CN109345101A - Evaluation in Education Quality analysis method based on comprehensive evaluation analysis method - Google Patents
Evaluation in Education Quality analysis method based on comprehensive evaluation analysis method Download PDFInfo
- Publication number
- CN109345101A CN109345101A CN201811107836.6A CN201811107836A CN109345101A CN 109345101 A CN109345101 A CN 109345101A CN 201811107836 A CN201811107836 A CN 201811107836A CN 109345101 A CN109345101 A CN 109345101A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- index
- comprehensive
- analysis method
- education
- 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.)
- Withdrawn
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 80
- 238000004458 analytical method Methods 0.000 title claims abstract description 53
- 238000010206 sensitivity analysis Methods 0.000 claims abstract description 12
- 238000000513 principal component analysis Methods 0.000 claims abstract description 7
- 238000010586 diagram Methods 0.000 claims abstract 2
- 238000003672 processing method Methods 0.000 claims abstract 2
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000013210 evaluation model Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 10
- 238000011002 quantification Methods 0.000 claims description 8
- 230000035945 sensitivity Effects 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 8
- 238000011161 development Methods 0.000 claims description 5
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000013441 quality evaluation Methods 0.000 abstract description 13
- 238000001308 synthesis method Methods 0.000 abstract 1
- 238000000034 method Methods 0.000 description 29
- 238000011160 research Methods 0.000 description 17
- 230000008859 change Effects 0.000 description 6
- 230000006872 improvement Effects 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 241001269238 Data Species 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007620 mathematical function Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 208000029091 Refraction disease Diseases 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000004430 ametropia Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000010921 in-depth analysis Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000000275 quality assurance Methods 0.000 description 1
- 208000014733 refractive error Diseases 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000004577 thatch Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Educational Administration (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Educational Technology (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of Evaluation in Education Quality analysis method based on comprehensive evaluation analysis method, step includes: to model to propose reasonable assumption and symbol description to problem;Abstract index relevant to Evaluation in Education Quality is embodied as multiple data targets, obtains standardized data with nondimensionalization processing method;Determine Evaluation in Education Quality analysis flow chart diagram;The comprehensive score of indicator layer is obtained with principal component analysis;The weight of each index is determined according to Information Entropy;The comprehensive score of multiple prefecture-level cities is calculated by comprehensive analysis, and the quality of education carries out overall merit accordingly;Significance analysis is done to overall merit;The critical index for having larger impact to comprehensive score is finally determined with sensitivity analysis.The present invention efficiently uses comprehensive evaluation analysis ability of the analysis by synthesis method when handling many factors, it is applied to education of undergraduate course Quality Evaluation Analysis problem, and judgement and key index determination is carried out to evaluation index influence power based on significance analysis and sensitivity analysis.
Description
Technical field
It is specifically a kind of based on comprehensive evaluation analysis method the invention belongs to the evaluation analysis method to the quality of education
Evaluation in Education Quality analysis method.
Background technique
From after Enrollment in Higher Education in 1999, China has entered the stage of the popularization of higher education.But in face of taking
Achievement while, more could envisage that the sternnesses such as graduate's quality, ability appeared in Higher Education Quality be irregular are asked
Topic.And due to increasingly fierce Global Competition for Professional Talents, we must not ametropia society new wanted to what Higher Education Quality proposed
It asks.The good quality of education is the lifeblood that institution of higher education is able to sustainable development, and the key for doing Evaluation in Education Quality well is really
Fixed scientific and reasonable assessment indicator system, therefore education of undergraduate course quality evaluating method becomes the hot spot of Research in higher education.
Numerous scholars study university teaching quality appraisal problem.It thanks to intelligent pine et al. and uses questionnaire method, reality
It tests the research methods such as method and constructs sports institutes undergraduate course monitoring system by taking Beijing Sport University as an example, in monitoring system
Thimble section teaching evaluation conducts in-depth analysis, and establishes sports institutes Surveillance System in Teaching Quality, has revised sports institutes class
Hall teaching evaluation mode and the specific targets of teaching evaluation provide reference frame to sports institutes teaching quality evaluation is improved.
Cai's spectrum et al. is illustrated by the Analysis and summary to school's undergraduate course construction of quality system and is established by managerial decision, held
Row ensures, evaluation monitors and the Teaching Quality Assurance System of four part of feedback improvements composition, and quality of instruction is pushed persistently to be promoted.Liu
Small ocean is started with from the status of current Undergraduate in Higher Education quality of instruction, is analyzed the not high profound cause of quality of instruction, is proposed
The evaluation of the quality of instruction of its College Teachers is realized with Bayes's classification technology.Wang Xing space et al. is to NSSE (NationalSu
RveyolStudentEngagement, the investigation of the whole America College Students'Learning investment) education of undergraduate course quality evaluating method ground
Study carefully, NSSE is enriched according to school work challenge degree, active cooperation learning level, raw teacher's interaction, campus environment support, pedagogical experience
The big core index of degree etc. five collects the learning information of student, pays close attention to the learning experience of student, has not only sufficiently practiced and " learned with student
Centered on habit " theory, strong supplement is also provided for existing evaluation system.The long prosperous system of Lee considers to influence quality of instruction
Each working link, and be guidance with Modern education evaluation theory, rationally design evaluation of programme, with systematicness, scientific, complete
Face property be basic principle, building total involvement, whole process supervision, scientific evaluation education of undergraduate course quality evaluation system.Wu Yaying
Based on catastrophe progression method, the mathematical model and evaluation method catastrophe progression method for establishing undergraduate course quality evaluation carry out target
Rank decomposition, the combination realizing qualitative analysis and quantitatively calculating are passed, evaluation result has higher confidence level.Wu's peaceful cloud tints et al. is utilized and is determined
24 classes support data are excavated and are analyzed in the undergraduate course quality reports in 2013 that plan model issues Jiangsu College, no
The objectivity for supporting data in undergraduate course quality report is only embodied, and has respected expert to support data Importance of Attributes
The degree of awareness.
