Return to Brian Schott @ GSU
Return to the list of chapters
1148-2 "In order to have a correlation coefficient between traits A and B,"
1426-3 Suppose a 95% confidence interval for the slope (BETA)
1526-1 0.80 is an estimate of ___________.
1543-1 Calculation of confidence interval for b(2) consists of
1656-2 you test the hypothesis that the slope (BETA) is zero
1726-1 YHAT = -2.5X + 60. We compute the average price per widget if 30
1731-1 "Which, if any, of these amounts do you recommend that the king use"
1732-1 "An economist is interested in the possible influence of ""Miracle Wheat"""
1733-1 why do we need to be concerned with the range of the independent (X)
1738-1 Extrapolation
1739-1 Interpolation
1751-1 What is Y(2)?
1753-1 Make a scatterplot for the following data.
1755-1 r**2 = (.93**2) = 0.871. What does it mean in this case?
1757-1 The regression line is YHAT(i) = -8.26 + 1.17(X(i)). Plot it
1762-2 A scatter diagram is a graphic device for detecting and analyzing
1763-1 Scatter Diagram
1861-3 A researcher finds that the correlation between the personality
1991-1 What model for Y is suggested by each of the following graphs?
1993-1 Propose a model (including a very brief indication of symbols used
1994-1 Propose a model that might be used to predict % alcohol in blood
2088-1 What is your estimate of the average height of all trees having
2091-1 Is this evidence consistent with the claim that the number of fleas is
2123-1 Describe the relation between income and experience
2135-1 T TEST OF A REGRESSION COEFFICIENT
2138-2 What is the smallest significance level at which you would reject
2443-1 The coefficient of multiple determination is:
2443-2 An interpretation of r = 0.5 is that the following part of
2444-2 Which of the following values of r indicates the most accurate
2445-1 If the correlation between age of an auto and money spent for repairs
2445-2 "If the coefficient of correlation equals 0.61, it indicates that the"
2446-2 test had a correlation of .40. What percentage of the variance do
2449-1 "If in a given experiment r = 0.70, then 49 percent of the variation of"
2449-2 The coefficient of determination can have values between
2449-3 the proportion of the variation in Y which is explained by Y's linear
2469-1 is -0.95. Which of the following conclusions is correct?
2470-1 plotted on a diagram (given below). A statistician asserts that the
2471-2 A sample correlation coefficient of -1 (minus one) tells us that
2471-3 The appropriate statistical analysis is:
2472-1 correlation of 0.75 was found. This indicates that the relationship
2473-1 The figure below indicates that Variable A and Variable B are:
2474-1 The correlation between Variable A and Variable B in the figure below
2475-1 -0.73. Which of the following may be concluded?
2475-2 If we obtain a negative r
2476-1 was found to be -1.08. On the basis of this you would
2481-1 the coefficient of correlation is.10. What does this mean?
2481-3 indicate a situation where more than half of the variation
2482-1 what is the approximate value of the correlation coefficient?
2484-1 The correlation coefficient for X and Y is known to be zero.
2486-1 [12 inches = one foot; 16 ounces = one pound]
2487-2 coefficient of correlation of -.90 was obtained. This indicates
2487-4 no comparison can be made between r=-.80 and r=+.80
2488-3 What would you guess the value of the correlation coefficient to be for
2490-4 between height measured in feet and weight measured in pounds is +.68.
2491-2 The sign (plus or minus) of a correlation coefficient indicates
2491-3 a neuroticism test and scores on an anxiety test is high and positive
2492-2 "In correlational analysis, when the points scatter widely about the"
2494-1 "Explain what correlation coefficients of -1, 0 and 1 mean, using"
2503-2 what conclusions might be drawn?
2504-1 to determine wrestling ability. EXPLAIN THIS STATEMENT.
2505-1 Write an interpretation of each of the following correlations:
2513-1 Discuss briefly the distinction between correlation and causality.
2514-4 "If r is close to + or -1, we shall say there is a strong correlation,"
2515-1 then geometrically speaking the regression of Y on X yields
2515-3 is proof of a cause-effect relationship between the variables.
2516-1 association rather than causation
2516-2 r is only an estimate of the true correlation coefficient
2518-3 Correlation Coefficient
2519-1 Simple Correlation or Simple Regression
2524-1 Complete the following Analysis of Variance Table
2532-1 Tukey's HSD (at ALPHA = .05) = 5.57113
2545-1 Individual statistical comparisons between pairs of means
Return to the list of chapters
Return to Brian Schott @ GSU
Q: In order to have a correlation coefficient between traits A and B,
it is necessary to have:
a. one group of subjects, some of whom possess characteristics of
trait A, the remainder possessing those of trait B
b. measures of trait A on one group of subjects and of trait B on
another group
c. two groups of subjects, one which could be classified as A or
not A, the other as B or not B
d. measures of traits A and B on each subject in one group
Back to this chapter's Contents
Q: True or False? If False, correct it.
Suppose a 95% confidence interval for the slope (BETA) of the straight
line regression of Y on X is given by -3.5 < BETA < -0.5. Then a two-
sided test of the hypothesis H(0): BETA = -1 would result in rejection
of H(0) at the 1% level of significance.
Back to this chapter's Contents
Q: An investigator has used a multiple regression program on 20 data points
to obtain a regression equation with 3 variables. Part of the computer
output is:
Variable Coefficient Standard Error of b(i)
1 0.45 0.21
2 0.80 0.10
3 3.10 0.86
a. 0.80 is an estimate of ___________.
b. 0.10 is an estimate of ___________.
c. Assuming the responses satisfy the normality assumption, we
can be 95% confident that the value of BETA(2) is in the interval,
_______ +/- [t(.025) * _______], where t(.025) is the criti-
cal value of the student's t distribution with ____ degrees
of freedom.
Back to this chapter's Contents
Q: A computer program for multiple regression has been used to fit
YHAT(j) = b(0) + b(1)*X(1j) + b(2)*X(2j) + b(3)*X(3j)
Part of the computer output includes:
i b(i) S(b(i))
0 8 1.6
1 2.2 .24
2 -.72 .32
3 .005 .002
a. Calculation of confidence interval for b(2) consists of _______
+/- (a student's t value) (_______)
b. The confidence level for this interval is reflected in the value
used for _______.
c. The degrees of freedom available for estimating the variance are
directly concerned with the value used for _______.
Back to this chapter's Contents
Q: True or False? If False, correct it.
Suppose you are performing a simple linear regression of Y on X and
you test the hypothesis that the slope (BETA) is zero against a two-
sided alternative. You have n = 25 observations and your computed
test (t) statistic is 2.6. Then your P-value is given by .01 < P <
.02, which gives borderline significance (i.e. you would reject H(0)
at ALPHA = .02 but fail to reject H(0) at ALPHA = .01).
Back to this chapter's Contents
Q: We are interested in finding the linear relation between the number
of widgets purchased at one time and the cost per widget. The
following data has been obtained:
X: Number of widgets purchased-- 1 3 6 10 15
Y: Cost per widget(in dollars)--55 52 46 32 25
Suppose the regression line is YHAT = -2.5X + 60. We compute the
average price per widget if 30 are purchased and observe:
a. YHAT = -15 dollars; obviously, we are mistaken; the prediction
YHAT is actually +15 dollars.
b. YHAT = 15 dollars, which seems reasonable judging by the data.
c. YHAT = -15 dollars, which is obvious nonsense. The regression
line must be incorrect.
d. YHAT = -15 dollars, which is obvious nonsense. This reminds us
that predicting Y outside the range of X values in our data is a
very poor practice.
