Scribd
Upload
30 views11 pages

Stats2016 PDF

Uploaded by

astrala5
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
30 views11 pages

Stats2016 PDF

Uploaded by

astrala5
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
You are on page 1/ 11
ISS1 AL4S64W1 Degree of Master of Science Social Science of the Internet Digital Social Research Methods: Statistics Michaelmas Tem 2016 “Thursday 8 December 2016 9:30am-1230 pm Pens tr the nsw to each question ona separate sheet Answer al questions Do nttum ove unt tld that yom may do 50 Instructions. Please answer ll questions below. Number your ansivers to correspond tothe {question numbers below. In caeulating your fina grade on this assessment the questions are ‘Weighted according to ther relative difficulty: Question I~ 10%; Question 2 = 10%; (Question 3~ 15% Question 4~ 15% Question 5= 35%; Question 6= 15%. Please ear this ‘mind when considering the amount of ime and text to dedicate to each question, ‘Question 1, [10%] Below are three statements about p-values, Assume that thenull hypothesis that ao relationship exists; that i, Ho: pavanteter~ O, and that you have taken random sample of data and performed a hypothesis test Only one othe following statements about p-values is tue (a) p quantifies the probability of observing results atleast as extreme as the ones observed ‘assuming tat the null hypothesis tue. (B) Ips very large then we ean be confident that the null hypothesis is tue (©)p quantities the proportion of reported results that are fase positives Identify the true statement and explain why, showing inthe process your understanding of| what p-values mean. Use atleast one example “Introduction to questions 2-5, You ae doing an investigation into whether afeling of being left uti relate to interest in the intemet. You also wonder whether the relatcnship would change if you contlled for edveation. The results of one of your analyses are below in & Series of igus. ‘You are making use of OxIS data with the dataset named exam, The 3 variables used in your analysis re Ggche at is jour nignest eabeatlonai or vocational quoli#ication? cee Lefeout.ehr Wo often do you feel ett aut? 3 cts ‘Question 2, [10%] Figure 1 shows frequency tables for the three variables. Intepret these tables. ‘Question 3, [15%] Figure 2 shows the relationship between fecing left out andinterest in the Internet in the form ofa twoeway table. Interpret this table. What do you conelude based on these results? Cite statistics & specific percentages to suppor your conclusion, ‘Question 4, [15%] Figure 3 shows the relationship between education and felig left out in the form of a two-way table Inerpet this table, What do you conclude based on these resulls? Cite statsties & specific pereentags fo support your conclusion ‘Question 5, [35%] Figure 4 Figure 7 show the relationship between feeling left out and {interest in the Internet after contolling foreach category of education. Interpre each table, ss al4s6awt ‘What do you conclude based on these results? Cite statistics and specific percentages in support ‘Question 6, [15%] As pat of a different investigation you look whether hours of Internet use can predict the number of bad experiences onthe internet. You make use of two variables: ‘number of bad experiences, which is the variable nbad, and isa count of numberof bad experiences on the Intemet Hours of Ineret use, ine, i simple count ofthe number of hour respondent ison the Intemet during an average week. You perform aregrestion, and ‘he output from your regression plus descriptive statistics is shown in Figure 8, Interpret the ‘output Cite specifi statistics to support your interpretations, Sst AI46S301 TunN over

You might also like