The quality of the data generated by a study depends on a researcher`s ability to collect accurate, consistent information. The training, experience and objectivity of researchers enhance the reliability and effectiveness of intra-European observers. For example, animal behaviour researcher D.K. Scott says she has trained to recognize 450 swans in the wild to give credibility to her observations of the social behaviour of birds. Researchers often videotape phenomenon and it checks several times to make sure of their facts. Intraobserver reliability leads to discoveries that can be replicated by other researchers. Krippendorffs Alpha is a versatile statistic that evaluates the agreement between observers who categorize, evaluate or measure a certain number of objects against the values of a variable. It generalizes several specialized agreement coefficients by accepting any number of observers applicable to nominal, ordinal, interval and proportional levels of measurement, capable of processing missing and corrected data for small sample sizes. The agreement between observers and intra-observer observers was calculated on the basis of Kappa`s statistic, which determines the agreement beyond what might be expected of chance . The Kappa statistic was established for each observer who compares between the first and second observation, in order to assess the intra-observer agreement and between the two observers for the first attempt, in order to assess the agreement between the observers. The interpretation of Kappa`s values was carried out according to the criteria of Landis and Koch , who recommended: a value greater than 0.8 as "almost perfect," between 0.6 and 0.8 "significant," between 0.4 and 0.6 "moderate," between 0.2 and 0.4 "fair," 0-0.2 "light" and 0-1 "bad." This study consisted of an inter-observer and intra-observer agreement study on the radiographic diagnosis of AVN after SCFE. The population studied was identified on the basis of a retrospective review of all SCFE cases treated at our centre between 1995 and 2005.
All cases in which AVN was diagnosed were included in the study. The diagnosis of AVN was made in this study on the basis of x-rays. While this may have resulted in fewer cases of AVN than could have occurred, it would not have affected the agreement on the radiological diagnosis of AVN, which was the objective of the study. Compliance with AVN`s bone or magnetic resonance imaging (MRI) went beyond the scope of this study. The only criterion for defining NVA was the diagnosis of complication in clinical records. To control the agreement estimate, a random sample of 19 of the other cases was taken using a random number generator. By comparing two methods of measurement, it is interesting not only to estimate both the bias and the limits of the agreement between the two methods (interdeccis agreement), but also to evaluate these characteristics for each method itself.