Download Exam 2 Extra Assignment

PSYC 2100 sec 01, 02, 03, 04 Fall 2013: Exam 2 Extra Assignment
* Anyone in the class can do this assignment regardless of exam 2 score.
* The assignment consists of 20 even-numbered questions from the PREVIOUS edition of the text, which do not have answers
provided for them. You are encouraged to use YOUR text's odd-numbered questions and their solutions in the back of the book, as
well as the examples in the chapters, as models of how to answer the assigned items. Items will be worth 0.5 points each.
* Maximum number of points to gain is 10, with these exceptions: 1) Maximum TOTAL number of points on the exam is still 40, so if
you got 37 you only have 3 points to gain - and to get those 3 points you still must complete the whole assignment, not just 30% of it!
2) A score of 10 guarantees an exam 2 score corresponding to least a "C" grade, regardless of initial score on the exam.
* YOU CAN USE YOUR TEXT AND LECTURE NOTES (and you may have to consult them more carefully now!).
* YOU CANNOT WORK TOGETHER ON THE ASSIGNMENT - THAT WILL BE CONSIDERED CHEATING! Remember, it's
an exam, not just homework. FYI, the typical operational definition of cheating is a striking pattern of identical incorrect calculations
and answers. If you cheat but get everything correct, you may not be detected, but the knowledge of what a bad person you are will eat
at your soul till your dying day and family and friends will turn away from you and animals will smell your foulness and you'll wish
you had just accepted a possibly slightly lower grade based on your own work. BE A GOOD PERSON.
* I will ease my scoring task by using a set of multiple choice alternatives for these questions, and a bubble sheet that the computer
center can score for me. Bubble sheets will be passed out in class, but there's absolutely no need to wait for them before completing
this assignment. You can bubble in your 20 answers later if you don't have a bubble sheet. The only ID information I need bubbled in
is your LAST NAME and FIRST NAME.
* Turn in BOTH the assignment with all work NEATLY written out or typed where possible, along with the corresponding bubble
sheet that I'll pass out to you.
* DUE DATE is Tuesday 11/19/13 though of course you should complete it immediately so as not to let it conflict with any exam
studying! If you don't have it in class on the due date you can put it in my mailbox. Don't skip class that day to finish this, that would
be considered lame -- there is no need, and you'd be missing important in-class information for the upcoming exam!
* Please LEARN this stuff as you do it, it's the only reason I'm offering this assignment and all these topics will be fair game on the
final anyway.
SOME USEFUL FORMULAS
including the correlation formula that I use even though it's not in Gravetter & Wallnau:
Population: mean =  , variance = 2 , standard deviation =  , size = N
Population Variance = 2 = SS/N = (X-)2 / N
standard deviation = variance
Sample: mean = M , variance = s2 , standard deviation = s , size = n, df = n-1
Sum of Squares (of deviations from the mean):
SS = (X-M)2 = (X-M)(X-M)
Variance:
s2 = SS/df = (X-M)2 / (n-1)
Sum of Products (of deviations from the mean):
SP = (X-Mx)(Y-My)
Covariance:
covxy = SP/(n-1) = (X-Mx)(Y-My) / (n-1)
Correlation (Pearson product-moment correlation coefficient):
r = covxy / sxsy
Read each question and all the alternatives carefully. Circle the letter of the BEST answer on this sheet, and fill in the corresponding
bubble on your bubble sheet.
Questions on Chapter 6:
1. For a normal distribution, what z-score would separate the distribution so that there is 30% in the tail on the left-hand side?
a.
.67
b.
-1.03
c.
-.52
d.
.84
2. For a normal distribution, what z-scores separate the middle 90% from the extreme 10% in the tails?
a.
+/- 1.28
b.
+/- 1.64
c.
+/- 1.96
d.
+/- 1.44
3. A population forms a normal distribution with  = 68 and  = 6. Find the probability of selecting a score with a value less than 60.
a.
.0918
b.
.9525
c.
.4082
d.
.9082
Questions on Chapter 7:
4. A sample was selected from a population with  = 75 and  = 20. What is the standard error of M for a sample of n = 25 scores?
a.
3
b.
15
c.
.80
d.
4
5. A normal distribution has  = 100 and  = 20. A sample mean of M = 106 is computed for a sample of n = 25 scores. Is this sample
mean in the extreme 5%?
a.
yes
b.
no
c.
can't think of
d.
anything funny to say
6. A normal population has  = 70 and  = 12.
A. What proportion of the scores have values greater than X = 73?
B. What proportion of sample means of size n = 16 have values greater than 73?
For part (A) and (B) respectively, the proportions are
a.
.1587 and .4013
b.
.1587 and .1587
c.
.4013 and .1587
d.
.4013 and .4013
7. Boxes of sugar are filled by machine with considerable accuracy. The distribution of box weights is normal and has a mean of 32
ounces with a standard deviation of only 2 ounces. A quality control inspector takes a sample of n = 16 boxes and finds the
sample contains, on average, M = 31 ounces of sugar. If the machine is working properly, what is the probability of obtaining a
sample of 16 boxes that averages 31 ounces or less? Should the inspector suspect that the filling machinery needs repair?
