3.8 Reliability and validity
Reliability is the extent to which a measurement of a phenomenon gives a stable and consistent results (Carmines and Zeller 1979). Moser and Kalton (1989: 353) define reliability as ‘a scale or test is said to be reliable to the extent that repeat measurements made by it under constant conditions will give the same result. Yin (1994) describes it as ‘demonstrating that the operations of a case study – such as the data collection procedures can be repeated, using the same results’. Applying the following three principles was undertaken in order to help the researcher deals with the problems of establishing validity (see below) and reliability of a case study: 1. The Use of multiple sources of evidence – A major …show more content…
Creating a case study database – A case study project should strive to create a specific, presentable database, so that, in principle other researchers can review the evidence directly and not be limited to the written reports. (This has been addressed in that a detailed database was compiled in order to keep a record of all case related sources for future reference.
3. Maintain a chain of evidence – This increases reliability by allowing an external observer to follow the derivation of any evidence from initial research questions to ultimate case study conclusions that is there should be a clear procedure followed by the researcher to arrive at the level of conclusion. The external observer should be able to trace the steps in either direction (from conclusions back to initial research questions or from questions to conclusions). (A chain of evidence was maintained by keeping a detailed account of tasks undertaken during the …show more content…
These include: not keeping an accurate record of sources, not using a wide range of sources and accuracy of sources. Reliability is often referred to as repeatability. In other words, if someone was to come along and repeat a study six-months later, they will have a clear ‘research trail’ in order to carry out the same research, thus therefore leading to higher levels of reliability. Maintaining high levels of reliability when conducting research in China can be problematic for two reasons. First, as the economic development is so rapid, research often becomes dated; thereby resulting in even relatively contemporary research becoming almost worthless e.g. “What will China be like following WTO?” Second, the accuracy and reliability of Chinese sources, particularly those of the state backed media and Ministry of Commerce need to be viewed with caution. Validity is the ability of an instrument to measure what it is designed to measure (Kumar 1996). Nachmias (1992) defines validity, as “Is one measuring what one intends to measure?” In other words, it refers to the relationship between a construct and its indicators. There are three types of validity – content validity, empirical validity and construct