Docsity
Docsity

Prepare for your exams
Prepare for your exams

Study with the several resources on Docsity


Earn points to download
Earn points to download

Earn points by helping other students or get them with a premium plan


Guidelines and tips
Guidelines and tips

Quiz 1 with Solutions - Regression | STAT 4601, Quizzes of Statistics

Material Type: Quiz; Class: Regression; Subject: Statistics; University: California State University-East Bay; Term: Fall 2004;

Typology: Quizzes

Pre 2010

Uploaded on 08/19/2009

koofers-user-09c
koofers-user-09c 🇺🇸

10 documents

1 / 3

Toggle sidebar

This page cannot be seen from the preview

Don't miss anything!

bg1
Jaimie Kwon Page 4 10/13/2004
Stat {4601, 6872} Quiz #1 (50 minutes)
Open book and open note.
Use a simple calculator if necessary.
Show your work. (E.g. Next to each numerical answer, you need to put things like
P0.01(B3) or something equivalent)
Grad students need to do problems with * as well. Undergrad will get extra credit by
solving them.
#1. (7 points)
For patients suffering from arthritis, a traditional pain relief treatment exists but has a side
effect of problems in the kidney and resulting in 5% risk of heart attacks and strokes after 3
months of treatment. A new medical treatment is proposed that reduces the chances of the
kidney problem. But a question has been raised that the new drug may increase the risk of
heart attacks and strokes. To test this, a clinical trial data has been collected for 10 patients
and it turned out that 1 of them had the problem.
1) What assumptions does one need to check before applying the binomial test? Use the plain
language and terms of the subject field that is understandable to general audience. (1 pt)
2) Formulate the null and alternative hypotheses. (1 pt)
3) Give a general definition of the p-value. Then compute the p-value for the above data. (1 pt)
4) What is the significance level of a test that rejects the null hypothesis when the number
of patients experiencing a heart attack is greater than or equal to 3? (1 pt)
5) What is the power of the test in 4) at the alternative ‘the true chance of a patient having a
heart attack or stroke is 10%’? What is the probability of Type II error in such case? (1 pt)
pf3

Partial preview of the text

Download Quiz 1 with Solutions - Regression | STAT 4601 and more Quizzes Statistics in PDF only on Docsity!

Stat {4601, 6872} Quiz #1 (50 minutes)

  • Open book and open note.
  • Use a simple calculator if necessary.
  • Show your work. (E.g. Next to each numerical answer, you need to put things like P0.01 (B≥3) or something equivalent)
  • Grad students need to do problems with * as well. Undergrad will get extra credit by solving them.

#1. (7 points) For patients suffering from arthritis, a traditional pain relief treatment exists but has a side effect of problems in the kidney and resulting in 5% risk of heart attacks and strokes after 3 months of treatment. A new medical treatment is proposed that reduces the chances of the kidney problem. But a question has been raised that the new drug may increase the risk of heart attacks and strokes. To test this, a clinical trial data has been collected for 10 patients and it turned out that 1 of them had the problem.

  1. What assumptions does one need to check before applying the binomial test? Use the plain language and terms of the subject field that is understandable to general audience. (1 pt)

  2. Formulate the null and alternative hypotheses. (1 pt)

  3. Give a general definition of the p-value. Then compute the p-value for the above data. (1 pt)

  4. What is the significance level of a test that rejects the null hypothesis when the number of patients experiencing a heart attack is greater than or equal to 3? (1 pt)

  5. What is the power of the test in 4) at the alternative ‘the true chance of a patient having a heart attack or stroke is 10%’? What is the probability of Type II error in such case? (1 pt)

  1. A more extensive clinical study has been performed to yield the new data, which consists of 100 patients and 10 cases of heart-attacks and strokes within 3 months. Compute the p-value for the hypotheses same as 2). (1 pt)

7)* Compare the P-value obtained in 6) and 3) and discuss the result. Advocate the ‘large sample size’ from the results. (Graduate; 1 pt)

#2. (4 points) You are designing a survey asking CSUH students how many of them support change of the name of CSUH to ‘CSU East Bay.’

  1. You want to make sure you get the true proportion of those who support the name change within 0.05 with 90% confidence. What’s the minimum number of responses you need? (1 pt)

2)* you have a strong suspicion that the true proportion of name change supporters is close to 10%. How would you change the answer to the above question given that suspicion? (1 pt)

  1. It occurred to you that the total student population may not be large enough to apply the binomial test etc. Which assumption(s) for binomial test is violated? (1 pt)

  2. What is the alternative model you can use to model the data? (You won’t find it in the textbook. I mentioned it in the class.) (1 pt)