Jack Noonan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jack Noonan has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Anatoly Zhigljavsky
Cardiff University
13 shared publications - Ivan Fesenko
University of Nottingham
2 shared publications - Kobi Kremnizer
University of Oxford
2 shared publications - Roger M. Whitaker
School of Computer Science and Informatics, Cardiff University, Cardiff, U.K.
2 shared publications - Adetola Adedamola Adediran1 shared publication
Daniel Gartner
Cardiff University
1 shared publication
Latest Publications
- 1 January 2023
- Published by International Press of Boston in Statistics and Its Interface
- Vol. 16 (2) , 163-179
Online change-point detection for a transient change
International Press of Boston - publishers of scholarly mathematical and scientific journals and books
- 1 January 2023
- Published by International Press of Boston in Statistics and Its Interface
- Vol. 16 (2) , 163-179
Online change-point detection for a transient change
International Press of Boston - publishers of scholarly mathematical and scientific journals and books
- Open Access
An integrated approach to test for missing not at random
Missing data can lead to inefficiencies and biases in analyses, in particular when data are missing not at random (MNAR). It is thus vital to understand and correctly identify the missing data mechanism. Recovering missing values through a follow up sample allows researchers to conduct hypothesis tests for MNAR, which are not possible when using only the original incomplete data. Investigating how properties of these tests are affected by the follow up sample design is little explored in the literature. Our results provide comprehensive insight into the properties of one such test, based on the commonly used selection model framework. We determine conditions for recovery samples that allow the test to be applied appropriately and effectively, i.e. with known Type I error rates and optimized with respect to power. We thus provide an integrated framework for testing for the presence of MNAR and designing follow up samples in an efficient cost-effective way. The performance of our methodology is evaluated through simulation studies as well as on a real data sample.
Open AccessAn integrated approach to test for missing not at random
Missing data can lead to inefficiencies and biases in analyses, in particular when data are missing not at random (MNAR). It is thus vital to understand and correctly identify the missing data mechanism. Recovering missing values through a follow up sample allows researchers to conduct hypothesis tests for MNAR, which are not possible when using only the original incomplete data. Investigating how properties of these tests are affected by the follow up sample design is little explored in the literature. Our results provide comprehensive insight into the properties of one such test, based on the commonly used selection model framework. We determine conditions for recovery samples that allow the test to be applied appropriately and effectively, i.e. with known Type I error rates and optimized with respect to power. We thus provide an integrated framework for testing for the presence of MNAR and designing follow up samples in an efficient cost-effective way. The performance of our methodology is evaluated through simulation studies as well as on a real data sample.
- Open Access
- 3 June 2022
- Published by Springer Nature in Discrete & Computational Geometry
- Vol. 68 (2) , 540-565
Efficient Quantisation and Weak Covering of High Dimensional Cubes
Let $${\mathbb {Z}}_n = \{Z_1, \ldots , Z_n\}$$ be a design; that is, a collection ofnpoints $$Z_j \in [-1,1]^d$$ . We study the quality of quantisation of $$[-1,1]^d$$ by the points of $${\mathbb {Z}}_n$$ and the problem of quality of coverage of $$[-1,1]^d$$ by $${{{\mathcal {B}}}}_d({\mathbb {Z}}_n,r)$$ , the union of balls centred at $$Z_j \in {\mathbb {Z}}_n$$ . We concentrate on the cases where the dimensiondis not small, $$d\ge 5$$ , andnis not too large, $$n\le 2^d$$ . We define the design $${{\mathbb {D}}_{n,\delta }}$$ as a $$2^{d-1}$$ design defined on vertices of the cube $$[-\delta ,\delta ]^d$$ , $$0\le \delta \le 1$$ . For this design, we derive a closed-form expression for the quantisation error and very accurate approximations for the coverage area $${\text {vol}}{([-1,1]^d \cap {{{\mathcal {B}}}}_d({\mathbb {Z}}_n,r))}$$ . We provide results of a large-scale numerical investigation confirming the accuracy of the developed approximations and the efficiency of the designs $${{\mathbb {D}}_{n,\delta }}$$ .- 3 June 2022
