Overview

The Quantitative Consulting Unit (QCU) is part of the Research Office at Charles Sturt University that provides statistical support to research students and staff across the University.

QCU's core statistics support services include:

    General consultancy on statistical theory and application related to research problems

    Tutorials/training for learning and using analysis software such as R, SPSS, G*Power3.1, @Risk and Netica

    Advice on, support to, and completion of statistical analysis needed from research projects

    Workshops for HDR students and researchers to enhance their statistical skills in special topics such as design and analysis of experiment, statistical graphics, and Bayesian Networks.

Through the QCU research Honours, Masters and PhD students are offered a free initial consultation to provide a kick-start to their research to ensure that they embark on a path that will lead to successful completion of their research.  Subject to the terms and conditions specified in QCU's service policy, further assistance is available to meet various needs for statistics support throughout the whole process of their research studies.  CSU staff researchers are also entitled receiving QCU's statistics support services as detailed in our service policy.

The QCU also runs statistics workshops/tutorials - if you are a CSU student or staff member doing research and wishing to update your quantitative statistical skills, these workshops/tutorials could be just what you need. If you are external to CSU you are welcome to attend, to register your interest in our workshops, please email the QCU Administrator - qcu@csu.edu.au

 

*** Latest News***

G*Power workshop

The main purpose underlying statistical power analysis is to help the researchers to determine the smallest sample size that is suitable to detect the effect of a given test at the desired level of significance.  Developed at the Institute for Experimental Psychology in Dusseldorf Germany, the free software G*Power was designed as a general stand-alone power analysis program for statistical tests commonly used in disciplines such as agriculture, animal studies, health science, social and behavioural research, etc.  Power analysis is often intentionally or unintentionally ignored because it involves several statistical concepts which may not be necessarily straight forward to understand and the power analysis formula is very model specific.  G*Power provides an effective and very user-friendly solution for promoting the application of power analysis as part of the routine statistical data analysis procedure.  It offers a wide variety of calculations related to power analysis along with graphics and protocol statement outputs.  Quantitative Consulting Unit (QCU) is going to launch the first one-day hands-on practice workshop for learning power analysis using GPower 3.1 for researchers (HDR students and staff members) at CSU.  The actual teaching and learning time is five hours divided into three sessions.  The workshop program details are as follows.

  • 9:30am – 10am: registration and morning tea
  • 10am – 12pm: learning and practice session 1 – attendees install the GPower software onto their laptop computers; basic concepts of statistical power analysis will be introduced; a first touch with GPower; apply GPower to perform power analysis for five different statistical models.
  • 12pm – 1pm: the lunch hour
  • 1pm – 2:30pm: learning and practice session 2 – attendees continue to learn and practise power analysis using GPower for six more statistical models including the ANOVA model with more than two categorical factors.
  • 2:30pm – 3pm: afternoon tea break
  • 3pm - 4:30pm: learning and practice session 3 – attendees continue to learn and practise power analysis using GPower for five more statistical models including a simple repeated measure regression model case.
  • 4:30pm: close of the workshop
  • Cost $100 per person

The GPower user manual (both the hard copy and the electronic copy) will be prepared for the attendees for the workshop.  A tentative date for this workshop is on 15 December (Friday) 2017.  This is a fee-based workshop for the purpose that anyone who would register and pay for the workshop is most likely to commit him/her time and effort for the expected learning outcomes.  This is going to be a face-to-face workshop.  We ask all interested researchers at CSU to express their interest.  We will run the workshop as scheduled and sketched as above with minimum two confirmed attendees.  The upper limit of the number of attendees for each workshop is 10 for a better learning and practice result.  If the demand is high we will run multiple sessions of this one-day workshop to suit the need, as well as running on different campus as long as the demand requires.  Please send us your Expression of Interest feedback by the end of November and pay the nominated fee by 12 December 2017.

 

Bi-Monthly Meeting

Our next mid-month R tutorial online Q & A session will be held Tuesday December 19 2017.

A three-hour mid-month R tutorial online Q & A session will be run between the monthly cRow meetings to help beginner R users who participated in the R tutorials.
Participants will be invited to attend a Bridgit meeting accompanied with an ad hoc teleconference meeting so that you may dial in the extension number 32229 or 6933 2229 (External) to talk with John at the same time if necessary. Please advise John if you plan to join in gxie@csu.edu.au

Modified QCU service Policy

(Effective 1st September 2017)

QCU provides a free (30-minute session) initial consultation service which may lead to

1.Further paid consultation services - $150 per hour (if necessary an extra free (30-min.) consultation session is available for further confirming the terms and conditions of the consulting services)

OR

2. Further free collaboration services (subject to an upper limit of the service hours allocated for each case) requiring co-authorship/ownership of research publications/outcomes

  •   A time limit (per case) available for the free services will be as follows:

10 hours for honours and masters students;

20 hours for doctoral candidate students;

20 hours for staff members. 

Service priority will be applied in the order of:

Masters by research and Doctoral students (first priority);

Staff members (second priority); and

Masters by course and Honours students (third priority).

