CN110010202B - Establishment and judgment standard and judgment method for judging similarity of pure varieties of dendrobium fimbriatum - Google Patents
Establishment and judgment standard and judgment method for judging similarity of pure varieties of dendrobium fimbriatum Download PDFInfo
- Publication number
- CN110010202B CN110010202B CN201710887053.3A CN201710887053A CN110010202B CN 110010202 B CN110010202 B CN 110010202B CN 201710887053 A CN201710887053 A CN 201710887053A CN 110010202 B CN110010202 B CN 110010202B
- Authority
- CN
- China
- Prior art keywords
- sample
- dendrobium fimbriatum
- confidence interval
- standard
- total length
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B25/00—ICT specially adapted for hybridisation; ICT specially adapted for gene or protein expression
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Genetics & Genomics (AREA)
- Molecular Biology (AREA)
- Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biotechnology (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Theoretical Computer Science (AREA)
- Complex Calculations (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method for judging the similarity of pure varieties of dendrobium fimbriatum, a judgment standard and a judgment method, wherein the establishment process of the judgment method is as follows: collecting dendrobium fimbriatum samples consistent with a gene sequencing conclusion, and determining the total length of each sample; s2: carrying out normal test on the total length variable of the sample; s3: standard interval: if the result obtained in the step S2 is subjected to normal distribution, a 95% confidence interval of the mean value and a 95% confidence interval of the standard deviation are obtained according to a normal distribution overall calculation formula; the confidence interval can be used as a standard range for identifying the purity of unknown samples. The judgment standard established according to the actually collected data is as follows: the 95% confidence interval of the mean and the 95% confidence interval of the standard deviation are respectively: (50.0149, 66.6251) and (15.7102, 27.9898), the measured flow Su Danhu sample need only be compared to that interval. The purity of the varieties of the dendrobium fimbriatum can be identified through the morphological related characteristics of the dendrobium fimbriatum, so that the value or existence of the dendrobium fimbriatum planted artificially can be simply judged; the identification accuracy is high, and the method has important practical significance.
Description
Technical Field
The invention relates to the fields of medicine and biology, in particular to a method for establishing and judging standards and a method for judging the similarity of the pure varieties of dendrobium fimbriatum, namely a method for establishing the correlation between morphological characteristics of dendrobium fimbriatum and gene sequencing conclusion, a method for identifying the purity of the varieties of dendrobium fimbriatum to be detected and the like.
Background
Dendrobium nobile is a common tonic traditional Chinese medicine, mainly dendrobium plants. The dendrobium plant is the largest genus in orchid plants and comprises a plurality of varieties of dendrobium fimbriatum, dendrobium candidum, dendrobium nobile, dendrobium chrysotoxum and the like. There are about 1100 kinds of dendrobe in the global scope, of which there are nearly hundred kinds found in our country. The medicinal history of the dendrobium is long, and is listed as a nourishing product as early as in Shennong Ben Cao Jing, and the dendrobium is always regarded as a precious Chinese herbal medicine by people along with the development of the era, so that the dendrobium has very important nourishing effect. Clinically, dendrobium nobile is used for treating various diseases and has pharmacological effects of enhancing immunity, resisting oxidization, reducing blood sugar, inhibiting cancers and the like. Dendrobium nobile including dendrobium fimbriatum has extremely important value in the fields of traditional Chinese medicine and health care.
However, as the dendrobium is artificially and uncontrollably excavated for a long time and is not reasonably utilized, the wild resources are gradually reduced, the artificial planting condition is gradually increased, and the dendrobium is even the source for mainly supplying the dendrobium fimbriatum. However, the long-term artificial planting also brings the phenomenon of false spurious and secondary filling to the dendrobium fimbriatum, because (1) the artificial planting changes the growth environment of the wild dendrobium fimbriatum; (2) a large amount of fertilizer, lesions, pesticide, new disease species, etc. are artificially applied to dendrobium fimbriatum; (3) moreover, as the varieties of the dendrobium are more, the hybridization among the varieties causes the phenomenon of character crossing of the adjacent varieties; (4) other uncontrollable or undetectable factors lead to the change of the medicinal components of some artificially planted dendrobium fimbriatum, even the disappearance of important medicinal components, and correspondingly, the gene sequence of the dendrobium fimbriatum with the changed or disappeared medicinal components is substantially different from that of the original wild gene sequence. However, once the medicinal value of these dendrobium fimbriatum is weakened or lost, the effect is very serious if the dendrobium fimbriatum is still applied continuously without knowledge in the field, and the effect is more serious if the dendrobium fimbriatum is lost from the medical field without knowledge.
The applicant discovers that certain morphological related characteristics of the dendrobium fimbriatum have very close relation with the gene sequencing conclusion thereof through long-term and extremely large-workload researches, and the gene sequencing conclusion is the gene sequencing result of standard dendrobium fimbriatum with traditional medicinal/nutritional values, and the wild dendrobium fimbriatum is basically consistent with the gene sequencing conclusion. That is to say, the association degree between the dendrobium fimbriatum and the gene sequencing conclusion can be judged through morphological characteristics of the dendrobium fimbriatum, the higher the association degree is, the higher the purity of the variety is, the traditional medicinal and health-care effects are easier to maintain, the lower the purity is, namely, the greater the substantial difference between the dendrobium fimbriatum and the gene sequencing conclusion is, and the greater the medicinal effects are reduced or disappeared.
The gene sequencing conclusion reflects the variety of the sample, and how to efficiently judge the purity of the sample variety by measuring morphological related characteristics on the basis of the gene sequencing conclusion is a problem which needs to be considered when the method is practically applied.
Disclosure of Invention
In view of the above problems in the prior art, the present invention is mainly aimed at solving the defects of the prior art, and provides a method for establishing and judging standards and a method for judging the similarity of the pure varieties of dendrobium fimbriatum.
