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 Solutions for Stat 3502/4612 Spring 2005 - Quiz #1, Quizzes of Statistics

The solutions to quiz #1 for the stat 3502/4612 spring 2005 course. The quiz covers topics such as calculating the median, mode, range, interquartile range, and identifying outliers for a given dataset. It also includes problems on probability theory, specifically finding the probability of two independent events occurring and approximating binomial distributions using normal distributions.

Typology: Quizzes

Pre 2010

Uploaded on 08/19/2009

koofers-user-1wo
koofers-user-1wo 🇺🇸

10 documents

1 / 2

Toggle sidebar

This page cannot be seen from the preview

Don't miss anything!

bg1
Stat 3502/4612 Spring 2005 Jaimie Kwon Name____________________
Quiz #1 (50 minutes) Name____________
Open book and open note. Use a simple calculator if necessary. Show your work. Each subproblem is 3
point each.
1. Here is the distribution of the duration
of 272 eruptions (in minutes) at Old
Faithful.
a. What’s the median duration? Where’s
the mode(s)? (The mean duration is
3.49 minutes, by the way)
b. What’s the range of the distribution?
c. What’s the IQR of the distribution?
d. How many outliers are there in the
distribution?
e. (6 pt) If you observe an eruption with
duration 10 minutes, would you count it
as an outlier in the boxplot? Explain.
f. How would you describe the eruption
duration distribution?
2. A smoke detector system uses two
devices, A and B. If smoke is present,
the probability that it will be detected by device A is .95; by device B, .90. Assume the two devices work
independently.
a. Find the probability that the smoke will be detected by both A and B.
b. Find the probability that the smoke will be detected by either device A or B or both devices.
2. You want to inspect whether a coin is weighted and probability of head is larger than 50%. You toss it 100
times to check it out.
a. Let Y be the number of heads appearing in 100 tosses. It has binomial distribution. What are the values of the
parameters n and π assuming the coin was fair?
b. Approximate the distribution in a) by normal distribution, again assuming the coin was fair. Specify the mean
and standard deviation.
c. At the end of the experiment, you have observed 55 heads. Were the true head probability be 50%, what
would be the chance that the observed number of heads is greater than or equal to 55? Is it very likely,
somewhat likely, or unlikely? Use the approximate distribution you gave in c).
d. (6 pt) Consider a similar experiment but assume you tossed 1,000 times instead of 100 and observed 600
heads. Repeat b and c for this new experiment.
pf2

Partial preview of the text

Download Quiz Solutions for Stat 3502/4612 Spring 2005 - Quiz #1 and more Quizzes Statistics in PDF only on Docsity!

Stat 3502/4612 Spring 2005 Jaimie Kwon Name____________________

Quiz #1 (50 minutes) Name____________

  • Open book and open note. Use a simple calculator if necessary. Show your work. Each subproblem is 3 point each.
  1. Here is the distribution of the duration of 272 eruptions (in minutes) at Old Faithful. a. What’s the median duration? Where’s the mode(s)? (The mean duration is 3.49 minutes, by the way) b. What’s the range of the distribution? c. What’s the IQR of the distribution? d. How many outliers are there in the distribution? e. (6 pt) If you observe an eruption with duration 10 minutes, would you count it as an outlier in the boxplot? Explain. f. How would you describe the eruption duration distribution?
  2. A smoke detector system uses two devices, A and B. If smoke is present, the probability that it will be detected by device A is .95; by device B, .90. Assume the two devices work independently. a. Find the probability that the smoke will be detected by both A and B. b. Find the probability that the smoke will be detected by either device A or B or both devices.
  3. You want to inspect whether a coin is weighted and probability of head is larger than 50%. You toss it 100 times to check it out. a. Let Y be the number of heads appearing in 100 tosses. It has binomial distribution. What are the values of the parameters n and π assuming the coin was fair? b. Approximate the distribution in a) by normal distribution, again assuming the coin was fair. Specify the mean and standard deviation. c. At the end of the experiment, you have observed 55 heads. Were the true head probability be 50%, what would be the chance that the observed number of heads is greater than or equal to 55? Is it very likely, somewhat likely, or unlikely? Use the approximate distribution you gave in c). d. (6 pt) Consider a similar experiment but assume you tossed 1,000 times instead of 100 and observed 600 heads. Repeat b and c for this new experiment.

Stat 3502/4612 Spring 2005 Jaimie Kwon Name____________________

Quiz #1 Solutions

  1. (All answers are approximate since no numerical clues are provided) a. median is 4.0. Two modes are at near 1.9 and 4. b. the range is ~5.1 – 1.6 = 3. c. the IQR is ~ 4.4 - 2.2 = 2. d. No outliers e. Right inner fence is Q3+1.5IQR = 4.4 + 1.52.2 = 4.4 + 3.3 = 7.7. 10 is larger than this so it will show as an outlier in the boxplot. f. It’s bimodal

a. P(A and B) = 0.95*0.90 = 0. b. P(A or B) = 0.95 + 0.90 – 0.855 = 0.

a. n = 100 and π = 0. b. μ= n π = 50 and σ = sqrt(1000.50.5) = 5 c. P(Y>55) ~ P(Z>(55-50)/5) = 1-pnorm(1) = 0.159. It is somewhat likely. d. μ= n π = 500 and σ = sqrt(10000.50.5) = 15.8. P(Y>550) ~ P(Z>(550-500)/15.8) = 1-pnorm(3.165) ~ 0. It is very unlikely.

R-codes used for the plots:

attach(faithful) par(mfrow=c(2,1)) hist(eruptions, nclass=20, col='gray') boxplot(eruptions, horizontal=TRUE, col='gray') grid(col='black')