The probability is
a.
.9772
b.
.0228
c.
.4772
d.
.0250
Questions on Chapter 8:
8. A sample of n = 4 individuals is selected from a normal population with  = 70 and  = 10. A treatment is administered to the
individuals in the sample, and after the treatment, the sample mean is found to be M = 75.
A. On the basis of the sample data, can you conclude that the treatment has a significant effect? Use a two-tailed test with  = .05.
B. Suppose that the sample consisted of n = 25 individuals and produced a mean of M = 75. Repeat the hypothesis test at the .05 level
of significance.
C. Compare the results from part (a) and part (b). How does the sample size influence the outcome of a hypothesis test?
Your answers for (A), (B), and (C) respectively are
a.
N.S. (meaning "Not Significant"); significant; larger n means MORE likely to be significant
b.
significant; N.S.; larger n means MORE likely to be significant
c.
N.S.; significant; larger n means LESS likely to be significant
d.
significant; N.S.; larger n means LESS likely to be significant
9. A researcher would like to determine whether there is any relationship between students’ grades and where they choose to sit in the
classroom. Specifically, the researcher suspects that the better students choose to sit in the front of the room. To test this
hypothesis, the researcher asks her colleagues to help identify a sample of n = 100 students who all sit in the front row in at
least one class. At the end of the semester, the grades are obtained for these students and the average grade point average is M =
3.25. For the same semester, the average grade point average for the entire college is  = 2.95 with  = 1.10. Use a two-tailed
test with  = .01 to determine whether students who sit in the front of the classroom have significantly different grade point
averages than other students.
NOTICE that you are asked to use  = .01!
a.
sig., p<.01
b.
N.S. ("not significant"), p>.01
c.
sig., p>.01
d.
N.S., p<.01
Questions on Chapter 9:
10. The following sample was obtained from a population with unknown parameters. Scores: 9, 1, 13, 1. Compute the estimated
standard error for M. (Note that this is an inferential value that describes how accurately the sample mean represents the
unknown population mean.)
The estimated standard error of the mean is
a.
36
b.
6
c.
3
d.
1
11. A random sample of n = 9 individuals is obtained from a population with a mean of  = 80. A treatment is administered to each
individual in the sample and, after treatment, each individual is measured. The average score for the treated sample is M = 86
with SS = 288.
A. How much difference is there between the mean for the treated sample and the mean for the original population? (Note: In a
hypothesis test, this value forms the numerator of the t statistic.)
B. How much difference is expected just by chance between the sample mean and its population mean? That is, find the standard error
for M. (Note: In a hypothesis test, this value is the denominator of the t statistic.)
C. Based on the sample data, does the treatment have a significant effect? Use a two-tailed test with  = .05.
The question asks you for the numerator and then the denominator of the t-test, and then has you do the t-test. I just want you to say
which of the following is TRUE of your t-test:
a.
this t is on 9 degrees of freedom
b.
the t you calculate is LARGER than 2.306
c.
the p-value for your t is LARGER than .05, so it's non-significant
d.
the estimated standard error is 6
12. A social psychologist suspects that the increased availability of e-mail may have an effect on the methods that people use to
communicate. The researchers obtain records from 1995 indicating that the average American spent  = 2.1 hours per month on
long distance phone calls. A random sample of n = 36 people was obtained and their phone records were monitored for all of
last year. The people in the sample averaged M = 1.9 hours of long distance calls per month with SS = 12.6. Do these data
indicate a significant change in the use of long distance telephone? Use a two-tailed test with  = .05.
Here I ask for the result, AND which value of t you compare it to in the table: The result of the t-test is
a.
significant BECAUSE t > 2.042
b.
significant BECAUSE t > 2.021
c.
non-significant BECAUSE t < 2.042
d.
non-significant BECAUSE t < 2.021
13. Several years ago, a survey in a school district revealed that the average age at which students first tried an alcoholic drink was  =
14 years. To determine whether anything has changed, a random sample of students was asked questions about alcohol use. The
age at which drinking behavior first began was reported by members of the sample as follows: 11, 13, 14, 12, 10. Has there
been a change in the mean age at which drinking began? Use  = .05 for two tails.
Again, I ask for the result AND why that is your conclusion: The result of the t-test is
a.
significant BECAUSE p > .05
b.
significant BECAUSE 2.83 > 2.776
c.
non-significant BECAUSE 2.776 < 2.83
d.
non-significant BECAUSE p < .05
Questions on Chapter 11:
14. A sample of difference scores (D values) from a repeated-measures experiment has a mean of MD = 5.00 with a variance of s2 =
16.
A. If n = 4, is this sample sufficient to reject the null hypothesis using a two-tailed test with  = .05?
B. Would you reject H0 if n = 16? Again, assume a two-tailed test with  = .05.
NOTICE that this question gives you the VARIANCE of the difference scores, not the standard deviation. Which of the following
statements is TRUE of your two analyses in parts (A) and (B)?
a.
