The standard error of regressions: a note on new evidence of significance misuse
OUTPUT TYPE: Journal Article
PUBLICATION YEAR: 2013
TITLE AUTHOR(S): C.N.Mbatha, M.A.Gustafsson
KEYWORDS: ECONOMETRICS, RESEARCH FINDINGS, STATISTICS
DEPARTMENT: Equitable Education and Economies (IED)
Print: HSRC Library: shelf number 7586
HANDLE: 20.500.11910/3099
URI: http://hdl.handle.net/20.500.11910/3099
If you would like to obtain a copy of this Research Output, please contact Hanlie Baudin at researchoutputs@hsrc.ac.za.
Abstract
There is a body of literature dealing with the improper use of statistical significance within economic analysis. Among the problematic usages that have been identified are fundamental misunderstandings about the influence of sample design and size on statistical significance, an excessive focus on statistical significance to the exclusion of economic and policy significance, and a harmful conflation of these two very different types of significance. An analysis of 51 agricultural economics papers reviewed and presented at an African conference in 2010 finds improper usage of statistical significance that is comparable or worse in nature and extent to that found in a previous meta analysis focusing on published articles in the American Economic Review in the 1980s and 1990s: well over half of the papers employed what is termed 'sign' and 'Asterisks' econometrics. Overall, the findings underline the need for clearly stated and consistent analytical methods in producing papers as well as for careful review and selection of papers that employ regression analysis.-
Related Research Outputs:
- Globalisation, regional integration, governance, and household viability envisaging a research, policy and advocacy agenda: roundtable report
- Utilisation of research findings: case study report
- Managing the design and development of a data warehouse: a case study of the HSRC's human resources development data warehouse project
- Towards more effective crime prevention in South Africa: the necessity of basic building blocks. Part 1
- Crime analysis and forecasting in South Africa: the need for information. Part 2
- Crime analysis and forecasting in South Africa: the need for information. Part 4
- Research methodology (approaches) and the implementation of research findings
- Dilemmas in ethics and artifact: a South African perspective
- 1998 crime statistics with 1996 census data
- The drug-crime nexus in South Africa: Part 1
- Writing about education at the HSRC
- The economics of culture and cultural statistics in South Africa
- Do practitioners use research results?: case study of education district officials and principals
- A Bayesian analysis of correlated interval-censored data
- Disability measurement and statistics: the state of the notion
- A Bayesian analysis of correlated interval-censored data
- Accuracy of serological assays for detection of recent infection with HIV and estimation of population incidence: a systematic review
- South African National Survey of Research and Experimental Development: statistical report 2017/18
- Results of the 2011 UIS pilot data collection of innovation statistics
- Constitutional court statistics for the 2011 term