Back to this chapter's Contents
Q: Once upon a time there was a wizard who invented a means of amplifying
the sounds produced by the king's musicians. By dropping a gold coin
into a slot, the king could amplify sound: 1 coin - 1 fold
2 coins - 2 fold
etc.
The wizard persuaded the king to write down a number indicating the
pleasure he experienced from various performances of the musicians.
Later he presented these results:
Coins Pleasure
0 10
1 15
2 20
3 25
Said the wizard, "Clearly, your majesty, we have found the fountain of
pure joy. The more coins, the greater amplification, and the greater
your pleasure."
Which, if any, of these amounts do you recommend that the king use for
his next investment in amplification (you should suggest more than one
if appropriate).
Explain your advice.
a. 3 coins
b. 100 coins
c. 1000 coins
d. 4 coins
e. 10 coins
Back to this chapter's Contents
Q: An economist is interested in the possible influence of "Miracle Wheat"
on the average yield of wheat in a district. To do so he fits a linear
regression of average yield per year against year after introduction of
"Miracle Wheat" for a ten year period. The fitted trend line is
YHAT(j) = 80 + 1.5*X(j)
(Y(j): Average yield in j year after introduction)
(X(j): j year after introduction).
a. What is the estimated average yield for the fourth year after
introduction?
b. Do you want to use this trend line to estimate yield for, say, 20
years after introduction? Why? What would your estimate be?
Back to this chapter's Contents
Q: In a linear regression, why do we need to be concerned with the range
of the independent (X) variable? (Be brief, coherent, and legible.)
Back to this chapter's Contents
Q: Define the following term and give an example of its use.
Your example should not be one given in class or in a handout.
Extrapolation
Back to this chapter's Contents
Q: Define the following term and give an example of its use.
Your example should not be one given in class or in a handout.
Interpolation
Back to this chapter's Contents
Q: A data set consists of:
Case X Y
1 7 101
2 9 119
3 1 121
4 5 108
5 2 112
a. What is Y(2)?
b. What is X(2)?
c. What is SUM(i=1,5) (X(i))?
d. What is SUM(i=1,5) (X(i)**2)?
e. Suppose that the relation between Y and X is said to be
Y(j) = 15 + 10*X.
1. What is YHAT(4)?
2. What is e(4)?
3. What is SUM(j=1,5) (e(j)**2) for this relation?
f. Plot Y vs X.
Back to this chapter's Contents
Q: Make a scatterplot for the following data.
X | Y
-------
1 | 2
4 | 8
0 | -1
3 | 6
Regression equation is: YHAT(i) = -.65 + 2.2X(i)
Back to this chapter's Contents
Q: Consider the following paired data:
X | 3 2 -1 -4
------------------------------
Y | -4 -1 2 3
a. Make a scatterplot for this data.
b. r**2 = (.93**2) = 0.871. What does it mean in this case?
Back to this chapter's Contents
Q: Consider the set of data below. Make a scatterplot. The
regression line is YHAT(i) = -8.26 + 1.17(X(i)). Plot it
(approximately) on your scatterplot.
X | 8 10 11 12
-------------------
Y | 2 2 4 7
Back to this chapter's Contents
Q: True or False? If False, correct it.
A scatter diagram is a graphic device for detecting and analyzing
association between two variables.
Back to this chapter's Contents
Q: Define the following term and give an example of its use.
Your example should not be one given in class or in a handout.
Scatter Diagram
Back to this chapter's Contents
Q: A researcher finds that the correlation between the personality
traits "greed" and "superciliousness" is -.40. What percentage of the
variation in greed can be explained by the relationship with
superciliousness?
a) 60%
b) 0%
c) 16%
d) 20%
e) 40%
Back to this chapter's Contents
Q: What model for Y is suggested by each of the following graphs?
a. Y b. Y
| |
| |
| *
| |
| * |
| |
| |
* |
| |
----------------------------> X ---------------*------------> X
c. | d. |
| | *
| | *
| | * *
| | *
| | *
| * * |
| | *
| |
| | *
| |
----------------------------> X ----------------------------> X
e. Y
|
| NOTE: In order to complete the
| above graphs, for a.-c.
| * connect the *'s with
| * * straight lines and for
| * d.-e. connect the *'s
| * with smooth curves.
|
*
|
----------------------------> X
Back to this chapter's Contents
Q: Suppose that you have at your disposal the information below for each
of 30 drivers. Propose a model (including a very brief indication of
symbols used to represent independent variables) to explain how miles
per gallon vary from driver to driver on the basis of the factors
measured.
Information:
1. miles driven per day
2. weight of car
3. number of cylinders in car
4. average speed
5. miles per gallon
6. number of passengers
Back to this chapter's Contents
Q: Suppose that you have been appointed Grand Nabob of Temperance. In
becoming a master of your new assignment you obtain the data listed
below on 20 seniors at UNH.
1. percent alcohol in blood
2. number of drinks consumed
3. weight
4. sex (male or female)
5. time spent in consuming drinks.
Propose a model that might be used to predict % alcohol in blood on the
basis of number of drinks, etc. (be sure to define symbols used for
independent variables).
Back to this chapter's Contents
Q: Suppose one collected the following information where X is diameter
of tree trunk and Y is tree height.
X Y
- -
4 8
2 4
8 18
6 22
10 30
6 8
Regression equation:
YHAT(i) = -3.6 + 3.1*X(i)
What is your estimate of the average height of all trees having a
trunk diameter of 7 inches?
Back to this chapter's Contents
Q: The manufacturers of a chemical used in flea collars claim that under
standard test conditions each additional unit of the chemical will
bring about a reduction of 5 fleas (i.e. where X(j) = amount of chemical
and Y(J) = B(0) + B(1)*X(J) + E(J), H(O): B(1) = -5)
Suppose that a test has been conducted and results from a computer
include: Intercept = 60
Slope = -4
Standard error of the regression coefficient = 1.0
Degrees of Freedom for Error = 2000
95% Confidence Interval for the slope -2.04, -5.96
Is this evidence consistent with the claim that the number of fleas is
reduced at a rate of 5 fleas per unit chemical?
Back to this chapter's Contents
Q: Suppose that a report contains this graph:
|
|
Annual Income |
(thousands of |
$ per year) |
|
50 + *
| *
|
|
|
|
|
|
| *
|
25 +
|
|
|
|
*
|
|
|
|
----------+---------+---------+---------->
10 20 30
Years of Experience in Trade
(Note: to complete graph, connect the *'s
with a smooth curve.)
a. What does the graph indicate as annual income for someone with no
experience in the trade?
b. Describe the relation between income and experience over the inter-
val from 0 to 20.
c. Describe the relation between income and experience over the inter-
val 20 to 30.
d. Describe the overall graph.
Back to this chapter's Contents
Q: Define the following term and give an example of its use.
Your example should not be one given in class or in a handout.
