401077 Introduction to Biostatistics
Read ‘Description of your data set.docx’ for the descriptions of the variables.
This assignment is assessing your skills, not the skills of the computer. You will need to include graphs from R Commander into your assignment but all other R Commander output will attract 0 marks and is discouraged. It is your task to identify the relevant results in the R Commander output and write these up in your assignment.
Question 1 (18 marks)
Read the paper Davoren, M. P., Shiely, F., Byrne, M., & Pe
y, I. J XXXXXXXXXXHazardous alcohol consumption among university students in Ireland: a cross-sectional study. BMJ open, 5(1), e006045.
Critically appraise of the statistical material in this paper against items 10, 12-17 of the STROBE checklist. Present your review as a XXXXXXXXXXword report.
Further instructions:
· Only review the provided paper Davoren et al, 2015. Do not read any other papers.
· Restrict your review to how well Davoren et al have documented their statistical methods – that is, items 10, 12-17 of STROBE only. You may not have to address every item; just describe the major strengths and weaknesses of the authors’ descriptions of their statistical methods and results.
· For each important STROBE item:
· state whether you believe the STROBE item is met or not,
· support your judgment with proof or examples from the paper, and
· describe why this inclusion or exclusion is important / how it will impact on the reader’s understanding and decision making.
· The XXXXXXXXXXwords is a guideline not a rule. There are no penalties for exceeding this guideline.
· There are no marks for adding a reference list. Referencing is optional.
Question 2 (22 marks) Note: Students will get different answers as the data sets differ.
Using the University of Eastern Sydney data set assigned to you for your Assignments and R Commander address the following research question:
Does student well-being score (WEMWBS) predict self-reported average alcohol consumption (alc and/or logalc) after co
ecting for gender (sex) for University of Eastern Sydney students?
Further instructions:
· You should only use the variables ‘alc’ and/or ‘logalc’, ‘WEMWBS’ and ‘sex’.
· Co
ecting for ‘sex’ is just including ‘sex’ in the regression model. When sex is in the model all other variables are co
ected for it.
· Do report the results of your descriptive analyses
· Well labelled graphs can be copied from R Commande
· Summary statistics and tables should be manually typed
· Summarise the main findings of your descriptive analyses in words and describe how these findings inform your expectations and interpretation of the more complex models.
· Do report the results of your statistical inference and/or regression models
· Any fitted regression models should be manually typed and described in the text.
· Any hypothesis tests should contain all relevant information (use the 5 step method to be sure)
· Any other results such as confidence intervals should be manually typed and described in the text.
· Summarise the main findings of your regression model and statistical inference in one or two paragraphs.
· If using ‘logalc’, results are expressed in units of log standard drinks (or use the exponential (exp or ex) function on your calculator if you wish to convert your results back into standard drinks).
· Do remember to answer the research question
· Write a final paragraph which summarises the key findings of your analysis and your answer to the research question.
· Do check the Learning Guide for the marking criteria
· Do write your answers yourself and keep them private.
untitled
Hazardous alcohol consumption
among university students in Ireland:
a cross-sectional study
Martin P Davoren,1 Frances Shiely,1 Michael Byrne,2 Ivan J Pe
y1
To cite: Davoren MP,
Shiely F, Byrne M, et al.
Hazardous alcohol
consumption
among university students in
Ireland: a cross-sectional
study. BMJ Open 2015;5:
e XXXXXXXXXXdoi:10.1136
mjopen XXXXXXXXXX
▸ Prepublication history fo
this paper is available online.
To view these files please
visit the journal online
(http:
dx.doi.org/10.1136
mjopen XXXXXXXXXX).
Received 5 July 2014
Revised 3 October 2014
Accepted 6 October 2014
1Department of Epidemiology
and Public Health, University
College Cork, Cork, Ireland
2Student Health Department,
University College Cork, Cork,
Ireland
Co
espondence to
Martin P Davoren;
XXXXXXXXXX
ABSTRACT
Objective: There is considerable evidence of a cultural
shift towards heavier alcohol consumption among
university students, especially women. The aim of this
study is to investigate the prevalence and co
elates of
hazardous alcohol consumption (HAC) among university
students with particular reference to gender and to
compare different modes of data collection in this
population.
Setting: A large Irish university.
Design: A cross-sectional study using a classroom
distributed paper questionnaire.
Participants: A total of 2275 undergraduates completed
the classroom survey, 84% of those in class and 51% of
those registered for the relevant module.
Main outcome measures: Prevalence of HAC
measured using the Alcohol Use Disorders Identification
Test for Consumption (AUDIT-C) and the proportion of
university students reporting 1 or more of 13 adverse
consequences linked to HAC. HAC was defined as an
AUDIT-C score of 6 or more among males and 5 or more
among females.
Results: In the classroom sample, 66.4% (95% CI 64.4
to 68.3) reported HAC (65.2% men and 67.3% women).
In women, 57.4% met HAC thresholds for men. Simila
patterns of adverse consequences were observed among
men and women. Students with a hazardous
consumption pattern were more likely to report smoking,
illicit drug use and being sexually active.
Conclusions: The findings highlight the high prevalence
of HAC among university students relative to the general
population. Public policy measures require review to
tackle the short-term and long-term risks to physical,
mental and social health and well-being.
