Email us
Upcoming events
Wed
Jun 28
14:00
Research Commons (4th floor of the library), Groenkloof Campus, University of Pretoria
Thu
Jun 29
17:00 - 18:45
SRC Chambers, Conference Centre, Hatfield Campus, University of Pretoria
Thu
Jun 29
29 Jun - 30 Jun
08:30 - 21:30
Moot Court, Ground Floor, Faculty of Law, Hatfield Campus, University of Pretoria
Fri
Jun 30
30 Jun - 1 Jul
Mamelodi Campus, University of Pretoria
Tue
Jul 04
4 Jul - 12 Jul
09:00 - 13:00
Sci-Enza, Hatfield Campus, University of Pretoria
Wed
Jul 05
Fri
Jul 21
09:00 - 14:00
Rautenbach Hall, Hatfield Campus, University of Pretoria
Fri
Jul 21
09:00 - 14:00
EMS Conference Centre and Sanlam Auditorium, Hatfield Campus
Tue
Jul 25
25 Jul - 26 Jul
09:00 - 14:00
Rautenbach Hall, Hatfield Campus, University of Pretoria
Mon
Aug 07
14:00 - 19:30
Conference Hall 100, Hatfield Campus, University of Pretoria
Sun
Aug 27
27 Aug - 1 Sep
Skukuza Conference Centre, Kruger National Park, South Africa
Thu
Oct 26
26 Oct - 27 Oct
Burgerspark Hotel, Pretoria, South Africa

Doctoral defense: PhD (Mathematical Statistics) Mr MT Loots

Board room 3-44, Plant Sciences Complex, Hatfield Campus
19/06/2017
9:00
You are cordially invited to a doctoral defense by Mr Theodor Loots from the Department of Statistics at the University of Pretoria with Prof Andriëtte Bekker as supervisor.

 

Title: Contemplating Statistics: estimation and regression according to arc lengths

 

Date: Monday, 19 June 2017

Time: 09:00

Venue: Board room 3-44, Plant Sciences Complex, Hatfield Campus

RSVP: to gamu.malela@up.ac.za by Thursday, 15 June 2017

Enquiries: Prof Andriette Bekker at 012 420 2523 or andriette.bekker@up.ac.za

 
Abstract:

Advances in computing have undoubtedly been one of the main catalysts in the formation of the discipline known as Statistics. A fundamental question addressed here is whether computing facilities, such as parallel or high performance computing, could assist in the development of methodologies that render stronger results, based on some predetermined optimality criterion. The candidate at the hand of which this enquiry is made, is the arc length of some statistical function. Estimation, goodness-of-fit, linear regression and non-linear regression, which may all be considered as central themes in Statistics, are revisited, and redefined in terms of this new measure. The results emanating from these arc length methodologies are obtained from simulation, as well as from real case studies, and contrasted with those obtained using their classical counterparts. Mathematical premises for the proposed methods are provided, together with the documentation accompanying the companion R package and the data utilised for the applications.

 
Kindly note that the invitation extends to the general public.

Contact: Prof Andriette Bekker, 012 420 2523 / andriette.bekker@up.ac.za