The aim of the invention is mainly achieved by the following technical scheme.
A method for establishing a method for judging or detecting the similarity of pure varieties of dendrobium fimbriatum comprises the following steps:
s1: standard data acquisition: collecting dendrobium fimbriatum samples consistent with a gene sequencing conclusion (all meeting morphological description of dendrobium fimbriatum), wherein the sample capacity is n, and measuring the total length of each sample to obtain a measurement value of a total length variable;
s2: and (3) normal performance test: carrying out normal test on the total length variable of the sample;
s3: standard interval: if the result obtained in the step S2 is subjected to normal distribution, a 95% confidence interval of the mean value and a 95% confidence interval of the standard deviation are obtained according to a normal distribution overall calculation formula;
if the result of the normalization test of the total length variable of the dendrobium fimbriatum in the step S2 is that the dendrobium fimbriatum does not follow the normal distribution, if the sample capacity exceeds 30, the sample can still calculate the 95% confidence interval of the mean value and the 95% confidence interval of the standard deviation according to the normal overall formula according to the central limit theorem;
the 95% confidence interval of the obtained mean value and the 95% confidence interval of the standard deviation can be used as a standard range for identifying the purity of the unknown sample.
Further, after the measured value of the total length variable is obtained in step S1, the basic statistics of the total length variable are calculated according to the measured value of the total length variable, wherein the basic statistics comprise average level and discrete degree, then the abnormal value of the data is determined according to the basic statistics, if the abnormal value exists, the investigation is performed, if the abnormal value belongs to measurement errors or recording errors, the abnormal point is deleted, and if the abnormal point does not belong to errors, the data should be kept.
Further, the average level includes at least one of a mean, a median, and a mode, and the degree of dispersion includes a standard deviation, an average absolute deviation, and a coefficient of variation;
the basic statistics also comprise making a histogram and/or box-shaped graph to visualize the data according to the measured values of the total length variable, so that the data is more convenient to determine the wrong outlier.
Further, the normalization test includes at least one of visual image analysis and hypothesis testing.
Further, the normalization test includes visual image analysis and hypothesis testing.
Further, the visual image analysis method comprises the following steps:
(1) according to a normal empirical distribution functionDrawing a normal empirical distribution function curve of dendrobium fimbriatum;
according to a normal probability density functionDrawing a normal probability density curve of dendrobium fimbriatum; when μ=0, σ=1 (the mean value is 0, the standard deviation is 1), the normal distribution becomes a standard normal distribution:
(2) according to step S1 and according to the formulaDrawing a true experience distribution function according to the experience distribution function of (1); />
According to the measured value of the total length variable obtained in the step S1 and the formulaDrawing a true probability density function graph according to the probability density function of (1);
(3) comparing the real experience distribution function graph with the experience distribution function curve of normal distribution, and preliminarily judging whether the sample data accords with the normal distribution by judging the degree of curve deviation; comparing the true probability density function graph with a normal probability density curve, and judging whether the sample data obeys normal distribution according to the deviation degree and the curve shape consistency degree;
if the deviation of the true empirical distribution function diagram and the normal distribution empirical distribution function diagram or the true empirical probability density function diagram and the normal distribution probability density function diagram is small and the shapes are consistent, the total length of the dendrobium fimbriatum samples to be detected accords with the normal distribution, and if the deviation is obviously large and the shapes are obviously inconsistent, the total length of the dendrobium fimbriatum samples to be detected does not accord with the normal distribution.
Further, the hypothesis test includes any one of a JB test, a KS test, and a liliferor test.
Further, the hypothesis test is a Lilliefors test, and the Lilliefors test statistic T=sup|F * (x) -S (x) |, wherein T is Liffiefors test statistic, F * (x) Is a normal distribution cumulative distribution function with a mean value of 0 and a standard deviation of 1, S (x) isUnder the significance level of alpha, rejecting the original hypothesis H0 when the test statistic T exceeds the test critical value; otherwise, the original hypothesis cannot be rejected.
A judgment standard for the similarity of the pure varieties of dendrobium fimbriatum is established, and the establishment of the standard comprises the following steps:
(1): 69 wild dendrobium fimbriatum samples consistent with the gene sequencing conclusion are collected, the total length of each sample is measured, and the measurement results are as follows: the total length of the dendrobium fimbriatum is changed within the range of 27.00 mm-94.00 mm, the average level is 37.00 mm-58.32 mm, and the calculated result is that: average value: 58.32mm, median: 58.00mm, mode: standard deviation of total length fluctuation of 37.00mm is 20.12mm, average absolute deviation: 16.89mm, coefficient of variation: 0.35;
(2): visual image analysis normal distribution: drawing an empirical distribution function diagram and a probability density function diagram according to the data in the step S1, and comparing the true empirical distribution function diagram with a normal empirical distribution function curve to obtain the following results: the curves of the two are basically consistent; the result of comparing the true probability density function graph with the normal probability density curve is as follows: the shape of the curves of the two is approximately the same;
through visual analysis of the graphs, the total length sample data of the dendrobium fimbriatum is more likely to accord with normal distribution;
(3): lilliefors test: the original assumption is H0: the data obeys normal distribution; alternative hypothesis H1: the data do not follow normal distribution; the test result obtained by the data in step S1 is:
statistics | Critical value of | P value | Level of significance alpha | Whether or not to accept the original hypothesis |
0.1514 | 0.1730 | 0.1405 | 0.05 | Is that |
The statistic has a value of 0.1514, which is less than a critical value 0.1730; p value is equal to 0.1405, greater than significance level (α=0.05), so that the standard distribution of the dendrobium fimbriae sample data can be confirmed by the original assumption;
(4): the average 95% confidence interval and the standard deviation 95% confidence interval of the dendrobium fimbriatum total length sample data are calculated according to a normal distribution overall calculation formula, and are respectively:
mean value of | 95% confidence interval of mean | Standard deviation of | 95% confidence interval of standard deviation |
58.3200 | (50.0149,66.6251) | 20.1199 | (15.7102,27.9898) |
The 95% confidence interval of the mean and the 95% confidence interval of the standard deviation are respectively: (50.0149, 66.6251) and (15.7102, 27.9898), the interval is a standard interval for judging the similarity of the varieties of the dendrobium fimbriatum, namely the interval is a standard interval for identifying the purity of the varieties of the dendrobium fimbriatum.
