CN112101770A - Audit quality model generation method and device and audit quality prediction method - Google Patents

Audit quality model generation method and device and audit quality prediction method Download PDF

Info

Publication number
CN112101770A
CN112101770A CN202010942415.6A CN202010942415A CN112101770A CN 112101770 A CN112101770 A CN 112101770A CN 202010942415 A CN202010942415 A CN 202010942415A CN 112101770 A CN112101770 A CN 112101770A
Authority
CN
China
Prior art keywords
company
audit
audit quality
audited
auditing
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.)
Granted
Application number
CN202010942415.6A
Other languages
Chinese (zh)
Other versions
CN112101770B (en
Inventor
陈璐
杨一丁
陶冶
刘伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China United Network Communications Group Co Ltd
Original Assignee
China United Network Communications Group Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China United Network Communications Group Co Ltd filed Critical China United Network Communications Group Co Ltd
Priority to CN202010942415.6A priority Critical patent/CN112101770B/en
Publication of CN112101770A publication Critical patent/CN112101770A/en
Application granted granted Critical
Publication of CN112101770B publication Critical patent/CN112101770B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/12—Accounting
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Technology Law (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

The invention provides an audit quality model generation method, an audit quality model generation device and an audit quality prediction method, wherein the method comprises the following steps: obtaining audit quality index sample data; calculating the controllability accrual profit corresponding to the audit quality index sample data; generating a linear regression model, taking each audit quality index in the audit quality index sample data as an independent variable and a controllable accrued profit as a dependent variable, and performing linear regression analysis on the independent variable and the dependent variable to obtain a regression equation; and carrying out significance test on the regression equation, and eliminating independent variables of which the significance test value P is greater than a preset threshold value, thereby obtaining an audit quality model. The method, the device and the auditing quality prediction method can solve the problems that the result academic circle is not unified due to the influence of each auditing quality index on the auditing quality, the auditing quality index related to the auditing quality cannot be obtained, and the prediction of the auditing quality in the future year cannot be realized.

