RACI titration competition

Table 1.2 The results of the 1997 RACI titration competition. The values are independent students results for the concentration of a solution of acetic acid (units M). The correct answer was 0.1147 M...

Figure 1.2 Results of the 1997 RACI titration competition. Inset results for teams 3-20. The line is the accepted result (0.1147M) and the dashed lines are 1%. 

Figure 1.3 Histogram of the 1997 RACI titration results. Each bar is the number of students whose result fell between the number indicated and the number to the right. Note that the 25 data points in table 1.2 represent a subset of all the data from the RACI titration competition. The entire data set of 75 results was used to generate this histogram.

The RSD of an analytical result is often quoted as it gives an immediate impression of the precision of the measurement. Less than 1 % is usually considered very good for routine measurements which are more often in the 1-5% range. For the RACI titration competition (see chapter 1) the mean and standard deviation were 0.1146M and 0.0006 M, respectively, after removing outliers from consideration. The RSD was therefore 0.0006/0.1146 x 100% =0.5%, a very good result. 

The average and sample standard deviation are known as estimators of the population mean and standard deviation. We have seen how the estimates improve as the number of data increases. As we have stressed, the use of these statistics requires data that are normally distributed, and for confidence intervals employing the standard deviation of the mean this tends to be so. Real data may be so distributed, but often the distribution will contain data that are seriously flawed, as with the RACI titration competition described in chapter 1. If we can identify such data and remove them from further... 

Table 2.1 The results of 25 competitors in the 1997 RACI titration competition of the concentration of a test acetic acid solution in units of mol L 1...

Use robust estimators to estimate the population mean and population standard deviation for the RACI titration competition data shown in table 2.1. Outliers from a normal distribution are shown in italics (see section 3.4 for details of how to do this) and the median is in bold. 

For the RACI titration competition data the median is 0.1146M and the normalized interquartile range is 0.00098 M. 

Figure 3.3 Rankit plots for results of the RACI titration competition (a) All data (b) with extreme outlier at 0.9083 M removed (c) with seven outliers removed. Note the shrinking x-axis range.

Although the above sounds plausible, do we have any evidence for these definitions of error Take as an example the Royal Australian Chemical Institute s (RACI) schools titration competition of 1997. In this competition, each of a team of three high school students is asked... 

---

See also in sourсe #XX -- [ ]

See also in sourсe #XX -- [ , , , , , ]

---