A method for judging similarity of pure varieties of dendrobium fimbriatum comprises the following steps:
A. collecting the total length data of the dendrobium fimbriatum sample to be detected, and eliminating abnormal values caused by measurement errors or recording errors in the sample;
B. calculating a mean 95% confidence interval and a standard deviation 95% confidence interval of the total length data of the dendrobium fimbriatum sample to be detected in the step A, and if the mean 95% confidence interval and the standard deviation 95% confidence interval are within the standard intervals [ namely, the mean 95% confidence interval and the standard deviation 95% confidence interval are respectively: (50.0149, 66.6251) and (15.7102, 27.9898), the similarity of the pure varieties of the dendrobium fimbriatum to be detected is high, namely the purity of the dendrobium fimbriatum to be detected is high; if at least one of the 95% confidence interval of the average value and the 95% confidence interval of the total length data of the sample of the dendrobium fimbriatum to be detected is not in the standard interval, the similarity of the pure varieties of the dendrobium fimbriatum to be detected is low, namely the purity of the dendrobium fimbriatum to be detected is low.
The invention has at least the following beneficial effects:
the method establishes connection between morphological characteristics of the dendrobium fimbriatum and a dendrobium fimbriatum gene sequencing conclusion, and can acquire the gene purity through the morphological characteristics. The purity of the varieties of the dendrobium fimbriatum can be identified through the total length data of the dendrobium fimbriatum; the method can simply and concisely judge the value of the artificially planted dendrobium fimbriatum, and even whether the value exists.
The method establishes the standard for judging the purity, can judge the purity degree of the detected flow Su Danhu through the 95% confidence interval of the mean value and the 95% confidence interval of the standard deviation, is simple and accurate, is known in a great number of researches of the applicant, can judge the purity degree of the dendrobium fimbriatum sample with the accuracy rate of more than 90%, and has important application value.
The method can basically judge the medicinal value of a certain batch of dendrobium fimbriatum, reflects the essential characteristics thereof through morphological characteristics, and has profound significance for the whole medical world and the plant world. In addition, the invention can develop an updated and more accurate morphological classification concept or thought.
Drawings
FIG. 1 is a schematic diagram of a histogram according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a box-shaped diagram according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an empirical distribution function curve according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a probability density curve according to an embodiment of the present invention.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described in conjunction with the specific embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
The establishment of the method for judging the similarity of the pure varieties of the dendrobium fimbriatum comprises the following steps:
s1: standard data acquisition: collecting dendrobium fimbriatum samples which completely meet the morphological description of dendrobium fimbriatum, namely collecting dendrobium fimbriatum samples consistent with a gene sequencing conclusion, wherein the sample capacity is n, and measuring the total length of each sample to obtain the measurement value of a total length variable;
s2: confirmation of data: calculating basic statistics of the total length variable according to the measured value of the total length variable, wherein the basic statistics comprise average level and discrete degree, the average level comprises at least one of mean value, median and mode, and the discrete degree comprises standard deviation, average absolute deviation and variation coefficient; and according to the corresponding data, a histogram and a box-shaped graph are manufactured to visualize the data, so that the variable distribution condition and abnormal values can be observed, analyzed and judged more clearly. Then, it is determined that the data has an erroneous outlier, if the outlier is found, the outlier is deleted if it belongs to a measurement error or a recording error, if it is not due to an error, the data should be retained, and if it is not due to an error, the data should be retained.
S3: and (3) normal performance test: carrying out normal test on the total length variable of the sample; the normalization test includes at least one, and preferably both, of visual image analysis and hypothesis testing, which are both subjective and objective.
The visual image analysis method comprises the following steps:
(1) according to a normal empirical distribution functionDrawing a normal empirical distribution function curve of dendrobium fimbriatum; x in the formula is a random variable, namely a sample observation value of dendrobium fimbriatum; mu is the average value of the obtained sample observation values; sigma is the standard deviation of the sample observations; e is a natural constant, which is about 2.71828; the normal distribution function curve is given, the normal empirical distribution curve can be simulated by a computer, and is not obtained according to the original data, and the normal empirical distribution function curve is drawn to compare the distribution function curve of the original data with the normal distribution function curve so as to check whether the original data obeys the normal distribution.
According to a normal probability density functionDrawing a normal probability density curve of dendrobium fimbriatum, and when μ=0 and σ=1 (the mean value is 0 and the standard deviation is 1), making the normal distribution into a standard normal distribution:x in the formula is a random variable, namely a sample observation value of dendrobium; e is a natural constant, which has a value of about 2.71828. Likewise, a probability density function curve for a normal distribution is already given,the normal empirical distribution curve can also be simulated by a computer, and is not obtained according to the original data. The normal probability density curve is drawn in hopes of comparing the probability density function curve of the original data with the normal probability density function curve to check whether the original data obeys the normal distribution.
The above raw data is the data obtained in step S1.
(2) Drawing a real empirical distribution function according to the empirical distribution function (EDF, empirical Distribution Functions) according to the measured value of the total length variable obtained in the step S1;
the empirical distribution function formula is: let x be 1 ,x 2 ,...,x n Is a group of sample measurement values with a sample volume of n, and the n measurement values are rearranged from small to largeFor any real number x (x is the measured value x for the sample 1 ,x 2 ,...,x n ) Defining a function
Then call F n (x) Is an empirical distribution function of the overall X. It can be abbreviated as F n (x)=1/n· * {x 1 ,x 2 ,...,x n }, wherein * {x 1 ,x 2 ,...,x n X represents x 1 ,x 2 ,...,x n Not greater than x. Another common form of representation is
Wherein I is an indication function, i.e
Thus, find the empirical distribution function F n (x) The value at a point x requires only n observations x of the random variable x 1 ,x 2 ,...,x n The number less than or equal to x is divided by the observation times n. It can be seen that F n (x) The frequency of occurrence of events { X.ltoreq.x } in n replicates of independent experiments.
