Dr Garth Tarr

Dr Garth Tarr

Lecturer

School of Mathematical and Physical Sciences

Career Summary

Biography

Garth received his PhD in Mathematical Statistics from the University of Sydney and has held postdoctoral positions at the University of Sydney and the Australian National University. His diverse interests include robust statistics, data visualisation, model selection, econometric modelling, educational research, meat science and biostatistics. He has received a number of citations for his teaching and was awarded first prize for the best oral presentation by a student at the Australian Young Statisticians Conference (2013) as well as the EJG Pitman Prize for the most outstanding talk presented by a young statistician at the Australian Statistical Conference (2012).

Qualifications

  • PhD, University of Sydney
  • Bachelor of Science, University of Sydney
  • Bachelor of Commerce, University of Sydney

Keywords

  • model selection
  • robust statistics
  • statistics

Fields of Research

Code Description Percentage
010405 Statistical Theory 40
010401 Applied Statistics 30
010499 Statistics not elsewhere classified 30

Professional Experience

UON Appointment

Title Organisation / Department
Lecturer University of Newcastle
School of Mathematical and Physical Sciences
Australia

Academic appointment

Dates Title Organisation / Department
2/03/2015 - 26/06/2015 Research Fellow The University of Sydney
School of Mathematics and Statistics
Australia
7/04/2014 - 27/02/2015 Postdoctoral Research Fellow Australian National University
Mathematical Sciences Institute
Australia
1/10/2013 - 31/03/2014 Research Associate The University of Sydney
School of Mathematics and Statistics
Australia

Membership

Dates Title Organisation / Department
1/11/2015 -  International Biometrics Society International Biometrics Society
Australia
1/01/2014 -  American Statistical Association American Statistical Association
United States
1/01/2011 -  Australian Mathematical Society Australian Mathematical Society
Australia
1/01/2009 -  Statistical Society of Australia Inc. NSW SSAI
Australia

Professional appointment

Dates Title Organisation / Department
1/01/2015 -  Statistical Consultant

The Meat Standards Australia pathways committee is the pre-eminent meat science research and development committee in Australia comprised of academics and industry representatives.

Meat Standards Australia Pathways Committee
Australia

Awards

Award

Year Award
2016 Teaching Excellence and Contribution to Student Learning
Faculty of Science and Information Technology, University of Newcastle
2013 First prize for the best oral presentation by a student at the 2013 Australian Young Statisticians Conference
Statistical Society of Australia Inc.
2012 EJG Pitman Prize for the most outstanding talk presented by a young statistician at the 2012 Australian Statistical Conference
Statistical Society of Australia Inc.

Teaching Award

Year Award
2011 University of Sydney Vice-Chancellor’s Award for Systems that Achieve Collective Excellence in Teaching and Learning
The University of Sydney
2010 University of Sydney Business School Excellence in Tutoring Award
The University of Sydney

Invitations

Committee Member

Year Title / Rationale
2013 SSAI Young Statisticians Conference

Organiser

Year Title / Rationale
2017 International Conference on Robust Statistics
2017 Invited paper session ‘Advanced Graphical and Computational Methods’, International Conference on Econometrics and Statistics (EcoSta)
2015 Much more than U-statistics: A symposium to celebrate Neville C. Weber
2011 SSAI Young Statisticians Conference

Speaker

Year Title / Rationale
2016 International Conference on Computational Statistics
2016 Institute of Mathematical Statistics Asia Pacific Rim Meeting
2015 International meeting on beef and lamb carcase grading to underpin consumer satisfaction
2015 International Conference on Robust Statistics
2015 Much more than U-statistics: A symposium to celebrate Neville C. Weber

Teaching

Code Course Role Duration
STAT1070 Statistics for the Sciences
Faculty of Science and Information Technology, University of Newcastle
Course coordinator 25/07/2016 - 11/11/2016
STAT1070 Statistics for the Sciences
Faculty of Science and Information Technology, University of Newcastle
Compressed mode summer school offering
Coordinator 4/01/2017 - 24/02/2017
STAT1070 Statistics for the Sciences
The University of Newcastle - Faculty of Science and Information Technology
Course coordinator 22/02/2016 - 10/06/2016
MATH1905 Statistics (Advanced)
The University of Sydney
Lecturer and course coordinator 27/08/2013 - 27/11/2013
Edit

Publications

For publications that are currently unpublished or in-press, details are shown in italics.


