Deck 13: Experimental Research

Question 1

Why are control groups necessary in certain experiments?

A) To make sure that the experimenter is honest
B) To make it easier to estimate the influence of the independent variable
C) To enable the researcher to repeat the experiment
D) To enable the researcher to identify the dependent variable

Answer 1

To make it easier to estimate the influence of the independent variable

Question 2

One difference between the experimental and other methods in research has to do with the:

A) number of subjects
B) control of variables
C) recording of data
D) time span of the study

Answer 2

control of variables

Question 3

In a large high school, the 25 students who scored highest on an English pretest were placed in a special class. At the end of one semester, they were given another English achievement test. The mean grade-level equivalents were compared for the two tests. This is an example of a:

A) one-group pretest-posttest design
B) randomized control group pretest-posttest design
C) time series design
D) static group comparison design

Answer 3

one-group pretest-posttest design

Question 4

The feature that best characterizes experimental research is the:

A) repetition of observations
B) systematic variation of conditions
C) making of exact measurements
D) concept of correlation

Question 5

Which of the following is a probable independent variable in an experiment?

A) Self-esteem
B) Reading achievement
C) Teacher friendliness
D) Aggressive behavior

Question 6

Experimental research is the most powerful research method for:

A) identifying important dependent variables
B) determining cause and effect
C) identifying possible relationships
D) generalizing the results of a study

Question 7

In order to do an experimental study of the effects of TV viewing, a researcher must:

A) determine how much TV is watched by each subject
B) locate groups that differ in amount of TV viewed
C) arrange for some subjects to view more TV than others
D) ask subjects a series of questions about the effects of TV viewing

Question 8

Which of the following can be present in an experimental study?

A) Random assignment and random selection
B) Random assignment without random selection
C) Random selection without random assignment
D) All of the above

Question 9

The primary defect of the one-shot case study is:

A) there is no way to tell whether the treatment had any effect
B) poor control over the subject characteristics threat
C) poor control of researcher bias
D) inability to control for maturation

Question 10

In order to be a threat to the internal validity of an experimental study, an extraneous variable such as age must:

A) be related to the dependent variable
B) differ among treatment groups
C) both A and B
D) neither A nor B

Question 11

Loss of subjects in a given experiment constitutes a probable threat to the internal validity of the study if:

A) those lost are representative of their original groups
B) a greater number are lost from one group than from the other(s)
C) losses are not randomly replaced
D) statistical adjustments are not made

Question 12

A major problem with experimental research in education is that:

A) there is no way to control a "history" threat
B) there is no way to control the subject characteristics threat
C) the researcher may not have sufficient control over treatments
D) there is no way to control data collector bias

Question 13

Which is not a serious threat in a one-group pretest-posttest design?

A) Maturation
B) Characteristics of subjects
C) History
D) Statistical regression

Question 14

Which is likely to be the most serious threat in a static-group comparison design?

A) Maturation
B) History
C) Testing
D) Characteristics of subjects

Question 15

An important difference between experimental and nonexperimental research is that the independent variable in experimental research is:

A) quantitative
B) randomly assigned
C) constant
D) manipulated

Question 16

The randomized posttest-only control group design is least effective in controlling:

A) maturation
B) subject characteristics
C) implementer effect
D) history

Question 17

The randomized pretest-posttest control group design requires the researcher to decide whether:

A) subject characteristics need to be controlled
B) information on the pretest is worth the possible bias
C) to randomize before or after the pretest is given
D) administration of the pretest is worth the effort required

Question 18

A researcher would be likely to use matching in a randomized posttest control group design:

A) only if he or she misunderstood randomization
B) in order to control for a possible history threat to internal validity
C) in order to control for loss of subjects
D) if the number in each treatment group is small

Question 19

An advantage of statistical matching over mechanical matching is that:

A) no subjects are lost due to matching
B) the data are easier to analyze
C) less reliable measures can be used
D) it provides better control of a possible testing threat

Question 20

A researcher would use matching rather than random assignment when:

A) the sample is large
B) better control is needed
C) random assignment is impossible
D) data on matching variables are easily obtained

Question 21

The counterbalanced design is subject to a(n):

A) subject characteristics threat
B) multiple treatment interference threat
C) attitude-of-subjects threat
D) maturation threat

Question 22

The purpose of the Solomon four-group design is to:

A) control for effects of pretesting
B) avoid having to assign subjects randomly to groups
C) permit use of a smaller sample
D) control for loss of subjects

Question 23

The time-series design is seldom used because:

A) data collection is so time consuming
B) data are likely to be unreliable
C) it provides poor control for a subject characteristics threat
D) it provides poor control for maturation

Question 24

A factorial design can be used to:

A) study the combined effect of two or more variables
B) control the subject characteristics threat
C) assess the effect of several independent variables
D) all of the above

Question 25

Which of the following threats are not controlled by any of the designs discussed in Chapter 13?

A) Subject characteristics and maturation
B) Testing and history
C) Implementer and data collector bias
D) Data collector characteristics and loss of subjects

Question 26

Matching

-Randomized Solomon four- group

A) Weak experimental design
B) Pretest effect
C) Repeated measurements of one
D) Interactions and moderator
E) Quasi-experimental design

Question 27

Matching

-Factorial design

A) Weak experimental design
B) Pretest effect
C) Repeated measurements of one
D) Interactions and moderator
E) Quasi-experimental design

Question 28

Matching

-Time-series design group

A) Weak experimental design
B) Pretest effect
C) Repeated measurements of one
D) Interactions and moderator
E) Quasi-experimental design

Question 29

Matching

-One-shot case study variables

A) Weak experimental design
B) Pretest effect
C) Repeated measurements of one
D) Interactions and moderator
E) Quasi-experimental design

Question 30

Matching

-Matching-only design

A) Weak experimental design
B) Pretest effect
C) Repeated measurements of one
D) Interactions and moderator
E) Quasi-experimental design

Question 31

Factorial designs extend the number of relationships that may be examined in an experimental study.

Question 32

In educational research, the term "comparison group is identical to a pure "control group in that it refers to a group within a study that receives no treatment whatsoever.

Question 33

Random assignment is intended to eliminate the threat of additional or extraneous variables that might affect the outcome of a study.

Question 34

The main cost associated with holding certain variables constant in an experimental study is that it can reduce the generalizability of the study's results.

Question 35

A major advantage with the randomized Solomon four-group design is that it requires a relatively small sample size.