Saturday, August 20, 2016

MIT/Edx MOOC on Economic Modelling

Following from the previous post, the MOOC on economic modelling also looks very useful. See below or on the link for details. It also starts on September 19th.

What is produced in an economy? How is it produced? Who gets the product? Microeconomics seeks to answer these fundamental questions about markets.

In this course, we’ll introduce you to microeconomic theory, together with some empirical results and policy implications. You’ll analyze mathematical models that describe the real-world behavior of consumers and firms, and you’ll see how prices make the world go ‘round.

You’ll join the ranks of business executives, policymakers, entrepreneurs, and global leaders who rely on the insights they derive from a working knowledge of microeconomics. Nobel memorial prize-winner Paul Samuelson invented the modern microeconomics curriculum at MIT. Now is your chance to learn the field from the intellectual tradition he began.

Topics include:

Consumer theory
Supply and demand
Market equilibrium
Producer theory
Monopoly
Oligopoly
Capital markets
Welfare economics
Public goods
Externalities

MIT Mooc: Data Analysis for Social Scientists

The MIT/Edx online course "Data Analysis for Social Scientists" will be very useful for many readers of this blog. Details on the link and below. It starts on September 19th and runs for 12 weeks.

About this course

This statistics and data analysis course will introduce you to the essential notions of probability and statistics. We will cover techniques in modern data analysis: estimation, regression and econometrics, prediction, experimental design, randomized control trials (and A/B testing), machine learning, and data visualization. We will illustrate these concepts with applications drawn from real world examples and frontier research. Finally, we will provide instruction for how to use the statistical package R and opportunities for students to perform self-directed empirical analyses.

This course is designed for anyone who wants to learn how to work with data and communicate data-driven findings effectively.

 See more about Data Analysis for Social Scientists
What you'll learn
Intuition behind probability and statistical analysis
How to summarize and describe data
A basic understanding of various methods of evaluating social programs
How to present results in a compelling and truthful way
Skills and tools for using R for data analysis

Friday, August 19, 2016

Behavioural Science in Law & Policy: Evidence, Ethics, & Expertise








Behavioural Science in Law & Policy:

Evidence, Ethics, & Expertise 

Organisers: Professor Muireann Quigley (Law, Innovation, and Society Research Group, Newcastle Law School) and Professor Liam Delaney (Behavioural Sciences Centre, Stirling Management School) 

Date: Friday, 23rd September 2016
Venue: Conference Room, Newcastle law School, Newcastle University

Behavioural economics, and behavioural science more generally, has become an increasingly salient aspect of modern policy debates. Governments throughout the world have begun to explicitly incorporate this literature across a wide range of policy domains. The potential for this literature to improve policy through evidence-based trials has been widely discussed. Furthermore, the implications of behavioural economics for regulation is now on the agenda of many leading regulatory agencies. The increasing traction within policy circles of behavioural approaches to law and policy is evident through the creation of specialist units across the globe; e.g. the United Kingdom’s Behavioural Insights Team, the Social and Behavioural Sciences Team in the United States, and the Behavioural Economics Team of the Australian Government. Within the European Commission, the Joint Research Centre offers support to Commission services wanting to conduct behavioural studies. Despite the current enthusiasm amongst governments and policy-makers for behavioural approaches, there are potential problems with the use of the behavioural sciences to formulate public policy, many of which remain underexplored. The aim of this workshop is to bring together papers from a range of different disciplinary, regulatory, and practical perspectives to examine these. 

Provisional Schedule 

08:45 – 09:00 Registration

09:00 – 09:15 Welcome

09:15 – 11:00 Session 1 – Matters of Principle & Practice: Ethics & the Behavioural Sciences

Dr Christian Schubert (Max Planck Institute of Economics) - Nudging, Integrity and Welfare.

Dr Magdelena Malecka & Dr Robert Leipnes (EUI) - Nudges, Law & Politics - beyond the individualist perspective.

Dr. Leonhard Lades (University of Stirling) – Nudges, Well-Being and Welfare.

Commentator: Prof. Liam Delaney (University of Stirling)

11:00-11:15 Coffee

11:15-13:00 Session 2 The Regulatory State in the Behavioural Era

TBC: Dr Fabiana Di Porto (University of Salento) & Dr Nicoletta Rangone (LUMSA University) - A Behavioural Approach to Consumer Empowerment Regulation: Applications in Gambling.