Summary of the invention
In place of the present invention is in order to overcome the shortcomings of the prior art, the aggregation of data of comprehensive evaluation analysis method is made full use of
Analysis and processing capacity, propose a kind of education of undergraduate course Quality Evaluation Analysis model based on comprehensive evaluation analysis method, it is therefore intended that
The various data for efficiently using education of undergraduate course quality evaluation index, establish evaluation model based on the correlativity between data, simultaneously
Each index is determined to the contribution of overall merit, the invention calculating process simplicity result is clear, convenient for education of undergraduate course matter
The horizontal judgement for carrying out accurate science of amount, and to how fast lifting education of undergraduate course quality level makees effectively guidance.
In order to achieve the above-mentioned object of the invention, the present invention adopts the following technical scheme:
The present invention is based on the Livable City evaluation model of principal component analysis, feature carries out as follows:
Step 1: basic assumption and symbol description
Step 1.1 evaluation model basic assumption
In order to effectively accurately evaluate education of undergraduate course quality, some rationalization basic assumptions are made.
1) assume from " institution of higher education's research funding system data compilation " and major colleges and universities " 2016-2017 academic year undergraduate course matter
Amount report " in collect data it is authentic and valid;
2) assume the index chosen of the present invention compared with can reflect education of undergraduate course quality comprehensively;
3) assume that data are comparable, be independent of each other between each colleges and universities' data.
Step 1.2 model mathematics symbol description
Step 2 data processing
Step 2.1 multiple variable synthetical evaluation method handles data
Index of correlation data are handled using multiple variable synthetical evaluation method, multiple variable synthetical evaluation method refers to fortune
The method that objective, fair and rational thoroughly evaluating is carried out to multiple universities and colleges that participate in evaluation and electing with multiple indexs.Technically, multi objective
Overall merit is the comprehensive evaluation value by certain mathematical function by multiple evaluation index values " synthesis " for a globality.It is comprehensive
The basic thought for closing evaluation assessment is to convert multiple indexs to one to be able to reflect the overall performane of comprehensive condition to evaluate.Its
Feature is that evaluation procedure is the evaluation of multiple indexs to be completed at the same time by some specific process, rather than index is sequentially complete one by one
At;In evaluation procedure, generally processing is weighted according to the importance of index;Most of all, the result of overall merit is not
It is the statistical indicator of concrete meaning again, but the sequence of " integrated status " of unit attending to judge is presented with index or score value.
Step 2.2 determines the influence factor of index
Step 2.3 gather data
Data source: " institution of higher education's research funding system data compilation " and major colleges and universities " 2016-2017 academic year undergraduate course matter
Amount report ".The abstract teaching with an assigned goal conditions of some of them and utilize, by the equal occupied area of life, teaching instrument and equipment total value increase volume,
A series of specific achievement datas such as raw total volumes and raw equal daily teaching funds expenditure carry out quantification treatment, as teaching item
Part and the calculation basis for utilizing index.
Step 2.4 data normalization
In order to eliminate on the data difference dimension come and the influence of order of magnitude difference bring is collected, data need to be marked
Quasi-ization processing.
(1) standard 0-1 is converted.If original decision matrix is A=(aij)m×n, decision matrix is denoted as B=after transformation
(bij)m×n。It is the maximum value in decision matrix jth column,It is the minimum value in decision matrix jth column.It is every in order to make
Optimal value after a attribute transformation is 1 and worst-case value is 0.To profit evaluation model attribute xj, enable
To cost type attribute xj, enable
(2) transformation of interval type attribute.Some attributes neither profit evaluation model again non-cost type, such as give birth to teacher's ratio index.Obviously
It cannot be handled using above two method, formula (3) can be used and carry out data processing.
If given optimum attributes section isa′jTo can not put up with lower limit, a "jTo can not put up with the upper limit, then
The standardization of data is carried out using MATLAB algorithm.
Step 2.5 quantification treatment mode and calculation basis
Step 3 determines education of undergraduate course Quality Evaluation Analysis flow chart
The comprehensive score of step 4 indicator layer
The weight that indicator layer items factor is calculated by principal component analysis, the score of each index is calculated according to weight.Add
The comprehensive score of the available rule layer indices of weight average.
The step of principal component analysis, is as follows:
(1) initial data is standardized, is claimed
For standardized index variable.
