Advanced Health Economics with STATA

Course content

The focus of the current course is the evaluation problem, i.e., how to identify causal effects from natural quantitive data. We elaborate on health economic theories know from the mandatory health economics courses at the public health department and combine these theories with the econometrician’s tool-box to analyze patterns in health surveys typically used in public health and health economics. 

During the course we will use the software STATA to analyze individual level data, e.g., from Survey on Health Aging and Retirement in Europe (SHARE) but other data sources could be applied, too. One application will be the socio-economic gradients in health, which have gained large attention in both epidemiology and economics. Using real data we take the economist’s approach and analyze how health measures relate to household choices and characteristics.

One central focus in the course will be to distinguish correlations from causal effects and the students will be introduced to state-of-the-art difference-in-differences estimators, instrumental variables and regression discontinuity designs. These topics requires algebra. Still, we will learn many of these techniques by doing. Therefore a central part of the course is the practical coding and the of estimation models in STATA.

 

Education

MSc in Public Health Science - elective course

MSc in Health Informatics - elective course

MSc in Global Health - elective course

MSc in Human Biology - elective course

MSc in Health Science - elective course

Learning outcome

After the course the students are expected to: 

  • Knowledge
    • Explain central health economic concepts related to micro behavior
    • Reflect on the counterfactual problem in health econometric applications
    • Explain and apply econometric techniques (eg. OLS, Instrumental variables, differences in differences) to identify causal relationships
    • Reflect on underlying assumptions for these models
  • Skills
    • be able to understand and extract relevant information from scientific papers in applied health econometrics 
    • be able to choose among econometric models for different applications and argue for the choice
    • formulate testable research questions related to casual relations
    • assess not only the advantages of different techniques, but also their pitfalls
    • be able to write clearly about data, econometric analyses and results
    • interpret empirical results within a health economic framework
    • STATA coding
    • be able to carry out micro-econometric analyses on individual level data using STATA software
  • Competencies
    • Independently plan and carry out health economic evaluations using micro data.
    • Professionally, being able to (cross-disciplinarily) understand empirical strategies of health economists and comparing them to those of epidemiologist.    

Lectures and exercises.
Student lecture-to-lecture hand-ins (homework) including STATA coding, results and written work. Supervised by the lecturer, the students will go through own STATA codes on projector.

Book:

Mastering 'Metrics: The path from cause to effect, Joshua D. Angrist and Jörn-Steffen Pischke

Papers (more papers may be added to the list during the course):

Cutler, DM and Lleras-Muney A. Education and Health: Evaluating Theories and Evidence. In RF Schoeni, JS House, G Kaplan and H Pollack (Eds.): Making Americans Healthier: Social and Economics Policy as Health Policy, , New York: Russell Sage Foundation 2008. Published as NBER working paper:
dx.doi.org/10.3386/w12352

Almond, D and Currie, J, ”Killing me softly: The Fetal Origins Hypothesis”, Journal of Economic Perspectives—Volume 25, Number 3—Summer 2011—Pages 153–172
http://dx.doi.org/10.1257/jep.25.3.153

Almond, Douglas. 2006. “Is the 1918 Influenza Pandemic Over? Long-Term Effects of in utero Influenza Exposure in the Post-1940 U.S. Population.” Journal of Political Economy, 114(4): 672–712
Link to paper

Smith, James P., 2009, “The Impact of Childhood Health on Adult Labor Market Outcomes”, The Review of Economics and Statistics, August 2009, 91(3): 478-489
http://www.mitpressjournals.org/doi/pdf/10.1162/rest.91.3.478

Angrist, Joshua D., and Alan B. Krueger. 2001. "Instrumental Variables and the Search for Identification: From Supply and Demand to Natural Experiments." Journal of Economic Perspectives, 15(4): 69-85.
http://dx.doi.org/10.1257/jep.15.4.69

Angrist,  Joshua D., “Instrumental variables methods in experimental criminological research: what, why and how”, Journal of Experimental Criminology (2006) 2: 23–44

http://dx.doi.org/10.1257/jep.15.4.69

Currie, J. & Madrian, BC. (1999): Health, health insurance and the labor market (eds.):  Handbook of Labor Economics, Vol. 3 , chapter 50, p. 3309-3416  http://dx.doi.org.ep.fjernadgang.kb.dk/10.1016/S1573-4463(99)30041-9
 

 

Knowledge of statistics at MSc/MA level

Because the course makes use of the Survey of Health, Ageing and Retirement in Europe (SHARE), the students must register as data users, sign a statement concerning the use of SHARE data and comply with the conditions for which the data can be used, see http:/​/​www.share-project.org/​data-access.html for details.
The students will receive detailed information from the course leader in the weeks prior to course start about the exact registration procedures.