  • Any consultation time which exceeds the limit may be charged at $75 per hour unless an exemption is granted by the Research Office (subject to the availability of QCU's consulting resources). 

Only the time directly related to the consulting services is counted as 'consulting hours' – for example, the time spent with the client in phone-call or email communications or in face-to-face meetings, and time spent on performing data treatment and/or analysis and/or presenting the analysis outcomes; time spent on background reading, finding reference materials or familiarisation with or learning specific topics related to the consulting problem normally will not be counted.

  1. Understanding and defining the research problem(s) qualitatively and quantitatively so that relevant information/data are collected and analysed using the most suitable analysis methodology are essential for students at all levels.   The use of QCU's services (free or paid) should not become an excuse for students not being able to understand and/or interpret their research outcomes/findings – if so, this may seriously compromise the integrity of their academic assessment outcomes.  Therefore, under their supervisor's guidance, students should try their best to build up their own ability in performing valid data analyses and correctly interpreting their analysis results with the help of QCU's services.

 

Next cRow meeting 

R is a free powerful open source programming language for statistical computing, data analysis and graphical visualization that that operates on all operating systems. Among R's strengths are its built-in tools for inferential statistics, its compact modelling syntax and its data visualisation capabilities – it produces fully-customisable, publication-quality graphics. In addition, R's open source nature and its add-on "packages" have allowed it to keep up with the leading edge in academic research. For all its strengths, though, R has an admittedly steep learning curve; the first steps towards learning and using R can be challenging.

Our next cRow meetings will be held on Tuesday December 12 Please contact me for the location and time, or if you would like to be kept informed of when these meetings are happening please send an email to cmoffat@csu.edu.au where your name will be added to the emailing list for this group.  The meetings are held once a month days and times will vary.  Keep an eye on this page meetings will run for 2-3 hours.

LaTeX Users Group (LUG) Meetings

LaTeX is a free powerful open source document preparation system that is widely used amongst the scientific research community. More and more LaTeX is being used by people who need to write documents that include complex non-Latin scripts or people who simply want to produce professional documents. LaTeX offers authors ready-made commands for common requirements such as chapter headings, footnotes, cross-references and bibliographies (and it can be used in conjunction with your EndNote library). That LaTeX is also the choice of people working in mathematical disciplines, because it has capabilities in mathematical typesetting that leave standard word-processing facilities for dead. For all its strengths, though, LaTeX has an admittedly steep learning curve; the first steps towards learning and using LaTeX can be challenging.

  • hear talks on LaTeX -related topics
  • share knowledge and experience
  • provide LaTeX beginners with an opportunity to meet more experienced users
  • support one another to learn how to use LaTeX effectively and efficiently

This service is for anyone who is currently using LaTeX, trying to learn how to use LaTeX or someone who thinks that LaTeX might provide a solution to their document preparation needs.

To this end, the CSU LaTeX User's Group has been formed and is dedicated to bringing together LaTeX users to exchange knowledge and inspire new users and will be meeting monthly both online and face-to-face in Wagga. All research candidates, other staff and students are very welcome to attend these meetings. The meetings will be either face to face or via Bridget and teleconference.

Due to the low interest shown in this group, LaTeX will now consist of a direct contact service. If you would like some assistance/help with LaTeX please contact John directly on 02 6933 2229 or email gxie@csu.edu.au.  if you would like to be kept informed regarding this group please email cmoffat@csu.edu.au

Workshops

Workshops and tutorials:

  • In the second session of each cRow meeting, a free one-hour tutorial of how to use R for statistical data analysis for beginner R users will be offered
  • Mid-monthly R Tutorial participants drop in session via Bridget meeting to provide guidance/answer/support/help to questions in using R for statistical analysis. Starting from 17 October (Tuesday). If you require any further information please contact us.
  • The fee based workshop on design and analysis of experiment using G*Power will be held December 15 2017, see above notice for details.
  • The fee based workshop on learning Bayesian Networks by hands-on practice with examples using Netica is expected to be ready  in early 2018

 

New: FREE Power analysis software.

The free power analysis software G*Power3.1 and its user manual are now available located under the resource tab.

The power of any test of statistical significance is defined as the probability that it will reject a false null hypothesis. Alternatively, the statistical power is defined as the probability of NOT committing a Type II error (which does not reject the null hypothesis when it is false).  Power analysis is normally conducted before the data collection.  The main purpose underlying power analysis is to help the researcher to determine the smallest sample size that is suitable to detect the effect of a given test at the desired level of significance.   G*Power was designed as a general stand-alone power analysis program for statistical tests commonly used in social and behavioral research. G*Power 3 is a major extension of, and improvement over, the previous versions. 

 G*Power3.1 offers five different types of statistical power analysis:

1. A priori (sample size N is computed as a function of power level 1 − β, significance level α, and the to be detected population effect size)

2. Compromise (both α and 1 − β are computed as functions of effect size, N, and an error probability ratio q = β/α)

3. Criterion (α and the associated decision criterion are computed as a function of 1− β, the effect size, and N)

4. Post-hoc (1− β is computed as a function of α, the population effect size, and N)

5. Sensitivity (population effect size is computed as a function of α, 1 − β, and N)