(2) correlation matrix R=(r is calculatedij)m×n, have
(3) characteristic value and feature vector are calculated.Calculate the eigenvalue λ of correlation matrix R1≥λ2≥…≥λm>=0, and
Corresponding feature vector u1, u2..., um, wherein uj=[u1j, u2j..., umj]T, m New Set variable is formed by feature vector:
(4) p principal component is selected, comprehensive evaluation value is calculated.
1. calculating the information contribution rate and contribution rate of accumulative total of characteristic value.Claim
For principal component yiInformation contribution rate.
2. calculating comprehensive score
The comprehensive score of step 5 rule layer
Here the weight of each index is determined by Information Entropy.Information Entropy is a kind of objectively to determine each index weights
Method.Information Entropy mainly uses for reference the theory and method of comentropy, determines it according to the index value data difference degree of each index
Weight.Generally, the difference degree of the index value of certain index is bigger, then its order is better, and entropy is smaller, the power finally assigned
It is again bigger.The step of determining index weights with Information Entropy include:
The first step calculates and is evaluated j-th of index value of object i-th and is evaluated j-th of index value summation of object all
In ratio.The calculating of the ratio is typically based on the index value after nondimensionalization, and calculation formula is
Second step calculates the entropy of j-th of index
The step has used for reference the theory and method of comentropy.In information entropy theory, PiIndicate a certain value in probability space
The probability of appearance, and comentropy is calculated based on above-mentioned formula, if the probability that each sample point occurs is average, the degree of disorder
Bigger, entropy is also bigger.Information Entropy uses for reference this theory and method, as ratio PijDifference gets over hour, and the entropy being calculated is got over
Greatly, show that its information content is fewer.It is set in calculating, works as PijWhen=0, ln (Pij)=0.From the point of view of calculated result, ej∈ [0,1] and
And work as PijWhen essentially equal, ej=1.
Third step calculates the weight of each index
wjMeet 0≤ωj≤1、It is the weight for each index that Information Entropy determines.
By Information Entropy calculate each index weight be weighted score it can be concluded that each school comprehensive score, meter
It calculates shown in formula such as formula (10):
Step 6 universities and colleges classify by prefecture-level city and calculating comprehensive score.
Determine the weight of each index of an each prefecture-level city in province and each universities and colleges after standardization
Data carry out weight distribution by nondimensionalization to 9 indexs of colleges and universities of multiple institutes, calculate the comprehensive score of colleges and universities of each institute,
Classify again by prefecture-level city, the ratio-dependent weight of the province universities and colleges of undergraduate course quantity accounted for 985,211, Camelliae oleifera quantity,
The corresponding comprehensive score of education of undergraduate course quality of each prefecture-level city can be calculated.
Step 7 index significance analysis
Establish evaluation criterion of the size of the relative distance value of prefecture-level city's comprehensive score as the index sensitivity.It calculates public
Formula are as follows:
Wherein, DiAfter removing for i-th of index, the opposite variation distance of the city integrated score recalculated.Q1jIt is jth
The comprehensive score value in a city, QijIt is the comprehensive score value in j-th of city after removing some index.
According to the size of distance sum, it may be said that the bright fluctuation size removed after a certain index.Distance and smaller, that is, illustrate
The fluctuation of the index is smaller, and the influence removed after this index to comprehensive score is smaller.
Step 8 model sensitivity analysis
It establishes sensitivity analysis model the education of undergraduate course of city-level cities of Jiangsu Province is developed to analyze specifically which index
Difference.Calculate the formula of susceptibility are as follows:
Wherein, Δ xiFor the amplitude of i-th of variable x variation;ΔyiWidth is changed due to caused by variable x for i-th of index y
Degree.
Its calculation method are as follows: according to+20% ,+40% and+60% variation range, change an index, do not change other
Index, the score after calculating index variation, and compared with former score, calculate the susceptibility of the variable;Then reselection is another
A index, repeats aforesaid operations, the comprehensive score after calculating all possible index variations influenced.According to calculated
For sensitivity value it is found that being worth maximum variable is most sensitive factor, the smallest is least sensitive factor.
Compared with the prior art, the beneficial effects of the present invention are embodied in:
1. abstract index relevant to Evaluation in Education Quality is embodied and dimensionless turns to as standardized data, with master
Constituent analysis obtains the comprehensive score of indicator layer, while the weight of each index is determined according to Information Entropy, thus based on comprehensive point
Analysis calculates the comprehensive score and ranking of each prefecture-level city, is scientific and accurate and effective.
2. doing significance analysis to overall merit with distance between score and formula, analyzing influences overall merit score
Minimum index.The critical index for having larger impact to comprehensive score is determined using sensitivity analysis, most can so as to pick out
The index of education of undergraduate course quality evaluation ranking is significantly affected, education of undergraduate course quality level is promoted for educational management worker and specifies
Make great efforts and improved direction and approach.
Detailed description of the invention
Fig. 1 is 13, Jiangsu Province prefecture-level city's education of undergraduate course quality overall evaluation flow chart.
Fig. 2 is the comprehensive score of 13 prefecture-level cities.
