The article "Plugged In, but Tuned Out"† summarizes data fromtwo surveys of kids age 8 to 18. One survey was conducted in 1999and the other was conducted in 2009. Data on number of hours perday spent using electronic media that are consistent with summaryquantities given in the article are given below (the actual samplesizes for the two surveys were much larger). For purposes of thisexercise, assume that it is reasonable to regard the two samples asrepresentative of kids age 8 to 18 in each of the 2 years that thesurveys were conducted.
2009   5   9   5  8   7   6   7  9   7   9   6  9   10   9   8
1999   4   5   7  7   5   7   5  6   5   6   7  8   5   6   6

(a)
Because the given sample sizes are small, in order for thetwo-sample t test to be appropriate, what assumption must be madeabout the distributions of electronic media usetimes?
o We need to assume that the populationdistribution in 1999 of time per day using electronic media arenormal.
o We need to assume that the populationdistribution in 2009 of time per day using electronic media arenormal.
o We need to assume that the populationdistributions in both 1999 and 2009 of time per day usingelectronic media are normal.
o We need to assume that the populationdistribution in either 1999 or 2009 of time per day usingelectronic media is normal.

Use the given data to construct graphical displays thatwould be useful in determining whether this assumption isreasonable. Do you think it is reasonable to use these data tocarry out a two-sample t test?
o The boxplot of the 2009 data is roughlysymmetrical with no outliers, so the assumption isreasonable.
o Both the boxplot of the 1999 data and the 2009data are skewed to the right, so the assumption is notreasonable.
o The boxplot of the 1999 data is roughlysymmetrical with no outliers, so the assumption isreasonable.
o Boxplots of the both the 1999 data and 2009 dataare roughly symmetrical with no outliers, so the assumption isreasonable.
o The boxplot of the 1999 data has an outlier tothe far right, so the assumption is not reasonable.

(b)
Do the given data provide convincing evidence that the mean numberof hours per day spent using electronic media was greater in 2009than in 1999? Test the relevant hypotheses using a significancelevel of 0.01. (Use a statistical computer package to calculate theP-value. Use ?2009 ? ?1999. Round your test statistic to twodecimal places, your df down to the nearest whole number, and yourP-value to three decimal places.)
t   =  
df   =  
P-value   =  

State your conclusion.
o Reject H0. There is convincing evidence that themean number of hours per day spent using electronic media wasgreater in 2009 than in 1999.
o Fail to reject H0. There is convincing evidencethat the mean number of hours per day spent using electronic mediawas greater in 2009 than in 1999.
o Fail to reject H0. There is not convincingevidence that the mean number of hours per day spent usingelectronic media was greater in 2009 than in 1999.
o Reject H0. There is not convincing evidence thatthe mean number of hours per day spent using electronic media wasgreater in 2009 than in 1999.

(c)
Construct and interpret a 98% confidence interval estimate of thedifference between the mean number of hours per day spent usingelectronic media in 2009 and 1999. (Use ?2009 ? ?1999. Round youranswers to two decimal places.)

_______ to _______ hours

Interpret the interval.
o We are 98% confident that the true difference inmean number of hours per day spent using electronic media in 2009and 1999 is between these two values.
o We are 98% confident that the true mean numberof hours per day spent using electronic media in 2009 is betweenthese two values.
o We are 98% confident that the true mean numberof hours per day spent using electronic media in 1999 is betweenthese two values.
o There is a 98% chance that the true mean numberof hours per day spent using electronic media in 2009 is directlyin the middle of these two values.
o There is a 98% chance that the true differencein mean number of hours per day spent using electronic media in2009 and 1999 is directly in the middle of these two values.

(everything bold needs an answer)