Description

Audit quality model generation method and device and audit quality prediction method
Technical Field
The invention relates to the technical field of information, in particular to an audit quality model generation method and device and an audit quality prediction method.
Background
However, the academic circles about the influence of each audit quality index on the audit quality are not unified at present, the audit quality index related to the audit quality cannot be obtained, and the prediction of the audit quality in the future year cannot be realized.
Therefore, it is an urgent need to solve the problems of the technical personnel in the art to provide an audit quality model generation method, an audit quality model generation device and an audit quality prediction method.
Disclosure of Invention
The invention aims to solve the technical problems that in order to overcome the defects of the prior art, the invention provides an audit quality model generation method, an audit quality model generation device and an audit quality prediction method, which are used for solving the problems that the academic circles of the influence results of audit quality indexes on the audit quality are not unified, the audit quality indexes related to the audit quality cannot be obtained, and the prediction of the audit quality in the future year cannot be realized.
In a first aspect, an embodiment of the present invention provides a method for generating an audit quality model, including:
obtaining audit quality index sample data;
calculating the controllability accrual profit corresponding to the audit quality index sample data;
generating a linear regression model, taking each audit quality index in the audit quality index sample data as an independent variable and a controllable accrued profit as a dependent variable, and performing linear regression analysis on the independent variable and the dependent variable to obtain a regression equation;
and carrying out significance test on the regression equation, and eliminating independent variables of which the significance test value P is greater than a preset threshold value, thereby obtaining an audit quality model.
Preferably, the obtaining of the audit quality indicator sample data includes:
acquiring audit quality statistical data of a preset region or country;
screening the audit quality statistical data, and eliminating incomplete data in the audit quality statistical data;
and performing correlation analysis on each audit quality index in the screened audit quality statistical data, and eliminating the audit quality index which has correlation with other audit quality indexes in the audit quality statistical data, thereby obtaining the audit quality index sample data.
Preferably, the calculating the controllability accrual profit corresponding to the audit quality index sample data includes:
and calculating the controllability accrued profit corresponding to the audit quality index sample data by adopting a Jones model based on section correction.
Preferably, the audit quality indicator sample data comprises a reputation indicator.
Preferably, the reputation index comprises public interest index of the audited company and public interest index of the audited company; the interest index of the public to the company to be audited is a search index of the public to the company to be audited in a given time period; the interest index of the public to the auditing company is a search index of the public to the audited company in a given time period;
the linear regression model conforms to the following formula:
DAABSit＝b+β1IOTit+β2IOTAit+β3TEit+β4SATit+β5AFit+β6SCit+β7NAFit+β8EXPit+β9TAit+β10LRit+β11SRit+β12ROAit+β13GRit+β14PROit+β15AGEit+β16NLDit+∈
wherein, DAABS is the absolute value of the controllability accrued profit of the company to be audited;
it is the data of ith company in the t year;
b is a constant term;
beta is the coefficient of each audit quality index;
IOT is the public interest index of the company to be audited;
the IOTA is the public interest index of an audit company;
TE is the auditing years of the audited company and the auditing company;
SAT is the auditing years of signed auditing personnel of the audited company and the auditing company;
AF is the auditing expense paid to the auditing company by the auditing company;
SC is whether the audit company is a preset four-meeting planning office or not, if so, the SC is 1, and if not, the SC is 0;
NAF is the non-auditing expense paid to the auditing company by the auditing company;
EXP is whether the auditing company is an expert in the industry, if so, the EXP is 1, otherwise, the EXP is 0;
TA is the total assets of the company to be audited;
LR is the flow rate of the company being audited;
SR is the repayment capacity ratio of the company to be audited;
ROA is the asset return rate of the company to be audited;
GR is the revenue growth rate of the company being audited;
PRO is whether the audited company is profitable, if yes, 1 is obtained, and otherwise, 0 is obtained;
AGE is the number of years that the company under audit holds;
NLD is the change of long-term liability of the company to be audited;
e is an error;
performing linear regression analysis on the independent variable and the dependent variable to obtain a regression equation, wherein the regression equation comprises:
and inputting the independent variable and the dependent variable into a linear regression model corresponding to the formula for training to obtain parameter values of target parameters in the linear regression model, thereby obtaining the regression equation.
Preferably, the performing significance test on the regression equation, and rejecting the independent variable with the significance test value P greater than the preset threshold value includes:
setting the significance level alpha to be 95%, and acquiring a significance test value P value of each independent variable in the regression equation;
if the p value is less than 0.05, the independent variable is reserved;
and if the p value is greater than 0.05, eliminating the independent variable until the regression equation does not have the independent variable with the p value greater than 0.05, thereby obtaining the final audit quality model.
In a second aspect, an embodiment of the present invention provides an audit quality model generating apparatus, including:
the obtaining module is used for obtaining audit quality index sample data;
the calculation module is connected with the acquisition module and used for calculating the controllability accrued profit corresponding to the audit quality index sample data;
the regression module is connected with the acquisition module and the calculation module and used for generating a linear regression model, taking each audit quality index in the audit quality index sample data as an independent variable and taking the controllable accrued profit as a dependent variable, and performing linear regression analysis on the independent variable and the dependent variable to obtain a regression equation;
and the generation module is connected with the regression module and used for carrying out significance test on the regression equation and eliminating the independent variable of which the significance test value P is greater than a preset threshold value so as to obtain the audit quality model.
Preferably, the acquiring module specifically includes:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring audit quality statistical data of a preset region or country;
the data screening unit is used for screening the audit quality statistical data and eliminating incomplete data in the audit quality statistical data;
and the analysis unit is used for performing correlation analysis on each audit quality index in the screened audit quality statistical data, and eliminating the audit quality index which has correlation with other audit quality indexes in the audit quality statistical data, so as to obtain the audit quality index sample data.
