Scribd
Upload
7 views

Problem Set 10 Problem 1: D) Runner's Hypothesis Is Wrong As The More She Runs During The Week The Faster

Problem 1 examines the relationship between miles run per week and Sunday run times. It finds a negative correlation, meaning run times decrease as weekly miles increase, disproving the runner's hypothesis. Problem 2 looks at the correlation between birth date and draft lottery number, finding a weak negative relationship between earlier birth dates and lower lottery numbers. This suggests the lottery was not truly random. Problem 3 analyzes the distribution of birth dates and draft lottery numbers, finding both follow a uniform distribution between 1 and 366. Problem 4 models test scores as a function of student-teacher ratios, finding test scores decrease significantly as ratios increase, with a confidence interval of -3.22 to -1.34 for the slope

Uploaded by

Alexander Milstein
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
7 views

Problem Set 10 Problem 1: D) Runner's Hypothesis Is Wrong As The More She Runs During The Week The Faster

Problem 1 examines the relationship between miles run per week and Sunday run times. It finds a negative correlation, meaning run times decrease as weekly miles increase, disproving the runner's hypothesis. Problem 2 looks at the correlation between birth date and draft lottery number, finding a weak negative relationship between earlier birth dates and lower lottery numbers. This suggests the lottery was not truly random. Problem 3 analyzes the distribution of birth dates and draft lottery numbers, finding both follow a uniform distribution between 1 and 366. Problem 4 models test scores as a function of student-teacher ratios, finding test scores decrease significantly as ratios increase, with a confidence interval of -3.22 to -1.34 for the slope

Uploaded by

Alexander Milstein
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Problem Set 10

Problem 1

a) indepvar= #of miles per week


b) see graph
c) see graph
d) r=-0.9601
negative correlation, meaning with the increase of number of hours run in a
week, 1mile time run on Sunday decreases
e) Find a ( y-intercept )
a = ((29.3) * (1768) - (102)*(495.2))/ (6*( 1768) - (102^2)) = 6.33
coefficient x variable 1= -0.0853
y= 6.33 -0.0853x
d) Runners hypothesis is wrong as the more she runs during the week the faster
she runs on Sunday ( less time)

Problem 2
a) the correlation is negative and not strong , men born earlier . The higher the
draft number the lottery number the the earlier is the birth date. Those
born earlier were less likely to win .
b) if the lottery was truly random, then r=0. There would be no correlation, no
linear relationship
c) the slope is b=-0.2557. So if we increase the birth date by one day, there
would be decrease of draft number by 0.2557, because the correlation is
negative.
d) the slope would be b=0. Truly random means no relationship and correlation ,
meaning a flat graph.

e) Y -intercept is 224.9. This means that men predicted with birth dates to be 0 ,
will have a draft number 224.9 . A birth date can not equal 0 , so the y intercept is not meaningless for us.
f)

224.9 - 0.2257(100) = 202.33

g)

224.9 - 0.2257(300) = 157.19

h) see graph
i)

224.9 - 0.2257(110) = 200.07

h) No, because birthday is an independent random variable. Birth dates can


automatically be treated as lottery.
Problem 3
a)

Uniform distribution ( see graph)

b) Uniform distribution ( see graph )


c) mean = 183.5 Both variables are integers beginning from 1 and going to
366
d) see graph
e) see graph

Problem 4
a) b1 = -2.279808 ( using stata)
b) Slope : for 1 student increase in student teacher ratio, test scores will decline
( predicted) by 2.279808 ( using stata)
Y-intercept : With a student-teacher ratio equal to 0 the predicted test score is 698.933 .
However ratio equal to 0 does is not relevant and possible in this example.
c) [-3.22298, -1.336637] ( using Stata)
d) y = 698.933 - (2.279808)(16.0) = 662.46
e) y = 698.933 - (2.279808)(24.1) = 643.99

y = 698.933 - (2.279808)(20.5) = 652.20


The predicted test score will increase from 643.99 to 652.20, by 8.21 points.
f) p=0.000 ( from Stata)

g) Due to r = -0.2264 , the XY correlation is negative and not too strong. ( from Stata)

You might also like