Author: admin

A researcher wants to test the effectiveness of two
different computer-based instructional methods on teaching a unit on weather in
seventh-grade science. The researcher fi nds a teacher who will permit three of
his classes to participate: Two classes use the computer-based instruction, and
the third receives conventional classroom instruction. The researcher
administers a pretest to all students, each class has a different method of
instruction, and then a posttest is administered.
a. Specify the design of this study and represent it using
the notation system used in this chapter.
b. What statistics would you choose to analyze the data?

What method would you use to investigate the following
research hypotheses?
a. High school students who work during the school year will
have lower grades and lower standardized test scores than students who do not
work.
b. First-grade students who are taught reading using phonics
will read at a higher level than fi rst-grade students taught by another
method.
c. Beginning teachers who are mentored will be more
effective and express more satisfaction with teaching than beginning teachers
who are not mentored.
d. Students who are in small classes (less than 15) in
grades kindergarten to 3 will perform at a higher level in grades 4 to 6 than
will students in regular-sized classes (more than 20)

1. Interpret this statement: “A statistical relationship
between two variables is a necessary but not a suffi cient condition for
inferring a causal relationship between the variables.”
2. What alternative hypotheses would you want to explore if
your causal-comparative research indicates that there is a relationship between
self-concept and achievement in school?

1. What steps would you take to avoid the post hoc fallacy
in your ex post facto research?
2. Try to control any relevant extraneous variables that
could affect the measured variable. Methods of control include (a) matching,
(b) using homogeneous groups, (c) building extraneous variables into the
design, and (d) using ANCOVA or other statistical means to partially control
unwanted variables

Identify the following as
1. Characteristic of correlational research
2. Characteristic of ex post facto research
3. Characteristic of both
4. Characteristic of neither
a. Actively manipulates variables
b. Looks at differences between two or
more groups
c. Assesses the direction and strength of
association among variables
d. Produces indexes that range from
−1.00 to +1.00
e. Studies preexisting variables

Which correlation in each pair indicates
the greatest extent of relationship between
two variables?
a. +.80 or –.80
b. +.60 or+.85
c. +.60 or –.85
d. +.04 or –.15

A state offi cial found a correlation of .65 between the
number of bars in cities in the state and the number of crimes reported in
those cities. He concluded that legislation to reduce the number of bars would
reduce crime. What would you say about the offi – cial’s conclusion?

A researcher is interested in anxiety and how it might
affect performance on scholastic aptitude tests. He has a clinical psychologist
assess the anxiety of subjects by ranking them from 1 through 20. Then he
administers a standardized aptitude test to each of the 20 subjects and
converts their IQ scores to ranks. Which correlation coeffi cient should the
researcher calculate for the data? Explain your answer.

1. A researcher wants to investigate the relationship
between class size and student satisfaction in sections of beginning psychology
at a university. Describe two research methodologies that might be appropriate
to answer this question.

A researcher found a moderate negative correlation between
two variables of interest. She concluded that the negative correlation meant
that it would be useless to try to predict one variable from the other. Do you
agree? Why or why not?