Journal article (8 outputs)

Year Citation Altmetrics Link
2017 Konarska M, Kuchida K, Tarr G, Polkinghorne RJ, 'Relationships between marbling measures across principal muscles', MEAT SCIENCE, 123 67-78 (2017) [C1]
DOI 10.1016/j.meatsci.2016.09.005
2016 Tarr G, Müller S, Weber NC, 'Robust estimation of precision matrices under cellwise contamination', Computational Statistics and Data Analysis, 93 404-420 (2016)
DOI 10.1016/j.csda.2015.02.005
Citations Scopus - 4Web of Science - 3
2015 Tarr G, Weber NC, Mueller S, 'The difference of symmetric quantiles under long range dependence', STATISTICS & PROBABILITY LETTERS, 98 144-150 (2015) [C1]
DOI 10.1016/j.spl.2014.12.022
Citations Scopus - 1Web of Science - 1
2015 Pethick, Thompson, Polkinghorne, Bonny, Tarr GM, Treford, et al., 'Prédiction de la qualité de la viande de ruminants (Prediction of quality of ruminant meat)', Viandes et produits Carnés (Meat and Meat Products), (2015)
2014 Dancer D, Morrison K, Tarr G, 'Measuring the effects of peer learning on students' academic achievement in first-year business statistics', Studies in Higher Education, (2014)

Peer-assisted study session (PASS) programs have been shown to positively affect students' grades in a majority of studies. This study extends that analysis in two ways: cont... [more]

Peer-assisted study session (PASS) programs have been shown to positively affect students' grades in a majority of studies. This study extends that analysis in two ways: controlling for ability and other factors, with focus on international students, and by presenting results for PASS in business statistics. Ordinary least squares, random effects and quantile regression models have been used to model data from first-year business statistics students. The findings indicate that the impact of PASS has remained highly significant in both years for both local and international students but is more pronounced for international students. We also find that lower-achieving students derive a higher marginal benefit from attending PASS than higher-achieving students using quantile regression. These findings are significant for institutions implementing similar programs as well as institutional efforts to enhance student performance and improve student retention, or specifically to support international students more effectively. © 2014 © 2014 Society for Research into Higher Education.

DOI 10.1080/03075079.2014.916671
Citations Scopus - 3Web of Science - 2
2012 Tarr G, 'Small sample performance of quantile regression confidence intervals', Journal of Statistical Computation and Simulation, 82 81-94 (2012)

Since the introduction of regression quantiles for estimating conditional quantile functions there has been ongoing research into how best to construct confidence intervals for pa... [more]

Since the introduction of regression quantiles for estimating conditional quantile functions there has been ongoing research into how best to construct confidence intervals for parameter estimates. The three main methods are direct estimation, rank test inversion and resampling methods. Kocherginsky et al. [Practical confidence intervals for regression quantiles, J. Comput. Graph. Statist. 14 (2005), pp. 41-55] gave an overview of some of the available procedures. Five years on, the aim of this paper is to revisit and extend their analysis, evaluating additional techniques with a focus on smaller sample sizes and more extreme conditional quantiles. In particular, we find the percentile bootstrap (pbs) to be an eminently viable alternative for confidence interval construction. We show that it provides empirical coverage probabilities generally as good as, or better than, the other more complex resampling methods. Furthermore, pbs confidence intervals typically exhibit smaller average lengths across a variety of models than those based on the rank inversion methods which, like the pbs, avoids explicitly estimating asymptotic variances. © 2012 Taylor and Francis Group, LLC.

DOI 10.1080/00949655.2010.527844
Citations Scopus - 5Web of Science - 5
2012 Tarr G, Müller S, Weber N, 'A robust scale estimator based on pairwise means', Journal of Nonparametric Statistics, 24 187-199 (2012)

We propose a new robust scale estimator, the pairwise mean scale estimator P n , which in its most basic form is the interquartile range of the pairwise means. The use of pairwis... [more]

We propose a new robust scale estimator, the pairwise mean scale estimator P n , which in its most basic form is the interquartile range of the pairwise means. The use of pairwise means leads to a surprisingly high efficiency across many distributions of practical interest. The properties of P n are presented under a unified generalised L-statistics framework, which encompasses numerous other scale estimators. Extensions to P n are proposed, including taking the range of the middle t × 100% instead of just the middle 50% of the pairwise means as well as trimming and Winsorising both the original data and the pairwise means. Furthermore, we have implemented a method using adaptive trimming, which achieves a maximal breakdown value. We investigate the efficiency properties of the pairwise mean scale estimator relative to a number of other established robust scale estimators over a broad range of distributions using the corresponding maximum likelihood estimates as a common base for comparison. © 2012 American Statistical Association and Taylor & Francis.