Preferably, the reputation index comprises public interest index of the audited company and public interest index of the audited company; the interest index of the public to the company to be audited is a search index of the public to the company to be audited in a given time period; the interest index of the public to the auditing company is a search index of the public to the audited company in a given time period;
the linear regression model conforms to the following formula:
DAABSit＝b+β1IOTit+β2IOTAit+β3TEit+β4SATit+β5AFit+β6SCit+β7NAFit+β8EXPit+β9TAit+β10LRit+β11SRit+β12ROAit+β13GRit+β14PROit+β15AGEit+β16NLDit+∈
wherein, DAABS is the absolute value of the controllability accrued profit of the company to be audited;
it is the data of ith company in the t year;
b is a constant term;
beta is the coefficient of each audit quality index;
IOT is the public interest index of the company to be audited;
the IOTA is the public interest index of an audit company;
TE is the auditing years of the audited company and the auditing company;
SAT is the auditing years of signed auditing personnel of the audited company and the auditing company;
AF is the auditing expense paid to the auditing company by the auditing company;
SC is whether the audit company is a preset four-meeting planning office or not, if so, the SC is 1, and if not, the SC is 0;
NAF is the non-auditing expense paid to the auditing company by the auditing company;
EXP is whether the auditing company is an expert in the industry, if so, the EXP is 1, otherwise, the EXP is 0;
TA is the total assets of the company to be audited;
LR is the flow rate of the company being audited;
SR is the repayment capacity ratio of the company to be audited;
ROA is the asset return rate of the company to be audited;
GR is the revenue growth rate of the company being audited;
PRO is whether the audited company is profitable, if yes, 1 is obtained, and otherwise, 0 is obtained;
AGE is the number of years that the company under audit holds;
NLD is the change of long-term liability of the company to be audited;
e is an error;
the regression module is specifically configured to input the independent variable and the dependent variable into a linear regression model corresponding to the above formula for training, so as to obtain a parameter value of a target parameter in the linear regression model, thereby obtaining the regression equation.
In a third aspect, an embodiment of the present invention provides an audit quality prediction method, including:
obtaining audit quality index data of a year to be predicted;
and inputting the audit quality index data of the year to be predicted into the audit quality model generated by the audit quality model generation method of the first aspect to predict the audit quality of the year to be predicted.
The audit quality model generation method, the device and the audit quality prediction method provided by the embodiment of the invention rely on big data analysis, and perform linear regression analysis on each audit quality index and the controllable accrued profit in the audit quality index sample data to obtain a regression equation, and simultaneously perform significance test on the regression equation to remove independent variables of which the significance test value P is greater than a preset threshold value, thereby obtaining a final audit quality model and obtaining the audit quality index related to the audit quality. In addition, the auditing quality qualitative concept can be visually displayed through the calculated numerical value through the auditing quality model, so that the auditing quality is visual and quantifiable. And after the generated audit quality model brings the relevant audit quality indexes, the subsequent audit quality can be predicted. By comparing with the audit report, the method is beneficial to reducing the information risk caused by information asymmetry in the public and the market and reducing the information risk of financial statement users to the socially acceptable level, thereby solving the problems that in the prior art, the academic circles of the influence results of each audit quality index on the audit quality are not unified, the audit quality index related to the audit quality cannot be obtained, and the prediction of the audit quality in the future year cannot be realized.
Drawings
FIG. 1: a flow chart of a method for generating an audit quality model according to embodiment 1 of the present invention;
FIG. 2: is a regression analysis experiment result;
FIG. 3: a structure diagram of an audit quality model generation device in embodiment 2 of the present invention;
FIG. 4: a flowchart of an audit quality prediction method according to embodiment 3 of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Example 1:
the embodiment provides an audit quality model generation method, as shown in fig. 1, the method includes:
and S102, obtaining audit quality index sample data.
Optionally, obtaining audit quality indicator sample data may include:
acquiring audit quality statistical data of a preset region or country;
screening the audit quality statistical data, and eliminating incomplete data in the audit quality statistical data;
and performing correlation analysis on each audit quality index in the screened audit quality statistical data, and eliminating the audit quality indexes which have correlation with other audit quality indexes in the audit quality statistical data, thereby obtaining audit quality index sample data.
In the embodiment, the generation of the audit quality model is based on big data analysis, and the data can be based on 1591 listed companies in all england (including scotland, england, welsh and north ireland), so as to eliminate financial industry companies and data-missing companies with different own industry and supervision characteristics, and finally form a sample of 732 companies, wherein the total number of data is 55632 in 2928 years.
In this embodiment, in order to ensure that the design of the audit quality model and the selection of the variables are reasonable, correlation analysis is performed on each audit quality index in the audit quality statistical data, whether correlation exists is judged through correlation analysis between every two indexes, if no correlation exists, the audit quality index is retained, and if yes, the highly correlated audit quality index is rejected.
Optionally, the audit quality indicator sample data may comprise a reputation indicator. The reputation index comprises the interest index of the public in the audited company and the interest index of the public in the audited company; the interest index of the public to the company to be audited is a search index of the public to the company to be audited in a given time period; the public interest index of the audited company is the search index of the audited company by the public in a given time period.
During the research and practice of the prior art, the inventor finds that: high-quality auditing is a core part of a well-functioning capital market, the existing research on factors related to auditing quality usually ignores the influence of external perspectives such as the capital market and auditing report users on auditing quality, and the inventor finds that the reputation of an auditing company and an audited company also influences the auditing quality. For example, for an audited company, if the company is in an up-date or maturity period and has a high reputation, it is easier to attract public attention to any information available to the company, including previous audit reports. The more attention a company attracts, the more likely the public is to discover problems with the company, whereas if a company is unwelcome, forged data and financial conditions are more secure.
