Challenges to the Reliability of Officially Published Statistics for Extension Work
Abstract
The crucial importance of secondary data for socio-economic analysis cannot be overemphasised. The results of research are only as good as the quality of data used: garbage in, garbage out. This paper questions the reliability of officially published statistics. Aggregate maize production data was collected from the official publications of the Central Bank of Nigeria based on the National Bureau of Statistics, for the period 1972-2007. This form our first set of data: published data. Literature on annual growth rate for maize in developing countries was reviewed, from which it was found that the highest ever recorded annual rate of growth for maize, over a period of 10 years was 4.84%; and 3.83% for a 40 years period. The sub-Saharan African average (less South Africa) was 1.93% and 1.04% for the 10-year and 40-year periods respectively. Based on this, an annual growth rate of 7.5%, about twice the highest rate for developing countries, was assumed for maize in Nigeria from 1972-2007. Taking 1972 as the baseline year, our second set of data was generated: expected data. Descriptive graph and the Student’s t Test technique for comparison of means of independent samples was then used to test the postulated hypothesis; the hypothesis was rejected indicating that the maize production figures given in our published statistics differ significantly from the corresponding set of expected figures. The paper concluded that data from officially published statistics differs significantly from expected data based on experience elsewhere. Thus, Nigerian published statistics may not be reliable.This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
JAE supports free online communication and exchange of knowledge as the most effective way of ensuring that the fruits of research and development practice are made widely available. It is therefore committed to open access, which, for authors, enables the widest possible dissemination of their findings and, for readers, increases their ability to discover pertinent information. The Journal adopts and uses the CC BY-NC-ND license. Under this license users are permitted to: Copy and distribute the article (non-commercially); you can’t change or alter the article in anyway; Users are not allowed to data mine the article.