PSYCH 1X03 Study Guide - Final Guide: Charles Bazerman, Observational Learning, Robert Zajonc

2 views31 pages
user avatar
Published on 14 Aug 2020
School
McMaster University
Department
Psychology
Course
PSYCH 1X03
Professor
Module 1: research methods
The Scientific Method: Formal way of asking and answering questions
1. Construct a theory
- Collect a general set of ideas about the way the world works
- Guides the creation of a set of testable statements called a hypothesis
2. Generate hypothesis
- Form a testable statement guided by theories that make specific predictions
about the relationship between variables
3. Choose research methods
- Determine the way in which the hypothesis will be tested
4. Collect data
- Take measurements of the outcomes of the test
5. Analyze data
- Understand the data and discover trends or relationships between the variables
- Leads to decision to accept or reject the hypothesis
6. Report the findings
- Publish articles in scholarly journals
7. Revise existing theories
- Incorporate new information into our understanding of the world
Paradigm shift: dramatic change in our way of thinking
Conducting an Experiment:
Anecdotal Evidence: Evidence gathered from others or self experience
- Single experience might not be representative
- Personal experience might not represent others
- Cannot be sure that the result is due to factor alone
Experiment: Scientific tool used to measure the effect of one variable on another
Independent Variable: Variable manipulated by the scientist
Dependent Variable: Variable being observed by the scientists
DEPENDENT IS DEPENDENT ON INDEPENDENT
Control Groups: the group that does not receive manipulation, differences between the control
and experimental group should be minimal, except for variable being tested
Within-Subjects Design: Manipulating the independent variable within each participant to
minimize the effect of the external variables on the dependent measure
- Time consuming and costly
- Practice effect: Improved performance over the course of an experiment due to
becoming more experienced
Between Subjects Design: one group receives manipulation, other group acts as the control
group, should be as similar as possible except for manipulated variable
- Confounding variable: A variable other than the independent variable that has an effect
on the results
- Strict selection criteria of populations may hinder generalizability (results from specific
groups cannot be generalized to other groups)
Sampling:
Unlock document

This preview shows pages 1-3 of the document.
Unlock all 31 pages and 3 million more documents.

Already have an account? Log in
- The general group of people you're trying to learn about is called the population
- Selected group of individuals the data is collected from is called the sample (must
accurately reflect the population so the results can be generalized)
Random Sample: Choosing a sample at random from the entire population to reduce bias
Random Assignment: Assigning subject to either the experimental or control group at random
to avoid any biases that may cause differences between the groups of subjects
Conducting an Experiment:
Placebo Effect: Effect that occurs when an individual exhibits a response to a treatment that
has no related therapeutic effect
- Must always be considered when participants might know in advance the expected
result of the experimental manipulation
Participant Bias: When a participant's actions in an experiment influence the results outside of
the manipulations of the experimenter
- Blinding subjects eliminates the placebo effect (ie. giving control group a mock
treatment)
Blinding: When participants do not know whether they belong to the experimental or control
group, or which treatment they are receiving
Experimenter Bias: Actions made by the experimenter, intentionally or not, to promote the
result they hope to achieve
- Experimenters promote the result they hope to achieve
Double-Blind Studies: Experiments in which neither the experimenter nor the participants
know which group each participant belongs to
- Helps to avoid experimenter bias
Descriptive Statistics: present information about the data “at-a-glance” to give an overall idea
of the results of experiment
Frequency Distribution: Type of graph illustrating the distribution of how frequently values
appear in the data set
Normal Distribution: A distribution with a characteristic smooth, symmetrical, bell-shaped
curve containing a single peak
Central Tendency:
- Mean: Average value of a data set
- Mode: Value that appears most frequently in the set
- Median: The centre value in a data set when the set is arranged numerically
- Outliers: Extreme points, distant from others in a data set
Measures of Variability: tell us how spread out our data is
Standard Deviation: Average distance of each data point from the mean
Unlock document

This preview shows pages 1-3 of the document.
Unlock all 31 pages and 3 million more documents.

Already have an account? Log in
- Smaller spread = smaller st. deviation
- Larger spread = large st. deviation
Inferential Statistics: Statistics that allow us to use results from samples to make inferences
about overall, underlying populations
- Scores without any manipulation follow a symmetrical distribution
T-Test: A statistical test that considers each data point from both groups to calculate the
probability that two samples were drawn from the same population (reveals how likely a
difference is due to chance = p-value)
P-Value: A value expressing the probability calculated by the T-Test
- The p value quantifies the probability of getting a difference between experimental and
control groups by chance
- represents the likelihood the results obtained were by chance and are not due to any
differences in the groups caused by the manipulation.
- p > 0.05 (5%) = not significant, greater than 5% chance of obtaining data by chance
- p < 0.05 = significant, less than 5% probability of obtaining data by chance
Statistical Significance: When the difference between two groups is due to some true
difference between the properties of the two groups and not simply due to random variation
- SIGNIFICANCE DOES NOT = MEANINGFUL
Observational Research: avoid unethical experimental manipulations
- Used to observe the effect of variable without performing explicit manipulation
Correlation: A measure of the strength of the relationship between 2 variables
- Correlation does not equal causation
- Scale from -1 (perfect negative correlation) to +1 (perfect positive correlation)
- 0 means no correlation
Key Terms:
Case Study: An in-depth investigation of an individual person of a small group of people, often
over an extended period of time
Construct Validity: The extent to which there is evidence that a test measures a particular
hypothetical construct
Empiricism: The philosophical perspective that states that knowledge should be gained by
direct observation of the word as it is, as opposed to rational perspectives that used logic and
reason to determine how the world ought to be
Null Hypothesis: The hypothesis where there is no significant difference between specified
populations
Paradigm: A set of assumptions and ideas about what kind of research questions can be asked
and how they can be answered
Operational Definition: This describes the actions or operations that will be made to
objectively measure or control a variable
Social Desirability Bias: A tendency to give socially approved answers to questions about
oneself
Replication: The replication of a study to see whether the earlier results can be duplicated,
often times by independent researchers
Unlock document

This preview shows pages 1-3 of the document.
Unlock all 31 pages and 3 million more documents.

Already have an account? Log in