Katy King & Elisabeth Costa (Behavioural Insights Team) - Applying Behavioural Insights to Regulated Markets.

Commentator: Dr. Leonhard Lades (University of Stirling)

13:00 – 14:00 Lunch

14:00 – 15:45 Session 3 - Translating Behavioural Science into Law & Policy: Problems, Pitfalls, & Solutions

Kathryn McKay (University of Birmingham) & Prof. Muireann Quigley (Newcastle University) - Exacerbating Inequalities? Health Policy & the Behavioural Sciences.

Dr Nicky Priaulx & Dr Martin Weinel (Cardiff University) - (Mis)understanding behaviour: Law, science and expertise'.

Prof. Peter John (University College London) – How Far to Nudge?.

Commentator Dr. Michael Daly (University of Stirling).

15:45 – 16:00 Coffee

16:00-17:00 Roundtable

18:30 Speakers’ Dinner

Please email the workshop organisers Prof Muireann Quigley (Muireann.Quigley@newcastle.ac.uk) and Prof Liam Delaney (Liam.Delaney@stir.ac.uk) if you have any queries. If you wish to register as a delegate for the event, you can do so at the following registration page. Registration is free but numbers are limited by space. The workshop is sponsored by Newcastle University Law School and Stirling University Management School. 

Thursday, August 18, 2016

Workshop on Methods for Missing Data: 15th and 16th September, London

A workshop on missing data with emphasis on sample selection models will take place in London in September. This workshop aims to provide an introduction to the issues raised by missing data with particular emphasis on missing not at random. The workshop is free but registration is required.

Who will benefit and how

This workshop provides a practical introduction to the use of a very flexible class of sample selection models which can be useful to analysts and quantitative researchers whose analyses are affected by missing not at random. There will be plenty of opportunity for discussion with the course instructors on sample selection models (but not only) for analysing missing data, and help will be provided with interpreting results. Throughout, there will be a focus on the policy implications of missing data and potential solutions to this problem. The workshop will also be relevant for practitioners conducting surveys on topics which are likely to be affected by missing information, as we will discuss how to incorporate methods to adjust for data not missing at random into the way surveys are designed.

Summary of workshop

This workshop aims to:

• Provide an introduction to the issues raised by missing data with particular emphasis on missing
not at random;
• Briefly introduce ad-hoc methods and principled methods;
• Briefly introduce pattern mixture models;
• Introduce and discuss sample selection models;
• Illustrate the use of SemiParBIVProbit to deal with missing not at random;
• Case studies from DHS studies, ageing studies and cost effectiveness analyses.

Workshop timetable
Thursday 15 September

10:00-10:15 Introduction (ALL)
10:15-11:00 Missing Mechanisms, Ad-Hoc and Principled Methods (GH)
11:00-11:30 Introduction to Pattern Mixture Models (MG)
11:30-11:45 Break
11:45-12:45 Sample Selection Models and Variants: Part I (GM/RR)
12:45-14:00 Lunch
14:00-14:45 Sample Selection Models and Variants: Part II (GM/RR)
14:45-15:15 Introduction to R Package SemiParBIVProbit (GM/RR)
15:15-15:30 Break
15:30-16:30 Practicals with SemiParBIVProbit (ALL)

Friday 16 September

10:00-10:30 Missing data in ageing studies (MM)
10:30-11:00 Missing data in DHS studies (or South Africa work) (GH)
11:00-11:15 Break
11:15-11:45 Missing data in cost-effectiveness analyses (MG)
11:45-12:15 Designing survey to incorporate sample selection approaches (MM)
12:15-13:00 Interactive discussion (ALL)

Prerequisites
Participants are expected to have some familiarity with R, as well as relevant statistical concepts such as linear regression.

Registration

The event is free but prior registration is required. To reserve a place, please contact Rosalba Radice r.radice@bbk.ac.uk and provide a brief explanation of your interest in the course and short CV.