Drawing a true probability density function graph according to the measured value of the total length variable obtained in the step S1 and the probability density function;
the probability density function (probability density function, PDF) is formulated as: if the distribution function F (X) for the random variable X is a non-negative function F (X) exists such that for any real numberThen X is called (X is the measured value of the sample X 1 ,x 2 ,...,x n ) Is a continuous random variable, where f (X) is called the probability density function of X, abbreviated as probability density. The probability density function of random data represents the probability that the instantaneous amplitude falls within some specified range and is therefore a function of the amplitude. Which varies with the amplitude of the range taken.
The probability density function has the following properties: f (x) is more than or equal to 0;since the probability density function is derived from a distribution function, the pattern of probability density functions can be directly based on each data x of the sample measurement data 1 ,x 2 ,...,x n Calculated.
(3) Comparing the real experience distribution function graph with a normal experience distribution function graph, and preliminarily judging whether the sample data accords with normal distribution or not by judging the deviation degree of the graph; comparing the true probability density function graph with a normal probability density curve, and judging whether the sample data obeys normal distribution according to the deviation degree and the consistency degree of the curve shape;
if the deviation of the true empirical distribution function diagram and the normal distribution function diagram or the true empirical probability density function diagram and the normal distribution probability density function diagram is small and the shapes are consistent, the total length of the dendrobium fimbriatum samples to be detected accords with the normal distribution, and if the deviation is obviously large and the shapes are obviously inconsistent, the total length of the dendrobium fimbriatum samples to be detected does not accord with the normal distribution.
And (3) through drawing a sample empirical distribution function diagram and a sample empirical probability density function diagram, comparing the sample empirical distribution function diagram and a normal distribution corresponding function diagram, visually observing the difference degree of the two curves, and judging whether the total length variable of the sample is from normal distribution.
Hypothesis testing
The hypothesis test includes any one of a JB test, a KS test and a Lilliefors test, preferably the Lilliefors test.
The Lilliefors test statistic T=sup|F * (x) -S (x) |, wherein T is Liffiefors test statistic, F * (x) Is a normal distribution cumulative distribution function with a mean value of 0 and a standard deviation of 1, S (x) isAt the significance level of alpha, rejecting the original hypothesis H when the test statistic T exceeds the test threshold 0 The method comprises the steps of carrying out a first treatment on the surface of the Otherwise, the original hypothesis cannot be rejected.
The Lillieforms normal distribution hypothesis test method can be used for more objectively judging whether the sample is from a normal distribution overall.
S4: standard interval: if the result obtained in the step S3 is subjected to normal distribution, a 95% confidence interval of the mean value and a 95% confidence interval of the standard deviation are obtained according to a normal distribution overall calculation formula;
if the result of the normalization test of the total length variable of dendrobium fimbriatum in step S3 is that the result does not follow the normal distribution, considering the property of the large sample, namely, when the sample size is relatively large, namely, the general requirement is >30, according to the central limit theorem, the sample can still calculate the 95% confidence interval of the mean value and the 95% confidence interval of the standard deviation according to the normal general formula.
The 95% confidence interval of the obtained mean value and the 95% confidence interval of the standard deviation can be used as a standard range for identifying the purity of the unknown sample.
Example 2
A judgment standard of the similarity of the pure varieties of dendrobium fimbriatum mainly comprises the following steps:
(1): collecting wild dendrobium fimbriatum samples consistent with a gene sequencing conclusion, wherein the sample capacity is 69, and measuring the total length of each sample, wherein the measurement result is as follows: the total length of the dendrobium fimbriatum is approximately 27.00 mm-94.00 mm, the average level is approximately 37.00 mm-58.32 mm, and the calculated result is that: average value: 58.32mm, median: 58.00mm, mode: standard deviation of total length fluctuation of 37.00mm is 20.12mm, average absolute deviation: 16.89mm, coefficient of variation: 0.35.
and from the above data, a histogram and box chart are made to visualize the data as shown in fig. 1 and 2. As can be seen from the box-shaped figures 1-2, the sample has no outliers.
(2) Standard interval for identifying purity of dendrobium fimbriatum sample to be measured
Drawing a curve of a real empirical distribution function according to the measured quantitative value of the total length of each plant in 69 samples and according to the empirical distribution function, as shown by a solid line in fig. 3; the curve of the empirical distribution function is a stepped curve with a jump. The smooth curve in the figure is a graph of the theoretical distribution function of the overall X.
The true probability density function curve was plotted from the measured quantitative value of the total length of each of the 69 samples and from the probability density function, as shown by the solid line in fig. 4.
And drawing a normal empirical distribution function curve of the dendrobium fimbriatum according to the data of the total length of the dendrobium fimbriatum and a formula of the normal empirical distribution function, as shown in figure 3.
And drawing a normal probability density function curve of the standard dendrobium fimbriatum according to the total length data of the dendrobium fimbriatum and a normal probability density function formula, as shown in fig. 4.