In this embodiment, the reputation indicator may include an interest index of the public in the company being audited and an interest index of the public in the auditing company, since the reputation of the company cannot be directly observed and is difficult to define from a company perspective. Thus, public interest in the company over time is selected to reflect the reputation of the company. Specifically, the public interest index of the company to be audited is a search index of the company to be audited by the public in the world or in a given period of time in a preset region or country, namely an index of online website search interest displayed relative to the given region and time. The larger the search index is, the larger the interest index representing the public to the company to be audited is, the search index or the interest index can range from 0 to 100, and the size of the interest index is determined by the preset search frequency peak value. For example, if the peak value of the search frequency is 10000, the total frequency of searches (such as google and hectometer) on each large known website of a certain audited company in a certain year is greater than or equal to 10000, the interest index is 100, if the total frequency of searches is less than 100, that is, the total frequency of searches is less than 1% of the peak value of the search frequency, the corresponding interest index is 0, and the reputation of the audited company is included in the formula of the regression model as a dependent variable. Similarly, the public interest index of the auditing company is a search index of the public to the auditing company in a given period of time in a global or preset region or country, and the search index can comprise a search index of the public searching the audited company and/or a search index of the public searching the auditors in the audited company.
In this embodiment, the audit quality indicator in the audit quality indicator sample data may be the following 16 indicators: public interest index in the company being audited; public interest index in auditing companies; auditing years of the audited company and the auditing company; auditing years of signature auditors of audited companies and auditing companies; auditing expenses paid to the auditing company by the auditing company; whether the auditing company is a preset four-meeting accounting firm or not is judged, if yes, the auditing company is 1, and if not, the auditing company is 0; non-audit expenses paid to the auditing company by the auditing company; whether an auditing company is an expert in the industry or not is judged, if yes, the auditing company is 1, and if not, the auditing company is 0; total assets of the company being audited; the flow rate of the company being audited; the liability capacity ratio of the company being audited; asset return rates for audited companies; revenue growth rate of audited companies; whether the audited company is profitable, if so, the value is 1, otherwise, the value is 0; the number of years an audited company has established; changes in long term liability of audited companies; correlation analysis is carried out on the 16 indexes pairwise, and the fact that no correlation exists among the indexes is determined, so that audit quality index data without correlation are used as audit quality index sample data.
In the embodiment, by introducing the reputation index into the audit quality index sample data and comprehensively considering the influence of the reputation indexes of the audit company and the company to be audited on the audit quality, since the reputation is important soft competitiveness of enterprises, no matter the enterprises or the audit companies, the enterprises or the audit companies should keep good reputation and be responsible for the public and the market, and the trust of the public and the market to the enterprises and the audit companies should not be consumed, the method is favorable for the public and the market to better judge the public trust of the audit company.
And step S104, calculating the controllability accrual profit corresponding to the audit quality index sample data.
Optionally, calculating a controllability accrual profit corresponding to the audit quality index sample data, including:
and calculating the controllability accrued profit corresponding to the audit quality index sample data by adopting the Jones model based on section correction.
In the embodiment, in order to visualize and quantify the audit quality, the influence of the reputation factor on the audit quality can be checked by using the controllability accrued profit as the index of the audit quality. Specifically, the manipulability accrued profit may be measured based on the cross-section modified jones model.
And S106, generating a linear regression model, taking each audit quality index in the audit quality index sample data as an independent variable and the manipulable accrued profit as a dependent variable, and performing linear regression analysis on the independent variable and the dependent variable to obtain a regression equation.
In this embodiment, assuming that the 16 analyzed audit quality indicators have no correlation, the 16 audit quality indicators are used as independent variables, the manipulatable accrual profit is used as a dependent variable, and the manipulatable accrual profit and the 16 independent variables are subjected to regression analysis, so that the linear regression model conforms to the following formula:
DAABSit＝b+β1IOTit+β2IOTAit+β3TEit+β4SATit+β5AFit+β6SCit+β7NAFit+β8EXPit+β9TAit+β10LRit+β11SRit+β12ROAit+β13GRit+β14PROit+β15AGEit+β16NLDit+∈
wherein, DAABS is the absolute value of the controllability accrued profit of the company to be audited;
it is the data of ith company in the t year;
b is a constant term;
beta is the coefficient of each audit quality index;
IOT is the public interest index of the company to be audited;
the IOTA is the public interest index of an audit company;
TE is the auditing years of the audited company and the auditing company;
SAT is the auditing years of signed auditing personnel of the audited company and the auditing company;
AF is the auditing expense paid to the auditing company by the auditing company;
SC is whether the auditing company is a preset four-party planning firm, if yes, the SC is 1, and if not, the SC is 0. Wherein, the four meeting institutions refer to Puhua Yongdao (PWC), Pimpie (KPMG), Duty (DDT) and Anyong (EY);
NAF is the non-auditing expense paid to the auditing company by the auditing company;
EXP is whether the auditing company is an expert in the industry, if so, the EXP is 1, otherwise, the EXP is 0;
TA is the total assets of the company to be audited;
LR is the flow rate of the company being audited;
SR is the repayment capacity ratio of the company to be audited;
ROA is the asset return rate of the company to be audited;
GR is the revenue growth rate of the company being audited;
PRO is whether the audited company is profitable, if yes, 1 is obtained, and otherwise, 0 is obtained;
AGE is the number of years that the company under audit holds;
NLD is the change of long-term liability of the company to be audited;
e is the error.
Optionally, performing linear regression analysis on the independent variable and the dependent variable to obtain a regression equation, which may include:
and inputting the independent variable and the dependent variable into the linear regression model corresponding to the formula for training to obtain the parameter value of the target parameter in the linear regression model, thereby obtaining the regression equation.
In this embodiment, after performing regression analysis on the manipulatable accrual profits and the 16 independent variables, a regression equation is obtained, and coefficients, constant terms and error values of each audit quality index in the linear regression model are obtained.
And step S108, carrying out significance test on the regression equation, and eliminating independent variables of which the significance test value P is greater than a preset threshold value, thereby obtaining an audit quality model.
Optionally, the performing significance test on the regression equation, and eliminating the independent variable with the significance test value P greater than the preset threshold value may include:
setting the significance level alpha to be 95%, and obtaining the significance test value P value of each independent variable in the regression equation;