T TEST OF A REGRESSION COEFFICIENT
Back to this chapter's Contents
Q: When testing the estimate of a linear regression coefficient based on a
sample of 14 (X,Y) pairs, the calculated value of the F-statistic was
6.92 What is the smallest significance level at which you would re-
ject the hypothesis H(O): BETA = 0 against H(A): BETA =/= 0?
a. .01 d. .05
b. .02 e. .1
c. .025
Back to this chapter's Contents
Q: Y X(1) X(2)
--------------------------------
-2 1 -2
-1 2 0
6 3 0
9 6 2
The coefficient of multiple determination, calculated as:
R**2 = (explained variation using X(1) and X(2) in the
regression)/(total variation)
is:
a. 142/122
b. 74/86
c. a negative number
d. 185/122
e. None of the above
ANOVA
df SS MS F
Regression 2 74 37 3.08333333
Residual 1 12 12
Total 3 86
Back to this chapter's Contents
Q: An interpretation of r = 0.5 is that the following part of
the Y-variation is associated with variation in X:
a. most d. one quarter
b. half e. none of these.
c. very little
Back to this chapter's Contents
Q: Which of the following values of r indicates the most accurate
prediction of one variable from another?
a) r = 1.18 b) r = -.77 c) r = .68
Back to this chapter's Contents
Q: If the correlation between age of an auto and money spent for repairs
is +.90
a. 81% of the variation in the money spent for repairs is
explained by the age of the auto
b. 81% of money spent for repairs is unexplained by the age of
the auto
c. 90% of the money spent for repairs is explained by the age of
the auto
d. none of the above
Back to this chapter's Contents
Q: If the coefficient of correlation equals 0.61, it indicates that the
proportion of the variation in the dependent variable explained by the
variation in the independent variable is
a. 37% b. 61% c. 98% d. cannot be determined
Back to this chapter's Contents
Q: Suppose that college grade-point average and verbal portion of an IQ
test had a correlation of .40. What percentage of the variance do
these two have in common?
a. 20 b. 16 c. 40 d. 80
Back to this chapter's Contents
Q: True or False?
If in a given experiment r = 0.70, then 49 percent of the variation of
the Y's can be accounted for (is perhaps caused) by differences in the
variable X.
Back to this chapter's Contents
Q: True or false? If false, explain why.
The coefficient of determination can have values between
-1 and +1.
Back to this chapter's Contents
Q: True or False? If False, correct it.
With respect to regression, the sample correlation coefficient r is
the proportion of the variation in Y which is explained by Y's linear
dependence on X.
Back to this chapter's Contents
Q: We are interested in finding the linear relation between the number
of widgets purchased at one time and the cost per widget. The
following data has been obtained:
X: Number of widgets purchased-- 1 3 6 10 15
(in hundreds)
Y: Cost per widget(in dollars)--55 52 46 32 25
Suppose the correlation between X and Y is -0.95. Which of the
following conclusions is correct?
a. The linear relation between X and Y is weak, and Y decreases
when X increases.
b. The linear relation between X and Y is strong, and Y decreases
when X increases.
c. The linear relation between X and Y is strong, and Y increases
when X increases.
d. The linear relation between X and Y is weak, and Y increases
when X increases.
Back to this chapter's Contents
Q: Suppose pairs of data values (X(i),Y(i)) have been gathered and are
plotted on a diagram (given below). A statistician asserts that the
product-moment correlation between X and Y in this case is very low.
Which of the following comments makes the most sense?
Y| .
| . . .
| . . . .
| . .. .
| .. . . ..
| . .. . .
| . . . .
| .. . . .
| . . . . .
| . .. .
| .. . ..
| . . . .
| ..
|
|
|
|
|
|__________________________________________
X
a. The statistician is wrong, because knowing X lets us predict the
average value of Y quite accurately.
b. The statistician is wrong, because X and Y increase and decrease
together.
c. The statistician is right, because the correlation measures how
much linear relationship there is, and the relationship is cer-
tainly not linear.
Back to this chapter's Contents
Q: Consider a sample least squares regression analysis between a dependent
variable (Y) and an independent variable (X). A sample correlation
coefficient of -1 (minus one) tells us that
a. there is no relationship between Y and X in the sample
b. there is no relationship between Y and X in the population
c. there is a perfect negative relationship between Y and X in the
population
d. there is a perfect negative relationship between Y and X in the
sample.
Back to this chapter's Contents
Q: In a study of the relationship between intelligence and achievement,
scores on the Dorge-Thorndike Intelligence Test and the Stanford
Achievement Test are collected from a large group of students. The
appropriate statistical analysis is:
a) the correlation coefficient
b) the analysis of variance.
c) the t-test
Back to this chapter's Contents
Q: In a study of the relationship between self-concept and achievement, a
correlation of 0.75 was found. This indicates that the relationship
between these two variables is:
a) weak and positive
b) strong and positive
c) weak and negative
d) strong and negative
e) one of independence
Back to this chapter's Contents
Q: The figure below indicates that Variable A and Variable B are:
|
High | *
| * A
| * *
| * *
| * * *
|
| * *
Variable | *
B | * *
| * *
| * * *
| * *
| *
| *
Low | * B
-------------------------------------------->
Low High
Variable A
NOTE: Connect letters A and B with a straight line segment to complete
the figure.
a. positively related
b. negatively related
c. independent
Back to this chapter's Contents
Q: The correlation between Variable A and Variable B in the figure below
indicates that:
|
High | *
| * A
| * *
| * *
| *
| * *
| * *
Variable | * * *
B | * *
| * * * *
| * * * *
| * * * *
| *
| * *
| * *
Low | * * B *
---------------------------------------->
Low High
Variable A
NOTE: Connect letters A and B with a straight line segment to complete
the figure.
a. increases in Variable A cause decreases in Variable B.
b. increases in Variable A are accompanied by decreases in Variable B.
c. increases in one variable are unrelated to increases in the other.
Back to this chapter's Contents
Q: The correlation between anxiety and performance on complex tasks is
-0.73. Which of the following may be concluded?
a. as anxiety increases, performance on complex tasks improves;
b. as performance on complex tasks improves, anxiety tends to decrease;
c. high levels of anxiety cause poor performance on complex tasks;
d. as anxiety decreases, so does performance.
Back to this chapter's Contents
Q: If we obtain a negative r (Pearson r: a coefficient of correlation)
this means that: (let's say r is -.75)
a. individuals scoring high on one variable tend to score low
on the other variable.
b. individuals scoring high on one variable tend to score high
on the other variable.
c. there is no relationship between the two variables.
d. the relationship is in the opposite direction to the one pre-
dicted.
e. we have made an error.
Back to this chapter's Contents
Q: A correlation between college entrance exam grades and scholastic
achievement was found to be -1.08. On the basis of this you would
tell the university that:
a. the entrance exam is a good predictor of success.
b. they should hire a new statistician.
c. the exam is a poor predictor of success.
d. students who do best on this exam will make the
worst students.
e. students at this school are underachieving.