The ordinate of fig. 3 shows the cumulative probability of occurrence of the event { X +.x } in 69 repeated independent experiments, the ordinate shows the sum of probabilities of the sample event being less than or equal to a certain value, the probability distribution of the variable can be described under a uniform angle by the cumulative empirical distribution function, and for normal distribution, the cumulative probability distribution function has a fixed curve, and then whether the sample data accords with the normal distribution can be intuitively seen by comparing the difference between the cumulative empirical distribution function diagram drawn by the sample data and the normal cumulative empirical distribution function diagram. The ordinate of fig. 4 represents the density of probabilities, the greater the density, the greater the probability at that range. The abscissa of fig. 3 and 4 represents the range of values of random variables, that is, the range of numbers of total lengths of dendrobium fimbriae, the ordinate of fig. 3 represents the sum of probability accumulations of sample data less than or equal to a certain value, and the ordinate of fig. 4 represents the density of probabilities, and the greater the density is, the greater the probability is at the range.
From the plotted empirical distribution function diagram and probability density function diagram, it is intuitively observed whether the distribution of the total length sample data is subject to normalization. An empirical distribution function curve can be used to evaluate the fit of the distribution to the data, estimate the percentile and compare the different sample distributions. The distribution condition of the dendrobium fimbriatum total length data can be intuitively seen through the figure 3.
In particular, as can be seen from the empirical distribution function diagram of fig. 3, the true empirical distribution function curve is not quite identical to the normal empirical distribution function curve; as can be seen from the probability density function diagram of fig. 4, the shape of the true probability density curve is approximately the same as that of the normal probability density curve, and is a bell-shaped curve, but the kurtosis value of the true probability density curve is much smaller, and the thick tail feature is obvious. The visual pattern can only roughly judge that the sample data possibly accords with normal distribution, but the distribution characteristics of the sample data cannot be completely determined, so that the judgment is carried out through the following hypothesis test.
In actual life, since many data satisfy the characteristic of normal distribution, we can judge the comparison situation of the real distribution and normal distribution of the original data by the method, and for the data which obviously accords with the normal distribution, no hypothesis test can be adopted.
Next, it is determined by means of hypothesis testing whether the sample is indeed from a normal distribution population.
The Lilliefors test method is adopted for verification, and the original assumption is H0: the data obeys normal distribution; alternative hypothesis H1: the data does not follow a normal distribution.
The test statistics and P values were calculated from the data of the total length in the collected dendrobium fimbriatum samples, and the test results are shown in table 1.
TABLE 1 Lilliefors test results
Statistics | Critical value of | P value | Level of significance alpha | Whether or not to accept the original hypothesis |
0.1514 | 0.1730 | 0.1405 | 0.05 | Is that |
The threshold values in table 1 are not subjectively given, but are determined by the test method and sample size. The role of the P value is to determine if the original hypothesis should be rejected, and if the P value is less than the significance level (typically 0.05), we reject the original hypothesis, i.e., consider the data not to follow a normal distribution. As can be seen from the test results in table 1, the statistic has a value of 0.1514, which is less than the critical value 0.1730; p-value is equal to 0.1405, greater than the significance level (α=0.05); so the original assumption is accepted that the dendrobium fimbriatum total length sample data is considered to be subjected to normal distribution.
The calculation formula of the P value is as follows: when H1 is alternatively assumed to be μ+.mu. 0 In the time-course of which the first and second contact surfaces,when H1 is alternatively assumed to be mu > mu 0 When p=1 to Φ (Z 0 ) The method comprises the steps of carrying out a first treatment on the surface of the When H1 is assumed to be μ < μ 0 When p=Φ (Z 0 ). Wherein Φ (Z) 0 ) Is a normal distribution empirical function, is obtained by looking up a table, μ is a statistic calculated, μ 0 Is the hypothesized value of the statistic and,the P value may be calculated directly by software, such as Matlab software.
The confidence interval and the like of the total length data of the dendrobium fimbriatum to be detected, which are collected according to the embodiment, are calculated, and specific results are shown in table 2.
TABLE 2 calculation of mean, standard deviation and confidence interval for total Length of Dendrobium fringing
Mean value of | 95% confidence interval of mean | Standard deviation of | 95% confidence interval of standard deviation |
58.3200 | (50.0149,66.6251) | 20.1199 | (15.7102,27.9898) |
The 95% confidence interval of the mean and the 95% confidence interval of the standard deviation are respectively: (50.0149, 66.6251) and (15.7102, 27.9898), the interval is a standard interval for judging the similarity of the varieties of the dendrobium fimbriatum, namely the interval is a standard interval for identifying the purity of the varieties of the dendrobium fimbriatum.
Example 3
A method for judging similarity of pure varieties of dendrobium fimbriatum comprises the following steps:
A. collecting the total length data of the dendrobium fimbriatum sample to be detected, and eliminating abnormal values caused by measurement errors or recording errors in the sample;
B. calculating a 95% confidence interval of the average value and a 95% confidence interval of the standard deviation of the total length data of the dendrobium fimbriatum sample to be detected in the step A, and if the two confidence intervals are within the standard interval obtained in the embodiment 2, then the similarity of the pure varieties of the dendrobium fimbriatum sample to be detected is high, namely the purity of the dendrobium fimbriatum sample to be detected is high; if at least one of the 95% confidence interval of the average value and the 95% confidence interval of the total length data of the sample of the dendrobium fimbriatum to be detected is not within the standard interval obtained in the embodiment 2, the similarity of the pure varieties of the dendrobium fimbriatum to be detected is low, namely the purity of the dendrobium fimbriatum to be detected is low.
In a further preferred embodiment, in step a, the presence or absence of an outlier may be determined in an assisted manner by the histogram and the box-shaped chart described in example 1 or example 2.
Example 4
The inventor conducts research on association of morphological characteristics and variety purity of the dendrobium fimbriatum, and along with research, the dendrobium fimbriatum with low purity has great influence on certain morphological characteristics, and basically obtains through summary, comparison, research and the like of a large number of data and samples of wild dendrobium fimbriatum and artificially planted samples: the empirical distribution function curve, probability density function curve and the like of the total length of the dendrobium fimbriatum with high purity (namely, high similarity of pure varieties) are basically consistent with the deviation and the shape of the normal distribution function curve, the 95% confidence interval of the mean value and the 95% confidence interval of the standard deviation are both in the standard interval obtained in the embodiment 2, and at least one of the 95% confidence interval of the mean value and the 95% confidence interval of the standard deviation of the dendrobium fimbriatum sample to be tested with lower purity (namely, low similarity of pure varieties) is not in the standard interval obtained in the embodiment 2, and the standard interval is the 95% confidence interval (50.0149, 66.6251) of the mean value and the 95% confidence interval (15.7102, 27.9898) of the standard deviation.