if the p value is less than 0.05, the independent variable is reserved;
and if the p value is greater than 0.05, rejecting the independent variable until the independent variable with the p value greater than 0.05 does not exist in the regression equation, thereby obtaining the final audit quality model.
In this embodiment, after obtaining the regression equations, in order to further verify whether linear relationships do exist between the respective variables and the dependent variables, and in order to further optimize the models so that the independent variables in the models are all variables having significant influence on the dependent variables, a significance test is performed on the regression equations, the independent variables having insignificant influence in the regression equations are removed, in the case that the significance level α is 95%, a significance test value P of the respective variables is obtained through the significance test, and if the P value is less than 0.05, it is stated that the association between the independent variables and the dependent variables is large, that is, the significance is large, and the independent variables are retained. If the p value is larger than 0.05, the correlation between the independent variable and the dependent variable is small or irrelevant, namely the significance is low, the independent variable has no statistical significance to the dependent variable, the independent variable is deleted, the corresponding regression equation is solved again, then the significance test is carried out on the regression equation until the independent variable with low significance does not exist in the regression equation, and the final audit quality model is obtained. In a specific implementation process, the value P can be calculated by using SPSS software, and the significance of the independent variable in the regression equation can be detected by using the value P.
In this embodiment, the relationship between each variable and the audit quality can be determined by the obtained coefficient of the regression equation, and if the coefficient is greater than 0, it represents that the independent variable is positively correlated with the audit quality, and if the coefficient is less than 0, it represents that the independent variable is negatively correlated with the audit quality.
In this embodiment, the final regression equation obtained by the significance test includes independent variables less than or equal to 16, and the obtained regression equation may be different according to the data condition of the actual region. Through experimental analysis, the reputation index has influence on audit quality: the reputation of the company to be audited is negatively related to the manageable receivable profit, namely based on the reputation theory, the attention of the public can help to restrict the opportunistic behaviors of managers, and the public is used as an audit report user and plays an important role in the audit process and the audit quality improvement. However, the reputation of the audited company is positively correlated with the manageable profit, although the public can know the condition of the audited company in various ways, such as online searching, visiting an official website, reading comments of others, and the like. But the public has less knowledge of the auditing expertise and skills than the company being audited, in which case the public would prefer to trust the auditor.
In a specific embodiment, the data of 732 companies and 2928 years of company in the uk is used as the sample data of the audit quality index to perform regression analysis, and when the significance level alpha is set to 95%, the results of the regression analysis are shown in fig. 2. The regression results show that the interest index IOT for the company being audited is significantly inversely related to the manageable accrued profit over time. This result is consistent with the assumption that higher quality audits are seen by marketable companies who are more concerned by the public. The higher the public concern, the higher the opportunistic behavior cost of the administrator, and the greater the implementation difficulty. At the same time, emerging or successful companies in general have attracted more public attention. These companies are likely to maintain good reputation for further development. Therefore, they are willing to guarantee good surplus quality and audit quality.
There is no significant evidence for the interest index IOTA of the auditing company to improve its relationship to manageable accrued profits. But the index is positive, this result may indicate that the public is more inclined to believe the auditing companies they are familiar with, and therefore these auditors have more opportunities to assist the customer in forging the financial data. There is no evidence to support the relationship between the tenure of the audit company and the tenure of the senior auditor and the manageable accrual profits. In terms of audit cost, audit cost is significantly and positively correlated with manageable receivable profit. This result demonstrates that economic dependence may have an impact on auditors, and that high audit costs may compromise auditors' independence.
The negative correlation with manipulability accrual profit and the larger coefficient in terms of whether the auditing company is a four-grand accountant firm SC, proves that the auditing quality of the "four-grand" accountant firm is better because their income is not dependent on a particular customer from the perspective of a quasi-rent. The non-audited service fee is inversely related to the manageable accrued profit. The results show that non-audited services help constrain the manager's opportunistic behavior. Although the non-audit service increases the economic connection between auditors and clients, the audit quality cannot be damaged on the premise that the auditors insist on audit independence and audit criteria, and the method is in line with the accountant ethics. Most auditing affairs at present survey the background and range of non-auditing service in order to avoid damaging auditing independence. In terms of the expertise of auditors, industry experts will greatly help improve audit quality and constrain manipulability accrued profits.
The total asset TA of the company to be audited is in positive correlation with the controllability accrued profit, which indicates that the business of a large enterprise is complex and more methods are possible to manage the profit. And the management of the system is relatively difficult to be achieved, so that the difficulty of auditing is increased. The virtual variable PRO is negatively correlated to the manipulatable accrued profit, but does not pass the significance test. This still suggests that it is unlikely that growing enterprises will consciously manage revenue. Revenue growth is negatively correlated to manipulatable accrual profits, but does not meet the significance test. For this reason, for a company that grows rapidly, the management system and the internal control system lag behind the growth of business. Thus, companies in the growth stage have more opportunities to manage revenue.
Fig. 2 shows only the regression analysis results when the significance level α is 95%, and different confidence intervals also have different results for the judgment, and it can be seen from fig. 2 that five indexes, i.e., IOT, AF, NAF, EXP, and TA, have significant influence on the manipulability profit.
In this embodiment, the obtained audit quality model can bring relevant indexes into the audit quality model based on the operation condition of the subsequent year, predict the audit quality condition of the subsequent year, compare the audit quality condition with the audit report, reduce the information risk caused by information asymmetry in the public and the market, and reduce the information risk of the financial statement user to a socially acceptable level. In addition, the audit quality model can also be applied to other countries and regions to realize the calculation of the audit quality of the countries and regions.