INTRODUCTION
Problem alcohol use is an ongoing, worldwide
phenomenon of considerable concern.1–4
Ireland displays a unique relationship with
alcohol with significantly higher intakes than
the Organisation for Economic Co-operation
and Development (OECD) average,5 the USA6
and the UK.7 In addition, the Eurobaromete
study notes that Irish adults report hazardous
drinking more frequently than any other EU
country.2 Recently, it was reported that 54% of
Irish adults reported hazardous alcohol con-
sumption (HAC).8 University students repre-
sent a unique subsection of society.9 In this
environment, there is a culture of HAC,10
defined as “a pattern of alcohol consumption
that increases the risk of harmful consequences
for the user or others”.11 The findings from
the 2002 to 2003 College Lifestyle Attitudinal
National Survey in Ireland indicated that at
least 60 in every 100 drinking occasions among
students involved HAC.10 This suggests that
HAC is a cultural norm among university stu-
dents in Ireland. Previous research using the
Alcohol Use Disorders Identification Test fo
Consumption (AUDIT-C) scale has reported
lower levels of hazardous consumption among
non-university peers (36%)12 and the general
population (54%).8
Strengths and limitations of this study
▪ The cu
ent study employed standardised methods
for the measurement of hazardous alcohol con-
sumption and a rigorous probability proportion to
size sampling strategy for the classroom-based
survey.
▪ In regard to gender and course of study, the
study participants were representative of the uni-
versity undergraduate student population from
which they were sampled.
▪ The overall response rate, defined in terms of stu-
dents registered for specific modules, was 51%.
However, the response rate for those in attendance
at lectures was 84%. There was over-representation
of first year students and under-representation of
fourth year students in the sample.
▪ Although the response rate was low, it is simila
to that achieved in major international studies of
student alcohol consumption. It should also be
noted that the majority of non-respondents were
students absent from class during the survey.
The latter group of students is unlikely to have a
more favourable pattern of alcohol consumption
than that observed in this study. Thus, this study
may be regarded as reporting the lower bound
estimates of hazardous alcohol consumption in
Irish university students.
Davoren MP, et al. BMJ Open 2015;5:e XXXXXXXXXXdoi:10.1136
mjopen XXXXXXXXXX
Open Access Research
http:
dx.doi.org/10.1136
mjopen XXXXXXXXXX
http:
dx.doi.org/10.1136
mjopen XXXXXXXXXX
http:
crossmark.crossref.org/dialog/?doi=10.1136
mjopen XXXXXXXXXX&domain=pdf&date_stamp= XXXXXXXXXX
http:
mjopen.bmj.com
In a number of countries, hazardous drinking has
een identified as the number one substance abuse
problem during university life.10 13–15 A comprehensive
eview of drinking habits in European universities found
a range of studies suggesting that hazardous levels of
alcohol consumption were associated with increased
levels of smoking and drug use.16 In Ireland, the
College Lifestyle Attitudinal National survey in Ireland
noted high levels of alcohol consumption and other risk-
taking behaviours among students.10 However, these
data were collected over 10 years ago and there is a clea
need for contemporary Irish data to guide public policy
esponse to this issue.
Differences in the volume of alcohol consumed by
women and men in universities have been reported in
some studies XXXXXXXXXX–20 Ha
ell and Karim18 found that
male students reported significantly higher alcohol
intakes than their female peers, a result mi
ored in
other studies.19 20 More recently, international research
has noted a shift in alcohol consumption among univer-
sity students with some studies reporting similar patterns
of hazardous drinking in men and women.21 A review
investigating the consequences of alcohol misuse noted
that gender differences in relation to the adverse conse-
quences of alcohol consumption were also beginning to
decrease.22 For instance, Hoeppner et al23 found that
females were more likely to exceed their recommended
weekly alcohol allowance than their male counterparts.
Thus, the aim of this study was to investigate the preva-
lence of HAC and the adverse consequences associated
with its use among university students in Ireland, with
particular reference to gender differences.
METHODS AND PARTICIPANTS
Undergraduate students attending one large university in
Ireland, University College Cork (UCC), were eligible fo
inclusion in the classroom-based study which was focused
on health and lifestyle with particular reference to
alcohol consumption. Students were sampled at degree
programme level using probability proportional to size
(PPS) sampling. We estimated the required sample size at
2686 students, based on an undergraduate student popu-
lation of 12 475, a required precision of 1.5% and an
expected prevalence of HAC of 73%, based on an earlie
unpublished masters dissertation.24 Lecturers or module
coordinators were contacted to request permission to dis-
tribute and collect questionnaires during 15 min of
lecture time on a date convenient to them between 12
March and 23 March 2012. Students were
iefed orally
and in writing (on the front sheet of the questionnaire)
on the aims and objectives of the study including details
of the confidential, anonymous and voluntary nature of
the exercise. Participating in the research was presumed
to imply consent. To enhance the response rate, the dis-
tribution of questionnaires was avoided on Mondays and
Fridays due to Irish student social and recreational
patterns.
Of the lecturers/module coordinators approached to
facilitate the study, 94.3% agreed to cooperate. A total,
2332 students completed this face-to-face lecture theatre-
ased survey; 57 students were subsequently identified as