Instructors

Rosalba Radice (Birkbeck, Department of Economics, Mathematics and Statistics)
http://www.ems.bbk.ac.uk/faculty/radice

Giampiero Marra (University College London, Department of Statistical Science)
http://www.ucl.ac.uk/statistics/people/giampieromarra

Manuel Gomes (London School of Hygiene and Tropical Medicine, Department of Health Services Research and Policy)
http://www.lshtm.ac.uk/aboutus/people/gomes.manuel

Guy Harling (Harvard School of Public Health, Department of Global Health and Population)
https://www.hsph.harvard.edu/guy-harling/

Mark McGovern (CHaRMS, Queen's University Belfast)
http://go.qub.ac.uk/MarkMcGovern

Key references
1. Marra, G., Radice, R., Bärnighausen, T., Wood, S.W., McGovern, M.E. (in press). A Simultaneous Equation Approach to Estimating HIV Prevalence with Non-Ignorable Missing Responses. Journal of the American Statistical Association

2. Marra, G., Radice, R. (2016). A Bivariate Copula Additive Model for Location, Scale and Shape.

3. Marra, G., Radice, R. (2016). SemiParBIVProbit: Semiparametric Copula Bivariate Probit Modelling. R package version 3.7-1.

4. McGovern, M.E., Marra, G., Radice, R., Canning, D., Newell, M.L., Bärnighausen, T. (2015). Adjusting for Non-Participation Bias at an HIV Surveillance Site in Rural South Africa. Journal of the International AIDS Society, 18, 19954.

5. Marra G., Radice R. (2013). A Penalized Likelihood Estimation Approach to Semiparametric Sample Selection Binary Response Modeling. Electronic Journal of Statistics, 7, 1432-1455.
6. Marra G., Radice R. (2013). Estimation of a Regression Spline Sample Selection Model. Computational Statistics and Data Analysis, 61, 158-173.

7. Radice R., Marra G., Wojtys M. (in press). Copula Regression Spline Models for Binary Outcomes. Statistics and Computing.

8. McGovern M.E., Bärnighausen T., Marra G., Radice R. (2015). On the Assumption of Joint Normality in Selection Models: A Copula Approach Applied to Estimating HIV Prevalence. Epidemiology, 26(2), 229-237.

9. Bärnighausen, T., Bor, J., Wandira-Kazibwe, S., Canning, D. (2011). Correcting HIV prevalence estimates for survey nonparticipation using Heckman-type selection models. Epidemiology, 22, 2735.

Sunday, August 14, 2016

9th Annual Irish Economics and Psychology Conference

9th Annual Economics and Psychology Conference
The ninth annual one day conference on Economics and Psychology will be held on November 25th in Queen's University Belfast, jointly organised by researchers in QUB, ESRI, Stirling and UCD. The purpose of these sessions is to develop the link between Economics, Psychology, and cognate disciplines throughout Ireland. A special theme of these events is the implications of behavioural economics for public policy. If you would like to present at this event please send a 200 word abstract to Liam.Delaney@stir.ac.uk before Friday 9th September.

As well as the annual workshop we have developed a broader network to meet more regularly to discuss work at the intersection of economics, psychology, and policy. This has had five meet-ups so far, as well as some offshoot sessions. Anyone interested in this area is welcome to attend. A website with more details and a mailing list to sign up to is available here. There are currently over 200 people signed up to the network and the events have been, at least in my view, very lively and interesting. There are several more planned for throughout 2016/2017 and we welcome suggestions.

Preliminary Programme:

9am to 915am: Welcome

915am to 10.30am: Behavioural Economics and Policy Case Studies

10.30am to 11am: Coffee

11am to 12.30pm: Ethics, Policy, and Behavioural Science

12.30pm to 1.30pm: Lunch

1.30 to 245pm: Measurement, Method, and Behavioural Science

2.45pm to 3pm: Coffee

3pm to 4pm: Keynote Speaker 1

4pm to 5pm: Keynote Speaker 2


Friday, August 12, 2016

Competition and Markets Authority Retail Banking Report

The Competition and Markets Authority in the UK published a report this week on retail banking. I commented on it briefly on the Radio 4 Today programme on Tuesday morning and the purpose of this post is to provide further information. The CMA has been operating since 2013 when it replaced for most purposes the Competition Commission and Office of Fair Trading. It is basically responsible for ensuring competition and fair practices in markets in the United Kingdom. 

