Significance and Use
4.1 The use of statistical analysis will enable the investigator to make better, more informed decisions when using the information derived from the analyses.
4.1.1 The goals when performing statistical analyses, are to summarize, display, quantify, and provide objective measures for assessing the relationships and anomalies in data. Statistical analyses also involve fitting a model to the data and making inferences from the model. The type of data dictates the type of model to be used. Statistical analysis provides the means to test differences between control and treatment groups (one form of hypothesis testing), as well as the means to describe the relationship between the level of treatment and the measured responses (concentration effect curves), or to quantify the degree of uncertainty in the end-point estimates derived from the data.
4.1.2 The goals of this practice are to identify and describe commonly used statistical procedures for toxicity tests. Fig. 1, Section 6, following statistical methods (Section 5), presents a flow chart and some recommended analysis paths, with references. From this guideline, it is recommended that each investigator develop a statistical analysis protocol specific to his test results. The flow chart, along with the rest of this guideline, may provide both useful direction, and service as a quality assurance tool, to help ensure that important steps in the analysis are not overlooked.
Scope
1.1 This practice covers guidance for the statistical analysis of laboratory data on the toxicity of chemicals or mixtures of chemicals to aquatic or terrestrial plants and animals. This practice applies only to the analysis of the data, after the test has been completed. All design concerns, such as the statement of the null hypothesis and its alternative, the choice of alpha and beta risks, the identification of experimental units, possible pseudo replication, randomization techniques, and the execution of the test are beyond the scope of this practice. This practice is not a textbook, nor does it replace consultation with a statistician. It assumes that the investigator recognizes the structure of his experimental design, has identified the experimental units that were used, and understands how the test was conducted. Given this information, the proper statistical analyses can be determined for the data.
1.1.1 Recognizing that statistics is a profession in which research continues in order to improve methods for performing the analysis of scientific data, the use of statistical methods other than those described in this practice is acceptable as long as they are properly documented and scientifically defensible. Additional annexes may be developed in the future to reflect comments and needs identified by users, such as more detailed discussion of probit and logistic regression models, or statistical methods for dose response and risk assessment.