Specific embodiment
In order to verify the validity of the education of undergraduate course Quality Evaluation Analysis model based on comprehensive evaluation analysis method proposed,
It is applied to the education of undergraduate course quality overall evaluation in 13, Jiangsu Province city.
Jiangsu Province is in the Changjiang river triangle economy-zone of Deposits in Eastern Coastal China, always with economically developed, flourishing culture, and teaching money
Source is numerous, and various levels of colleges and universities stand in great numbers.As the big province of an education, the education of undergraduate course in Jiangsu Province develops before the whole nation is ranked
Thatch, and the education of undergraduate course Quality Developing of prefecture-level city of 13, Jiangsu Province and imbalance.The Jiangsu College quality of education is assessed
Research, is conducive to the more healthy steady development of Jiangsu Province's education of undergraduate course.
Case-study step are as follows:
Step 1. basic assumption and symbol description
Step 1.1 evaluation model basic assumption
In order to effectively accurately evaluate education of undergraduate course quality, some rationalization basic assumptions are made.
1) assuming that the present invention needs the education of undergraduate course mass range analyzed is 49, Jiangsu Province Regular Colleges;
2) assume from " institution of higher education's research funding system data compilation " and major colleges and universities " 2016-2017 academic year undergraduate course matter
Amount report " in collect data it is authentic and valid;
3) assume the index chosen of the present invention compared with can reflect education of undergraduate course quality comprehensively;
4) assume that data are comparable, be independent of each other between each colleges and universities' data.
Step 1.2 model mathematics symbol description
Some symbol descriptions needed for assessment models are established are provided, as shown in table 1
1 undergraduate course Environmental Evaluation Model correlation mathematics symbol description of table
Step 2. data processing
Step 2.1 multiple variable synthetical evaluation method handles data
Index of correlation data are handled using multiple variable synthetical evaluation method, multiple variable synthetical evaluation method refers to fortune
The method that objective, fair and rational thoroughly evaluating is carried out to multiple universities and colleges that participate in evaluation and electing with multiple indexs.Technically, multi objective
Overall merit is the comprehensive evaluation value by certain mathematical function by multiple evaluation index values " synthesis " for a globality.It is comprehensive
The basic thought for closing evaluation assessment is to convert multiple indexs to one to be able to reflect the overall performane of comprehensive condition to evaluate.Its
Feature is that evaluation procedure is the evaluation of multiple indexs to be completed at the same time by some specific process, rather than index is sequentially complete one by one
At;In evaluation procedure, generally processing is weighted according to the importance of index;Most of all, the result of overall merit is not
It is the statistical indicator of concrete meaning again, but the sequence of " integrated status " of unit attending to judge is presented with index or score value.
Step 2.2 determines the influence factor of index
Jiangsu Province's education of undergraduate course quality evaluation influence index is as shown in table 2.
2 Jiangsu Province's education of undergraduate course quality evaluation index of table
Step 2.3 gather data
Data source: " institution of higher education's research funding system data compilation " and major colleges and universities " 2016-2017 academic year undergraduate course matter
Amount report ".The abstract teaching with an assigned goal conditions of some of them and utilize, by the equal occupied area of life, teaching instrument and equipment total value increase volume,
A series of specific achievement datas such as raw total volumes and raw equal daily teaching funds expenditure carry out quantification treatment, as teaching item
Part and the calculation basis for utilizing index.
Step 2.4 data normalization
In order to eliminate on the data difference dimension come and the influence of order of magnitude difference bring is collected, data need to be marked
Quasi-ization processing.
(1) standard 0-1 is converted.If original decision matrix is A=(aij)m×n, decision matrix is denoted as B=after transformation
(bij)m×n。It is the maximum value in decision matrix jth column,It is the minimum value in decision matrix jth column.It is every in order to make
Optimal value after a attribute transformation is 1 and worst-case value is 0.To profit evaluation model attribute xj, enable
To cost type attribute xj, enable
(2) transformation of interval type attribute.Some attributes neither profit evaluation model again non-cost type, such as give birth to teacher's ratio index.Obviously
It cannot be handled using above two method, formula (3) can be used and carry out data processing.
If given optimum attributes section isa′jTo can not put up with lower limit, a "jTo can not put up with the upper limit, then
The standardization of data is carried out using MATLAB algorithm in the present invention.
Step 2.5 quantification treatment mode and calculation basis
Quantification treatment mode and calculation basis are as shown in table 3
3 quantification treatment mode of table
Step 3 Jiangsu Province education of undergraduate course Quality Evaluation Analysis evaluation rubric figure (as shown in Figure 1)
The comprehensive score of step 4 indicator layer
The weight that indicator layer items factor is calculated by principal component analysis, the score of each index is calculated according to weight.Add
The comprehensive score of the available rule layer indices of weight average.
The step of principal component analysis, is as follows:
(1) initial data is standardized, is claimed
For standardized index variable.
(2) correlation matrix R=(r is calculatedij)m×n, have
(3) characteristic value and feature vector are calculated.Calculate the eigenvalue λ of correlation matrix R1≥λ2≥…≥λm>=0, and
Corresponding feature vector u1, u2..., um, wherein uj=[u1j, u2j..., umj]T, m New Set variable is formed by feature vector:
(4) p principal component is selected, comprehensive evaluation value is calculated.