- Published by Springer Nature in Discrete & Computational Geometry
- Vol. 68 (2) , 540-565
Open AccessEfficient Quantisation and Weak Covering of High Dimensional Cubes
Let $${\mathbb {Z}}_n = \{Z_1, \ldots , Z_n\}$$ be a design; that is, a collection ofnpoints $$Z_j \in [-1,1]^d$$ . We study the quality of quantisation of $$[-1,1]^d$$ by the points of $${\mathbb {Z}}_n$$ and the problem of quality of coverage of $$[-1,1]^d$$ by $${{{\mathcal {B}}}}_d({\mathbb {Z}}_n,r)$$ , the union of balls centred at $$Z_j \in {\mathbb {Z}}_n$$ . We concentrate on the cases where the dimensiondis not small, $$d\ge 5$$ , andnis not too large, $$n\le 2^d$$ . We define the design $${{\mathbb {D}}_{n,\delta }}$$ as a $$2^{d-1}$$ design defined on vertices of the cube $$[-\delta ,\delta ]^d$$ , $$0\le \delta \le 1$$ . For this design, we derive a closed-form expression for the quantisation error and very accurate approximations for the coverage area $${\text {vol}}{([-1,1]^d \cap {{{\mathcal {B}}}}_d({\mathbb {Z}}_n,r))}$$ . We provide results of a large-scale numerical investigation confirming the accuracy of the developed approximations and the efficiency of the designs $${{\mathbb {D}}_{n,\delta }}$$ . - Open Access
Efficient quantization and weak covering of high dimensional cubes
Let $\mathbb{Z}_n = \{Z_1, \ldots, Z_n\}$ be a design; that is, a collection of $n$ points $Z_j \in [-1,1]^d$. We study the quality of quantization of $[-1,1]^d$ by the points of $\mathbb{Z}_n$ and the problem of quality of coverage of $[-1,1]^d$ by ${\cal B}_d(\mathbb{Z}_n,r)$, the union of balls centred at $Z_j \in \mathbb{Z}_n$. We concentrate on the cases where the dimension $d$ is not small ($d\geq 5$) and $n$ is not too large, $n \leq 2^d$. We define the design ${\mathbb{D}_{n,\delta}}$ as a $2^{d-1}$ design defined on vertices of the cube $[-\delta,\delta]^d$, $0\leq \delta\leq 1$. For this design, we derive a closed-form expression for the quantization error and very accurate approximations for {the coverage area} vol$([-1,1]^d \cap {\cal B}_d(\mathbb{Z}_n,r))$. We provide results of a large-scale numerical investigation confirming the accuracy of the developed approximations and the efficiency of the designs ${\mathbb{D}_{n,\delta}}$.Open AccessEfficient quantization and weak covering of high dimensional cubes
Let $\mathbb{Z}_n = \{Z_1, \ldots, Z_n\}$ be a design; that is, a collection of $n$ points $Z_j \in [-1,1]^d$. We study the quality of quantization of $[-1,1]^d$ by the points of $\mathbb{Z}_n$ and the problem of quality of coverage of $[-1,1]^d$ by ${\cal B}_d(\mathbb{Z}_n,r)$, the union of balls centred at $Z_j \in \mathbb{Z}_n$. We concentrate on the cases where the dimension $d$ is not small ($d\geq 5$) and $n$ is not too large, $n \leq 2^d$. We define the design ${\mathbb{D}_{n,\delta}}$ as a $2^{d-1}$ design defined on vertices of the cube $[-\delta,\delta]^d$, $0\leq \delta\leq 1$. For this design, we derive a closed-form expression for the quantization error and very accurate approximations for {the coverage area} vol$([-1,1]^d \cap {\cal B}_d(\mathbb{Z}_n,r))$. We provide results of a large-scale numerical investigation confirming the accuracy of the developed approximations and the efficiency of the designs ${\mathbb{D}_{n,\delta}}$. - Open Access
- 12 February 2021
- Published by Springer Nature in Extremes
- Vol. 24 (3) , 565-589
First passage times for Slepian process with linear and piecewise linear barriers
In this paper, we derive explicit formulas for the first-passage probabilities of the processS(t) =W(t) −W(t+ 1), whereW(t) is the Brownian motion, for linear and piece-wise linear barriers on arbitrary intervals [0,T]. Previously, explicit formulas for the first-passage probabilities of this process were known only for the cases of a constant barrier orT≤ 1. The first-passage probabilities results are used to derive explicit formulas for the power of a familiar test for change-point detection in the Wiener process.
- 12 February 2021
- Published by Springer Nature in Extremes
- Vol. 24 (3) , 565-589
Open AccessFirst passage times for Slepian process with linear and piecewise linear barriers
In this paper, we derive explicit formulas for the first-passage probabilities of the processS(t) =W(t) −W(t+ 1), whereW(t) is the Brownian motion, for linear and piece-wise linear barriers on arbitrary intervals [0,T]. Previously, explicit formulas for the first-passage probabilities of this process were known only for the cases of a constant barrier orT≤ 1. The first-passage probabilities results are used to derive explicit formulas for the power of a familiar test for change-point detection in the Wiener process.