Since November 2014 the CMA has been investigating the market for personal current accounts (PCAs) and of banking services to small and medium size enterprises (SMEs). Details of their preliminary reports and various other resources are available on the investigation website. A useful document for those who don't have the time to read the thousands of pages on that website is the 55 page summary document available here. The core task of the investigation is summarised below.
"We are required to decide whether any feature, or combination of features, of each relevant market prevents, restricts or distorts competition in connection with the supply or acquisition of any goods or services in the UK or a part of the UK. If we decide that there is such a feature or a combination of features, then there is an adverse effect on competition (AEC). Should an AEC be found, we are also required to decide whether action should be taken by the CMA or a recommendation be made to others to take action for the purpose of remedying, mitigating or preventing the AEC or any resulting detrimental effect on customers. This final report sets out our decisions on these questions."
The PCA and SME banking services markets are large and important in the UK. As noted in the report, 97% of adults have a PCA and there are over 70 million PCAs in the UK, generating 8.7 billion in revenue for banks in 2014. As well as traditional questions of competition policy, there are clearly many potential behavioural issues in these markets that could lead to welfare consequences for consumers.
In light of these reviews and the market studies into PCAs and SME banking which led to this investigation, we investigated three broad areas in which we had concerns that retail banking may not be working well for customers:  
(a) whether there is a weak customer response due to lack of engagement and/or barriers to searching and switching reducing the incentives on banks to compete on price and/or quality and/or to innovate;(b) whether there are barriers to entry and expansion constraining the ability of banks to enter or expand; and(c) whether the level of concentration is having an adverse effect on customers.  
The findings with respect to the above questions show very low levels of consumer engagement in both PCA and SME banking markets. Half of consumers had been with the same PCA for the last 10 years. Only 3 per cent had switched within the last year.  The figures are not dramatically different for SME banking customers with many of the same issues arising.

As well as this, there is an important question as to how customers use these accounts, in particular the extent to which they incur overdraft fees. The most striking feature of the report for me from a behavioural perspective relates to the use of unarranged overdrafts. Unarranged overdrafts are a very expensive form of credit. Nearly half of the people using them were unaware they were doing so. It is one of the clearest areas I know where there is a potential behavioural market failure, as can be seen from the report's findings below.
In addition, there are particular concerns for overdraft users. Around 4.5% of active PCAs used an overdraft in 2014 with around a quarter of PCA customers using an unarranged overdraft. Despite overdraft users tending to have the most to gain from switching, we found that:
(a) Overdraft charges are particularly difficult to compare across banks, due to both the complexity and multiplicity of the charging structures and the difficulties in understanding their own usage. In particular, customers exceeding their pre-arranged credit limit can incur substantial charges but
there is no easy way for a customer to find and compare the charges or
credit limits an alternative PCA might offer them.
(b) Overdraft users generally have limited awareness of and engagement with their overdraft usage. For example, over half of overdraft users we surveyed underestimated their usage by two or more months in a year and over a third were not aware that they had gone into overdraft. Moreover, around half of unarranged overdraft users did not believe they had gone into unarranged overdraft.
(c) There are additional barriers to switching for overdraft users due to uncertainty surrounding the acceptance and timing of any overdraft approval when opening a new account. In addition, a new bank may not be willing to offer the same level of overdraft facility as a customer’s bank, for example because the new bank will not have access to the customer’s transaction data but will need to rely on information from the customer and from CRAs. 
The report outlines a range of remedies to encourage active consumption on behalf of PCA and SME banking consumers. These are nested under four broad headings, as outlined below. There are many innovative and interesting ideas contained within these remedies, many of which have been discussed in various papers and reports on behavioural regulation over the last 10 years. As such, the roll-out of these remedies offers a particularly useful case-study as to whether this approach can actively shape outcomes in markets of this nature.
Our integrated package of remedies is illustrated below, and consists of four
elements:
(a) Three cross-cutting foundation measures that will underpin increased competition in our reference markets. They have the object of increasing customer engagement and making it easier for personal and business customers to compare the prices and service quality of different providers
and of encouraging the development of new services.
(b) Additional measures to make current account switching work better, including building on and improving the existing CASS.
(c) A set of measures aimed at PCA overdraft users, a group of customers who suffer particularly from the competition failures in the PCA market.
(d) A set of measures targeted at the specific problems in SME banking, making it easier for SMEs to compare different providers and reducing the hold that incumbent banks have in the market for BCAs and SME loans
The potential remedies for the levels of low engagement and high frequency of incurring overdraft fees and unplanned overdraft fees merit a lot of debate. Several consumer groups had advocated for mandating centrally imposed caps on the amount that banks can charge customers for exceeding their overdraft limit rather than allowing banks to set this limit themselves. Instead they recommend what could be considered a Nudge approach that forces banks to provide more transparent and timely information about the likelihood of incurring different types of overdraft fees. This is one of the most contentious aspects of the report and one of the most contentious aspects of this literature and policy area more generally. To use the phrase from the well-known Bubb and Pildes paper, why should behavioural economics trim its sails in this manner? Why focus on soft intervention when a harder more mandated approach might be more effective? I have blogged about this issue before. It is one of the central issues in behavioural economics, law and regulation and will likely shape this debate long into the future.
(a) requiring banks to automatically enrol all their customers into an unarranged overdraft alert;
(b) requiring banks to offer, and alert customers to the opportunity to benefit from, grace periods during which they can take action to avoid or reduce all charges resulting from unarranged overdraft use;
(c) recommending to the FCA that it undertakes further work to identify, research, test and, as appropriate, implement measures to increase overdraft customers’ engagement with their overdraft usage and charges. This will be facilitated by an Order to require banks to cooperate with the FCA in its research programme, including RCTs; and
(d) to increase PCA customers’ engagement with overdraft features, we are recommending that the FCA looks at ways for banks to engage customers more in considering overdraft features and their potential relevance and impact, during the PCA opening process. 
There are several other issues that people have been debating on this report. The extent to which competition in these markets is constrained by the market power of the largest established banks is an ongoing debate and is not widely addressed in the report, other than to say they have largely concluded that market power itself is likely not the source of low consumer engagement. The behavioural economics approach is a key feature of British regulation across several areas over recent year (see BIT report, FCA report, CMA Chairman speech on behavioural economics, and University of East Anglia book for very useful papers; see also Bar-Gill Seduction by Contract for a recent book on the behavioural law approach). The extent to which it tends in Britain to be associated with a soft-mandatory or Nudge type approach needs to be kept under scrutiny and debate. Behavioural barriers do not necessarily imply softer interventions. It will be fascinating to see whether this comprehensive package of recommended behavioural interventions has an effect of the levels of engagement and quality of consumer outcomes in this market. If it does not, it will certainly tip the balance back in favour of those advocating harder approaches.

