STA2020F 2006
Class Test 1
Date: 30
th
March 2006
Time: 1 hour 30 minutes
Total marks: 60
Instructions: Answer all the questions in your blue answer book. Your answer
should be T or F for each question in section A and a written answer for section B.
There is no penalty
for incorrect answers in section A. A formula sheet and the
relevant statistical tables are provided at the end of this test paper.
SECTION A
:
Total marks
8
State whether each of the following statements is true (T) or false (F).
Each question
carries
1 mark
.
1)
If we reject a null hypothesis at the 5% level of significance then we may or may
not reject it at the 6% level of significance.
2)
If the significance level of a test is stated as 3%, then a pvalue of 0.025 would
lead us to reject the alternate hypothesis for the test.
3)
An article in an anthropology journal reports a pvalue of 0.043 for testing H
0
:
μ
=
0 against H
1
:
μ
≠
0. If the authors had instead reported a 95% confidence interval
for
μ
, then the interval would not have contained zero.
4)
A 95% confidence interval for
μ
is given by (3, 5). If we were testing H
0
: µ =
3.2, then we would not reject the null hypothesis.
5)
If you were testing whether the mean STA100S mark for the students in the 2005
class was the same for male and female students, the appropriate null and
alternate hypotheses would be: H
0
: μ
male
≠ μ
female
and H
1
: μ
male
= μ
female
.
6)
If you were testing whether the mean STA100S mark for the students in the 2005
class was the same for male and female students, at the 10% level of significance,
and you obtained a pvalue of 0.075, you would conclude that there was a
difference in the mean marks for males and females.
7)
If you were testing whether the mean STA100S mark for the students in the 2005
class was the same for male and female students, at the 10% level of significance,
and you obtained a pvalue of 0.075, then the 90% confidence interval for the
difference in mean marks would contain zero.
8)
One of the advantages of using ANOVA instead of multiple ttests to test for a
difference between population means, is that the overall probability of making a
type I error is reduced.
1
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
SECTION B
:
Total marks 52
Question 1:
The recent power cuts experienced in Cape Town have been a source of frustration for
everyone.
One particular STA2020F lecturer has been determined to save power at home
and has taken various powersaving measures to try and accomplish this.
In order to
This is the end of the preview.
Sign up
to
access the rest of the document.
 Three '09
 JAMES
 Linear Regression, Regression Analysis, Statistical hypothesis testing, alternate hypotheses

Click to edit the document details