Lecturer | Prof. Tom Stanley School of Business, Deakin University, Melbourne, Australia |
Date | 25./26.04.2024 10:00 am to 1:15 pm (with a short break) and 2:30 pm to 4:00 pm each day |
Room/Address | TU Chemnitz, Faculty of Economics and Business Administration |
Seminar content | 2-day program consisting of lectures on meta-analysis methods, discussion of numerous actual meta-analysis applications, and interactive exercises. Each day there will be a morning session with a short break and an afternoon session. Although not required: 2 recorded lectures from a similar class are available for you to preview and to reinforce what was covered in this class. See the class folder
Before day 1: Please view recorded lecture 1 (1:18) and read selections from Borenstein et al. (2009) as well as Stanley (2013): “Does economics add up?”
Workshop outline:
Day 1 Morning Session:
I) Motivation and Background
- The ‘Replication/Credibility’ Crisis
- What meta-analyses can tell us about contemporary research.
- Publication Selection Bias (PSB): Its consequences and solutions
- What’s wrong with Social Science research?
Ans: Low power, high heterogeneity, and publication selection bias
- What’s the cause of the Replication Crisis? {see above}
II) What Meta-Regression Analysis (MRA) can do.
- MRA can detect and greatly reduce publication bias.
- MRA can remove other biases and explain systematic heterogeneity.
- Unlike most social science research, MRAs are often successfully replicated.
Afternoon Session:
III) Conducting Basic Meta-Analysis
- Methods
- Applications
- Meta-analysis with STATA and/or R
Day 2 Morning Session:
IV) Meta-Regression Analysis
- Methods
- Problems/Remedies
- Applications, Applications, Applications
- Meta-regression analysis with STATA and/or R
V) Recent Advances in Meta-Analysis and Meta-Regression Analysis
- Excess Statistical Significance and testing for publication selection bias
- Bayesian modeling averaging across alternative methods to correct PSB
- New Metrics of Misleading and Informative Evidence
Afternoon Session:
VI) Students individually replicate existing meta-analyses using STATA or R. |
Requirements | Students are expected to have taken Statistics and/or Econometrics classes and to know some regression analysis. Also, they should have STATA and R installed on their laptops, either by buying a 6-month STATA license for $48 or by downloading it from your university if available. |
Required Readings | - Selections from Borenstein et al. (2009). Introduction to meta-analysis, Chichester, U.K. John Wiley & Sons.
See class folder.
- Stanley, T. D. “Does economics add up? An introduction to meta-regression analysis.” European Journal of Economics and Economic Policy 10(2013): 207-220.
Free download here.
- De Linde Leonard, M. and Stanley, T. D. (2015). Married with children: What remains when observable biases are removed from the reported male marriage wage premium. Labour Economics 33 (2015), 72-80.
See class folder.
- Irsova, Z., Doucouliagos, H., Havranek, T., Stanley, T.D. (2023). Meta-analysis of social science research: A practitioner’s guide. Journal of Economics Surveys.
Free download here.
- Bem D, Tressoldi P, Rabeyron T and Duggan M. Feeling the future: A meta-analysis of 90 experiments on the anomalous anticipation of random future events. F1000Research 2016, 4:1188.
Available here.
- Askarov, Z., Doucouliagos A, and Doucouliagos H., and Stanley, T.D. (2023b). Selective and (mis)leading economics journals: Meta-research evidence. Journal of Economics Surveys.
Available here.
Further Suggested Readings:
- Askarov, Z., Doucouliagos A, Doucouliagos H. & Stanley (2023a). The significance of data-sharing policy. J. European Economic Association, 21:1191–1226.
- Bartoš F, Maier M, Wagenmakers EJ, Doucouliagos H, Stanley TD. (2023). Robust Bayesian meta-analysis: Model averaging across complementary publication bias adjustment methods. Research Synthesis Methods,14:99-116.
- Bartoš F, Maier M, Quintana DS, Wagenmakers EJ (2022). Tutorial: Adjusting for Publication Bias in JASP and R. Adv Meth & Pract Psyc Sci, 5: 1-19.
Available here.
- Havránek, T., Stanley, T.D., Doucouliagos, H. et al. (2020): Reporting guidelines for meta-analysis in economics. Journal of Economic Surveys, 34: 469-75.
Available here.
- Stanley, T.D. and H. Doucouliagos. (2012). Meta-Regression Analysis in Economics and Business, Oxford: Routledge.
|
Certificate | Doctoral candidates from the Faculty of Business and Economics, TU Dresden can earn a certificate according to § 9 of the Ph.D. doctoral regulations (PromO 2018): Doctoral candidates of Business Administration: § 9 (1) Nr. 5 or 6 Doctoral candidates of Business Information Systems: § 9 (1) Nr. 6 Doctoral candidates of Economics: § 9 (1) Nr. 6
Doctoral candidates from other universities can earn a certificate as well. |
Assignment |
Students need to use STATA or R to do meta-analysis and meta-regression analysis calculations for an actual meta-analysis dataset. There will be a lab with individual help on the second day to ensure that each student can complete the assignment. Students need to copy and paste their findings in a MS Word document and briefly interpret their findings. That is, what do the statistical results reveal about this research and the underlying phenomenon studied. Full credit requirement: Students need to attend class, read and be ready to discuss the assigned material, and to demonstrate that they can use STATA or R to do meta-analysis and meta-regression analysis calculations for an actual meta-analysis dataset and briefly interpret their findings.
|
Registration | Participation is limited (max. 25). To register, send an e-mail to Dr. Uta Schwarz: uta.schwarz@tu-dresden.de. |