The report also brings home the vast numbers of small businesses and retail consumers who clearly have difficulty engaging with what are, for many, complex services. The wider effects this might be having on constraining start-up formation, impacting on family solvency, mental health, and other welfare outcomes are worth considering, and they provide a substantive area of inquiry for people who are bringing psychological and behavioural perspectives to these areas.

Thursday, August 11, 2016

Workshop on Naturalistic Behavioural Science

On Friday the 28th of October, 2016, the Stirling Behavioural Science Centre will organise a workshop on conducting behavioural science research "in the wild". We aim to discuss how behavioural scientific concepts can be tested in a naturalistic environment in settings that are less artificial than labs or surveys. In particular, we aim to identify how smartphones and diary studies can be used to measure concepts such as preferences, personality, and well-being in everyday life. 

Please send an email to Leonhard Lades (l.k.lades@stir.ac.uk) if you are interested in this topic and want to contribute to the workshop. We will also update this post with more information in the next weeks.

Themes of the workshop include, but are not limited to:

(1) Experience Sampling: Smartphones are used with increasing frequency in experience sampling studies in which people are signalled multiple times a day and asked to answer questions about their current feelings and behaviours. A strength of experience sampling is that the same individuals answer similar questions on multiple occasions which allows identifying intra-individual differences driven by factors such as time of the day, mood, locations, and many more contextual factors. This offers ample opportunities to measure and better understand fluctuations of preferences, personality, and well-being, as well as decision-making in real live.

(2) Diary studies: An alternative to smartphone studies are diary methods such as the Day Reconstruction Methodology (DRM). We plan to discuss pros and cons of diary studies compared to smartphone studies. When and why should we use diary studies and when should we use smartphone studies? 

(3) Experimentation on the Smartphone: While lab experiments benefit from a highly controlled context, many outcome variables and manipulations in the lab are rather artificial. Mood inductions, for example, are difficult to implement and it is not always clear whether the induced mood in the lab corresponds to a similar mood in the real world. By running experiments on the smartphone in peoples' real lives, one can elicit the effects of real moods on peoples' behaviour in the experiments. We will discuss, among other aspects, whether the reduction in control that goes along with experimentation in real life is warranted.

(4) Measurement as intervention: When using smartphones and diary studies as research tools, it is likely that we do not only measure, but also change participants' feelings and behaviours. How can we control or make use of this intervention-character of our measures?