Back to this chapter's Contents
Q: Under a "scatter diagram" there is a notation that the coefficient of
correlation is .10. What does this mean?
a. plus and minus 10% from the means includes about 68% of the
cases
b. one-tenth of the variance of one variable is shared with the
other variable
c. one-tenth of one variable is caused by the other variable
d. on a scale from -1 to +1, the degree of linear relationship
between the two variables is +.10
Back to this chapter's Contents
Q: Which, if any, of the values listed below for a correlation coefficient
indicate a situation where more than half of the variation in one
variable is associated with variation in the other variable?
a. r = -.7
b. r = .3
c. r = -.9
d. r = .6
e. r = 1.0
Back to this chapter's Contents
Q: ] X
25-]
]
20-] X
] X
Tail 15-] X
Length ] X
10-] X
]
5-X X
]
]____X______________________
0 5 10
Horn Length
On the basis of the above plot of horn length versus tail length of
peppermint flavored unicorns, what is the approximate value of the
correlation coefficient?
a. -1
b. -.6
c. 0
d. +.6
e. +1
Back to this chapter's Contents
Q: The correlation coefficient for X and Y is known to be zero. We then
can conclude that:
a. X and Y have standard distributions
b. the variances of X and Y are equal
c. there exists no relationship between X and Y
d. there exists no linear relationship between X and Y
e. none of these
Back to this chapter's Contents
Q: Suppose the Pearson correlation coefficient between height as measured
in feet versus weight as measured in pounds is 0.40. What is the cor-
relation coefficient of height measured in inches versus weight measured
in ounces? [12 inches = one foot; 16 ounces = one pound]
a. .4 d. cannot be determined from information given
b. .3 e. none of these
c. .533
Back to this chapter's Contents
Q: In a study to determine the relationship between two variables, a
coefficient of correlation of -.90 was obtained. This indicates
a. The computations are wrong since r cannot be negative
b. There is a fairly low relationship between the two
variables
c. The coefficient of determination is the square root of .90
d. Variable Y tends to decrease as Variable X increases
Back to this chapter's Contents
Q: A coefficient of correlation of -.80
a. is lower than r=+.80
b. is the same degree of relationship as r=+.80
c. is higher than r=+.80
d. no comparison can be made between r=-.80 and r=+.80
Back to this chapter's Contents
Q: What would you guess the value of the correlation coefficient to be for
the pair of variables: "number of man-hours worked" and "number of
units of work completed"?
a) Approximately 0.9
b) Approximately 0.4
c) Approximately 0.0
d) Approximately -0.4
e) Approximately -0.9
Back to this chapter's Contents
Q: In a given group, the correlation between height measured in feet and
weight measured in pounds is +.68. Which of the following would alter
the value of r?
a. height is expressed centimeters.
b. weight is expressed in Kilograms.
c. both of the above will affect r.
d. neither of the above changes will affect r.
Back to this chapter's Contents
Q: The sign (plus or minus) of a correlation coefficient indicates
a. the direction of the relationship.
b. the practical importance of the relationship.
c. the probability that the degree of relationship is greater than
zero.
d. the statistical significance of the relationship.
Back to this chapter's Contents
Q: The correlation between scores on a neuroticism test and scores on an
anxiety test is high and positive; therefore
a. anxiety causes neuroticism.
b. those who score low on one test tend to score high on the other.
c. those who score low on one test tend to score low on the other.
d. no prediction from one test to the other can be meaningfully made.
Back to this chapter's Contents
Q: In correlational analysis, when the points scatter widely about the
regression line, this means that the correlation is
a. negative.
b. low.
c. heterogeneous.
d. between two measures that are unreliable.
Back to this chapter's Contents
Q: Explain what correlation coefficients of -1, 0 and 1 mean, using
graphs to illustrate. What is the accuracy of prediction in each
of these three cases given by YHAT = a + b*X and why?
Back to this chapter's Contents
Q: Body weight (pounds) was correlated with an exercise variable (as
measured by Balke Treadmill Test) on n=14 college men. If an r=0.01
was obtained, what conclusions might be drawn?
Back to this chapter's Contents
Q: If one obtained an r = -.23 between wrestling ability and performance
on a 50 yd. sprint run when testing 30 individuals, then one would be
just as well off in prediction by just "flipping a coin" for each per-
son to determine wrestling ability. EXPLAIN THIS STATEMENT.
Back to this chapter's Contents
Q: Write an interpretation of each of the following correlations:
a) GIVEN: r(X,Y) = -.68
X = New York State Endurance Test
Y = Fleishman's 600 yd. run
Group = 11 college PE majors
b) GIVEN: r(X,Y) = .255
X = speed of movement: foot reaction time
Y = speed of movement: sprint running
Group = 32 college PE majors
c) GIVEN: r(X,Y) = .00
X = standing height
Y = flexibility (trunk twist)
Group = 25 college PE majors
d) GIVEN: r(X,Y) = .902
X = right grip strength
Y = left grip strength
Group = 25 college PE majors
Back to this chapter's Contents
Q: Discuss briefly the distinction between correlation and causality.
Back to this chapter's Contents
Q: True or False?
If r is close to + or -1, we shall say there is a strong correlation,
with the tacit understanding that we are referring to a linear rela-
tionship and nothing else.
Back to this chapter's Contents
Q: True or False? If false, correct it.
If we know that the simple linear correlation coefficient is positive
for pairs of observations (X(i),Y(i)), then geometrically speaking the
regression of Y on X yields a regression line that slopes downward
going from left to right.
Back to this chapter's Contents
Q: True or False? If false, correct it.
A correlation coefficient, r, measures the strength of the linear rela-
tionship between variables and is proof of a cause-effect relationship
between the variables.
Back to this chapter's Contents
Q: True or False?
It is safer to interpret correlation coefficients as measures of
association rather than causation because of the possibility of
spurious correlation.
Back to this chapter's Contents
Q: True or False?
Whenever r is calculated on the basis of a sample, the value which we
obtain for r is only an estimate of the true correlation coefficient
which we would obtain if we calculated it for the entire population.
Back to this chapter's Contents
Q: Define the following term and give an example of its use.
Your example should not be one given in class or in a handout.
Correlation Coefficient
Back to this chapter's Contents
Q: Define the following term and give an example of its use.
Your example should not be one given in class or in a handout.
Simple Correlation or Simple Regression
Back to this chapter's Contents
Q: A sample survey was conducted to study the relationship between
education and residence. The following data were collected:
No. of Persons Mean Number of Years
Residence in Sample of School Completed
Urban 40 11
Rural 40 9
a) Complete the following Analysis of Variance Table for this
data:
Source of
Variation df SS MS F
Among Residences 1 80 __ __
Within Residences 78 390 __
Total 79 470
b) What hypothesis does the above F-value test?
c) What do you conclude? Give the proper F-value from the
table for ALPHA = .05.
Back to this chapter's Contents
Q: Thirty patients in a leprosorium were randomly selected to be treated
for several months with one of the following:
A - an antibiotic
B - a different antibiotic
C - an inert drug used as a control
At the end of the test period, laboratory tests were conducted to
provide a measure of abundance of leprosy bacilli in each patient.
Scores obtained were:
Patient 1 2 3 4 5 6 7 8 9 10
Drug A 6 0 2 8 11 4 13 1 8 0
Drug B 0 2 3 1 18 4 14 9 1 9
Drug C 13 10 18 5 23 12 5 16 1 20
Analyze and interpret the results of this trial assuming that
a oneway ANOVA already rejected the null hypothesis that all
drugs are equal. (use ALPHA = .05).