The method for generating the audit quality model provided by this embodiment is based on big data analysis, and performs linear regression analysis on each audit quality index and the controllable accrued profit in the audit quality index sample data to obtain a regression equation, and performs significance test on the regression equation to remove the independent variable of which the significance test value P is greater than the preset threshold value, so as to obtain the final audit quality model and obtain the audit quality index related to the audit quality. In addition, the auditing quality qualitative concept can be visually displayed through the calculated numerical value through the auditing quality model, so that the auditing quality is visual and quantifiable. And after the generated audit quality model brings the relevant audit quality indexes, the subsequent audit quality can be predicted. By comparing with the audit report, the method is beneficial to reducing the information risk caused by information asymmetry in the public and the market and reducing the information risk of financial statement users to the socially acceptable level, thereby solving the problems that in the prior art, the academic circles of the influence results of each audit quality index on the audit quality are not unified, the audit quality index related to the audit quality cannot be obtained, and the prediction of the audit quality in the future year cannot be realized.
Example 2:
as shown in fig. 3, the present embodiment provides an audit quality model generating apparatus, including:
an obtaining module 202, configured to obtain audit quality index sample data;
the calculating module 204 is connected with the obtaining module 202 and is used for calculating the controllability accrued profit corresponding to the audit quality index sample data;
the regression module 206 is connected with the obtaining module 202 and the calculating module 204, and is configured to generate a linear regression model, take each audit quality index in the audit quality index sample data as an independent variable, take the manipulable accrued profit as a dependent variable, and perform linear regression analysis on the independent variable and the dependent variable to obtain a regression equation;
and the generating module 208 is connected with the regression module 206 and is used for performing significance test on the regression equation and eliminating the independent variable of which the significance test value P is greater than the preset threshold value so as to obtain the audit quality model.
Optionally, the obtaining module 202 may specifically include:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring audit quality statistical data of a preset region or country;
the data screening unit is used for screening the audit quality statistical data and rejecting incomplete data in the audit quality statistical data;
and the analysis unit is used for performing correlation analysis on each audit quality index in the screened audit quality statistical data, and eliminating the audit quality indexes which have correlation with other audit quality indexes in the audit quality statistical data, so as to obtain audit quality index sample data.
Optionally, the reputation index comprises public interest index of the audited company and public interest index of the audited company; the interest index of the public to the company to be audited is a search index of the public to the company to be audited in a given time period; the interest index of the public to the auditing company is a search index of the public to the audited company in a given time period;
the linear regression model conforms to the following formula:
DAABSit＝b+β1IOTit+β2IOTAit+β3TEit+β4SATit+β5AFit+β6SCit+β7NAFit+β8EXPit+9TAit+β10LRit+β11SRit+β12ROAit+β13GRit+β14PROit+β15AGEit+β16NLDit+∈
wherein, DAABS is the absolute value of the controllability accrued profit of the company to be audited;
it is the data of ith company in the t year;
b is a constant term;
beta is the coefficient of each audit quality index;
IOT is the public interest index of the company to be audited;
the IOTA is the public interest index of an audit company;
TE is the auditing years of the audited company and the auditing company;
SAT is the auditing years of signed auditing personnel of the audited company and the auditing company;
AF is the auditing expense paid to the auditing company by the auditing company;
SC is whether the audit company is a preset four-meeting planning office or not, if so, the SC is 1, and if not, the SC is 0;
NAF is the non-auditing expense paid to the auditing company by the auditing company;
EXP is whether the auditing company is an expert in the industry, if so, the EXP is 1, otherwise, the EXP is 0;
TA is the total assets of the company to be audited;
LR is the flow rate of the company being audited;
SR is the repayment capacity ratio of the company to be audited;
ROA is the asset return rate of the company to be audited;
GR is the revenue growth rate of the company being audited;
PRO is whether the audited company is profitable, if yes, 1 is obtained, and otherwise, 0 is obtained;
AGE is the number of years that the company under audit holds;
NLD is the change of long-term liability of the company to be audited;
e is an error;
the regression module 206 is specifically configured to input the independent variable and the dependent variable into the linear regression model corresponding to the above formula for training, so as to obtain a parameter value of a target parameter in the linear regression model, thereby obtaining a regression equation.
Example 3:
as shown in fig. 4, the present embodiment provides an audit quality prediction method, including:
obtaining audit quality index data of a year to be predicted;
and inputting the audit quality index data of the year to be predicted into the audit quality model generated by the audit quality model generation method in the embodiment 1 so as to predict the audit quality of the year to be predicted.
The generation device of the audit quality model and the audit quality prediction method provided in embodiments 2 to 3 rely on big data analysis, and perform linear regression analysis on each audit quality index and the manipulatable receivable profit in the audit quality index sample data to obtain a regression equation, and perform significance test on the regression equation to remove the independent variable of which the significance test value P is greater than the preset threshold value, thereby obtaining a final audit quality model and obtaining the audit quality index related to the audit quality. In addition, the auditing quality qualitative concept can be visually displayed through the calculated numerical value through the auditing quality model, so that the auditing quality is visual and quantifiable. And after the generated audit quality model brings the relevant audit quality indexes, the subsequent audit quality can be predicted. By comparing with the audit report, the method is beneficial to reducing the information risk caused by information asymmetry in the public and the market and reducing the information risk of financial statement users to the socially acceptable level, thereby solving the problems that in the prior art, the academic circles of the influence results of each audit quality index on the audit quality are not unified, the audit quality index related to the audit quality cannot be obtained, and the prediction of the audit quality in the future year cannot be realized.
It will be understood that the above embodiments are merely exemplary embodiments taken to illustrate the principles of the present invention, which is not limited thereto. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and substance of the invention, and these modifications and improvements are also considered to be within the scope of the invention.

