Students or researchers conducting studies often face the dilemma of authenticity of the information they have collected or obtained from other sources. Researchers generally collect data and is properly organized and processed to develop information. Finally the information is analysed and tested and interpreted. So during the process there can be some distortions or diversions which are inevitable. So to test the information or data we conduct validity, reliability and accuracy tests.
Reliability is the extent to which we can rely on the information so that it will produce stable and consistent results. Proper care must be taken while collecting the data either from the primary sources or from secondary sources. Reliable data will be genuine, trustworthy, dependable, reputable and dependable. Some of the types of reliability are Test-retest reliability, Parallel forms reliability, Inter-rater reliability and Internal consistency reliability. Internal consistency reliability is again divided into Average inter-item correlation and Split-half reliability.
Reliable information is not sufficient itself and needs to be also valid. Validity is the extent to which the data collection method is truly able to meet our expectations or what it is purported to measure. Validity can be conducted through various methods depending on the data and required output. Some of the methods to check validity are Face validity, Construct validity, Criterion-Related Validity, Formative validity and Sampling validity.
Accuracy is the sensitivity to change. If some false information is added or the available information is tampered the output accuracy changes. So to determine the quality of data a method called triangulation technique is commonly used to maintain accuracy. Triangulation techniques can be of various types like Data triangulation, Investigator triangulation, Theory triangulation and Methodological triangulation. Although we have methods other than triangulation to find the accuracy of information all those methods are problematic, time consuming, costly and prohibitive as they require filed study and testing’s. So triangulation is the best method to determine the validity and reliability of the data.