Using the program CARROT*** you get the following results:
Means for Antibiotics
Treatment Mean (leprosy bacilli)
Placebo 12.3
Drug A 5.3
Drug B 6.1
Tukey's HSD (at ALPHA = .05) = 5.57113
Back to this chapter's Contents
Q: Individual statistical comparisons between pairs of means
in an analysis of variance must be preceded by:
a. a demonstrated significant correlation between the means
b. a significant over-all F value
c. neither of the above
d. both of the above
Back to this chapter's Contents
Return to the list of chapters
Return to Brian Schott @ GSU
A: d. measures of traits A and B on each subject in one group
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: False. Since H(O): BETA = -1 would not be rejected at ALPHA = 0.05,
it would not be rejected at ALPHA = 0.01.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: a. The population value for BETA(2), the change that occurs in Y
with a unit change in X(2), when the other variables are held
constant.
b. The population value for the standard error of the distribution
of estimates of BETA(2).
c. .8, .1, 16 = 20 - 4.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: a. -.72, .32
b. the t value
c. the t value
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: True.
t(critical, df = 23, two-tailed, ALPHA = .02) = +/- 2.5
t(critical, df = 23, two-tailed, ALPHA = .01) = +/- 2.8
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: d. YHAT = -15 dollars, which is obvious nonsense. This reminds us
that predicting Y outside the range of X values in our data is a
very poor practice.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: I would recommend only 3 coins because not having any observations over
3 coins, I have no idea what may happen when extrapolating. Another
factor may enter the problem at higher levels that may be very
unpleasant. Don't forget that kings can be very nasty people, liable to
chop off heads as their whims take them.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: a. 80 + 1.5*4 = 86
b. No. I would not want to extrapolate that far. If I did, my estimate
would be 110, but some other factors probably come into play with
20 years.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: The precision of the estimate of the Y variable depends on the range of
the independent (X) variable explored. If we explore a very small range
of the X variable, we won't be able to make much use of the regression.
Also, extrapolation is not recommended.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: Definition: The act of making an estimate of response outside the
observed range of the independent variable or outside
the observed region of a set of independent variables.
This is usually regarded as a dangerous pasttime.
Example: Suppose that relative sobriety has been observed for
some person at various times after consumption of 1/10,
2/10, and 3/10 of some alcoholic drink. Suppose that
the relation between relative sobriety and number of
drinks is described exactly by a straight line:
Sobriety(i) = 1.0 - .01 X(i), (X(i) = no. of drinks).
If we use this relation to estimate relative sobriety
for less than 1/10 drink or more than 3/10 drink, we
will have indulged in extrapolation. e.g. If we ask
what will be relative sobriety after 5 drinks, the above
expression says that it will be .95 (95% of sobriety
when no drinks have been consumed). This may or may
not be a reasonable estimate depending on how well
reaction in the range 1/10 to 3/10 agrees with what
happens around 5. Many would suspect substantial
disagreement in this case.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: Definition: The act of making an estimate of response within the
observed range of the independent variable or within
the observed region of a set of independent variables.
While this is usually regarded as a reasonably safe
undertaking, it should be noted that there have been
some famous cases where responses show irregular
behavior that is most disrespectful of interpolation.
Example: Suppose that relative sobriety has been observed for
some person at various times after consumption of 1,2,3,
and 5 portions of some alcoholic beverage. Suppose that
the observed responses agree perfectly with
Sobriety(i) = 1.0 - .01X(i) - .01X(i)**2
(X(i): no. of drinks)
If we ask what will be sobriety at 4 drinks, we obtain
estimated sobriety as 1.0 - .01(4) - .01(16) = .8.
The process of obtaining this estimate is called inter-
polation. While it is regarded as much less dangerous
than extrapolation, it too can go awry if there are
peculiar squiggles in the true relation between
sobriety and number of drinks around 4 drinks.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: a. 119
b. 9
c. 7+9+1+5+2=24
d. 49+81+1+25+4=160
e. 1. YHAT(4) = 15 + (10*5) = 65
2. 108 - 65 = 43
3. j e(j) e(j)**2
1 16 256
2 14 196
3 96 9216
4 43 1849
5 77 5929
SUM (e(j)**2) = 17446
f. Y |
|
| *
120 +
| *
|
|
|
115 +
|
|
| *
|
110 +
|
| *
|
|
105 +
|
|
|
| *
100 +
|
/
|
-----+----+----+----+----+----+----+----+----+------> X
1 2 3 4 5 6 7 8 9
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: N = 4
Plotting Points:
YHAT(A) = -.65 + 2.2(1) = 1.55; Pt. A (1,1.5)
YHAT(B) = -.65 + 2.2 (3.5) = 7.05; Pt. B (3.5,7)
|
|
8 + x
|
7 + B
|
6 + x
|
Y 5 +
|
4 +
|
3 +
|
2 + x
| A
1 +
|
0 ----+---+---+---+---+---+---+---+---+---+---+---+--->
| 1 2 3 4 5 6
-1 x X
|
|
Note: - Connect points A and B with a straight line to
obtain the graph of the regression line.
- x denotes points in the data set.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: a.
Y
- 4
|
|
x - 3
|
|
x - 2
|
|
- 1
|
|
-------|----|----|----|----|----|----|----|----|----------- X
-4 -3 -2 -1 |0 1 2 3 4
|
- -1 x
|
|
- -2
|
|
- -3
|
|
- -4 x
b. This means that 87.1% of the variation in the Y variable is
explained by the X variable.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: Scatterplot:
|
|
12 +
|
11 +
|
10 +
|
9 +
Y |
8 +
|
7 + x
|
6 + B
|
5 +
|
4 + x
|
3 +
|
2 + x x
|
1 +
|
-----+----+----+----+----+----+----A----+----+----+----+----+-->
0 1 2 3 4 5 6 7 8 9 10 11 12
X
NOTE: - x indicates data points.
- connect points A and B with a straight line to get
an approximation of the regression line.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: True.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: Definition: A graph in which values of one variable (i.e. X) are
plotted against corresponding values of another vari-
able (i.e. Y).
Example: Suppose that a data set is:
Happiness (Y) No. of Wives (X)
10 0
7 1
5 2
8 1
7 2
4 3
9 0
Scatter diagram for this set is:
|
Y |
|
10 x
Happiness |
9 x
|
8 + x
|
7 + x x
|
6 +
|
5 + x
|
4 + x
|
|
----+---+---+---------------------> X
0 1 2 3
No. of Wives
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: c) 16%
(-.4)**2 = .16 or 16 percent
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: a. Y(j) = b(0) + b(1)*X(j) + e(j)
b. Y(j) = b(0) - b(1)*X(j) + e(j)
c. Y(j) = YBAR + e(j)
d. Y(j) = b(0) + b(1)*X(j) + b(11)*X(j)**2 + b(111)*X(j)**3 + e(j)
e. Y(j) = b(0) + b(1)*X(j) + b(11)*X(j)**2 + e(j)
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: Y(j) = b(0) + b(1)*X(1) + b(2)*X(2) + b(3)*X(3) + b(4)*X(4) + b(5)*X(6)
+ e(j)
where the dependent variable is variable 5 - miles per gallon and the
independent variables are
X(1) - miles driven per day
X(2) - weight of car
X(3) - number of cylinders in car
X(4) - average speed
X(6) - number of passengers
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: Y = B(0) + B(1)*X(2) + B(2)*X(3) + B(3)*X(5)
where Y is the estimated response - % alcohol in blood
and the independent variables are
X(2) - number of drinks consumed
X(3) - weight
X(5) - time spent in consuming drinks
I have excluded sex from my proposed model because I don't think it
would have much of an effect on the percent of alcohol in blood.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: YHAT = -3.6 + (3.1 * 7)
= 18.1
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: Most simply, since -5 is included in the confidence interval for the
slope, we can conclude that the evidence is consistent with the claim
at the 95% confidence level.
Using a t test: H(O): B(1) = -5
H(A): B(1) =/= -5
t(calculated) = (-5 - (-4))/1 = -1
t(critical) = -1.96
Since t(calc) < t(crit) we retain the null hypothesis that B(1) = -5.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: a. Around 12,500 dollars per year.
b. There appears to be approximately a straight line relation in which
income increases with experience over the interval from 0 to 20.