1. calculating the information contribution rate and contribution rate of accumulative total of characteristic value.Claim
For principal component yiInformation contribution rate.
2. calculating comprehensive score
The comprehensive score of step 5 rule layer
Here the weight of each index is determined by Information Entropy.Information Entropy is a kind of objectively to determine each index weights
Method.Information Entropy mainly uses for reference the theory and method of comentropy, determines it according to the index value data difference degree of each index
Weight.Generally, the difference degree of the index value of certain index is bigger, then its order is better, and entropy is smaller, the power finally assigned
It is again bigger.The step of determining index weights with Information Entropy include:
The first step calculates and is evaluated j-th of index value of object i-th and is evaluated j-th of index value summation of object all
In ratio.The calculating of the ratio is typically based on the index value after nondimensionalization, and calculation formula is
Second step calculates the entropy of j-th of index
The step has used for reference the theory and method of comentropy.In information entropy theory, PiIndicate a certain value in probability space
The probability of appearance, and comentropy is calculated based on above-mentioned formula, if the probability that each sample point occurs is average, the degree of disorder
Bigger, entropy is also bigger.Information Entropy uses for reference this theory and method, as ratio PijDifference gets over hour, and the entropy being calculated is got over
Greatly, show that its information content is fewer.It is set in calculating, works as PijWhen=0, ln (Pij)=0.From the point of view of calculated result, ej∈ [0,1] and
And work as PijWhen essentially equal, ej=1.
Third step calculates the weight of each index
wjMeet 0≤wj≤1、It is the weight for each index that Information Entropy determines.Calculated result is shown in Table 4.
The weight of each index of table 4
By Information Entropy calculate each index weight be weighted score it can be concluded that each school comprehensive score, meter
It calculates shown in formula such as formula (10):
Step 6 universities and colleges classify by prefecture-level city and calculating comprehensive score
Step 6.1 universities and colleges classify by prefecture-level city
The quantity of each city universities and colleges of undergraduate course of table 5
The data of each universities and colleges in conjunction with the weight of each index in table 4 and after standardization are high to 49 institutes
9 indexs in school carry out weight distribution by nondimensionalization, calculate the comprehensive score of colleges and universities of each institute, then divided by prefecture-level city
Class is accounted for the ratio-dependent weight of universities and colleges of undergraduate course of Jiangsu Province quantity with 985,211, Camelliae oleifera quantity, can calculate each ground level
The corresponding comprehensive score of education of undergraduate course quality in city.
Step 6.2 calculates the comprehensive score of each prefecture-level city
The comprehensive score of 613 prefecture-level cities of table
Step 7 index significance analysis
Establish evaluation criterion of the size of the relative distance value of prefecture-level city's comprehensive score as the index sensitivity.It calculates public
Formula are as follows:
Wherein, DiAfter removing for i-th of index, the opposite variation distance of the city integrated score recalculated.Q1jIt is jth
The comprehensive score value in a city, QijIt is the comprehensive score value in j-th of city after removing some index.Prefecture-level city of 13, Jiangsu Province is comprehensive
The opposite variation distance (such as table 7) for closing score can be calculated with such as formula (11).
According to the size of distance sum, it may be said that the bright fluctuation size removed after a certain index.Distance and smaller, that is, illustrate
The fluctuation of the index is smaller, and the influence removed after this index to comprehensive score is smaller.
Table 7 removes the distance and sequence after a certain index
According to table 7 it is found that the comprehensive score relative distance and more big then index of 13 prefecture-level cities are sensitiveer.Sensitivity is most
Low is " raw teacher's ratio ", and from first ask in it is also seen that the weight of the index is minimum, meet that sensitivity is bigger, and weight is just
Bigger rule.It can be seen that raw teacher's ratio and Specialized Construction and these indexs of the reform in education to undergraduate course from the weighted data in table 7
The influence of the quality of education is smaller.
Step 8 model sensitivity analysis
It establishes sensitivity analysis model the education of undergraduate course of city-level cities of Jiangsu Province is developed to analyze specifically which index
Difference.Calculate the formula of susceptibility are as follows:
Wherein, Δ xiFor the amplitude of i-th of variable x variation;ΔyiWidth is changed due to caused by variable x for i-th of index y
Degree.
Its calculation method are as follows: according to+20% ,+40% and+60% variation range, change an index, do not change other
Index, the score after calculating index variation, and compared with former score, calculate the susceptibility of the variable;Then reselection is another
A index, repeats aforesaid operations, the comprehensive score after calculating all possible index variations influenced.According to calculated
For sensitivity value it is found that being worth maximum variable is most sensitive factor, the smallest is least sensitive factor.It is calculated such as table 8
Shown in result.
8 sensitivity analysis table of table
It is least sensitive index that sensitivity value, which can be seen that raw teacher than, enrollment etc., from table 8, science research input with
Output etc. is most sensitive index.I.e. city-level cities increase the science research input to colleges and universities, reinforce ranks of teachers and structure can be effective
Improve undergraduate course quality, reduces the difference of education of undergraduate course development between prefecture-level city.
