You are on page 1of 12

10/22/2016

ParametricModelsforRegression|Coursera

Parametric Models for Regression

4/12pointsearned(33%)
Youhaven'tpassedyet.Youneedatleast70%topass.
Reviewthematerialandtryagain!Youhave3attemptsevery
8hours.

Review Related Lesson

1/1
points

1.
A manufacturer has developed a specialized metal alloy for use in jet
engines. In its pure form, the alloy starts to soften at 1500 F. However,
small amounts of impurities in production cause the actual temperature
at which the alloy starts to lose strength to vary around that mean, in a
Gaussian distribution with standard deviation = 10.5 degrees F.
If the manufacturer wants to ensure that no more than 1 in 10,000
of its commercial products will suer from softening, what should it
set as the maximum temperature to which the alloy can be
exposed?
Hint: Refer to the Excel NormSFunctions Spreadsheet.

ExcelNormSFunctionsSpreadsheet.xlsx

39.0497 F
1496.281
1460.9503 F
Correct Response

The manufacturer needs to nd the z-score on


https://www.coursera.org/learn/analyticsexcel/exam/c4Qel/parametricmodelsforregression

the Gaussian

1/12

10/22/2016

ParametricModelsforRegression|Coursera

The manufacturer needs to nd the z-score on the Gaussian


distribution such that .0001 of the probability will be to the left of
that temperature, and .9999 to the right. Using Excel NormSInv,
the z-score for .0001 is z = -3.7190.
The maximum temperature that achieves the desired reliability is
= mean ((z-score)*(standard deviation) )
= 1500 (3.7190*10.5)
= 1460.9503 F

1539.0497

0/1
points

2.

A carefully machined wire comes o an assembly line within a certain


tolerance. Its diameter is 100 microns, and all the wires produced have a
uniform distribution of error, between -11 microns and +29 microns.
A testing machine repeatedly draws samples of 180 wires and
measures the sample mean. What is the distribution of sample
means?
Hint: Use the CLT and Excel Rand() Spreadsheet.

CLTandExcelRand.xlsx

A Gaussian Distribution that, in Phi notation, is written (109,


.7407).
A Gaussian distribution that, in Phi notation, is written, (109,
133.33).
Incorrect Response

133.33 is the variance of the uniform distribution of wire


diameters, not the variance of sample means. Although the
probability distribution of wire diameters is Uniform, the Central
Limit Theorem explains that the distribution of sample means is a

Gaussian. Remember that in "PHI" notation the second number is

https://www.coursera.org/learn/analyticsexcel/exam/c4Qel/parametricmodelsforregression

2/12

10/22/2016

ParametricModelsforRegression|Coursera

Gaussian. Remember that in "PHI" notation the second number is


the variance (standard deviation squared) not the standard
deviation.

A Uniform Distribution with mean = 109 microns and standard


deviation = .8607 microns.
A Uniform Distribution with mean = 109 microns and standard
deviation = 11.54 microns.

1/1
points

3.
A population of people su ering from Tachycardia (occasional rapid heart
rate), agrees to test a new medicine that is supposed to lower heart rate.
In the population being studied, before taking any medicine the mean
heart rate was 120 beats per minute, with standard deviation = 15 beats
per minute.
After being given the medicine, a sample of 45 people had an
average heart rate of 112 beats per minute. What is the probability
that this much variation from the mean could have occurred by
chance alone?
Hint: Use the Typical Problem with NormSDist Spreadsheet.

TypicalProblem_NormSDist.xlsx

99.9827%
1.73%
.0173%
Correct Response

The distribution of sample means has an expected mean of 120


and standard deviation of 15/sqrt(45) = 2.236. The z-score of the
sample average of 112 is (112-120)/2.236 = -3.577. A z-Score this
small or smaller has a probability of occurring by chance of only
( 1 NormSDist(3.577)) = .0173% .

29.690%

https://www.coursera.org/learn/analyticsexcel/exam/c4Qel/parametricmodelsforregression

3/12

10/22/2016

29.690%

ParametricModelsforRegression|Coursera

0/1
points

4.
Two stocks have the following expected annual returns:
Oil stock expected return = 9% with standard deviation = 13%
IT stock expected return = 14% with standard deviation = 25%
The Stocks prices have a small negative correlation: R = -.22.
What is the Covariance of the two stocks?
Hint: Use the Algebra with Gaussians Spreadsheet.