(There seems to be some curvature or flattening for experience near
20.) The change in income in this range is from around 12.5 to
around 48, so the rate of increased income is roughly $35,500/20 =
$1775 per year.
c. The relation between experience and income for experience between
20 and 30 years also appears to be roughly a straight line, but a
flat straight line, indicating that income stays roughly constant
at a little less than $50,000 per year.
d. The overall graph indicates income initially around $12,500 (no ex-
perience), increasing income in the range from 0 to 20 years exper-
ience, approaching a limit that seems to be a little below $50,000.
That limit seems to be reached sometime between 10 and 25 years.
(Income seems to remain about constant afterward.)
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: Definition: A t test is obtained by dividing a regression coefficient
by its standard error and then comparing the result to
critical values for Students' t with Error df. It provides
a test of the claim that BETA(i) = 0 when all other
variables have been included in the relevant regression
model.
Example: Suppose that 4 variables are suspected of influencing
some response. Suppose that the results of fitting:
Y(i) = BETA(0) + BETA(1)X(1i) + BETA(2)X(2i) + BETA(3)
X(3i) + BETA(4)X(4i) + e(i) include:
Variable Regression coefficient Standard error of
reg. coef.
1 -3 .5
2 +2 .4
3 +1 .02
4 -.5 .6
t calculated for variables 1, 2, and 3 would be 5 or
larger in absolute value while that for variable 4 would be
less than 1. For most significance levels, the hypothesis
BETA(1) = 0 would be rejected. But, notice that this is
for the case when X(2), X(3), and X(4) have been included
in the regression. For most significance levels, the
hypothesis BETA(4) = 0 would be continued (retained) for
the case where X(1), X(2), and X(3) are in the regression.
Often this pattern of results will result in computing
another regression involving only X(1), X(2), X(3), and
examination of the t ratios produced for that case.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: c. .025
F(critical, df = 1,12, ALPHA = .025) = 6.55
F(critical, df = 1,12, ALPHA = .01) = 9.33
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: b. 74/86
Coeff. of Mult. Det. = explained variation / total variation
= SUM((Y(est) - YBAR)**2) / SUM((Y - YBAR)**2)
= 74/86
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: d. one quarter
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: b) r = -.77
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: a. 81% of the variation in the money spent for repairs is explained
by the age of the auto
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: a. 37%
r = 0.61
r**2 = .37 (coefficient of determination)
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: b. 16
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: True
.7**2 = .49 = 49%.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: False.
The coefficient of determination is r**2 with 0 <= r**2 <= 1,
since -1 <= r <= 1.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: False, the sample correlation coefficient squared (r**2) is the pro-
portion of variation in Y which is explained by Y's linear dependence
on X.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: b. The linear relation between X and Y is strong, and Y decreases
when X increases.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: c. The statistician is right, because the correlation measures how
much linear relationship there is, and the relationship is cer-
tainly not linear.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: d. there is a perfect negative relationship between Y and X in the
sample.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: a) the correlation coefficient.
Of these four tests only the correlation coefficient gives a
measure of the relationship between variables.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: b) strong and positive
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: b. negatively related
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: b. increases in Variable A are accompanied by decreases in Variable B.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: b. as performance on complex tasks improves, anxiety tends to decrease.
(c.) is objectionable because of the word "cause". Correlation
alone does not support "cause and effect" relationships.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: a. individuals scoring high on one variable tend to score low
on the other variable.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: b. they should hire a new statistician.
Correlation scores range from -1 to 1.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: d. on a scale from -1 to +1, the degrees of linear relationship between
the two variables is +.10
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: c and e, since r**2 is greater that .5 in each case.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: d.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: d. there exists no linear relationship between X and Y
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: a. .4
Correlation coefficient will remain the same.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: d. Variable Y tends to decrease as Variable X increases
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: b. is the same degree of relationship as r=+.80
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: a) Approximtely 0.9
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: d. neither of the above changes will affect r.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: a. the direction of the relationship.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: c. those who score low on one test tend to score low on the other.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: b. low.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A:
| r = 1
|
| *
|
| *
|
Y | *
|
|
| *
|
|*
------------------------->
X
(Connect the points to form a straight line.)
If X is one variable and Y the other, when r=1 we have all ordered
pairs (X,Y) on a straight line as shown. Thus, as one variable
increases, the other does also in such a way that each ordered pair
(X,Y) of values lies on the line. This is the strongest possible
direct relationship.
| r = -1
|
|*
|
| *
|
| *
Y |
| *
|
| *
|
| *
--------------------------->
X
(Connect the points to form a straight line.)
When r=-1, we have all ordered pairs on a straight line as shown.
Thus, as one variable increases, the other decreases in such a way
that each ordered pair (X,Y) of values lies on a line. This is the
strongest possible inverse relationship.
| r = 0
|
| * * *
|* * *
| * *
| * **
Y | * * *
| * ** *
|
| ** ****
| * * *
|** ** * * *
----------------------->
X
When r=0, there is no linear relationship between X and Y. The points
have no linear pattern.
The formula given predicts Y given X perfectly if r=-1 or r=1 and
extremely poorly if r=0. The closer to 1 or -1 r is, the better a
predictor of Y given by the formula.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: No information is provided on diet, so no conclusions can be drawn.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: An r value of -.23 is so small that it would probably not prove to
be significant. Therefore, one can assume that there is no corre-
lation between wrestling ability and time to run a 50 yd. sprint.
The 50 yard sprint is as poor in predicting wrestling ability as is
flipping a coin for each person to determine wrestling ability.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: a) The moderately high inverse correlation between X and Y suggests
that PE majors who score high on the New York State Endurance Test
tend to complete the 600 yd. run in less time.
b) The correlation coefficient is positive but weak. Therefore, one
can conclude that there is little relationship between speed of
movement: foot reaction time and speed of movement: sprint running
for PE majors.
c) Since r = 0, there is no relationship between standing height and
flexibility (trunk twist) for PE majors.
d) The high, positive correlation coefficient suggests a strong
relationship between right grip strength and left grip strength
for PE majors.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: Some variables seem to be related, so that knowing one variable's
status allows us to predict the status of the other. This
relationship can be measured and is called correlation. However, a
high correlation between two variables in no way proves that a cause
and effect relation exists between them. It is entirely possible that
a third factor causes both variables to vary together.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: True
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: False, it slopes upward going from left to right.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: False, it does not provide any proof of a cause-effect relationship.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: True
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: True
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: Definition: A measure of the degree to which variation of one
variable is related to variation in one or more
other variables. The most commonly used correlation
coefficient indicates the degree to which variation
in one variable is described by a straight line
relation with another variable.
Example: Suppose that sample information is available on
Family income and Years of schooling of the head
of the household. A correlation coefficient = 0
would indicate no linear association at all between
these two variables. A correlation of 1 would indicate
perfect linear association (where all variation in
family income could be associated with schooling and
vice versa).
Symbol: r
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: Definition: Correlation or regression involving two variables -
one of which may be regarded as dependent and one
which may be regarded as independent.
