07

Chapter 7: Experimental Design I: Single-Factor Designs

Chapter Objectives

• Identify and understand the defining features of the four varieties of single-factor designs:

  • Independent groups

  • Matched groups

  • Nonequivalent groups

  • Repeated measures

• Describe two reasons for using more than two levels of an independent variable.

• Decide when to use a bar graph and when to use a line graph.

• Describe the goals of the Ebbinghaus memory research, his methodology, and the results he obtained.

Continued Objectives

Control Groups

• Understand the logic behind the use of three special types of control groups:

  • Placebo

  • Wait list

  • Yoked

• Understand the ethical issues involved when using certain types of control groups.

• Know when to use an independent samples t-test and when to use a dependent samples t-test for inferential analysis of a single-factor, two-level design.

• Understand why a one-way ANOVA, rather than multiple t-tests, is appropriate for examining data from single-factor, multilevel studies.

• Understand why post hoc statistical analyses typically accompany 1-factor ANOVAs for single-factor, multilevel studies.

Single-Factor - Designs Decision Tree

• Determine if it is a between-subjects or within-subjects design:

  • Between-subjects: Independent groups or matched groups.

  • Within-subjects: Repeated measures.

• Consider manipulation of variables:

  • Independent variable manipulated by researcher or subject variable.

• Options for forming groups:

  • Random assignment for independent groups.

  • Matching to produce equivalent groups for matched designs.

• Additional considerations include reverse/block counterbalancing strategies for within-subject designs.

Single-Factor—Two Levels

Between-Subjects Designs

• Independent Groups Designs

  • Independent variable (IV) – manipulated through random assignment.

  • Example: Note-taking methods (laptop vs. handwritten) affecting performance on memory tests.

  • Concepts include conceptual replication, ecological validity, and "what’s next thinking."

Matched Groups Designs

• Types of independent variable manipulation.

• Example: Type of social skills training (direct teaching vs. play activities) based on matching (e.g., Autism Quotient).

• Dependent variable (DV) measured through Social Interaction Observation Code.

• Relevant concepts: operational definitions, double-blind procedure, inter-rater reliability.

Ex Post Facto Designs

• Use of subject variables as independent variables with attempts to reduce nonequivalence.

• Example: Participants with and without traumatic brain injury (TBI) compared on ability to detect insincerity.

• Focus on external validity and matching.

Within-Subjects Designs

• Known as repeated measures designs; all participants tested across all IV levels.

• Famous example includes Stroop task utilizing reverse counterbalancing.

• Example: Sharing experiences vs. unsharing and measuring chocolate flavorfulness.

• Other concepts: confederate and cover story.

Single-Factor—More Than Two Levels

Advantages of Multilevel Designs

• Advantage #1: Ability to discover nonlinear effects (e.g., optimal arousal-performance relationships).

• Advantage #2: Rule out alternative explanations, illustrated by Bransford and Johnson’s laundry study.

• Example: IV with three levels affecting recall of ideas.

Analyzing Data from Single-Factor Designs

Data Presentation

• Importance of choosing appropriate graphical forms: bar graphs for categories vs. line graphs for trends.

• Review Bransford and Johnson’s data presentation methods.

Statistical Analysis

• Analyzing two-level designs using t-tests and applying assumptions:

  • Interval or ratio data

  • Normal distribution and homogeneity of variances.

• Critique of using multiple t-tests for multilevel designs due to increased Type I error rates.

• Appropriate to use one-way ANOVA for multilevel independent groups and repeated measures designs.

• Post hoc testing to compare levels of the IV following significant findings.

Special-Purpose Control Group Designs

Types of Control Groups

• Placebo Control Groups: Participants believe they are receiving treatment but do not.

  • Example: Study assessing efficacy of subliminal tapes for weight loss.

  • Concepts include pilot study and Hawthorne effect.

Yoked Control Groups

• Each control subject is "yoked" to a corresponding experimental subject; matched in session length.

• Example: Comparing EMDR therapy for stress with yoked control conditions.

• Understanding null hypothesis value in research contexts.

Summary of Single-Factor Designs

• Single-factor designs involve one independent variable, can be between- or within-subjects.

• More than two independent variable levels can indicate nonlinear effects and rule out alternative explanations.

• Result data can be presented in tables or graphs and analyzed using t-tests or one-way ANOVAs.

• Special-purpose control groups help determine treatment effects definitively.