Scribd
Upload
25 views1 page

2024spring 340 Final Solutions

The document contains solutions for the STAT 340 Spring 2024 Final Exam, including multiple-choice and short-answer questions. Key concepts addressed include statistical estimations, confidence intervals, and cross-validation techniques. The solutions provide specific calculations and explanations for various statistical scenarios.

Uploaded by

Margita Kon-Popovska
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
25 views1 page

2024spring 340 Final Solutions

The document contains solutions for the STAT 340 Spring 2024 Final Exam, including multiple-choice and short-answer questions. Key concepts addressed include statistical estimations, confidence intervals, and cross-validation techniques. The solutions provide specific calculations and explanations for various statistical scenarios.

Uploaded by

Margita Kon-Popovska
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/ 1

STAT 340 Spring 2024 Final Exam Solutions

----------------------------------------------------------------------------------
MC1: a, c; For a geometric E(X̅ )/E(S²)=p, for an exponential E(X̅ )/E(S²)=λ
MC2: b, c, d;
MC3: b; because P(B|A)=1
MC4: d
MC5: a, b, c
MC6: c, d
MC7: b
MC8: a: Y1
b: Y3
c: Y4
d: N/S
MC9: e
MC10: a, d
----------------------------------------------------------------------------------
SA1: a. (.01*.9)/(.01*.9 + .99*.05)
b. (.01*.1)/(.01*.1 + .99*.95)

SA2: a. Because of the bad data, sample mean will underestimate mu


b. median is a very good candidate
c. s would also underestimate sigma due to the bad data
d. 84th percentile - median for example

SA3: a. TRUE; β̂₀= ȳ-r*x̄ = 0-r*0


b. FALSE; RSE could be higher or lower, depends on sy size
c. TRUE: β̂₁= r*sy/sx = r*1/1
d. FALSE: R²=r² does not change

SA4: a. Fare; each additional $1 in fare is associated with a log-odds increase


of .0125
b. -1.31 +/- 1.96*.414; we are 95% confident that this interval captures
log-oddsRatio of being male compared to female passenger
c. e^(10*.012747)
d. LO= .3156 + .0125(8) + .0127(35) - 1.31(1) - .038(35)(1)
prob = e^LO / (1 + e^LO) or 1/(1+e^-LO)

SA5: a. FALSE; the goal is to estimate out-of-sample error


b. TRUE; LOOCV has no randomization in the fold splits
c. FALSE; k-fold CV is sensitive to the random spliting of folds
d. TRUE; n-fold CV is simply another name for LOOCV

file:///C/Users/brpowers2/Box/STAT340/final_exam/2024_1_spr/SP24%20STAT340%20Final%20Solutions.txt[5/10/2024 12:22:29 PM]

You might also like