Transcript Wiederholungssendung A

Competition
1
Wiederholungssendung
The name of a famous
Russian mathematician is …
A: Smirnoff
B: Gorbatschoff
C: Kolmogoroff
D: Stroganoff
2
Wiederholungssendung
The name of a famous
Russian mathematician is …
A: Smirnoff
B: Gorbatschoff
C: Kolmogoroff
D: Stroganoff
3
Wiederholungssendung
The name of a famous
English statistician is …
A: Miller
B: Fisher
C: Churchill
D: Butler
4
Wiederholungssendung
The name of a famous
English statistician is …
A: Miller
B: Fisher
C: Churchill
D: Butler
5
Wiederholungssendung
In order to describe the relation of
two categorial variables, we use
A: Boxplots
B: Cross tables
C: Histograms
D: Bar plots
6
Wiederholungssendung
In order to describe the relation of
two categorial variables, we use
A: Boxplots
B: Cross tables
C: Histograms
D: Bar plots
7
Wiederholungssendung
In order to describe the distribution
of a continuous variable in several
groups we use
A: Boxplots
B: Cross tables
C: Histograms
D: Bar plots
8
Wiederholungssendung
In order to describe the distribution
of a continuous variable in several
groups we use
A: Boxplots
B: Cross tables
C: Histograms
D: Bar plots
9
Wiederholungssendung
100 measurements of a continuous
variable are to be displayed in a
histogram. How many bins should the
histogram approximately have?
A: 1 Bin
B: 10 Bins
C: 100 Bins
D: 1000 Bins
10
Wiederholungssendung
100 measurements of a continuous
variable are to be displayed in a
histogram. How many bins should the
histogram approximately have?
A: 1 Bin
B: 10 Bins
C: 100 Bins
D: 1000 Bins
11
Wiederholungssendung
Which is the most robust measure of
location for continuous data?
A: Mean
B: 1st Quartile
C: Standard deviation
D: Median
12
Wiederholungssendung
Which is the most robust measure of
location for continuous data?
A: Mean
B: 1st Quartile
C: Standard deviation
D: Median
13
Wiederholungssendung
The maths grades of girls and boys of a school
class are compared in a cross table
(rows=grades, columns = gender). Which
quantities are most informative for the
comparison of grades within each group?
A: Relative frequencies
B: Row %
C: Column %
D: Total %
14
Wiederholungssendung
The maths grades of girls and boys of a school
class are compared in a cross table
(rows=grades, columns = gender). Which
quantities are most informative for the
comparison of grades within each group?
A: Relative frequencies
B: Row %
C: Column %
D: Total %
15
Wiederholungssendung
The binary endpoint „pain“ (yes/no) is
measured twice a day (morning, evening)
for each participant of a clinical trial.
Which are the variables that constitute the
rows/columns in a cross table?
A: Pain, Time
B: Patient #, Pain
C:
Pain (morning), Pain (evening)
D:
Time (morning), Time (evening)
16
Wiederholungssendung
The binary endpoint „pain“ (yes/no) is
measured twice a day (morning, evening)
for each participant of a clinical trial.
Which are the variables that constitute the
rows/columns in a cross table?
A: Pain, Time
B: Patient #, Pain
C:
Pain (morning), Pain (evening)
D:
Time (morning), Time (evening)
17
Wiederholungssendung
The distribution of a continuous
variable is skewed to the right.
Thus,
A: Mode = Median
B: Median > 65% Quantile
C: 1.Quartile > Mean
D: Median < Mean
18
Wiederholungssendung
The distribution of a continuous
variable is skewed to the right.
Thus,
A: Mode = Median
B: Median > 65% Quantile
C: 1.Quartile > Mean
D: Median < Mean
19
Wiederholungssendung
The distribution of a continuous
variable is skewed to the left. A
typical boxplot looks like:
A:
B:
C:
D:
20
Wiederholungssendung
The distribution of a continuous
variable is skewed to the left. A
typical boxplot looks like:
A:
B:
C:
D:
21
Wiederholungssendung
A t-Test at a 5% type I error level should be
preferred over the „Offenbach Oracle“
because
A: It produces only 5% false positives
B: It produces less true negatives
C: It does not make any assumption about
the null distribution
D: It produces less false negatives
22
Wiederholungssendung
A t-Test at a 5% type I error level should be
preferred over the „Offenbach Oracle“
because
A: It produces only 5% false positives
B: It produces less true negatives
C: It does not make any assumption about
the null distribution
D: It produces less false negatives
23
Wiederholungssendung
The decision boundary for a one-sided test
statistic is d=7 at a significance level of α=5%.
A valid acceptance region A for a corresponding
two-sided test is:
A: A = [-10,10]
B: A = [-5,5]
C: A = (∞,-10] ∪ [10,∞)
D: A = (∞,-5] ∪ [5,∞)
24
Wiederholungssendung
The decision boundary for a one-sided test
statistic is d=7 at a significance level of α=5%.
A valid acceptance region A for a corresponding
two-sided test is:
A: A = [-10,10]
B: A = [-5,5]
C: A = (∞,-10] ∪ [10,∞)
D: A = (∞,-5] ∪ [5,∞)
25
Wiederholungssendung
A two-group t-test at a significance
level of α=1% yields a p-value of
p=0.011. One can conclude that
A:
There is a difference between the two groups
B:
The type II error of the test is too high
C: There is no significant difference
D: The significance level has to be adjusted
26
Wiederholungssendung
A two-group t-test at a significance
level of α=1% yields a p-value of
p=0.011. One can conclude that
A:
There is a difference between the two groups
B:
The type II error of the test is too high
C: There is no significant difference
D: The significance level has to be adjusted
27
Wiederholungssendung
A two-sided (symmetrical) test at a
significance level of α=5% yields a pvalue of p=0.002. One can conclude that
A:
There is a differnce between the groups
B:
The one-sided test would also be positive
C: The test at a level of α=1% would also be positive
D: The result is significant at a 1%-level
28
Wiederholungssendung
A two-sided (symmetrical) test at a
significance level of α=5% yields a pvalue of p=0.002. One can conclude that
A:
There is a differnce between the groups
B:
The one-sided test would also be positive
C: The test at a level of α=1% would also be positive
D: The result is significant at a 1%-level
29
Congratulations!
30