This course is available without pre-approval for students at the MSc in Health Informatics, MSc in Global Health, MSc in Human Biology and MSc in Health Science: It should the noted that it is recommended to have passed statistics course at MSc level in order to pass the exam.

Written
Oral
Individual
Collective
Continuous feedback during the course of the semester
Peer feedback (Students give each other feedback)

Feedback takes place during the entire course. Students upload homework and feedback is given from peers and lecturer at a dedicated poster session midway in the course. At the end of the course, students hand in an outline of their course paper (not the final final paper). Each outline is given written teacher feedback.

ECTS
10 ECTS
Type of assessment
Written assignment
The final course paper can be submitted individual or in groups of two students. The maximum number of pages assessed is 15 for individual papers and 24 for groups of two students. In addition the students must submit an appendix including the STATA-codes used to produce results (no page limits) and can choose to submit an additional appendix (of up to 20 pages) of STATA output (incl. comments and notes).

Extent of written assignments:
Students are obliged to disclose the number of characters of the submission of written assignments with maximum length. A standard page contains 2,400 characters including spaces. The individual pages can consist of fewer or more than 2,400 characters, but the total number of characters must not exceed 2,400 characters x max. number of pages. On the tasks and projects, which is a maximum length of the number of standard pages of 2,400 characters with spaces, the front page must contain an indication of number of characters in the assignment, excluding table of contents, abstract, tables, figures, bibliography and appendices, but including footnote or endnotes. It is allowed to attach attachments if it is agreed with the supervisor. Appendix, as a student wishes to be included in the overall assessment shall be identified and counted in the number of pages. If assignments exceed the permitted number of pages/characters, this must affect the assessment.

Management of receipts:
For written take-home assignments, the student must be aware that additional appendices, such as audio files, central computer printouts, etc., may be forwarded to the examiner or co-examiner if they require it. The student has an obligation to keep relevant material, until the assignment is assessed.

Group assignments:
Requirements for individualisation of written assignments means that the student must account for the students who have been the main responsibility for which section. This division must follow a meaningful division of the assignment, e.g. in sections and subsections. Up to 1/3 of the assignment may be prepared with collective responsibility, which obviously can include the introduction and conclusion. The division of responsibility is displayed on a separate page, which is included in the task, but does not count towards characters, so that the assignment of roles and responsibilities is a single file that can easily be submitted in digital exam.
Marking scale
7-point grading scale
Censorship form
External censorship
Criteria for exam assessment

To achieve the grade 12 the student is expected to: 

  • Knowledge
    • Explain central health economic concepts related to micro behavior
    • Reflect on the counterfactual problem in health econometric applications
    • Explain and apply econometric techniques (eg. OLS, Instrumental variables, differences in differences) to identify causal relationships
    • Reflect on underlying assumptions for these models
  • Skills
    • be able to understand and extract relevant information from scientific papers in applied health econometrics 
    • be able to choose among econometric models for different applications and argue for the choice
    • formulate testable research questions related to casual relations
    • assess not only the advantages of different techniques, but also their pitfalls
    • be able to write clearly about data, econometric analyses and results
    • interpret empirical results within a health economic framework
    • STATA coding
    • be able to carry out micro-econometric analyses on individual level data using STATA software
  • Competencies
    • Independently plan and carry out health economic evaluations using micro data.
    • Professionally, being able to (cross-disciplinarily) understand empirical strategies of health economists and comparing them to those of epidemiologist.    
  • Category
  • Hours
  • Class Instruction
  • 40
  • Preparation
  • 110
  • Exam
  • 125
  • English
  • 275