AlgebrawithGaussians.xlsx

-.00573
-.00219
-.00715
-.0286
Incorrect Response

Covariance is de ned as R*Std.Dev(1)*Std.Dev(2).

0/1
points

5.

Two stocks have the following expected annual returns:


https://www.coursera.org/learn/analyticsexcel/exam/c4Qel/parametricmodelsforregression

4/12

10/22/2016

ParametricModelsforRegression|Coursera

Two stocks have the following expected annual returns:

Oil stock expected return = 9% with standard deviation = 13%


IT stock expected return = 14% with standard deviation = 25%
The Stocks prices have a small negative correlation: R = -.22.
Assume return data for the two stocks is standardized so that each is
represented as having mean 0 and standard deviation 1. Oil is plotted
against IT on the (x,y) axis.
What is the covariance?
Hint: Use the Standardization Spreadsheet.

StandardizationSpreadsheet.xlsx

-.22
-.00573
Incorrect Response

See the Standardization Spreadsheet.

0
-1

0/1
points

6.

Two stocks have the following expected annual returns:


https://www.coursera.org/learn/analyticsexcel/exam/c4Qel/parametricmodelsforregression

5/12

10/22/2016

ParametricModelsforRegression|Coursera

Oil stock expected return = 9% with standard deviation = 13%


IT stock expected return = 14% with standard deviation = 25%
The Stocks prices have a small negative correlation: R = -.22.
What is the standard deviation of a portfolio consisting of 70% Oil
and 30% IT?
Hint: Use either the Algebra with Gaussians or the Markowitz Portfolio
Optimization Spreadsheet.

AlgebrawithGaussians.xlsx
MarkowitzPortfolioOptimization.xlsx

10.44%
12.68%
11.79%
Incorrect Response

Use the Markowitz Portfolio Optimization Spreadsheet. Enter Oil


Expected return in Cell C6, Oil standard deviation in cell C7, IT
expected return in Cell D6, IT standard deviation in Cell D7, Oil
weighting in Cell C9 and IT weighting in Cell D9. Results in Cell
E12.

17.93%

0/1
points

7.

Two stocks have the following expected annual returns:


https://www.coursera.org/learn/analyticsexcel/exam/c4Qel/parametricmodelsforregression

6/12

10/22/2016

ParametricModelsforRegression|Coursera

Oil stock expected return = 9% with standard deviation = 13%


IT stock expected return = 14% with standard deviation = 25%
The Stocks prices have a small negative correlation: R = -.22.
Use MS Solver and the Markowitz Portfolio Optimization Spreadsheet to
Find the weighted portfolio of the two stocks with lowest volatility.

SolverAddIn.xlsx
MarkowitzPortfolioOptimization.xlsx
What is the minimum volatility?
11.58%
10.43%
10.36%
9.5%
Incorrect Response

1/1
points

8.

An automobile parts manufacturer uses a linear regression model to


forecast the dollar value of the next years orders from current customers

https://www.coursera.org/learn/analyticsexcel/exam/c4Qel/parametricmodelsforregression

7/12

10/22/2016

ParametricModelsforRegression|Coursera

forecast the dollar value of the next years orders from current customers
as a function of a weighted sum of their past-years orders. The model
error is assumed Gaussian with standard deviation of $130,000.
To the nearest dollar, what is the range above and below each Point
Forecast required to have 90% condence that the dollar value of
next years orders will fall within that range?
Hint: you can answer this question by making small modi cations to the
Correlation and Model Error Spreadsheet.

CorrelationandModelError.xlsx

The 90% con dence interval is from $213,831 below to


$213,831 above the point forecast.
Correct Response

A 90% con dence interval means 5% above and 5% below the


interval. Using p = .95, Excel "Normsinv(.95)" = 1.64485. This is the
z-Score. Therefore the interval ranges from (1.64485)*(130,00) or
$213,831 below the point forecast, to (1.64485)*($130,000) =
$213,831 above the forecast.

The 90% con dence interval is from $83,831 below to $83,831


above the Point Forecast
The 90% con dence interval is from $316,831 below to
$316,831 above the Point Forecast.
The 90% con dence interval is from $164,831 below to
$164,831 above the Point Forecast.

1/1
points

9.

