# PSY-2150 Final: Book Notes for Final

11 views4 pages
4 Feb 2020
School
Department
Course
Chapter 8: Single Factor Experimental Designs
Random assignment for between-subjects, counterbalancing for within-subjects (refer to diagram
on 253)
Independent groups design--participants are randomly assigned to the various conditions of the
experiment (between-subjects, random assignment
Block randomization--we conduct a single round of all the conditions, then another round,
then another for as many rounds as needed to complete the experiment; within each round,
the order of conditions is randomly determined (between-subjects)
Matched groups design--(not assigning on a purely random basis; using a matching variable) each
set of participants that has been matched on one or more attributes is randomly assigned to the
various conditions of the experiment (still involves random assignment, but not completely
random; match on some variable that you think may be a possible confounding factor) (between-
subjects)
Natural groups design--(possible causal relation examined not by manipulating an independent
variable, but instead by selecting different groups of people based on personal characteristics;
matched on subject variable) a researcher measures a subject variable, forms different groups
based on people's level of that variable, and then measures how the different groups respond on
other variables (between-subjects)
All possible orders design--(participants exposed to each condition once, also called complete
counterbalancing, within-subjects) the conditions of an independent variable are arranged in
every possible sequence, and an equal number of participants are assigned to each sequence (ex.
if you have 4 conditions, you need a minimum of 4x3x2x1 = 24 participants to have one per
sequence)
Latin square design--(participants exposed to each condition only once) an n (number of positions
in a series) x n (number of orders) matrix in which each condition will appear only once in each
column and each row (within-subjects)
Random-selected orders design-- (participants exposed to each condition only once) from the
entire set of all possible orders, a subset of orders is randomly selected and each order is
administered to one participant (to be most effective, this counterbalancing approach should not
be used when the number of participants is small; with only a few participants, there will not be
enough random orders selected to let chance have a good opportunity to balance the order
effects)
Block randomization design--(exposing participants to each condition more than once) every
participant is exposed to multiple blocks of trials, with each block for each participant containing a
newly randomized order of all the conditions [**block randomization is applied differently in
within vs. between-subjects designs; in a between-subjects design, each participant only engages
in a total of one condition within one particular block; in contrast, in within-subjects designs, each
participant not only performs all the conditions within a block, but is also exposed to multiple
blocks) (within-subjects design)
Reverse counterbalancing design (ABBA counterbalancing design)--each participant receives a
random order of all the conditions and then receives them again in the reverse order (within-
subjects)
Chapter 9: Factorial Designs
Factorial design--includes two or more independent variables and crosses every level of each
independent variable with every level of all the other independent variables
Unlock document

This preview shows page 1 of the document.
Unlock all 4 pages and 3 million more documents.

## Document Summary

Chapter 8: single factor experimental designs: random assignment for between-subjects, counterbalancing for within-subjects (refer to diagram on 253) Chapter 10: experimentation and validity: construct validity--concerns the issue of whether the construct that researchers claim to be studying are in fact the constructs they truly are manipulating and measuring. Statistical conclusion validity--concerns the proper statistical treatment of data and the soundness of researchers" statistical conclusions. Switching replication with treatment removal (allows to see if results are maintained) Second, the baseline phase is switched to a treatment phase only for the first person, behavior, or setting. In this phase, the researcher hopes to see a clear, immediate change in scores on the dv, but only for that person, behavior, or setting. Meanwhile all the other baseline phases remain in effect and no change in the dv is expected because there is no exposure to the treatment.