
- An explanation for a large number of findings in the natural world
- A testable prediction is called a hypothesis
- We like to be able to show evidence that some variable (x, independent variable) causes
people to behave a certain way (y, dependant variable) while other variables (z, control)
that might affect behavior are held constant.
- To show that “X causes Y” we have to measure the behaviour (Y) twice
- Once when X is present
- Once when X is not there
- While controlling for other relevant causes (Zs)
Variables and operational definitions
- types of variables
- Independent variable (IV) - the variable that you manipulate
- Dependent variable (DV) - the variable that you measure (or the variable that is
changed by the IV)
Averaging
- To control for RANDOM ERROR we use averaging
- Measure repeatedly and take the average
find more resources at oneclass.com
find more resources at oneclass.com
- It gives a better estimate of behaviour
Week 3B (statistics and testing)
Mid term
- Scientific methods
- Critical thinking
- A little bit more emphasis
- Neuroscience
- Multiple choice is still the entire chapter, but written will only be on what is
covered in the lecture
- 45-50 multiple choice
- 3 sets of questions
- Written questions from lecture
- Multiple choice more likely on textbook
- No history of psychology
Descriptive research method:
- Research method used to observe and describe behaviour
- Used to determine the existence of a relationship between variables
- Has a more real life effect
Scientific methods:
- Naturalistic observations
- Watching behaviour in a real-world settings
- Extremely high external validity
- Findings are generalizable in the real world
- Low internal validity
- Doesn’t allow us to infer causations
- Case study
- One or small number of people for an extended period
- Breadth traded for depth
- Less people, but more in depth
- Used to study rare brain damage or mental illness
- Excellent for existence proofs, but can be misleading or anecdotal
- Self-Report measures and surveys
- Self-report measures assess characteristics such as personality or mental illness
- Surveys ask for opinions or abilities
- In order for these measures to be accurate certain protocol must be met:
- Random selection
- Essential in order to generalize findings from survey and
questionnaires
- Ensures every person in a population has a chance to
participate
- Non-random selection can skew results
- Validity
find more resources at oneclass.com
find more resources at oneclass.com
Document Summary
The universe operates according to certain natural laws. Test specific hypothesis derived from broader theories. Theories are never proven , but hypotheses can be confirmed or disconfirmed. We want to avoid subjective impressions at all costs. Used to determine the existence of a relationship between the variables. To demonstrate a cause and effect relationships between the variables. An explanation for a large number of findings in the natural world. A testable prediction is called a hypothesis. We like to be able to show evidence that some variable (x, independent variable) causes people to behave a certain way (y, dependant variable) while other variables (z, control) that might affect behavior are held constant. To show that x causes y we have to measure the behaviour (y) twice. While controlling for other relevant causes (zs) Independent variable (iv) - the variable that you manipulate. Dependent variable (dv) - the variable that you measure (or the variable that is changed by the iv)