Claims (10)

1. An audit quality model generation method, comprising:
obtaining audit quality index sample data;
calculating the controllability accrual profit corresponding to the audit quality index sample data;
generating a linear regression model, taking each audit quality index in the audit quality index sample data as an independent variable and a controllable accrued profit as a dependent variable, and performing linear regression analysis on the independent variable and the dependent variable to obtain a regression equation;
and carrying out significance test on the regression equation, and eliminating independent variables of which the significance test value P is greater than a preset threshold value, thereby obtaining an audit quality model.
2. The method for generating the audit quality model according to claim 1, wherein the obtaining the audit quality index sample data includes:
acquiring audit quality statistical data of a preset region or country;
screening the audit quality statistical data, and eliminating incomplete data in the audit quality statistical data;
and performing correlation analysis on each audit quality index in the screened audit quality statistical data, and eliminating the audit quality index which has correlation with other audit quality indexes in the audit quality statistical data, thereby obtaining the audit quality index sample data.
3. The audit quality model generation method of claim 1, wherein the calculating the manipulability accrual profit corresponding to the audit quality index sample data comprises:
and calculating the controllability accrued profit corresponding to the audit quality index sample data by adopting a Jones model based on section correction.
4. The audit quality model generation method of claim 3, wherein the audit quality indicator sample data includes a reputation indicator.
5. The audit quality model generation method of claim 4, wherein the reputation indicators include public interest indices for audited companies and public interest indices for audited companies; the interest index of the public to the company to be audited is a search index of the public to the company to be audited in a given time period; the interest index of the public to the auditing company is a search index of the public to the audited company in a given time period;
the linear regression model conforms to the following formula:
DAABSit＝b+β1IOTit+β2IOTAit+β3TEit+β4SATit+β5AFit+β6SCit+β7NAFit+β8EXPit+β9TAit+β10LRit+β11SRit+β12ROAit+β13GRit+β14PROit+β15AGEit+β16NLDit+∈
wherein, DAABS is the absolute value of the controllability accrued profit of the company to be audited;
it is the data of ith company in the t year;
b is a constant term;
beta is the coefficient of each audit quality index;
IOT is the public interest index of the company to be audited;
the IOTA is the public interest index of an audit company;
TE is the auditing years of the audited company and the auditing company;
SAT is the auditing years of signed auditing personnel of the audited company and the auditing company;
AF is the auditing expense paid to the auditing company by the auditing company;
SC is whether the audit company is a preset four-meeting planning office or not, if so, the SC is 1, and if not, the SC is 0;
NAF is the non-auditing expense paid to the auditing company by the auditing company;
EXP is whether the auditing company is an expert in the industry, if so, the EXP is 1, otherwise, the EXP is 0;
TA is the total assets of the company to be audited;
LR is the flow rate of the company being audited;
SR is the repayment capacity ratio of the company to be audited;
ROA is the asset return rate of the company to be audited;
GR is the revenue growth rate of the company being audited;
PRO is whether the audited company is profitable, if yes, 1 is obtained, and otherwise, 0 is obtained;
AGE is the number of years that the company under audit holds;
NLD is the change of long-term liability of the company to be audited;
e is an error;
performing linear regression analysis on the independent variable and the dependent variable to obtain a regression equation, wherein the regression equation comprises:
and inputting the independent variable and the dependent variable into a linear regression model corresponding to the formula for training to obtain parameter values of target parameters in the linear regression model, thereby obtaining the regression equation.
6. The audit quality model generation method of claim 5, wherein the significance testing the regression equation to eliminate the independent variable with a significance test value P value greater than a preset threshold value comprises:
setting the significance level alpha to be 95%, and acquiring a significance test value P value of each independent variable in the regression equation;
if the p value is less than 0.05, the independent variable is reserved;
and if the p value is greater than 0.05, eliminating the independent variable until the regression equation does not have the independent variable with the p value greater than 0.05, thereby obtaining the final audit quality model.
7. An audit quality model generation apparatus, comprising:
the obtaining module is used for obtaining audit quality index sample data;
the calculation module is connected with the acquisition module and used for calculating the controllability accrued profit corresponding to the audit quality index sample data;
the regression module is connected with the acquisition module and the calculation module and used for generating a linear regression model, taking each audit quality index in the audit quality index sample data as an independent variable and taking the controllable accrued profit as a dependent variable, and performing linear regression analysis on the independent variable and the dependent variable to obtain a regression equation;
and the generation module is connected with the regression module and used for carrying out significance test on the regression equation and eliminating the independent variable of which the significance test value P is greater than a preset threshold value so as to obtain the audit quality model.
8. The audit quality model generation device of claim 7, wherein the obtaining module specifically includes:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring audit quality statistical data of a preset region or country;
the data screening unit is used for screening the audit quality statistical data and eliminating incomplete data in the audit quality statistical data;
and the analysis unit is used for performing correlation analysis on each audit quality index in the screened audit quality statistical data, and eliminating the audit quality index which has correlation with other audit quality indexes in the audit quality statistical data, so as to obtain the audit quality index sample data.
9. The audit quality model generation apparatus of claim 8, wherein the reputation indicator comprises a public interest index for an audited company and a public interest index for an audited company; the interest index of the public to the company to be audited is a search index of the public to the company to be audited in a given time period; the interest index of the public to the auditing company is a search index of the public to the audited company in a given time period;
the linear regression model conforms to the following formula:
DAABSit＝b+β1IOTit+β2IOTAit+β3TEit+β4SATit+β5AFit+β6SCit+β7NAFit+β8EXPit+β9TAit+β10LRit+β11SRit+β12ROAit+β13GRit+β14PROit+β15AGEit+β16NLDit+∈
wherein, DAABS is the absolute value of the controllability accrued profit of the company to be audited;
it is the data of ith company in the t year;
b is a constant term;
beta is the coefficient of each audit quality index;
IOT is the public interest index of the company to be audited;
the IOTA is the public interest index of an audit company;
TE is the auditing years of the audited company and the auditing company;
SAT is the auditing years of signed auditing personnel of the audited company and the auditing company;
AF is the auditing expense paid to the auditing company by the auditing company;
SC is whether the audit company is a preset four-meeting planning office or not, if so, the SC is 1, and if not, the SC is 0;
NAF is the non-auditing expense paid to the auditing company by the auditing company;
EXP is whether the auditing company is an expert in the industry, if so, the EXP is 1, otherwise, the EXP is 0;
TA is the total assets of the company to be audited;
LR is the flow rate of the company being audited;
SR is the repayment capacity ratio of the company to be audited;
ROA is the asset return rate of the company to be audited;
GR is the revenue growth rate of the company being audited;
PRO is whether the audited company is profitable, if yes, 1 is obtained, and otherwise, 0 is obtained;
AGE is the number of years that the company under audit holds;
NLD is the change of long-term liability of the company to be audited;
e is an error;
the regression module is specifically configured to input the independent variable and the dependent variable into a linear regression model corresponding to the above formula for training, so as to obtain a parameter value of a target parameter in the linear regression model, thereby obtaining the regression equation.
10. An audit quality prediction method, comprising:
obtaining audit quality index data of a year to be predicted;
inputting the audit quality indicator data of the year to be predicted into the audit quality model generated by the audit quality model generation method according to any one of claims 1 to 6 to predict the audit quality of the year to be predicted.
CN202010942415.6A 2020-09-09 2020-09-09 Audit quality model generation method and device and audit quality prediction method Active CN112101770B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010942415.6A CN112101770B (en) 2020-09-09 2020-09-09 Audit quality model generation method and device and audit quality prediction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010942415.6A CN112101770B (en) 2020-09-09 2020-09-09 Audit quality model generation method and device and audit quality prediction method

