In class we’ve talked about confidence intervals and significance tests being two sides of the same coin.The goal of this assignment is to better understand this relationship by: vFinding confidence...

1 answer below »

In class we’ve talked about confidence intervals and significance tests being two sides of the same coin.The goal of this assignment is to better understand this relationship by:


vFinding confidence intervals by hand


vCompleting significance tests by hand


vUsing StatCrunch to find confidence intervals and run significance tests


vInterpretingand comparing the results ofsignificance tests and confidence intervals



1.For this question we will revisit the example of the 2010 gubernatorial race in California that was discussed in class and that you worked on in HW3.In this race, the exit poll on which TV networks relied for their projections on election night found that, after sampling 3,889 voters, 53.1% said they voted for Democrat Jerry Brown over Republican Meg Whitman.


a.(6pts)By hand, find a 95% confidence interval for the proportion of the population who voted for Brown.Show all of your work, and clearly state:


üYour value of


üYour value ofz


üThe standard error (rounded to 3 decimal places)


üThe confidence interval





b.(3pts)Using StatCrunch, find a 95% confidence interval for the proportion of the population who voted for Brown.


üInsert an image of the output.





c.(10pts)By hand,conduct a significance test to see if there is evidence to support the research hypothesis that the proportion of the population who voted for Brown is greater than 50%.


üShow all five parts of the significance test


üShow all of your calculations.


üInclude an image of the calculator results from StatCrunch in step 4, finding theP-value.


d.(3pts)Using StatCrunch, conduct a significance test to see if there is evidence to support the research hypothesis that the proportion of the population who voted for Brown is greater than 50%.


üInsert an image of the output.





e.(4pts)The media used the results of this exit poll to predict a win for Brown.Based on what you’ve seen in this exercise, answer the questions:


-If only half the population voted for Brown; would it then be surprising that 53.1% of the sampled individuals voted for him?



- Does it make sense that the race was called for Brown?


üExplain your thoughts usingat least 3 sentences.




2.In HW3, you also investigated the 2014 gubernatorial election in Florida, where, in an exit poll of 2696 voters, 50.5% said they voted for Rick Scott and 49.5% said they voted for Charlie Crist.



a.(6pts)By hand, find a 95% confidence interval for the proportion of the population who voted for Scott.Show all of your work, and clearly state:


üYour value of


üYour value ofz


üThe standard error (rounded to 4 decimal places)


üThe confidence interval





b.(3pts)Using StatCrunch, find a 95% confidence interval for the proportion of the population who voted for Scott.


üInsert an image of the output.





c.(10pts)By hand,conduct a significance test to see if there is evidence to support the research hypothesis that the proportion of the population who voted for Scott is greater than 50%.


üShow all five parts of the significance test


üShow all of your calculations.


üInclude an image of the calculator results from StatCrunch in step 4, finding theP-value.





d.(3pts)Using StatCrunch, conduct a significance test to see if there is evidence to support the research hypothesis that the proportion of the population who voted for Scott is greater than 50%.


üInsert an image of the output.





e.(4pts)The media would have used the results of this exit poll to decide if they could predict a win for Scott.Based on what you’ve seen in this exercise, answer the questions:



- If only half the population voted for Scott; would it then be surprising that 50.5% of the sampled individuals voted for him?



- Should the race have been called for Scott based on this exit poll?


üExplain your thoughts usingat least 3 sentences.



3.For this question you will need your GSS data.There are instructions for finding a confidence intervalwith dataand conducting a significance testwith datain the “Working with StatCrunch” file posted in Teams.


a.(4pts)In StatCrunch, find a 99% confidence interval for the mean for the variable “Ideal number of children”.


üInsert an image of the output


üInterpret the output.





b.(6pts)In StatCrunch, run a significance test for the mean for this same variable, letting2, 2.5, and then 3, in each case selecting “” in the alternative hypothesis.


üInsert images of thethreedifferent output windows


üInterpret theP-value in each case.



c.(3pts)In this setting, does the confidence interval approach or the significance test approach seemmore useful in predicting the population parameter?


üExplain your thoughts usingat least 3 sentences.




Answered Same DayApr 26, 2021

Answer To: In class we’ve talked about confidence intervals and significance tests being two sides of the same...

Rajeswari answered on Apr 27 2021
146 Votes
82102 Assignment
Qno.1
a)
    1)
    p
    53.10%
     
    n
    3889
     
     
     
     
    q
    0.469
     
    Var
    6.40368E-05
     
    Std error
    0.008002298
     
     
     
     
    Conf level
    95%
     
    Z critical
    1.96
     
    Margin of error
    0.015684504
     
    Confidence interval
     
     
    Lower bound
    0.515315496
     
    Upper bound
    0.546684504
Hence we get confidence interval 95% = (0.5153, 0.5467)
b)
One sample proportion summary confidence interval:
p : Proportion of successes
Method: Standard-Wald
95% confidence interval results:
    Proportion
    Count
    Total
    Sample Prop.
    Std. Err.
    L. Limit
    U. Limit
    p
    2065.06
    3889
    0.53100026
    0.0080022976
    0.51531604
    0.54668447
c) H0: p = 0.5
Ha: p>0.5
(Right tailed test at 5% significance level)
d)
Manually:
p : Proportion of successes
H0 : p = 0.5
HA : p > 0.5
Std error = 0.08017723
    var
    6.42839E-05
    std error
    0.008017723
    p difference
    0.031
    z
    3.866434533
    p value
    <0.0001
Since p < alpha, we conclude there is sufficient evidence to support the claim that proportion is greater than 0.50.
One sample proportion summary hypothesis test:
p : Proportion of successes
H0 : p = 0.5
HA : p > 0.5
Hypothesis test results:
    Proportion
    Count
    Total
    Sample Prop.
    Std. Err.
    Z-Stat
    P-value
    p
    2065.06
    3889
    0.53100026
    0.0080177227
    3.8664666
    <0.0001
e) Yes because the hypothesis test reveals that definitely more than 50% and hence exactly half is a little surprising . But however he got exactly by getting 50% , thus making the opposite party also not to win .. Only if more than 50% is won he would get majority. So this result is surprising. May be samples are taken with bias and not at random. Race should have been called...
SOLUTION.PDF

Answer To This Question Is Available To Download

Related Questions & Answers

More Questions »

Submit New Assignment

Copy and Paste Your Assignment Here