In addition, in the past few years, the inventor performs numerous sample collection, calculation, comparison and the like in various places throughout the country, and performs gene sequence measurement for many times, and through big data comparison, the accuracy of the judging method in the invention is found to be above 90%, that is, if the 95% confidence interval of the mean value and the 95% confidence interval of the standard deviation of the dendrobium nobile sample to be tested are not within the standard interval, the similarity of the gene sequence of the measured flow Su Danhu and the true dendrobium nobile is below 95%, and the similarity of the gene sequence of the measured flow Su Danhu sample within the standard interval and the gene sequence of the true dendrobium nobile is basically above 95%.
Samples of the recorded measured stream Su Danhu were randomly drawn and calculated as in example 3 for the 95% confidence interval for the mean and the 95% confidence interval for the standard deviation, as shown in table 3 below.
TABLE 3 part of case schematic Condition Table (Total Length)
In the table, the place is the province where the tested sample is located, and the average 95% confidence interval and the standard deviation 95% confidence interval refer to the interval obtained by the tested flow Su Danhu sample, and whether the place is in the standard interval is whether the value of the tested flow Su Danhu sample is in the average 95% confidence interval obtained by the invention; the closeness is the percentage of the number of samples of the measured flow Su Danhu over the interval to the sample capacity ratio.
As for the samples, the actual measurement proves that the method has high accuracy and important application reference value.
In specific implementation, the formula needed to be used in the invention is as follows:
average value: the mean value is an arithmetic mean (mean) and the calculation method is thatWhere n is the sample size of the dendrobe.
Median: for a finite set of numbers, the median can be found by sorting all observations up and down and then finding the middle one, if there are an even number of observations, the average of the two values in the middle is usually taken as the median.
When N is odd, m 0.5 =X (N+1)/2 The method comprises the steps of carrying out a first treatment on the surface of the When N is an even number, the number,
mode: generally M 0 Meaning that the most populated one of a set of data.
Standard deviation: the standard deviation is a measure of the degree of dispersion of a set of data averages, a larger standard deviation representing a larger difference between most of the values and their averages; a smaller standard deviation represents values closer to average. The calculation formula is thatWhere μ is the average value. Since we are touching a large number of samples, the sample standard deviation is commonly calculated, which can be understood as an unbiased estimate of the given overall standard deviation, calculated as +.>Wherein->Is the sample mean.
Average absolute dispersion: usually denoted as MAD (Mean Absolute Deviation), the sum of the distances of each observation from the average is calculated and then averaged. The calculation formula is that
Coefficient of variation: when the degree of dispersion of the two sets of data needs to be compared, if the measurement scale of the two sets of data is too large or the data dimensions are different, the standard deviation is directly used for comparison inappropriately, the influence of the measurement scale and the dimensions should be eliminated at this time, and the variation coefficient (CV, coefficient of Variation) can achieve the effect, which is the ratio of the standard deviation of the original data to the average number of the original data. The coefficient of variation is calculated as
Confidence interval: the mean and standard deviation calculated above are both point estimates of the parameters, which are calculated from the samples to estimate the unknown parameters. But the point estimate is only an approximation of the unknown parameter, it does not reflect the error range of this approximation, which is usually given in intervals. It is desirable to determine an interval that is believed to contain true parameter values with a relatively high degree of reliability, commonly referred to as a confidence level, denoted 1- α, where α is a significant level, a small positive number, typically α= 0.025,0.05,0.1, etc.
when the mean μ is unknown, the statistic isThe confidence interval for standard deviation sigma is:
lilliefors test:
the hypothesis testing is a statistical inference method for determining whether a sample-to-sample, sample-to-population, is due to sampling errors or intrinsic differences. The basic principle is that some assumption is made on the characteristics of the population, and then through statistical reasoning of sampling study, an inference is made on whether the assumption should be rejected or accepted. The normal distribution test in the hypothesis test includes three types: JB test, KS test, liliferors test for checking whether the sample is from a normal distribution population.
The Liffiefors test is a modification of the KS test, which is to compare a sample with a standard normal distribution (mean of 0, variance of 1), while the Liffiefors test is aimed at a normal distribution that is not a standard normal, but has the same mean and variance as the sample. The method is suitable for normal distribution detection of small samples and unknown parameters, so that Liffiefors detection is most suitable for normal detection of dendrobium sample data.
The inspection principle and method are as follows:
(1) the test hypothesis: h0: the data obeys normal distribution; h1: the data does not follow a normal distribution. Significance level α=0.05.
(2) Test statistics:
T=sup|F * (x)-S(x)|
wherein T is Liffiefors test statistic, F * (x) Is a normal component with a mean value of 0 and a standard deviation of 1Cloth cumulative distribution function, S (x) isIs a function of the empirical distribution. The sample size and raw data values are needed to calculate S (x).
Judging principle: rejecting the original hypothesis H0 when the test statistic T exceeds the test critical value at the significance level of alpha; otherwise, the original hypothesis cannot be rejected.
In the specific implementation, the applicant obtains that the total length of the dendrobium fimbriatum is closely related to the purity of the dendrobium fimbriatum through years of gene sequencing conclusion and dendrobium fimbriatum morphological characteristic research, and the accuracy of judgment is more than 90% in a conservation way
The larger the standard deviation is, the higher the degree of dispersion of data is among the respective indexes calculated by the present invention. The standard deviation is not uniform, and can be compared with the data with the same mean value in the other group, and the smaller the standard deviation is, the smaller the discrete degree of the data is. However, for two groups of numbers with different mean values, it is not significant to compare the standard deviation sizes.