Publications (2)

Publication Number Publication Date
CN112101770A true CN112101770A (en) 2020-12-18
CN112101770B CN112101770B (en) 2023-07-18

Family

ID=73752610

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010942415.6A Active CN112101770B (en) 2020-09-09 2020-09-09 Audit quality model generation method and device and audit quality prediction method

Country Status (1)

Country Link
CN (1) CN112101770B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101556666A (en) * 2009-05-21 2009-10-14 中国建设银行股份有限公司 Method, device and auditing system for establishing auditing model
CN105787259A (en) * 2016-02-17 2016-07-20 国网甘肃省电力公司武威供电公司 Method for analyzing influence correlation of multiple meteorological factors and load changes
CN106776868A (en) * 2016-11-29 2017-05-31 浙江工业大学 A kind of restaurant score in predicting method based on multiple linear regression model
CN109753684A (en) * 2018-11-29 2019-05-14 国网江苏省电力有限公司盐城供电分公司 One kind being used for the modified multiple linear regression modeling method of substation's energy consumption benchmark

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101556666A (en) * 2009-05-21 2009-10-14 中国建设银行股份有限公司 Method, device and auditing system for establishing auditing model
CN105787259A (en) * 2016-02-17 2016-07-20 国网甘肃省电力公司武威供电公司 Method for analyzing influence correlation of multiple meteorological factors and load changes
CN106776868A (en) * 2016-11-29 2017-05-31 浙江工业大学 A kind of restaurant score in predicting method based on multiple linear regression model
CN109753684A (en) * 2018-11-29 2019-05-14 国网江苏省电力有限公司盐城供电分公司 One kind being used for the modified multiple linear regression modeling method of substation's energy consumption benchmark

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
刘珈菱: "A+H股交叉上市对会计信息质量的影响研究", 《中国优秀硕士学位论文全文数据库经济与管理科学辑》, no. 2, pages 152 - 3209 *

Also Published As

Publication number Publication date
CN112101770B (en) 2023-07-18

Similar Documents

Publication Publication Date Title
Damgaard et al. What is real and what is not in the global FDI network?
CN108564286B (en) Artificial intelligent financial wind-control credit assessment method and system based on big data credit investigation
CN110188198B (en) Anti-fraud method and device based on knowledge graph
Abdul Hameed et al. Assessing the influence of environmental and CEO characteristics for adoption of information technology in organizations
US20090287509A1 (en) Method and system for automating insurance claims processing
Alsmairat et al. The effect of audit tenure and audit firm size on the audit quality: evidence from Jordanian auditors
CN106651584B (en) Investment management system
Alrashidi et al. The impact of big data analytics on audit procedures: Evidence from the Middle East
CN109508825A (en) Employee's image method for prewarning risk and relevant apparatus
Rashedi et al. How influence the accounting information systems quality of internal control on financial reporting quality
US20100121746A1 (en) Financial statement risk assessment and management system and method
Özdemir et al. The Effects of the Degree of Internationalization on Export Performance: A Research on Exporters in Turkey 1
Owais et al. Readiness and challenges for applying IFRS 17 (insurance contracts): The case of Jordanian insurance companies
CN111563673A (en) Computer technology digitization degree evaluation method and device
Herraiz et al. Impact of installation counts on perceived quality: A case study on debian
CN114493686A (en) Operation content generation and pushing method and device
CN110544052A (en) method and device for displaying relationship network diagram
CN114004691A (en) Line scoring method, device, equipment and storage medium based on fusion algorithm
CN112287039A (en) Group partner identification method and related device
CN112101770A (en) Audit quality model generation method and device and audit quality prediction method
De Stefano et al. Information communication technologies and firm performance: evidence for UK firms
Silva et al. Collaborative risk management in software projects
Albawwat External auditors' reliance on the internal audit functions and audit fees
Bright et al. Explaining download patterns in open government data: citizen participation or private enterprise?
Yuan et al. Critical risks identification of Public Private Partnerships in China and the analysis on questionnaire survey

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