Below with index science research input and output, by taking the prefecture-level city of ranking slightly rearward as an example, using Nantong City as reference
Standard, this refers to target value for modification Taizhou City, Xiuqian City etc., after verifying its change, if can effectively reduce undergraduate course between prefecture-level city
Educational development.Guarantee that other indexs are constant, by the initial data of science research input and output increase separately 20%, 40%, 60% with
80%, comprehensive score is calculated, the results are shown in Table 9.
Table 9 modifies the urban score rank calculated result after science research input and output index
As can be seen from Table 9, after science research input and this index of output increase by 60%, Changzhou is more than Huai'an from the
Four rise to third, and Lianyungang is ranked the first more than Nantong City.It can illustrate that established sensitivity analysis model has
Effect, when the increasing of ground level municipal government can reduce the education of undergraduate course developmental difference of prefecture-level city to science research input of colleges and universities etc. as far as possible.
Jiangsu Province's education of undergraduate course Quality Evaluation Analysis suggestion:
The improvement of key index has stronger limit to influence effect on the quality of education is promoted, therefore in order in limited religion
The ranking for promoting education of undergraduate course quality under resource precondition by a relatively large margin is educated, can be improved in terms of the following:
1) from ranks of teachers with from the point of view of structure, it is proposed that optimization staff structures, major colleges and universities will also focus on matching for human resources
It sets, implements the index of state education resource.It is recommended that government can also propose resource by capital investment in relatively weak school
Shared policy, utilizes the idle teacher resource of other colleges and universities, reasonable distribution.
2) from science research input with from the point of view of output, it is proposed that colleges and universities can A clear guidance and call student participate in and investment innovation work
Make, increase the investment of scientific research, turn out Innovation Talent, establishes some innovation matches more, excite the enthusiasm of student.
3) from Specialized Construction with from the point of view of the reform in education, it is proposed that school can go out key specialty according to its advantage Characteristic education,
Profession is not added blindly, and school should be understood that and strengthen the Connotation Construction and corresponding Training Object of Characteristic Speciality.
By specific embodiment and its result it is found that the undergraduate course quality education evaluation model based on comprehensive evaluation can be quasi-
Overall merit and ranking effectively really are carried out to the universities and colleges of undergraduate course of each prefecture-level city, in a particular embodiment, Nanjing universities and colleges it is comprehensive
Close highest scoring.Significance analysis is done to overall merit using distance between score and formula simultaneously, as the result is shown teacher, enrollment
Influence of the indexs such as number to score is minimum, and determining with sensitivity analysis has the key finger of larger impact to comprehensive score
Mark, science research input and output are maximum to the influence of change of comprehensive score.In a particular embodiment, evaluation model shows Jiangsu Province not
With the education of undergraduate course quality in city, there are significant regional disparities.Model, which can analyze different indexs, influences education of undergraduate course quality
The size of degree determines that the improvement of key index also has the influence of highly significant to the promotion quality of education.The model can help
Education of undergraduate course manager makees science accurately judgement to local education of undergraduate course quality level, while educating matter to local undergraduate is promoted
Amount level does effective guidance, so that the improvement and management for China's education of undergraduate course quality provide scientific basis and method.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention.It is all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (9)
1. the Evaluation in Education Quality analysis method based on comprehensive evaluation analysis method, which comprises the steps of:
Step 1: problem being modeled and proposes reasonable assumption and model mathematics symbol description;
Step 2: abstract index relevant to Evaluation in Education Quality being embodied as multiple data targets, by the data of these indexs
Quantification treatment, which is carried out, with nondimensionalization processing method obtains standardized data;
Step 3: determining Evaluation in Education Quality analysis flow chart diagram;
Step 4: obtaining the comprehensive score of indicator layer with principal component analysis;
Step 5: the weight of each index is determined according to Information Entropy;
Step 6: calculate the comprehensive score of multiple prefecture-level cities by comprehensive analysis, according to comprehensive score ranking to the quality of education into
Row overall merit;
Step 7: significance analysis being done to overall merit with distance between score and formula;
Step 8: the critical index for having larger impact to comprehensive score is determined with sensitivity analysis.
2. the Evaluation in Education Quality analysis method according to claim 1 based on comprehensive evaluation analysis method, which is characterized in that
Model mathematic sign in the step 1 includes: the standardized data x of j-th of index of i-th of universities and collegesij, i-th universities and colleges
The weight w of j-th of indexij, comprehensive score Si, entropy ej, susceptibility β.
3. the Evaluation in Education Quality analysis method according to claim 1 based on comprehensive evaluation analysis method, which is characterized in that
The step 2 includes:
Step 2-1 handles data using multiple variable synthetical evaluation method;
Step 2-2 determines the influence factor of index, including destination layer A, rule layer B and indicator layer C;
Step 2-3, gather data;
Step 2-4, data normalization;
Step 2-5, quantification treatment mode and calculation basis determine.
