Interpercentile interval

Three kinds of reference intervals have been suggested tolerance interval, prediction interval, and interpercentile interval. The choice from among these types of intervals may be important for certain well-defined statistical problems, but their numerical differences are negligible when based on at least 100 reference values. 

The interpercentile interval is simple to estimate, more commonly used, and recommended by the IFCC. This chapter, therefore, focuses on this type of interval. It is defined as an interval bounded by two percentiles of the reference distribution. A percentile denotes a value that divides the reference distribution such that a specified percentage of its values have magnitudes less than or equal to the limiting value. For example, if 2.32 mmol/L is the 97,5 percentile of serum triglycerides, 97.5% of the concentration values are equal to or below this value. 

The percentiles are point estimates of population pa-rameters. Accordingly, they are unbiased estimates only if the subset of values was selected randomly from the population. But, as was discussed earlier, random sampling is often difficult to achieve. The interpercentile interval may always be used, however, as a summary or description of the subset reference distribution. 

The interpercentile interval can be determined by parametric, nonparametric, and bootstrap statistical techniques. ... 

---

See also in sourсe #XX -- [ ]

---