DOI 10.1080/10485252.2011.621424
Citations Scopus - 3Web of Science - 3
TARR GARTH, 'QUANTILE BASED ESTIMATION OF SCALE AND DEPENDENCE', Bulletin of the Australian Mathematical Society, 1-3 [C3]
DOI 10.1017/S0004972715000283
Show 5 more journal articles

Conference (1 outputs)

Year Citation Altmetrics Link
2015 Hendry GD, Tarr GM, Morrison K, 'The benefits of peer review versus peer observation: Facilitators¿ experiences in a peer assisted study program' (2015)

Software / Code (3 outputs)

Year Citation Altmetrics Link
2016 Tarr GM, Patrick E, 'edgebundleR: Circle plot with bundled edges', 0.1.4 (2016)
2015 Tarr GM, 'pairsD3: D3 scatterplot matrices', 0.1.0 (2015) [G1]
2015 Tarr GM, Mu¨ller S, Welsh AH, 'mplot: Graphical model stability and model selection procedures', 0.7.7, CRAN (2015) [G1]

Report (3 outputs)

Year Citation Altmetrics Link
2016 Tarr GM, 'Parallel computation in R', International Biometrics Society (2016)
2016 Tarr GM, 'Getting data into R' (2016)
2015 Tarr GM, Müller S, 'Much more than U-statistics: A symposium to celebrate Neville C. Weber' (2015)

Thesis / Dissertation (1 outputs)

Year Citation Altmetrics Link
2014 Tarr GM, Quantile Based Estimation of Scale and Dependence, University of Sydney (2014)
Edit

Grants and Funding

Summary

Number of grants 9
Total funding $53,456

Click on a grant title below to expand the full details for that specific grant.


20163 grants / $12,500

New Staff Grant$7,500

Funding body: Faculty of Science and Information Technology,The University of Newcastle

Funding body Faculty of Science and Information Technology,The University of Newcastle
Project Team

Garth Tarr

Scheme New Staff Grant Scheme
Role Lead
Funding Start 2016
Funding Finish 2016
GNo
Type Of Funding Internal
Category INTE
UON N

International Biometric Society Australasian Region Travel Grant$3,000

Travel grant to attend International Biometric Conference, Victoria, Canada, July 2016.


Funding body: International Biometric Society

Funding body International Biometric Society
Project Team

Garth Tarr

Scheme Early Career Researcher Travel Grant
Role Lead
Funding Start 2016
Funding Finish 2016
GNo
Type Of Funding External
Category EXTE
UON N

CARMA funding$2,000

Funding body: Priority Research Centre for Computer-Assisted Research Mathematics and its Applications (CARMA), The University of Newcastle

Funding body Priority Research Centre for Computer-Assisted Research Mathematics and its Applications (CARMA), The University of Newcastle
Project Team

Garth Tarr

Scheme Research Purposes
Role Lead
Funding Start 2016
Funding Finish 2016
GNo
Type Of Funding Internal
Category INTE
UON N

20153 grants / $7,100

International collaboration on beef and lamb carcase grading to underpin consumer satisfaction$3,000

Funding body: Meat and Livestock Australia

Funding body Meat and Livestock Australia
Project Team

David Pethick

Scheme MLA project L.EQT.1605
Role Investigator
Funding Start 2015
Funding Finish 2015
GNo
Type Of Funding External
Category EXTE
UON N

Australian National University Early Career Researcher Travel Grant$2,100

Funding body: Australian National University

Funding body Australian National University
Scheme Early Career Researcher Travel Grant
Role Lead
Funding Start 2015
Funding Finish 2015
GNo
Type Of Funding Internal
Category INTE
UON N

PVC Conference Assistance Grant$2,000

Funding body: Faculty of Science and Information Technology, The University of Newcastle | Australia

Funding body Faculty of Science and Information Technology, The University of Newcastle | Australia
Scheme PVC Conference Assistance Grant
Role Lead
Funding Start 2015
Funding Finish 2015
GNo
Type Of Funding Internal
Category INTE
UON N

20131 grants / $1,000

Statistical Society of Australia Inc. Golden Jubilee Travel Grant$1,000

Funding body: Statistical Society of Australia Inc.

Funding body Statistical Society of Australia Inc.
Scheme Golden Jubilee Travel Grant
Role Lead
Funding Start 2013
Funding Finish 2014
GNo
Type Of Funding External
Category EXTE
UON N

20121 grants / $25,000

Student diversity: What do we know about our students and how does it affect our teaching?$25,000

Funding body: The University of Sydney

Funding body The University of Sydney
Project Team

Meloni Muir

Scheme Widening Participation Grant
Role Investigator
Funding Start 2012
Funding Finish 2013
GNo
Type Of Funding Internal
Category INTE
UON N

20101 grants / $7,856

Knowing your students: A faculty wide initiative to provide student demographic data to support curriculum change$7,856

Funding body: The University of Sydney

Funding body The University of Sydney
Project Team

Kellie Morrison

Scheme Small Teaching Improvement and Equipment Scheme
Role Investigator
Funding Start 2010
Funding Finish 2011
GNo
Type Of Funding Internal
Category INTE
UON N
Edit