Example: Suppose that we collect data on the height, weight,
and a number of additional characteristics of 100
college students. If we calculate a correlation
using just the data for height and weight, that
correlation is called a simple correlation. If we
calculate a regression of, say, weight on height,
that regression is called a simple regression.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: a) Source of
Variation df SS MS F
Among Residences 1 80 80 16
Within Residences 78 390 5
Total 79 470
b) H(0): MU(1) = MU(2)
or no difference in mean number of years of school completed
by residences.
c) F(critical, df = 1, 78, ALPHA = .05, onetail) == 3.96
Reject H(0) and conclude that difference is significant with
urban residents having a higher mean number of years of
school.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: HSD tests on means:
H(0): XBAR(1) - XBAR(2) = 0
H(A): XBAR(1) - XBAR(2) =/= 0
(XBAR(1) - XBAR(2)) +/- HSD
Placebo and drug B
6.2 +/- 5.57
Interval is from +.63 to +11.77
The interval does not contain zero, therefore, we reject H(0).
Since both antibiotic treatments are significantly different from
the placebo, one would conclude that they have a significant effect
on reducing leprosy bacilli. However, antibiotics A and B are not
significantly different from each other. The differences in their
means could be attributed to chance variation alone.
Back to review this question
Look at this question's identification
Back to this chapter's Contents
A: b. a significant over-all F value
Back to review this question
Look at this question's identification
Back to this chapter's Contents
Return to the list of chapters
Return to Brian Schott @ GSU
Item is still being reviewed
Multiple Choice
EXPERDESIGN/TERM DESIGN CONCEPT
CORRELATION/P ANOVA PARAMETRIC
STATISTICS
T= 2 Comprehension
D= 1 General
Back to this chapter's Contents
Item is still being reviewed
True/False
SIMPLE/REG CONFIDENCEINTERV TESTOFSIGNIFICAN
REGRESSION PARAMETRIC STATISTICS
ESTIMATION CONCEPT
T= 2 Comprehension
D= 5 General
Back to this chapter's Contents
Based upon item submitted by A. Bugbee - UNH
Fill-in
MULTIPLE/REG OTHER/CI STANDERROR/OTHER
REGRESSION PARAMETRIC STATISTICS
CONFIDENCEINTERV ESTIMATION CONCEPT
DESCRSTAT/P
T= 5 Computation Comprehension
D= 3 General
***Multiple Parts***
Back to this chapter's Contents
Based upon item submitted by J. Warren - UNH
Short Answer
MULTIPLE/REG OTHER/CI
MODEL DEGREESOFFREEDOM I650A
REGRESSION PARAMETRIC STATISTICS
CONFIDENCEINTERV ESTIMATION CONCEPT
ANOVA
T= 5 Computation Comprehension
D= 5 General
***Multiple Parts***
Back to this chapter's Contents
Based upon item submitted by D. Kleinbaum - Univ of North Carolina
True/False
TESTOFSIGNIFICAN TWOTAIL/T SIMPLE/REG
CONCEPT STATISTICS TTEST
PARAMETRIC REGRESSION
T= 2 Comprehension
D= 4 General
***Statistical Table Necessary***
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
SCOPEOFINFERENCE SIMPLE/REG
CONCEPT STATISTICS REGRESSION
PARAMETRIC
T= 5 Comprehension
D= 3 General Business
Back to this chapter's Contents
Item is still being reviewed
Short Answer
OTHER/REG SCOPEOFINFERENCE
COMMONPITFALLS I650A REGRESSION
PARAMETRIC STATISTICS CONCEPT
T= 5 Comprehension
D= 4 General
Back to this chapter's Contents
Based upon item submitted by J. Warren - UNH
Short Answer
SIMPLE/REG SCOPEOFINFERENCE
MODEL I650A REGRESSION
PARAMETRIC STATISTICS CONCEPT
T= 5 Comprehension Computation
D= 4 Natural Sciences Biological Sciences
***Multiple Parts***
Back to this chapter's Contents
Based upon item submitted by J. Inglis
Short Answer
SIMPLE/REG SCOPEOFINFERENCE
REGRESSION PARAMETRIC STATISTICS
CONCEPT
T= 2 Comprehension
D= 3 General
Back to this chapter's Contents
Based upon item submitted by J. Warren - UNH
Definition
BASICTERMS/REG SCOPEOFINFERENCE
RANGE I650A REGRESSION
PARAMETRIC STATISTICS CONCEPT
VARIABILITY/NP DESCRSTAT/NP NONPARAMETRIC
T= 5 Comprehension
D= 3 General
Back to this chapter's Contents
Based upon item submitted by J. Warren - UNH
Definition
BASICTERMS/REG SCOPEOFINFERENCE
I650A REGRESSION PARAMETRIC
STATISTICS CONCEPT
T= 5 Comprehension
D= 3 General
Back to this chapter's Contents
Based upon item submitted by J. Warren - UNH
Numerical Answer
SIMPLE/REG SCATDIAGRAM/P
I650A REGRESSION PARAMETRIC
STATISTICS DESCRSTAT/P
T= 5 Comprehension
D= 3 General
***Multiple Parts***
Back to this chapter's Contents
Item is still being reviewed
Numerical Answer
SCATDIAGRAM/P SIMPLE/REG SIMPLE/COR
DESCRSTAT/P PARAMETRIC STATISTICS
REGRESSION CORRELATION/P
T=15 Computation
D= 5 General
Back to this chapter's Contents
Item is still being reviewed
Numerical Answer
SCATDIAGRAM/P SIMPLE/COR COEFFDETERMINAT
DESCRSTAT/P PARAMETRIC STATISTICS
CORRELATION/P REGRESSION
T=10 Computation Comprehension
D= 5 General
***Calculator Necessary***
***Graph or Chart Necessary***
***Multiple Parts***
Back to this chapter's Contents
Item is still being reviewed
Numerical Answer
SCATDIAGRAM/P SIMPLE/REG
DESCRSTAT/P PARAMETRIC STATISTICS
REGRESSION
T=15 Computation
D= 5 General
***Calculator Necessary***
***Graph or Chart Necessary***
Back to this chapter's Contents
Item is still being reviewed
True/False
SCATDIAGRAM/P
DESCRSTAT/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Item is still being reviewed
Definition
SCATDIAGRAM/P
I650A DESCRSTAT/P PARAMETRIC
STATISTICS
T= 5 Comprehension
D= 3 General
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
SIMPLE/COR VARIABILITY/P
CORRELATION/P PARAMETRIC STATISTICS
DESCRSTAT/P
T= 2 Computation
D= 3 Psychology General
Back to this chapter's Contents
Based upon item submitted by J. Warren - UNH
Short Answer
MODEL OTHER/REG POPULATIONMODELS
TYPICALPIC/GRAPH I650A REGRESSION
PARAMETRIC STATISTICS DESCRSTAT/P
T= 5 Comprehension
D= 3 General
***Multiple Parts***
Back to this chapter's Contents
Item is still being reviewed
Short Answer
MULTIPLE/REG POPULATIONMODELS
MODEL I650A REGRESSION
PARAMETRIC STATISTICS DESCRSTAT/P
T=10 Comprehension
D= 4 General Natural Sciences
Back to this chapter's Contents
Based upon item submitted by J. Warren - UNH
Short Answer
MULTIPLE/REG POPULATIONMODELS
MODEL I650A REGRESSION
PARAMETRIC STATISTICS DESCRSTAT/P
T= 5 Application
D= 4 Biological Sciences General
Back to this chapter's Contents
Item is still being reviewed
Numerical Answer
VARIANCE/OTHER SIMPLE/REG STANDERROR/OTHER
DESCRSTAT/P PARAMETRIC STATISTICS
REGRESSION
T= 2 Application Computation
D= 2 Biological Sciences General
***Calculator Necessary***
Back to this chapter's Contents
Based upon item submitted by J. Warren - UNH
Short Answer
SIMPLE/REG TWOTAIL/T STANDERROR/OTHER
I650A REGRESSION PARAMETRIC
STATISTICS TTEST DESCRSTAT/P
TESTOFSIGNIFICAN CONCEPT
T=10 Application
D= 6 General
***Statistical Table Necessary***
Back to this chapter's Contents
Item is still being reviewed
Short Answer
GRAPH/PICTOGRAPH