This can be measured by the coefficient of variation, which was calculated in the previous version and which is equal to 100% of the standard deviation/mean (CV, coefficient of Variation). The smaller the coefficient of variation, the smaller the degree of data dispersion, and if the coefficient of variation is greater than 15%, the greater the degree of data dispersion is considered.
The interval (20.8831, 23.8163) means: if we repeatedly sample, confidence intervals are constructed after each sampling, and 95% confidence is obtained that the constructed confidence intervals will contain true values of the sample mean.
If there is a new sample value that does not fall within this interval, then we have a 95% likelihood that this sample value is considered an outlier or abnormal.
The interval (5.2291,7.3361) means: if we repeatedly sample, confidence intervals are constructed after each sampling, and 95% confidence is obtained that the constructed confidence intervals will contain true values of the standard deviation of the samples.
In the present invention, the total length refers to the entire length of the stem.
Finally, it should be noted that: the embodiments described above are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced with equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (7)
1. The method for establishing the method for judging the similarity of the pure varieties of the dendrobium fimbriatum is characterized by comprising the following steps of: the establishing method comprises the following steps:
s1: standard data acquisition: collecting dendrobium fimbriatum samples consistent with a gene sequencing conclusion, and measuring the total length of each sample to obtain a measurement value of a total length variable;
s2: and (3) normal performance test: carrying out normal test on the total length variable of the sample;
s3: standard interval: if the result obtained in the step S2 is subjected to normal distribution, a 95% confidence interval of the mean value and a 95% confidence interval of the standard deviation are obtained according to a normal distribution overall calculation formula;
if the result of the normal test of the total length variable of the dendrobium fimbriatum in the step S2 is that the dendrobium fimbriatum does not follow normal distribution, if the sample capacity exceeds 30, the sample calculates a 95% confidence interval of the mean value and a 95% confidence interval of the standard deviation according to a normal overall formula;
the 95% confidence interval of the obtained mean value and the 95% confidence interval of the standard deviation are used as standard ranges for identifying the purity degree of the unknown sample,
the normalization test includes visual image analysis and hypothesis testing,
the visual image analysis method comprises the following steps:
(1) drawing a normal distribution empirical distribution function curve sum
A probability density curve; (2) according to the measured value of the total length variable obtained in the step S1, drawing a true empirical distribution function and a true empirical distribution function of the dendrobium fimbriatum
A true probability density function graph;
(3) comparing the real experience distribution function graph with the experience distribution function curve of normal distribution, and preliminarily judging whether the sample data accords with the normal distribution by judging the degree of curve deviation; comparing the true probability density function graph with a probability density curve of normal distribution, and judging whether the sample data obeys the normal distribution according to the deviation degree and the consistency degree of the curve shape;
if the deviation of the true empirical distribution function diagram and the normal distribution empirical distribution function diagram or the true empirical probability density function diagram and the normal distribution probability density function diagram is small and the shapes are consistent, the total length of the dendrobium fimbriatum samples accords with the normal distribution, if the deviation is obviously large and the shapes are obviously inconsistent, the total length of the dendrobium fimbriatum samples to be detected does not accord with the normal distribution,
the hypothesis test includes any one of a JB test, a KS test and a Lilliefors test.
2. The method for establishing the method for judging the similarity of the pure varieties of dendrobium fimbriatum according to claim 1, wherein the method is characterized in that: step S1, after obtaining the measured value of the total length variable, calculating the basic statistic of the total length variable according to the measured value of the total length variable, wherein the basic statistic comprises an average level and a discrete degree, determining whether the data has an abnormal value according to the basic statistic, checking if the data has the abnormal value, deleting the abnormal point if the data belongs to a measurement error or a recording error, and retaining the data if the data does not belong to the error.
3. The method for establishing the method for judging the similarity of the pure varieties of dendrobium fimbriatum according to claim 2, wherein the method is characterized in that: the average level includes at least one of a mean, median, and mode, and the degree of dispersion includes a standard deviation, an average absolute deviation, and a coefficient of variation.
4. The method for establishing the method for judging the similarity of the pure varieties of dendrobium fimbriatum according to claim 1, wherein the method is characterized in that: the normalization test includes at least one of visual image analysis and hypothesis testing.
5. The method for establishing the method for judging the similarity of the pure varieties of dendrobium fimbriatum according to claim 1, which is characterized in that: the 95% confidence interval of the obtained mean value and the 95% confidence interval of the standard deviation are used as standard ranges for identifying the purity similarity of unknown samples, wherein the standard ranges are as follows: (50.0149, 66.6251) and (15.7102, 27.9898).
6. A method for judging similarity of pure varieties of dendrobium fimbriatum is characterized by comprising the following steps of: the method comprises the following steps:
A. collecting the total length data of the dendrobium fimbriatum sample to be detected, and eliminating abnormal values caused by measurement errors or recording errors in the sample;
B. calculating a 95% confidence interval of the average value and a 95% confidence interval of the standard deviation of the total length data of the dendrobium fimbriatum sample to be detected in the step A, and if the two confidence intervals are in the standard interval, the similarity of the pure varieties of the dendrobium fimbriatum sample to be detected is high, namely the purity of the dendrobium fimbriatum sample to be detected is high; if at least one of the average 95% confidence interval and the standard deviation 95% confidence interval of the total length data of the sample of the dendrobium fimbriatum to be detected is not in the standard interval, the similarity of the pure varieties of the dendrobium fimbriatum to be detected is low, namely the purity of the dendrobium fimbriatum to be detected is low; the standard interval is a standard range obtained by the establishment method of claim 1.