Research Opportunities

Statistical issues in evaluating the eating quality of meat

The beef industry in Australia is worth $13 billion annually and the sheep meat industry is worth another $4 billion. A key question concerning the red meat industry is the ability to predict the eating quality of cuts of meat. Doing this well has major financial implications for the industry. This project would focus on the statistical issues associated with predicting meat eating quality. Examples of subprojects include: the analysis of consumer data which often contains many outliers; determining the relative importance of eating quality factors such as flavour, tenderness and juiciness; modelling issues in the presence of missing or limited amounts of data – this may include investigations into imputation or borrowing strength from similar data sets. Inclusion of genetic marker information in the modelling process; and comparing the use of new automated techniques to existing manual grading techniques, e.g. the analysis of colour spectral readings or or the use of chemical fat meters. There would also be scope to compare data from Australia with other countries around the world including Ireland, France, Poland, Japan, China and the United States as the global meat industry moves towards an international data sharing model.

PHD

School of Mathematical and Physical Sciences

27/01/2016 - 28/08/2018

Contact

Doctor Garth Tarr
University of Newcastle
School of Mathematical and Physical Sciences
garth.tarr@newcastle.edu.au

Outlier identification in functional data

Functional data is where we observe a curve for each sample. Examples of functional data include growth curves, brain electrical activity and colour spectra measurements. It is important to be able to identify any unusual sample curves that do not align closely with the other observations so that they can be dealt with appropriately in any subsequent analysis of the data. This project will look at existing (and perhaps new) approaches to outlier identification in functional data. The research will compare colour measurements from beef carcases obtained using a Hunter colour meter to the colour classification given by a trained human assessor.

Honours

School of Mathematical and Physical Sciences

27/01/2016 - 28/08/2018

Contact

Doctor Garth Tarr
University of Newcastle
School of Mathematical and Physical Sciences
garth.tarr@newcastle.edu.au

Classification with functional data

Functional data is where we observe a curve for each sample. Examples of functional data include growth curves, brain electrical activity and colour spectra. A key problem with functional data analysis is classification of curves into multiple categories. An example is assessing the colour of beef carcases for meat grading purposes. This project will investigate appropriate methods of classifying colour spectra readings into multiple categories and assessing the accuracy of such automated approaches to colour measurement.

Honours

School of Mathematical and Physical Sciences

27/01/2016 - 28/08/2018

Contact

Doctor Garth Tarr
University of Newcastle
School of Mathematical and Physical Sciences
garth.tarr@newcastle.edu.au

Improved model averaging through better model weights

Model averaging seeks to address the issue post model selection inference by incorporating model uncertainty into the estimation process. This project will investigate different weighting approaches used to obtaining model averaged estimates. Existing approaches will be compared to a new method where model weights are obtained through bootstrapping.

Honours

School of Mathematical and Physical Sciences

27/01/2016 - 28/08/2018

Contact

Doctor Garth Tarr
University of Newcastle
School of Mathematical and Physical Sciences
garth.tarr@newcastle.edu.au

The use of approximations in bootstrap model selection

Exhaustive model searches for generalised linear models are computationally burdensome. Hosmer et al (1989, Best Subsets Logistic Regression, Biometrics) considers approximating logistic regression models using a form of weighted least squares. This project will explore using linear models to approximate generalised linear models for the purposes of computationally efficient bootstrap model selection. The results of this research will be added to the mplot R package.

Honours

School of Mathematical and Physical Sciences

27/01/2016 - 28/08/2018

Contact

Doctor Garth Tarr
University of Newcastle
School of Mathematical and Physical Sciences
garth.tarr@newcastle.edu.au

Finite sample performance of robust location estimators

Consumer data often exhibits numerous outliers. This project will consider various existing robust location estimators (e.g. median, trimmed mean, Hodges-Lehmann estimator) and assess their small sample performance, especially in samples of size n=10, which corresponds to the number of consumers who eat each piece of meat in standard meat tasting consumer trials. There is an extensive consumer database (40,000+ observations) on which to apply various approaches. An extension to this project would include finding an “optimal” robust location estimator for bounded data with a focus on small sample performance.

Honours

School of Mathematical and Physical Sciences

27/01/2016 - 28/08/2018

Contact

Doctor Garth Tarr
University of Newcastle
School of Mathematical and Physical Sciences
garth.tarr@newcastle.edu.au

Edit

Dr Garth Tarr

Position

Lecturer
Statistics
School of Mathematical and Physical Sciences
Faculty of Science

Contact Details

Email garth.tarr@newcastle.edu.au
Phone (02) 4921 6741
Fax (02) 4921 6898
Links Twitter
Personal webpage

Office

Room V232
Building Mathematics Building
Location Callaghan
University Drive
Callaghan, NSW 2308
Australia
Edit