AMCP (version 2.0.0)

chapter_7_table_11: The data used in Chapter 7, Table 11

Description

The data used in Chapter 7, Table 11

Usage

data(chapter_7_table_11)

Format

An object of class data.frame with 45 rows and 3 columns.

Variables

Diagnosis

diagnostic group: amnesic, Huntington's disease, or control (three levels)

Task

task type (1 = artificial grammar, 2 = classification learning, 3 = recognition memory)

Y

the dependent variable: the task performance score

Synonym

C7T11

Author

Ken Kelley

Details

Table 7.11 presents this hypothetical data for 15 amnesiacs, 15 Huntington individuals, and 15 controls. The data represents a two way factorial design where diagnosis and task are fully crossed, each with three levels. Of interest for the results displayed in Table 7.12 is whether the interaction contrast specified in Figure 7.3 and 7.4 is statistically significant. Namely the question pertains to whether the relationship of the mean of grammar and classification versus recognition differs for those in the amnesic and Huntington's group. Interaction contrasts of this kind are readily specified and tested within the model comparison framework.

Consider an example of a cognitive neuroscience study of patient groups. Specifically, suppose that a certain theory implies that amnesic patients will have a deficit in explicit memory but not in implicit memory. According to this theory, Huntington patients, on the other hand, will be just the opposite: They will have no deficit in explicit memory, but will have a deficit in implicit memory. Further suppose that a study is designed yielding a 3x3 factorial design to test this theory. The rows of this study will represent three types of individuals: amnesic patients, Huntington patients, and a control group of individuals with no known neurological disorder. Each research participant will be randomly assigned to one of three tasks: (1) artificial grammar task, which consists of classifying letter sequences as either following or not following grammatical rules; (2) classification learning task, which consists of classifying hypothetical patients as either having or not having a certain disease based on symptoms probabilistically related to the disease; and (3) recognition memory task, which consists of recognizing particular stimuli as stimuli that have previously been presented during the task.

References

Maxwell, S. E., Delaney, H. D., & Kelley, K. (2027). Designing experiments and analyzing data: A model comparison perspective (4th ed.). New York, NY: Routledge.

Examples

# Load the data
data(chapter_7_table_11)

# Or, alternatively load the data as
data(C7T11)

# View the structure
str(chapter_7_table_11)

# ---------------------------------------------------------------------
# Optional: a factor-coded copy for factorial ANOVA / model comparison.
# Diagnosis and Task are stored as numeric codes so the book's contrast
# and model-comparison examples reproduce exactly. For a factorial ANOVA
# you want them as factors; otherwise a code enters the model as a single
# linear (1 df) term. Build a *copy* (suffix "_factors") so the canonical
# data set is left unchanged. Labels (and their order) are taken from the
# "Variables" section / description above.
C7T11_factors <- chapter_7_table_11
C7T11_factors$Diagnosis <- factor(C7T11_factors$Diagnosis, levels = 1:3,
  labels = c("Amnesic", "Huntington's Disease", "Control"))
C7T11_factors$Task <- factor(C7T11_factors$Task, levels = 1:3,
  labels = c("Artificial Grammar", "Classification Learning",
             "Recognition Memory"))

# This design is balanced, so the factorial ANOVA is order-invariant.
anova(lm(Y ~ Diagnosis * Task, data = C7T11_factors))
# (The book then tests a specific interaction contrast; see Table 7.12.)