4. the Evaluation in Education Quality analysis method according to claim 3 based on comprehensive evaluation analysis method, which is characterized in that
The step 2-4 includes:
1) standard 0-1 is converted;
If original decision matrix is A=(aij)m×n, decision matrix is denoted as B=(b after transformationij)m×n;It is decision matrix jth
Maximum value in column,It is the minimum value in decision matrix jth column;In order to make the optimal value 1 after each attribute transformation and
Worst-case value is 0;To profit evaluation model attribute xj, it enables:
To cost type attribute xj, it enables:
2) transformation of interval type attribute;
For neither profit evaluation model again non-cost type attribute, using formula (3) carry out data processing;
If given optimum attributes section isa′jTo can not put up with lower limit, a "jTo can not put up with the upper limit, then:
The standardization of data is carried out using MATLAB algorithm.
5. the Evaluation in Education Quality analysis method according to claim 1 based on comprehensive evaluation analysis method, which is characterized in that
The step 4 includes:
Step 4-1: being standardized initial data, claims
For standardized index variable;
Step 4-2: correlation matrix R=(r is calculatedij)m×n, have
Step 4-3: characteristic value and feature vector are calculated;Calculate the eigenvalue λ of correlation matrix R1≥λ2≥…≥λm>=0, and
Corresponding feature vector u1, u2..., um, wherein uj=[u1j, u2j..., umj]T, m New Set variable is formed by feature vector:
Step 4-4: p principal component of selection calculates comprehensive evaluation value.
6. the Evaluation in Education Quality analysis method according to claim 5 based on comprehensive evaluation analysis method, which is characterized in that
The step 4-4 includes:
1) the information contribution rate and contribution rate of accumulative total of characteristic value are calculated;Claim
For principal component yjInformation contribution rate;
2) comprehensive score is calculated
7. the Evaluation in Education Quality analysis method according to claim 1 based on comprehensive evaluation analysis method, which is characterized in that
The step 5 includes:
Step 5-1: i-th of calculating is evaluated j-th of index value of object and is evaluated in j-th of index value summation of object all
Ratio;The calculating of the ratio is typically based on the index value after nondimensionalization, and calculation formula is
Step 5-2: the entropy of j-th of index is calculated
Step 5-3: the weight of each index is calculated
wjMeet 0≤ωj≤1It is the weight for each index that Information Entropy determines;
The weight of each index calculated by Information Entropy be weighted score it can be concluded that each school comprehensive score, calculate public
Shown in formula such as formula (10):
8. the Evaluation in Education Quality analysis method according to claim 1 based on comprehensive evaluation analysis method, which is characterized in that
The step 7 includes:
Establish evaluation criterion of the size of the relative distance value of prefecture-level city's comprehensive score as the index sensitivity;Calculation formula
Are as follows:
Wherein, DiAfter removing for i-th of index, the opposite variation distance of the city integrated score recalculated;Q1jIt is j-th of city
The comprehensive score value in city, QijIt is the comprehensive score value in j-th of city after removing some index.
9. the Evaluation in Education Quality analysis method according to claim 1 based on comprehensive evaluation analysis method, which is characterized in that
The step 8 includes:
Sensitivity analysis model is established to analyze specifically which index to the difference of city-level cities of Jiangsu Province educational development;It calculates
The formula of susceptibility are as follows:
Wherein, Δ xiFor the amplitude of i-th of variable x variation;ΔyiFor i-th of index y amplitude of fluctuation due to caused by variable x.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811107836.6A CN109345101A (en) | 2018-09-21 | 2018-09-21 | Evaluation in Education Quality analysis method based on comprehensive evaluation analysis method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811107836.6A CN109345101A (en) | 2018-09-21 | 2018-09-21 | Evaluation in Education Quality analysis method based on comprehensive evaluation analysis method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109345101A true CN109345101A (en) | 2019-02-15 |
Family
ID=65306336
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811107836.6A Withdrawn CN109345101A (en) | 2018-09-21 | 2018-09-21 | Evaluation in Education Quality analysis method based on comprehensive evaluation analysis method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109345101A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110348717A (en) * | 2019-06-28 | 2019-10-18 | 中国移动通信集团吉林有限公司 | Base station value methods of marking and device based on grid granularity |
CN110490352A (en) * | 2019-05-31 | 2019-11-22 | 武汉大学 | A kind of urban education service facility evaluation optimization method |
CN111612352A (en) * | 2020-05-22 | 2020-09-01 | 北京易华录信息技术股份有限公司 | Student expression ability assessment method and device |
CN112700132A (en) * | 2020-12-30 | 2021-04-23 | 河北地质大学 | Interval model-based student education quality evaluation system and method |
CN112734221A (en) * | 2021-01-06 | 2021-04-30 | 安徽易测评信息技术有限公司 | Statistical calculation method for estimating task quantity of each responsibility unit based on civilized city assessment item |
CN112950075A (en) * | 2021-03-31 | 2021-06-11 | 西南大学 | Evaluation method for teacher teaching ability expressive property based on knowledge processing mechanism |
