Random stratified sampling method

There are four major types of sampling methods random, stratified, systematic, and cluster. Random is by far the most commonly employed method in toxicology. It stresses the fulfillment of the assumption of avoiding bias. When the entire pool of possibilities is mixed or randomized (procedures for randomization are presented in a later section), then the members of the group are selected in the order that are drawn from the pool. 

Data are not random but are representative in other ways. This may mean, for example, that the data are a stratified sample applicable to the real-world situation for the assessment scenario of interest. In this case, frequentist methods can be used to make inferences for the strata that are represented by the data (e.g. particular exposed subpopulations), but not necessarily for all aspects of the scenario. However, for the components of the scenario for which the data cannot be applied, there is a lack of representative data. For example, if the available data represent one subpopulation, but not another, frequentist methods can be applied to make inferences about the former, but could lead to biased estimation of the latter. Bias correction methods, such as comparison with benchmarks, use of surrogate (analogous) data or more formal application of expert judgement, may be required for the latter. 

Stratified sampling is appropriate to the case in which a certain logical or natural grouping may be expected within the population. Examples are the element or compound distribution in soil due to the water circulation, or the element distribution in biological tissues. Such a layer in the soil may be called a stratum. Here we want to know the mean of the stratum the samples within the stratum are selected by a random method. Further on, the number of samples selected from any stratum should be proportional to the product of the total number of particles in the stratum N and the standard deviation a-,. 

A Latin Hypercube sampling method was used in the Risk simulation to generate the input parameter values from the probability distribution functions. This method was chosen over the Monte Carlo technique, which samples randomly from the distribution function and causes clustering when low probability values are not sampled due to insufficient computational sampUng iterations. In contrast, the Latin Hypercube stratified sampling technique systematically samples all segments (stratifications) of the distribution just once, resulting in fewer computational iterations required to produce a representative probability curve. 

Figure 3.2 Basic methods used for sampling (a) random (b) systematic (c) stratified random (1) - sub-division into equal areas (d) stratified random (2) - weight related to sub-area of habitat.

The persons are selected on a stratified random sampling basis, with stratifications designated according to the type of exposure, quantity of exposure, degree of hazard present, and other criteria considered important to the representativeness of the sample. The objective is to discover causal factors that are critical, that is, that have contributed to an accident or potential accident situation. The unsafe acts and unsafe conditions identified by this method then serve as the basis for the identification of accident potential problem areas and the ultimate development of countermeasures designed to control accidents at the no-loss stage [p. 304],... 

In the language of statistics, this is a stratified experiment, that is, the samples are grouped according to some criteria. In this case, the criteria is consecutive production of the units. This is not, therefore, a random selection of samples as is required in many statistical methods. It also is not a control chart even though the plot may resemble one. It is a snapshot of the process taken at the time of the sampling. Incidentally, the multivari chart is not a new procedure, dating from the 1950s, but it has been incorporated into this system by Shainen. 

This is a method of identifying errors and unsafe conditions that contribute to both potential and actual accidents or incidents within a given population by means of a stratified random sample of participant-observers selected from within the population. Operational personnel can collect information on potential or past errors or unsafe conditions. Hazard controls are then developed to minimise the potential error or unsafe condition. 

---