Class Notes (834,735)
Psychology (2,710)
PSYC 2001 (163)
Lecture

# 11 Factorial research designs.docx Premium

14 Pages
63 Views

School
Department
Psychology
Course
PSYC 2001
Professor
Guy Lacroix
Semester
Fall

Description
Factorial research designs Factorial research design - An experimental research design that involves two or more independent variables (factors) - With more than 4, it becomes harder to interpret the data. Ideally, but 3 is best. - Want IQ to be independent variable - Assign high and low IQ to either 2 or 4 hour study. See its effect on dependent variable Analyses of Variance (ANOVA) - ANOVAs are a set of statistical methods used mainly to compare the means of two or more samples. - Estimates of variance are the key intermediate statistics calculated. - The different types of ANOVAreflect the different experimental designs and situations for which they have been developed. - Look for the biggest difference between any of the 2 by 2 **** Designs ***** - Number of independent variables (1, 2, or 3): n-WayANOVA - Type of independent variable (between-subjects, within-subjects → Mixed designs) - Inclusion of a Covariate (yes or no) - Examples: • 1-Way between-subjects ANOVA • 2-Way within-subjects ANCOVA • 3-Way mixed-DesignANOVA - 2 or more can do it all between (everyone does things only once), do within (everyone does everything), or mixed - IQ is between - Study time is within Possible outcomes KNOW FOR EXAM - When you runANOVAs, main effect and interaction can occur - Main effect: An outcome that is a consistent difference between levels of a factor. • Involves only 1 independent variable - Interaction: An outcome that exists when differences on one factor depend on the level you are on another factor. • Difference between levels of independent variables. Look at both independent variables simultaneously • Low IQ 2hr and 4hr all low. High IQ 2hr low, but 4hr high. Only about IQ? No. Must think about IQ and study time together (interaction). Six possible patterns of results PSYC 2001 – Introduction to Research Methods 4 - IQ and study hours - All have different interpretation. Some have main effect, some have interaction, some have both No effects Significance Factors Study time No IQ No Study time X IQ No IQ Low High 24.5 24.5 Study time 2 hours 4 hours 24.5 24.5 PSYC 2001 – Introduction to Research Methods 5 - Nothing happened. Something is wrong. No interaction or main effect One main effect Factors Significance Study time No IQ Yes Study time X IQ No IQ Low High 25 40 Study time 2 hours 4 hours 32.5 32.5 PSYC 2001 – Introduction to Research Methods 6 - There is 1 main effect on IQ - No interaction - Smart people are doing better than not so smart people One main effect Factors Significance Study time Yes IQ No Study time X IQ No IQ Low High 32.5 32.5 Study time 2 hours 4 hours 25 40 PSYC 2001 – Introduction to Research Methods 1 - Is a main effect on study time - No main effect on IQ - INTERACTION??? Two main effects, no interaction Significance Factors Study time Yes IQ Yes Study time X IQ No IQ Low High 24.5 38.5 Study time 2 hours 4 hours 24.5 38.5 PSYC 2001 – Introduction to Research Methods 2 - 2 main effects (one on IQ and 1 on study time) - Higher IQ doing better than lower IQ - No interaction (between them) Two main effects and an interaction Factors Significance Study time Yes IQ Yes Study time X IQ Yes IQ Low High 24.5 35.5 Study time 2 hours 4 hours 24.5 35.5 PSYC 2001 – Introduction to Research Methods 1 - 2 main effects - There is an interaction An interaction, but no main effects Factors Significance Study time No IQ No Study time X IQ Yes IQ Low High 35 35 Study time 2 hours 4 hours 35 35 PSYC 2001 – Introduction to Research Methods 2 - This is a cross over interaction - One interaction - No main effect - If there are only 2 variables, can’t have more than 1 interaction Within-category attribute correlations - Knowledge of the category: • Beak • Feathers • Most fly - Within-category attribute correlations (W-Cs): • Typically, small birds sing (cardinals, sparrows…) • Bigger birds don’t (chickens, ostriches…) Research - In the laboratory, participants: • Are very sensitive to family resemblances (Rosch during the 70s) • Nevertheless, they rarely learn W-Cs:  Inductive category learning (Nosofsky, Palmeri, & McKinley, 1994; Chin-Parker & Ross, 2004)  Free sorting (Ahn
More Less

Related notes for PSYC 2001
Me

OR

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Join to view

OR

By registering, I agree to the Terms and Privacy Policies
Just a few more details

So we can recommend you notes for your school.