Review – Exam One
Define The Following:
Statistical Hypothesis
Experimental Unit
Nuisance Variables
Distinguish Between The Following Research Strategies.
Experiments
Quasi-Experiments
Surveys
Case Studies
Naturalistic Observations
Ex Post Facto Studies
Retrospective And Prospective Studies
Retrospective Cohort Studies
Historical Cohort Studies
Case Control Study
Longitudinal Study
Cross-Sectional Study
Longitudinal-Overlapping Study
Time-Lag Study
Time-Series Study
Single-Subject Study
Define The Following Types Of Validity
Statistical Conclusion Validity
Internal Validity
Construct Validity Of Causes And Effects
External Validity
Define The Following Threats To Statistical Conclusion Validity
Low Statistical Power
Violated Assumptions Of Statistical Tests
Fishing For Significant Results And The Error-Rate Problem
Reliability Of Measures
Reliability Of Treatment Implementation
Random Irrelevancies In The Experimental Setting
Random Heterogeneity Of Respondents
Define The Following Threats To Internal Validity
History
Maturation
Testing
Instrumentation
Statistical Regression
Selection
Mortality
Interactions With Selections
Ambiguity About The Direction Of Causal Influence
Diffusion Or Imitation Of Treatments
Compensatory Rivalry By Respondents Receiving Less Desirable Treatments
Resentful Demoralization Of Respondents Receiving Less Desirable
Treatments
Define The Following Threats To External Validity
Interaction Of Testing And Treatment
Interaction Of Selection And Treatment
Interaction Of Setting And Treatment
Interaction Of History And Treatment
Reactive Arrangements
Multiple-Treatment Interference
Define These Other Threats To Valid Inference Making
Experimenter-Expectancy Effect
Demand Characteristics
Subject-Predisposition Effects
Cooperative-Subject Effects
Screw You Effect
Evaluation Apprehension
Faithful Subjects
Placebo Effect
Define The Following Approaches To Control
Single-Blind Procedure
Double-Blind Procedure
Deception
Disguised-Experiment Technique
Multiple Researchers
Debriefing
Experimenter-Expectancy Control Groups
Unrelated-Experiment Technique
Quasi-Control Group
Yoked Control Procedure
Introduction to Designs
Write the null hypotheses available to be tested, the experimental design
model equation, describe each component in the equation, and write the
layout for each of the following designs.
CR-p
RB-p
LS-p
CRF-pq
Fundamental Assumptions in ANOVA
Who derived the chi-square distribution and what are its characteristics?
What is the importance of the chi-square distribution in ANOVA?
Who derived the F distribution and what are its characteristics?
What is the importance of the F distribution in ANOVA?
Who derived the t distribution and what are its characteristics?
What is the importance of the t distribution in ANOVA?
What are four general assumptions in using the F distribution in hypothesis
testing?
Partitioning Variances
Discuss the partitioning of SSTO in the CR-p design.
Distinguish between a fixed-effects and a random-effects model.
List the rules associated with deriving the expected mean squares for a CR-p
design.
List the three fundamental assumptions in deriving the expected mean
squares for a CR-p design.
More on ANOVA Assumptions
List, again, the four assumptions necessary to use the F.
List, again, the three assumptions necessary to use the CR-p design.
Describe the effect of violation of each of the above assumptions on
computation and interpretation.
Multiple Comparison Tests
Distinguish between per-contrast, familywise, and per-family error rates.
Define the three kinds of test statistics in multiple comparison procedures.
Distinguish between a single-step and a multiple-step procedure.
What is coherence?
Which multiple comparison procedure is appropriate for each of the following
(form two columns for each: one when assumptions are tenable and
one when they are not):
A priori orthogonal
A priori nonorthogonal (control mean)
A priori nonorthogonal (C contrasts)
A posteori orthogonal
A posteori nonorthogonal (all pairwise)
A posteori nonorthogonal (all contrasts)
What are the assumptions associated with using the Student’s t?
When is Dunnet’s test applicable?
What does Dunn’s procedure involve? Discuss alpha.
When is the Dunn-Sidak test appropriate? What is the difference between
this procedure and the Dunn procedure?
Discuss the differences between Holm’s procedure and the D-S procedure.
When is Tukey’s HSD test appropriate?
What is the procedure for Tukey’s HSD?
What is / are the procedure(s) when the n’s are equal?
What is / are the procedure(s) when the n’s are unequal?
What is / are the procedure(s) when the variances are heterogeneous?
When is the Fisher-Hayter test appropriate?
Discuss the contribution of each of the following to the REGW procedure.
Ryan
Einot and Gabriel
Welsch
Shaffer
When is Scheffe’s S test appropriate?
When is the Brown-Forsythe test appropriate?
Completely Randomized Design
List two conditions (in addition to those of ANOVA) required for the CR-p
design.
Write the layout for a CR-p design.
Write the experimental design model equation for a CR-p design and indicate
what each term means.
Why is exploratory data analysis performed?
What are the null hypotheses that can be tested in the CR-p design?
Write the general ANOVA table for a CR-p design.
Compare the expected mean squares for models I and II.
List five major advantages and two major disadvantages to the CR-p design.
General Linear Model
What is a linear model?
What is the linear model in matrix terms?
What is a structural matrix?
How are parameters estimated in the regression model?
What is dummy coding?
Write the regression equation using dummy coding.
What is effect coding?
Write the regression equation using effect coding.
What is orthogonal coding?
What is the correspondence between parameters of the regression and
ANOVA models?
What is the cell means model?
Why is the cell means model used?