With n=4, the mean difference score is significant
b.
With n=4, the t value you calculate is LARGER than 3.182
c.
With n=16, the mean difference score is not significant
d.
With n=16, the p-value you get is SMALLER than .05
15. A researcher studies the effect of cognitive psychotherapy on positive self-regard. The number of positive statements made about
oneself is recorded for each participant during the first meeting. After 8 weekly therapy sessions, the measures are repeated for
each person. For the following data, is there a significant treatment effect? Use  = .05, two tails.
Participant
A
B
C
D
a.
b.
Before
Treatment
0
4
0
12
After
Treatment
12
10
4
18
the effect is significant
the effect is non-significant
16. The following data are from an experiment comparing two treatments:
Treatment 1
10
2
1
15
7
M=7
SS = 134
Treatment 2
11
5
2
18
9
M=9
SS = 150
Assume that the data are from a repeated-measures experiment using the same sample of n = 5 subjects in both treatments. Calculate
the difference score (D) for each subject and use the sample of difference scores to determine whether there is a significant
difference between the two treatments. Again, use a two-tailed test with  = .05.
For the repeated measures analysis you did, which of the following is TRUE:
a.
the t you look up is on 8 degrees of freedom
b.
the t you compute is LESS than 2.776
c.
the treatment's effect is significant
d.
the treatment's effect is non-significant
17. A researcher investigates whether single people who own pets are generally happier than singles without pets. A group of non-pet
owners is compared to pet owners using a mood inventory. The pet owners are matched one to one with the non-pet owners for
income, number of close friendships, and general health. The data are as follows:
Matched
Pair
A
B
C
D
E
F
Non-Pet
Owner
10
9
11
11
5
9
Pet
Owner
15
9
10
19
17
15
Is there a significant difference in the mood scores for non-pet owners versus pet owners? Test with  = .05 for two tails.
When two groups of participants are MATCHED, we compare them as if they were the SAME group of participants, so you would
use the Repeated Measures t-test. When you do that t-test, which of the following is true of your analysis:
a.
the t you look up is on 10 degrees of freedom
b.
the difference is significant
c.
the difference is non-significant
d.
the difference would have been more significant using an independent groups t-test
Questions on Chapter 16:
Use my formula for correlation for #18 and #19, but for #20 you can use formulas 15.2 for "SP" and 15.3 for "r" on pp. 515 and
517 (8th Ed. 16.2 and 16.3 on pp. 526 and 528) if you want. Or just use mine again -- you'll need a calculator either way. You
DON'T have to do the graphing part of these questions, but making a scatterplot as described in figure 15.2 on p. 511 (8th Ed.
16.2 on p. 521) will help you understand and interpret any correlation.
18.
For the following set of data,
X
1
2
4
5
3
Y
0
2
6
8
4
A. OPTIONAL BUT HELPFUL: Sketch a graph showing the location of the five X, Y points.
B. OPTIONAL BUT HELPFUL: Just looking at your graph, estimate the value of the Pearson correlation.
C. Compute the Pearson correlation for this data set.
WAIT A MINUTE! Did you really do this by hand, or did you just use Excel or something? From the choices below, please
pick the COVARIANCE, not the correlation! The covariance is a step along the way if you're using the formula I gave you, so
you should have it already done at this point.
a.
1.0
b.
4.0
c.
5.0
d.
9.0
19.
With a very small sample, a single point can have a large influence on the magnitude of a correlation. For the following data
set,
X
0
10
4
8
8
Y
1
3
1
2
3
A. OPTIONAL BUT HELPFUL: Sketch a graph showing the X, Y points.
B. OPTIONAL BUT HELPFUL: Estimate the value of the Pearson correlation.
C. Compute the Pearson correlation.
D. Now we will change the value of one of the points. For the first individual in the sample (X = 0 and Y = 1), change the Y
value to Y = 6. What happens to the graph of the X, Y points? What happens to the Pearson correlation? Compute the new
correlation.
This time just choose the values of the correlation for parts C and D respectively:
a.
(C) .875; (D) .535
b.
(C) .875; (D) -.535
c.
(C) -.875; (D) .535
d.
(C) -.875; (D) -.535
20.
Researchers who measure reaction time for human participants often observe a relationship between the reaction time scores
and the number of errors that the participants commit. This relationship is known as the speed-accuracy trade-off. The
following data are from a reaction time study where the researcher recorded the average reaction time (milliseconds) and the
total number of errors for each individual in a sample of n = 8 participants.
X
A
B
C
D
E
F
G
H
Reaction Time
184
213
234
197
189
221
237
192
Errors
10
6
2
7
13
10
4
9
A. Compute the Pearson correlation for the data.
B. In words, describe the speed-accuracy trade-off.
Compute the correlation in part A, but then answer part B from these choices:
a.
there is a perfect relationship between reaction time and number of errors
b.
there is a strong tendency for longer reaction times to go along with fewer errors
c.
there is zero relationship between reaction time and number of errors
d.
there is a strong tendency for longer reaction times to go along with more errors