Statistical interpretation of suspension particle concentration calculation in clean room
According to GBT16292-2010 pharmaceutical industry clean room (area) suspended particles Test Method, the calculation of suspended particles is divided into 4 steps:
First step: average suspended particle concentration of sample points A
A——Average particle concentration at a certain sampling point, grain per cubic meter (particles/m3)
Ci——particle concentration at a certain sampling point (i=1, 2,… , n), grain per cubic meter (particles /m3)
N – the number of sampling times at a sampling point.
Statistical significance: By repeatedly sampling a sample point and eliminating the random error by calculating the arithmetic mean, usually in the actual test, continuous sampling is detected 3 times
Step 2: Mean of the mean M
M – the mean of the mean, That is, the average particle concentration of the clean room (zone), the particle per cubic meter (particles/m3)
Ai——the particle concentration of a sampling point (i=1,2,…,n) , grain per cubic meter (particles /m3)
L – the total number of sampling points in a clean room (area).
Statistical significance: This step is to calculate the total average of multiple samplings over multiple points
Step 3: Standard deviation SE
According to the formula:
SE—the standard error of the mean mean, grain per cubic meter (particles/m3)
Statistical significance: This step is for no Students who have studied statistics may understand some difficulties. We divide this into two steps to understand.
1 standard deviation
This calculation is actually the difference between the sample variance and the population variance. We select several sampling points and detect the suspended particle concentration at the sampling point to sample The situation to infer the overall suspended particle situation, so we should use the formula of the sample variance to calculate,
This step can be understood as, we continue to extract the sample size from a population (a room) to L The sample (sampling point) is estimated, so what is the relationship between the total and the sampled result (the statistical term is the sample distribution of the sample mean), the great mathematician directly gives the conclusion
the central limit theorem:
Let a sample with a sample size n be taken from any population with a mean of μ and a variance of σ^2; (finite), when n is sufficiently large The sampling distribution of the sample mean approximates a normal distribution with a mean of μ and a variance of σ^2/n.
According to this theorem, we obtain the variance of the sample distribution of the sample mean as one-nth of the total method. Converted to standard deviation is obtained:
Statistical significance: The calculation of the upper confidence limit is an interval estimate in statistics, because we do not know the variance of the population here, we use the sample variance to approximate the population variance, It can only be considered that the distribution is applicable to the t distribution, not the normal distribution. This requires everyone to pay attention. The t distribution freedom is L-1, so we see that the value of t in the above table is consistent with the color labeling part of the t distribution table. .
Source: Guangzhou Haolun Purification www.bacclean.com