- Open Access
- 13 August 2020
- Published by Springer Nature in Operations Research Forum
- Vol. 1 (3) , 1-32
Covering of High-Dimensional Cubes and Quantization
As the main problem, we consider covering of ad-dimensional cube bynballs with reasonably larged(10 or more) and reasonably smalln, liken= 100 orn= 1000. We do not require the full coverage but only 90% or 95% coverage. We establish that efficient covering schemes have several important properties which are not seen in small dimensions and in asymptotical considerations, for very largen. One of these properties can be termed ‘do not try to cover the vertices’ as the vertices of the cube and their close neighbourhoods are very hard to cover and for largedthere are far too many of them. We clearly demonstrate that, contrary to a common belief, placing balls at points which form a low-discrepancy sequence in the cube, results in a very inefficient covering scheme. For a family of random coverings, we are able to provide very accurate approximations to the coverage probability. We then extend our results to the problems of coverage of a cube by smaller cubes and quantization, the latter being also referred to as facility location. Along with theoretical considerations and derivation of approximations, we provide results of a large-scale numerical investigation.
- 13 August 2020
- Published by Springer Nature in Operations Research Forum
- Vol. 1 (3) , 1-32
Open AccessCovering of High-Dimensional Cubes and Quantization
As the main problem, we consider covering of ad-dimensional cube bynballs with reasonably larged(10 or more) and reasonably smalln, liken= 100 orn= 1000. We do not require the full coverage but only 90% or 95% coverage. We establish that efficient covering schemes have several important properties which are not seen in small dimensions and in asymptotical considerations, for very largen. One of these properties can be termed ‘do not try to cover the vertices’ as the vertices of the cube and their close neighbourhoods are very hard to cover and for largedthere are far too many of them. We clearly demonstrate that, contrary to a common belief, placing balls at points which form a low-discrepancy sequence in the cube, results in a very inefficient covering scheme. For a family of random coverings, we are able to provide very accurate approximations to the coverage probability. We then extend our results to the problems of coverage of a cube by smaller cubes and quantization, the latter being also referred to as facility location. Along with theoretical considerations and derivation of approximations, we provide results of a large-scale numerical investigation.
- Open Access
- 7 May 2020
- Published by Springer Nature in Methodology and Computing in Applied Probability
- Vol. 23 (3) , 873-892
Approximations for the Boundary Crossing Probabilities of Moving Sums of Random Variables
In this paper we study approximations for the boundary crossing probabilities of moving sums of i.i.d. normal random variables. We approximate a discrete time problem with a continuous time problem allowing us to apply established theory for stationary Gaussian processes. By then subsequently correcting approximations for discrete time, we show that the developed approximations are very accurate even for a small window length. Also, they have high accuracy when the original r.v. are not exactly normal and when the weights in the moving window are not all equal. We then provide accurate and simple approximations for ARL, the average run length until crossing the boundary.
- 7 May 2020
- Published by Springer Nature in Methodology and Computing in Applied Probability
- Vol. 23 (3) , 873-892
Open AccessApproximations for the Boundary Crossing Probabilities of Moving Sums of Random Variables
In this paper we study approximations for the boundary crossing probabilities of moving sums of i.i.d. normal random variables. We approximate a discrete time problem with a continuous time problem allowing us to apply established theory for stationary Gaussian processes. By then subsequently correcting approximations for discrete time, we show that the developed approximations are very accurate even for a small window length. Also, they have high accuracy when the original r.v. are not exactly normal and when the weights in the moving window are not all equal. We then provide accurate and simple approximations for ARL, the average run length until crossing the boundary.