CN113554271A (en) * | 2020-09-29 | 2021-10-26 | 中国传媒大学 | Method and device for analyzing influence degree of standard adoption relation on organization |
CN113592737A (en) * | 2021-07-27 | 2021-11-02 | 武汉理工大学 | Evaluation method for terrain correction effect of remote sensing image based on entropy weight method |
CN114720582A (en) * | 2021-11-26 | 2022-07-08 | 韩山师范学院 | Comprehensive evaluation method for aged and yellow wine in different aging years |
CN117350561A (en) * | 2023-10-10 | 2024-01-05 | 西南石油大学 | CO of depleted gas reservoir cap layer 2 Tightness evaluation method and device |
-
2018
- 2018-09-21 CN CN201811107836.6A patent/CN109345101A/en not_active Withdrawn
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110490352A (en) * | 2019-05-31 | 2019-11-22 | 武汉大学 | A kind of urban education service facility evaluation optimization method |
CN110348717A (en) * | 2019-06-28 | 2019-10-18 | 中国移动通信集团吉林有限公司 | Base station value methods of marking and device based on grid granularity |
CN110348717B (en) * | 2019-06-28 | 2021-11-30 | 中国移动通信集团吉林有限公司 | Base station value scoring method and device based on grid granularity |
CN111612352A (en) * | 2020-05-22 | 2020-09-01 | 北京易华录信息技术股份有限公司 | Student expression ability assessment method and device |
CN113554271A (en) * | 2020-09-29 | 2021-10-26 | 中国传媒大学 | Method and device for analyzing influence degree of standard adoption relation on organization |
CN112700132A (en) * | 2020-12-30 | 2021-04-23 | 河北地质大学 | Interval model-based student education quality evaluation system and method |
CN112734221A (en) * | 2021-01-06 | 2021-04-30 | 安徽易测评信息技术有限公司 | Statistical calculation method for estimating task quantity of each responsibility unit based on civilized city assessment item |
CN112950075A (en) * | 2021-03-31 | 2021-06-11 | 西南大学 | Evaluation method for teacher teaching ability expressive property based on knowledge processing mechanism |
CN113592737A (en) * | 2021-07-27 | 2021-11-02 | 武汉理工大学 | Evaluation method for terrain correction effect of remote sensing image based on entropy weight method |
CN113592737B (en) * | 2021-07-27 | 2024-04-30 | 武汉理工大学 | Remote sensing image topography correction effect evaluation method based on entropy weight method |
CN114720582A (en) * | 2021-11-26 | 2022-07-08 | 韩山师范学院 | Comprehensive evaluation method for aged and yellow wine in different aging years |
CN114720582B (en) * | 2021-11-26 | 2023-10-20 | 韩山师范学院 | Comprehensive evaluation method for old fragrance yellow in different ageing years |
CN117350561A (en) * | 2023-10-10 | 2024-01-05 | 西南石油大学 | CO of depleted gas reservoir cap layer 2 Tightness evaluation method and device |
CN117350561B (en) * | 2023-10-10 | 2024-05-24 | 西南石油大学 | CO of depleted gas reservoir cap layer2Tightness evaluation method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109345101A (en) | Evaluation in Education Quality analysis method based on comprehensive evaluation analysis method | |
CN109191001A (en) | Evaluation in Education Quality method based on principal component analysis | |
Wiley et al. | The validity of the Medical College Admission Test for predicting performance in the first two years of medical school | |
Liu et al. | Evaluation of college English teaching quality based on grey clustering analysis | |
Contino | A case study of the alignment between curriculum and assessment in the New York State Earth Science standards-based system | |
Witkin | An Analysis of Needs Assessment Techniques for Educational Planning at State, Intermediate, and District Levels. | |
Leung | Assessment for learning: Using SOLO taxonomy to measure design performance of design & technology students | |
Li et al. | An artificial intelligence based model for evaluation of college students’ ability and characteristics through teaching evaluation | |
CN108335047A (en) | Carry out the personal competitiveness intelligent evaluation system and method for school's application | |
Riyadi et al. | The Effect of Principal Managerial and Professionalism of Teachers on the Implementation of School-Based Management | |
Ikram et al. | Unlocking the potential of education quality: A systematic literature review | |
Sun et al. | A framework and indicators for information literacy of vocational school students | |
Yang et al. | Comprehensive evaluation of majors offered by universities based on combination weighting | |
Luo et al. | A multi-dimensional assessment model and its application in E-learning courses of computer science | |
CN111861106A (en) | College entrance examination selection model and establishment method thereof | |
Florian et al. | International perspectives: What can be known about effective inclusive schools? | |
Paz et al. | Development of college completion model based on K-Means clustering algorithm | |
Zhang et al. | Evaluation of the graduate attributes achievement on specialty of remote sensing science and technology | |
Airey et al. | Standards, benchmarks and assurance of learning | |
Yüksel | Evaluating the Effectiveness of the Chemistry Education by Using the Analytic Hierarchy Process. | |
Liu et al. | Application of Apriori Algorithm in Professional Elective Course Data Mining for University | |
CN110782156A (en) | Veterinary site epidemiology project training effect evaluation system and method | |
Wu et al. | Evaluation Model and System of ICT in Education Based on Gray Fuzzy Method | |
Wu | Application of BPNN’s intelligent ETQ model in network English teaching | |
Xu et al. | Design of Comprehensive Quality Evaluation Management of Teachers' Teaching Function Based on Analytic Hierarchy Process |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190215 |