DESCRSTAT/P PARAMETRIC STATISTICS
T=10 Comprehension
D= 2 General Economics Business
***Multiple Parts***
Back to this chapter's Contents
Based upon item submitted by J. Warren - UNH
Definition
REGRESSION TTEST
I650A PARAMETRIC STATISTICS
T= 5 Comprehension
D= 4 General
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
SIMPLE/REG
FTEST PARAMETRIC STATISTICS
REGRESSION
T= 5 Comprehension
D= 5 General
***Statistical Table Necessary***
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
COEFFDETERMINAT
REGRESSION PARAMETRIC STATISTICS
T=10 Computation
D= 6 General
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
SIMPLE/COR COEFFDETERMINAT
CORRELATION/P PARAMETRIC STATISTICS
REGRESSION
T= 2 Comprehension
D= 3 General
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
SIMPLE/COR COEFFDETERMINAT
CORRELATION/P PARAMETRIC STATISTICS
REGRESSION
T= 2 Comprehension
D= 3 General
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
COEFFDETERMINAT SIMPLE/COR
REGRESSION PARAMETRIC STATISTICS
CORRELATION/P
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
COEFFDETERMINAT
REGRESSION PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
COEFFDETERMINAT
REGRESSION PARAMETRIC STATISTICS
T= 2 Comprehension Computation
D= 4 General Education Psychology
Back to this chapter's Contents
Item is still being reviewed
True/False
SIMPLE/COR COEFFDETERMINAT
CORRELATION/P PARAMETRIC STATISTICS
REGRESSION
T= 2 Comprehension
D= 3 General
Back to this chapter's Contents
Item is still being reviewed
True/False
SIMPLE/COR COEFFDETERMINAT
CORRELATION/P PARAMETRIC STATISTICS
REGRESSION
T= 2 Computation
D= 2 General
Back to this chapter's Contents
Item is still being reviewed
True/False
COEFFDETERMINAT CORRELATION/P
REGRESSION PARAMETRIC STATISTICS
T= 2 Comprehension
D= 5 General
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Based upon item submitted by F. J. Samaniego - UC Davis
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Based upon item submitted by A. Bugbee - UNH
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Based upon item submitted by R. Shavelson - UCLA
Multiple Choice
SIMPLE/COR
ANOVA TTEST CORRELATION/P
PARAMETRIC STATISTICS NONPARAMETRIC
T= 5 Comprehension
D= 4 General Education Psychology
Back to this chapter's Contents
Based upon item submitted by W. Dixon - UCLA
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 Psychology
Back to this chapter's Contents
Based upon item submitted by R. Shavelson - UCLA
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Based upon item submitted by R. Shavelson - UCLA
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Based upon item submitted by R. Shavelson - UCLA
Multiple Choice
SIMPLE/COR
I650A CORRELATION/P PARAMETRIC
STATISTICS
T= 2 Comprehension
D= 3 Psychology
Back to this chapter's Contents
Based upon item submitted by W. J. Hall - Univ. of Rochester
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 1 General
Back to this chapter's Contents
Based upon item submitted by W. J. Hall - Univ. of Rochester
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 1 General
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Based upon item submitted by J. Warren - UNH
Multiple Choice
SIMPLE/COR
I650A CORRELATION/P PARAMETRIC
STATISTICS
T= 2 Comprehension
D= 3 General
Back to this chapter's Contents
Based upon item submitted by J. Warren - UNH
Multiple Choice
SIMPLE/COR
I650A CORRELATION/P PARAMETRIC
STATISTICS
T= 2 Comprehension
D= 3 General
Back to this chapter's Contents
Based upon item submitted by J. Inglis
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 4 General
Back to this chapter's Contents
Based upon item submitted by J. Inglis
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 3 General
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 Business Economics
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 Psychology General
Back to this chapter's Contents
Item is still being reviewed
Multiple Choice
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Based upon item submitted by J. Mowbray - Shippensburg State
Essay
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T=10 Comprehension
D= 2 General
Back to this chapter's Contents
Based upon item submitted by K. Amsden - UNH
Short Answer
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 Education
Back to this chapter's Contents
Based upon item submitted by K. Amsden - UNH
Short Answer
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 Biological Sciences Education General
Back to this chapter's Contents
Based upon item submitted by K. Amsden - UNH
Short Answer
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 5 Comprehension
D= 2 Education
***Multiple Parts***
Back to this chapter's Contents
Item is still being reviewed
Short Answer
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 5 Comprehension
D= 4 General
Back to this chapter's Contents
Item is still being reviewed
True/False
SIMPLE/COR
MODEL CORRELATION/P PARAMETRIC
STATISTICS MISCELLANEOUS
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Based upon item submitted by B. Bosworth - St. John's Univ.
True/False
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Based upon item submitted by B. Bosworth - St. John's Univ.
True/False
SIMPLE/COR
MODEL ASSUMPTCUSTOMARY CORRELATION/P
PARAMETRIC STATISTICS MISCELLANEOUS
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Based upon item submitted by B. Bosworth - St. John's Univ.
True/False
SIMPLE/COR
CORRELATION/P PARAMETRIC STATISTICS
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Item is still being reviewed
True/False
SIMPLE/COR
SAMPLE SAMPDIST/C CORRELATION/P
PARAMETRIC STATISTICS SAMPLING
ESTIMATION CONCEPT
T= 2 Comprehension
D= 2 General
Back to this chapter's Contents
Based upon item submitted by J. Warren - UNH
Definition
SIMPLE/COR
I650A CORRELATION/P PARAMETRIC
STATISTICS
T= 5 Comprehension
D= 3 General
Back to this chapter's Contents
Based upon item submitted by J. Warren - UNH
Definition
SIMPLE/COR
I650A CORRELATION/P PARAMETRIC
STATISTICS
T= 5 Comprehension
D= 2 General
Back to this chapter's Contents
Based upon item submitted by A. Bugbee - UNH
Short Answer
FTEST ANOVA
PARAMETRIC STATISTICS
T=10 Application
D= 4 Social Sciences General
***Multiple Parts***
***Statistical Table Necessary***
Back to this chapter's Contents
Based upon item submitted by J. Warren - UNH
Short Answer
COMPLETELYRANDOM ANOVA MULTIPLECOMPARIS
MODEL TYPICALSUMMARY I650C
PARAMETRIC STATISTICS
T= 5 Application
D= 4 Biological Sciences General Natural Sciences
Back to this chapter's Contents
Based upon item submitted by R. L. Stout & R. M. Paolino - Brown
Multiple Choice
OTHER/AN EXPERDESIGN/TERM
ANOVA PARAMETRIC STATISTICS
T= 5 Comprehension
D= 6 General
Back to this chapter's Contents
Return to the list of chapters
Return to Brian Schott @ GSU