- Open Access
A prototype for decision support tool to help decision-makers with the strategy of handling the COVID-19 UK epidemic
Summary: The primary objective of this work is to model and compare different exit scenarios from the lock-down for the COVID-19 UK epidemic. In doing so we provide an additional modelling basis for laying out the strategy options for the decision-makers. The main results are illustrated and discussed in Part I. In Part II, we describe the stochastic model that we have developed for modelling this epidemic. As argued in Part II, the developed model is more flexible than the SEIR/SEIRS models and can be used for modelling the scenarios which may be difficult or impossible to model with the SEIR/SEIRS models. To compare different scenarios for exiting from the lock-down, in Part III we provide our previous report on the same topic where similar (although not as detailed) scenarios were considered. As the possible exit dates, we have chosen May 4, May 11, May 18 and May 25. We model differently the regions with high initial reproductive number chosen to be R 0 = 2.5, medium R 0 = 2.3 and low R 0 = 2. The numbers for the whole of the UK can be obtained by appropriate averaging of the numbers given in the report. Typical figures are given in Section 4. For each scenario considered, we plot the expected proportion of infected at time t and the expected number of deaths at time t . To compute the expected numbers of deaths we used the total mortality rate 0.66%. Many recent studies suggest lower values and therefore the numbers in our projections should be considered as rather pessimistic. Our analysis suggests a value around 0.5% for the mortality rate. In the model, we assume that the isolation of older and vulnerable people continues and the public carries on certain level of isolation until the end of 2020; also we assume that immunity is kept for at least a year and there is no international travel influence. Our main conclusions are: In regions with higher initial reproductive number 2.5 the proportion of susceptible at the start of the lock-down should be not smaller than 0.95, the epidemic curve in such regions is in the fast monotonic decline irrespectively of the date of the lock-down lift; In regions with lower initial reproductive number 2.0 the second mild wave can be expected, the difference between the expected mortality rates is very small for all May 2020 lifting lock-down dates; In regions with initial reproductive number 2.3, a mild second wave can be expected in the case of large proportion of susceptible at the start of the lock-down, but its severity and resulting mortality depend very little on the date of lifting the lock-down; For the overall UK epidemic, even for rather pessimistic scenarios considered, the second wave is much less pronounced (in terms of the expected mortality rate) than the first one, and the total numbers of expected deaths are within 2% for all May 2020 dates of lifting the lock-down. Moreover, by keeping R 0 -value after lifting the lock-down below 1.75 is likely to lead to the avoidance of a UK-wide second wave, see Section 4. We believe that the model build in this work can be considered as an important decision support tool to help decision-makers with the strategy of handling the epidemic. We invite other scholars to participate in an open discussion of the strategy options. We feel that this kind of models should be used in the short and long term management of the disease. We recommend the development of a permanent and modularised modelling suite for COVID-19 management to which additional modules can be added as anti-viral drugs and vaccination are introduced, extending the options. We trust that this work makes a start in that direction and demonstrates the advantages of a heterogeneous demographic refinement, which can only improve targeting role out of treatments.
Open AccessA prototype for decision support tool to help decision-makers with the strategy of handling the COVID-19 UK epidemic
Summary: The primary objective of this work is to model and compare different exit scenarios from the lock-down for the COVID-19 UK epidemic. In doing so we provide an additional modelling basis for laying out the strategy options for the decision-makers. The main results are illustrated and discussed in Part I. In Part II, we describe the stochastic model that we have developed for modelling this epidemic. As argued in Part II, the developed model is more flexible than the SEIR/SEIRS models and can be used for modelling the scenarios which may be difficult or impossible to model with the SEIR/SEIRS models. To compare different scenarios for exiting from the lock-down, in Part III we provide our previous report on the same topic where similar (although not as detailed) scenarios were considered. As the possible exit dates, we have chosen May 4, May 11, May 18 and May 25. We model differently the regions with high initial reproductive number chosen to be R 0 = 2.5, medium R 0 = 2.3 and low R 0 = 2. The numbers for the whole of the UK can be obtained by appropriate averaging of the numbers given in the report. Typical figures are given in Section 4. For each scenario considered, we plot the expected proportion of infected at time t and the expected number of deaths at time t . To compute the expected numbers of deaths we used the total mortality rate 0.66%. Many recent studies suggest lower values and therefore the numbers in our projections should be considered as rather pessimistic. Our analysis suggests a value around 0.5% for the mortality rate. In the model, we assume that the isolation of older and vulnerable people continues and the public carries on certain level of isolation until the end of 2020; also we assume that immunity is kept for at least a year and there is no international travel influence. Our main conclusions are: In regions with higher initial reproductive number 2.5 the proportion of susceptible at the start of the lock-down should be not smaller than 0.95, the epidemic curve in such regions is in the fast monotonic decline irrespectively of the date of the lock-down lift; In regions with lower initial reproductive number 2.0 the second mild wave can be expected, the difference between the expected mortality rates is very small for all May 2020 lifting lock-down dates; In regions with initial reproductive number 2.3, a mild second wave can be expected in the case of large proportion of susceptible at the start of the lock-down, but its severity and resulting mortality depend very little on the date of lifting the lock-down; For the overall UK epidemic, even for rather pessimistic scenarios considered, the second wave is much less pronounced (in terms of the expected mortality rate) than the first one, and the total numbers of expected deaths are within 2% for all May 2020 dates of lifting the lock-down. Moreover, by keeping R 0 -value after lifting the lock-down below 1.75 is likely to lead to the avoidance of a UK-wide second wave, see Section 4. We believe that the model build in this work can be considered as an important decision support tool to help decision-makers with the strategy of handling the epidemic. We invite other scholars to participate in an open discussion of the strategy options. We feel that this kind of models should be used in the short and long term management of the disease. We recommend the development of a permanent and modularised modelling suite for COVID-19 management to which additional modules can be added as anti-viral drugs and vaccination are introduced, extending the options. We trust that this work makes a start in that direction and demonstrates the advantages of a heterogeneous demographic refinement, which can only improve targeting role out of treatments.
