The Linguist List is a mailing list focussed on jobs, software and other interests related to linguistics (the scientific study of human language).

Two different researchers took random samples of messages from this mailing list to analyse.

There were 40 emails in the sample taken by Researcher 1 and 40 emails in the sample taken by Researcher 2.

The researchers now each want to estimate the mean number of characters in an email subject line (subject_length) for this mailing list.

Use the plots above to answer the following questions.

A research question that asks What is the mean subject line length for emails in Researcher 1's sample? would require a sample-to-population inference. [ Select ] ["FALSE", "TRUE"]

The mean subject line length for Researcher 1's sample is approximately [ Select ] ["83", "33", "183"] .

The standard deviation of subject line length for Researcher 1's sample is approximately [ Select ] ["163", "63", "13"] .

The variability of the data in Researcher's 1 sample is [ Select ] ["pretty similar to", "quite different to"] the variability of the data in Researcher's 2 sample.

If both researchers construct VIT bootstrap confidence intervals, Researcher 1's will be [ Select ] ["a similar width to", "narrower than", "wider than"] Researcher 2's.

Flag question: Question 2

Question 22.5 pts

Researchers 3 and 4 are also interested in the Linguist List email data, but instead of the length of the subject lines, they have taken random samples and labelled the messages as either 'information about software' or 'not information about software'.

Researcher 3 had a sample of 96 emails, of which 5 were information about software and Researcher 4 had a sample of 96 emails, of which 53 were information about software .

Use this information to answer the following questions.

You may find the simple modelling toolLinks to an external site. helpful to your thinking.

A research question that asks What proportion of the emails in Researcher 3's sample are information about software ? would require a sample-to-population inference (enter TRUE or FALSE).

Rounded to the nearest whole number (e.g. 21%), % of Researcher 3's emails were information about software and % of Researcher 4's emails were information about software .

If both researchers constructed VIT bootstrap confidence intervals for the proportion of all emails in the Linguist List that were information about software , the confidence interval constructed by Researcher would be less precise as the interval would be (enter narrower or wider) .

Flag question: Question 3

Question 35 pts

Previous research has lead to the following two claims.

The mean number of words in the message for lecturer's emails is 263.3.

36 of lecturer's emails have at least one question mark in the message.

A random sample of emails was taken from the Linguist List email data to investigate these claims.

Load the sample data into iNZight Lite using this link and use the Summary and VIT tab to answer the following questions.

The sample size is .

A mean of 263.3 (enter is or is not) one of the plausible values provided by a VIT bootstrap confidence interval for the mean number of words in the message.

Therefore, the claim about the mean number of words in the message for emails (enter is or is not) supported by a VIT bootstrap confidence interval for the mean number of words in the message.

A proportion of 36 (enter is or is not) one of the plausible values provided by a VIT bootstrap confidence interval for the proportion of emails that have at least one question mark in the message.

Therefore, the claim about the proportion of emails that have at least one question mark in the message (enter is or is not) supported by a VIT bootstrap confidence interval for the proportion of emails that have at least one question mark in the message.

The population referred to in the claim (enter is or is not) the same as the population the sample was taken from. IS THIS RIGHT