An automobile parts manufacturer uses a linear regression model to


forecast the dollar value of the next years orders from current customers

https://www.coursera.org/learn/analyticsexcel/exam/c4Qel/parametricmodelsforregression

8/12

10/22/2016

ParametricModelsforRegression|Coursera

forecast the dollar value of the next years orders from current customers
as a function of a weighted sum of their past-years orders. The model
error is assumed Gaussian with standard deviation of $130,000.
If the correlation is R = .33, and the point forecast orders $5.1
million, what is the probability that the customer will order more
than $5.3 million?
Hint: Use the Typical Problem with NormSDist Spreadsheet.

TypicalProblem_NormSDist.xlsx

93.8%
4.3%
6.2%
Correct Response

Convert $5.3 million to a z-score. The z-Score is (5.3-5.1)/.13 =


(.2/.13) = 1.538.
Input the z-score in the Excel formula (1 - Normsdist(z)) to get the
probability of a score at least that high. The probability is 1- 93.8%
= 6.2%.

12.4%

0/1
points

10.

An automobile parts manufacturer uses a linear regression model to


forecast the dollar value of the next years orders from current customers
https://www.coursera.org/learn/analyticsexcel/exam/c4Qel/parametricmodelsforregression

9/12

10/22/2016

ParametricModelsforRegression|Coursera

forecast the dollar value of the next years orders from current customers
as a function of a weighted sum of that customers past-years orders. The
linear correlation is R = .33.
After standardizing the x and y data, what portion of the
uncertainty about a customers order size is eliminated by their
historical data combined with the model?
Hint: Use the Correlation and P.I.G. Spreadsheet.

CorrelationandP.I.G..xlsx

4.2%
3.5%
Incorrect Response

4.5%
5.2%

0/1
points

11.
Customers who use online chat support can rate the help they receive
from a customer support worker as a 0 (useless), a 1, 2, 3, 4, or 5
(excellent). The mean rating is 3.935, with standard deviation = 1.01.
A new support worker named Barbara has received, over her rst 100
chat sessions, an average rating of 3.7. Her boss calls her in and
threatens to re her if her performance does not improve.
Barbara replies Its just bad luck - Ive had more than my share of
unhappy customers today. Who is most likely right?
Hint: Use the Typical Problem with NormSDist Spreadsheet.

TypicalProblem_NormSDist.xlsx

The boss
https://www.coursera.org/learn/analyticsexcel/exam/c4Qel/parametricmodelsforregression

10/12

10/22/2016

ParametricModelsforRegression|Coursera

Barbara
Incorrect Response

Barbaras performance has a Z score = (mean - actual) /standard


deviation of the sample means = (3.7 - 3.935) / (1.01/sqrt(100)) =
-2.327.
If Barbaras performance is due to chance, the probability of
observing a z-score as low, or lower, than -2.327 would be less
than 1%.
Note that due to the Central Limit Theorem, even though the raw
customer scores do not have a Gaussian distribution, the sample
means will have a Gaussian distribution, so that use of the
NormSDist function is appropriate. NormSDist(-2.327) = .0099898.

0/1
points

12.
Your company currently has no way to predict how long visitors will
spend on the Companys web site. All it known is the average time spent
is 55 seconds, with an approximately Gaussian distribution and standard
deviation of 9 seconds. It would be possible, after investing some time
and money in analytics tools, to gather and analyzing information about
visitors and build a linear predictive model with a standard deviation of
model error of 4 seconds.
How much would the P.I. G. of that model be?
Hint: Use the Correlation and P.I.G. Spreadsheet

HowtousetheAUCcalculator.pdf

48.2%
61.5%
Incorrect Response

With no model, the correlation R = 0 and the model error is


equal to the standard deviation of Y = 9 seconds. Standardized,
the model error when R = 0 is equal to 1. Reducing the model
error to 4 seconds is equivalent to reducing the standardized
model error to 4/9 = .4444 Since Sqrt(1-R^2) = .4444, R^2 = 1.4444^2 = .8958.
https://www.coursera.org/learn/analyticsexcel/exam/c4Qel/parametricmodelsforregression

11/12

10/22/2016

ParametricModelsforRegression|Coursera

.4444^2 = .8958.

53.3%
57.2%

https://www.coursera.org/learn/analyticsexcel/exam/c4Qel/parametricmodelsforregression

12/12