- Open Access
Comparison of different exit scenarios from the lock-down for COVID-19 epidemic in the UK and assessing uncertainty of the predictions
We model further development of the COVID-19 epidemic in the UK given the current data and assuming different scenarios of handling the epidemic. In this research, we further extend the stochastic model suggested in [1] and incorporate in it all available to us knowledge about parameters characterising the behaviour of the virus and the illness induced by it. The models we use are flexible, comprehensive, fast to run and allow us to incorporate the following: time-dependent strategies of handling the epidemic; spatial heterogeneity of the population and heterogeneity of development of epidemic in different areas; special characteristics of particular groups of people, especially people with specific medical pre-histories and elderly. Standard epidemiological models such as SIR and many of its modifications are not flexible enough and hence are not precise enough in the studies that requires the use of the features above. Decision-makers get serious benefits from using better and more flexible models as they can avoid of nuanced lock-downs, better plan the exit strategy based on local population data, different stages of the epidemic in different areas, making specific recommendations to specific groups of people; all this resulting in a lesser impact on economy, improved forecasts of regional demand upon NHS allowing for intelligent resource allocation. In this work, we investigate the sensitivity of the model to all its parameters while considering several realistic scenarios of what is likely to happen with the dynamics of the epidemic after the lock-down, which has started on March 23, is lifted. The main findings from this research are the following very little gain, in terms of the projected hospital bed occupancy and expected numbers of death, of continuing the lock-down beyond April 13, provided the isolation of older and vulnerable people continues and the public carries on some level of isolation in the next 2-3 months, see Section 3.1; in agreement with [1], isolation of the group of vulnerable people during the next 2-3 months should be one of the main priorities, see Section 3.2; it is of high importance that the whole population carries on some level of isolation in the next 2-3 months, see Section 3.5; the timing of the current lock-down seems to be very sensible in areas like London where the epidemic has started to pick up by March 23; in such areas the second wave of epidemic is not expected, see figures in Sections 2.2 and 3; the epidemic should almost completely finish in July, no global second wave should be expected, except areas where the first wave is almost absent, see Section 3.4.
Open AccessComparison of different exit scenarios from the lock-down for COVID-19 epidemic in the UK and assessing uncertainty of the predictions
We model further development of the COVID-19 epidemic in the UK given the current data and assuming different scenarios of handling the epidemic. In this research, we further extend the stochastic model suggested in [1] and incorporate in it all available to us knowledge about parameters characterising the behaviour of the virus and the illness induced by it. The models we use are flexible, comprehensive, fast to run and allow us to incorporate the following: time-dependent strategies of handling the epidemic; spatial heterogeneity of the population and heterogeneity of development of epidemic in different areas; special characteristics of particular groups of people, especially people with specific medical pre-histories and elderly. Standard epidemiological models such as SIR and many of its modifications are not flexible enough and hence are not precise enough in the studies that requires the use of the features above. Decision-makers get serious benefits from using better and more flexible models as they can avoid of nuanced lock-downs, better plan the exit strategy based on local population data, different stages of the epidemic in different areas, making specific recommendations to specific groups of people; all this resulting in a lesser impact on economy, improved forecasts of regional demand upon NHS allowing for intelligent resource allocation. In this work, we investigate the sensitivity of the model to all its parameters while considering several realistic scenarios of what is likely to happen with the dynamics of the epidemic after the lock-down, which has started on March 23, is lifted. The main findings from this research are the following very little gain, in terms of the projected hospital bed occupancy and expected numbers of death, of continuing the lock-down beyond April 13, provided the isolation of older and vulnerable people continues and the public carries on some level of isolation in the next 2-3 months, see Section 3.1; in agreement with [1], isolation of the group of vulnerable people during the next 2-3 months should be one of the main priorities, see Section 3.2; it is of high importance that the whole population carries on some level of isolation in the next 2-3 months, see Section 3.5; the timing of the current lock-down seems to be very sensible in areas like London where the epidemic has started to pick up by March 23; in such areas the second wave of epidemic is not expected, see figures in Sections 2.2 and 3; the epidemic should almost completely finish in July, no global second wave should be expected, except areas where the first wave is almost absent, see Section 3.4.