ASSESSMENT TASK

General instructions and dataset guide -

This assessment task uses the Longitudinal Survey of ACU Student Health and Wellbeing, a (fictional) cohort study involving a survey administered to students on enrolment with ACU (first year baseline) and selected follow up data (during third year). For this task, you are presented with baseline data, along with selected follow-up data (where indicated) on: Road traffic accidents.

Assessment task -

Please provide answers to all of the following six questions:

1. In your SPSS file, age (at time of enrolment) is given as a continuous variable.

a. Please check the age variable for outliers. If you find students that are younger than 16 or older than 80 then please delete those values (do not delete the whole participant) and report how many outliers you found and what their value for age was. What are your initial thoughts on the distribution of age? Is the distribution sensible? If not, what will you do? (HINT: Do this before continuing on with the rest of the task). What are the mean and standard deviation and the minimum and maximum values for age?

b. Describe the distribution of age. Which is the best summary measure to use for age?

c. Recode "age" into a new variable (named "age_category") using the guide from the table below and adding the words from the Description column as value labels for your categorical age variable:

What is the frequency (% and number) of students in each of these new age categories? Produce a table, suitable for publication, to present this data.

2. Create a table that provides descriptive statistics (variables measured at baseline) for ACU students overall (including n and % values, respectively mean and standard deviation, or median and interquartile range, as appropriate). Please provide descriptive statistics for all variables apart from the 'cohort' variable and the 'RTA_twoplus_crashes' variable. Then, provide a written description (2-3 paragraphs) of your findings that informs the reader about the ACU cohort.

3. Perform a statistical test(s) that compares the mean scores for aggression, thrill seeking and risk acceptance scores across the following demographics:

a. Gender (male/female)

b. Metropolitan background status (metro/non-metro)

c. Study mode (fulltime/part-time)

d. One or more road traffic accidents in the past 12 months (from follow-up survey; one or more accidents/none)

e. Two or more road traffic accidents in the past 12 months (from follow-up survey; two or more accidents/none)

Present your results in a table (use Table 1 in the Turner et al. paper as a guide - Note: report standard deviations in place of 95% CIs)

Provide a brief interpretation of your findings.

4. Using "RTA_one_crash" as the dependent variable, perform a binary logistic regression using the following predictor variables (potential confounders) relating to the RTA study:

a. Provide a table of odds ratios, confidence intervals and significance values for each predictor variable. For categorical predictor variables please list all categories and mark one of them as the reference category. For question four you just need to provide the table with all the information, but no text that describes your findings.

5. After adjusting for potential confounders, how do living arrangements impact upon road traffic accidents? (Data contained in the table produced in 4a is sufficient to answer this question with a few lines of text).

6. Provide a preliminary interpretation and conclusion about the influence of the 'driving behaviour' predictor variables on road traffic accidents (i.e. what is the effect of changes (increase or decrease) in "driver aggression", "Thrill seeking" and "Risk acceptance" on the odds of experiencing a road traffic accident?)

Attachment:- Assignment Files.rar