7. The method of claim 6, wherein the standard interval is a 95% confidence interval of the mean and a 95% confidence interval of the standard deviation, namely (50.0149, 66.6251) and (15.7102, 27.9898).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710887053.3A CN110010202B (en) | 2017-09-22 | 2017-09-22 | Establishment and judgment standard and judgment method for judging similarity of pure varieties of dendrobium fimbriatum |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710887053.3A CN110010202B (en) | 2017-09-22 | 2017-09-22 | Establishment and judgment standard and judgment method for judging similarity of pure varieties of dendrobium fimbriatum |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110010202A CN110010202A (en) | 2019-07-12 |
CN110010202B true CN110010202B (en) | 2023-04-21 |
Family
ID=67164014
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710887053.3A Active CN110010202B (en) | 2017-09-22 | 2017-09-22 | Establishment and judgment standard and judgment method for judging similarity of pure varieties of dendrobium fimbriatum |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110010202B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111121946B (en) * | 2019-12-18 | 2021-09-28 | 东南大学 | Method for accurately determining abnormal value at multiple points in large dynamic range and large discrete single area |
CN112649324B (en) * | 2020-12-30 | 2023-03-24 | 上海电缆研究所有限公司 | Analysis method for evaluating consistency of non-metallic material for nuclear power station cable |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104765945A (en) * | 2015-02-09 | 2015-07-08 | 广东电网有限责任公司电力科学研究院 | Device failure rate detecting method based on quantity confidence coefficient |
CN105069296A (en) * | 2015-08-10 | 2015-11-18 | 国网浙江省电力公司电力科学研究院 | Determination method and system of equipment threshold value |
CN106599271A (en) * | 2016-12-22 | 2017-04-26 | 江苏方天电力技术有限公司 | Emission monitoring time series data abnormal value detection method for coal-fired unit |
CN106615417A (en) * | 2016-10-20 | 2017-05-10 | 广东省农业科学院环境园艺研究所 | Preparation method of dendrobium officinale leaf tea |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140156718A1 (en) * | 2012-11-30 | 2014-06-05 | Ligong Chen | Definition of Two Self-weights for Continuous Random Variable and Their Applications in Basic Statistics |
-
2017
- 2017-09-22 CN CN201710887053.3A patent/CN110010202B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104765945A (en) * | 2015-02-09 | 2015-07-08 | 广东电网有限责任公司电力科学研究院 | Device failure rate detecting method based on quantity confidence coefficient |
CN105069296A (en) * | 2015-08-10 | 2015-11-18 | 国网浙江省电力公司电力科学研究院 | Determination method and system of equipment threshold value |
CN106615417A (en) * | 2016-10-20 | 2017-05-10 | 广东省农业科学院环境园艺研究所 | Preparation method of dendrobium officinale leaf tea |
CN106599271A (en) * | 2016-12-22 | 2017-04-26 | 江苏方天电力技术有限公司 | Emission monitoring time series data abnormal value detection method for coal-fired unit |
Non-Patent Citations (3)
Title |
---|
Protective effect of Dendrobium officinale polysaccharides on experimental Sjogren"s syndrome;Xiang Lin等;《ournal of Complementary and Integrative Medicine》;20101231;第1卷(第7期);第1-20页 * |
井下导线观测中仪器高量测数据的统计检验;潘进波等;《矿山测量》;20121031(第5期);第30-34页 * |
郭鹏等.区间估计.《数据、模型与决策》.西北工业大学出版社,2016,第59-62页. * |
Also Published As
Publication number | Publication date |
---|---|
CN110010202A (en) | 2019-07-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108875308B (en) | Method for judging and detecting pure phase proximity of dendrobium nobile lindl | |
CN114627125B (en) | Stainless steel tablet press surface quality evaluation method based on optical means | |
CN113838054B (en) | Mechanical part surface damage detection method based on artificial intelligence | |
CN112435756B (en) | Intestinal flora associated disease risk prediction system based on multi-dataset difference interaction | |
CN112365927B (en) | CNV detection device | |
CN110010202B (en) | Establishment and judgment standard and judgment method for judging similarity of pure varieties of dendrobium fimbriatum | |
CN114841986A (en) | Herbal pieces-quality monitoring analytic system based on machine vision | |
CN106228190A (en) | Decision tree method of discrimination for resident's exception water | |
CN117906726B (en) | Abnormal detection system for weight data of live cattle body ruler | |
CN114595956B (en) | Eucalyptus soil fertility analysis method based on gray scale correlation method fuzzy clustering algorithm | |
CN117289778B (en) | Real-time monitoring method for health state of industrial control host power supply | |
CN112949735A (en) | Liquid hazardous chemical substance volatile concentration abnormity discovery method based on outlier data mining | |
CN113128567A (en) | Abnormal electricity consumption behavior identification method based on electricity consumption data | |
CN116564409A (en) | Machine learning-based identification method for sequencing data of transcriptome of metastatic breast cancer | |
CN108874732B (en) | Method for judging and detecting pure phase similarity of dendrobium aphyllum | |
CN113140325A (en) | Method for establishing prediction model of incidence probability of Marneffei pannieri disease of HIV patient | |
CN108875313B (en) | Method for judging and detecting pure phase proximity of dendrobium officinale | |
CN114944208B (en) | Quality control method, quality control device, electronic equipment and storage medium | |
CN108874746B (en) | Method for judging and detecting pure phase similarity of dendrobium chrysotoxum | |
CN114693646B (en) | Corneal endothelial cell active factor analysis method based on deep learning | |
CN108875101B (en) | Method for judging and detecting pure phase proximity of dendrobium devonianum | |
Bhar | Non-parametric tests | |
CN112071434A (en) | Novel abnormal body temperature sequence detection method | |
CN110473382A (en) | A kind of fall detection algorithm | |
Bhargavi et al. | A COMPARATIVE STUDY FOR STATISTICAL OUTLIER DETECTION USING COLON CANCER DATA |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |