Adoption of ISO9000

Chinese Service Industry

Executive Summary

The ISO 9000 series of quality management systems standard has been widely applied all over the world since its introduction in 1987. By the end of 2013, ISO 9000 had been adopted by over 1,129,000 facilities in 189 countries. Both academics and practitioners are interested in understanding the relationship between adoption of ISO 9000, and other factors (Christmann & Taylor, 2006; Du, Yin, & Zhang, 2016; Fikru, 2014a, 2014b, 2016; Nakamura, Takahashi, & Vertinsky, 2001; Pekovic, 2010; Wu, Chu, & Liu, 2007).

In 2008, the National Bureau of Statistics of China conducted an Economic Census of the service firms. The descriptions of variables, the coding are shown in the table which is available in Appendices section. The data for these variables has been sourced from Moodle.

Some of the data from National Bureau of Statistics of China was analysed through quantitative methods to draw conclusions about the Chinese service industry with respect to adoption of ISO9000. The analysis indicated that ISO certification in fact, makes a difference to a firm particularly its key financial numbers. 

However, this analysis is based on a slice of limited informational data that can be further expanded to include more classifications of industries as well as geographies to further validate the results. 

Additionally, the statistical assumptions behind a statistical tool also need to be considered. Further, more variety of statistical tools can be added to make it more comprehensive. 

Apart from the quantitative methods, qualitative methods will add much more value in terms of opinions of the people in these firms and their views regarding importance of ISO 9000 and its corresponding impact.

Introduction

The ISO 9000 series of quality management systems standard has been widely applied all over the world since its introduction in 1987. By the end of 2013, ISO 9000 had been adopted by over 1,129,000 facilities in 189 countries. Both academics and practitioners are interested in understanding the relationship between adoption of ISO 9000, and other factors (Christmann & Taylor, 2006; Du, Yin, & Zhang, 2016; Fikru, 2014a, 2014b, 2016; Nakamura, Takahashi, & Vertinsky, 2001; Pekovic, 2010; Wu, Chu, & Liu, 2007). 

In 2008, the National Bureau of Statistics of China conducted an Economic Census of the service firms. The descriptions of variables, the coding are shown in the table which is available in Appendices section. The data for these variables has been sourced from Moodle.

The above mentioned data will be analysed to draw conclusions about the Chinese service industry with respect to adoption of ISO9000. For this purpose, Microsoft Excel and in-built tools such as correlation, regression and ANOVA testing will be used so as to see statistical viability of the drawn conclusions.

The above analysed data will be then used to draw conclusions about the Chinese service industry along with recommendations and limitations of the research.

Methodology

As mentioned above, the research methodology utilized is quantitative in nature such that the data related to variables as available in Appendices section will be analysed. The data used for the purpose of this research project is secondary data in nature as it is available on websites such as, Moodle.

For the purpose of data analysis, Microsoft Excel and its inbuilt data tools will be used such as, Descriptive Statistics, ANOVA, Regression, Correlation etc. Sample characteristics will be described with descriptive analysis. This will include at least the following analysis: Frequency, percentage; Measures of central tendency; Measures of dispersion (variance, standard deviation). Inferential statistics will be used to analyse relationship between variables. This will include at least the following analysis (Chi-square, Pearson’s r, t-test, ANOVA test). 

Effort will also be made to understand the statistical significance of conclusions and analysis drawn basis the mentioned data.

Analysis and Findings

Descriptive Statistics

The Descriptive Statistics data tool in Microsoft Excel was used on all the available variables to generate various sample characteristics, such as, mean, median, mode, frequency, standard deviation, variance, kurtosis, skewness etc. The details are available in Appendices section.

Maximum sample data is from business services as can be seen from Industry mode of 74 which is the classification code for business services. Also, maximum number of companies seems to have been founded in 2006. Average age of the firms is 7.62 years.

Average number of employees is 45 with an average of 1.4 (or 1) employee with master or doctor. It seems maximum employees have a diploma with the mean number being 12.9 (or 13). The next most popular level of education is bachelor (average of 11.9) and high school (average of 12.3). 

Average revenue is 11,698.57 with average profit being 2,067.97 and average total assets at 16,473.16. The average equity of the company and average total capital stand at 7,693.77 and 4,765.67, respectively.

Inferential Statistics

Inferential statistics will be used to analyse relationship between variables. This will include at least the following analysis (Chi-square, Pearson’s r, t-test, ANOVA test). 

ANOVA

The first technique used is ANOVA test which is part of data tools in Microsoft Excel. The factors assessed include Certification, that is, whether a company is ISO certified or not and Operating Profit of various types of services companies. The output of ANOVA test is available in Appendices section.

Under the assessment whether there is significance variance between groups that are certified (1) and not certified (0), variables analysed include: Operating Profit, Number of Employees, Return on Assets and Age of the Firm.

At an assumed significance level of α = 0.05, it was found that: 

• There is significant difference in means of operating profit of groups that are not ISO certified and that are ISO certified. This can be concluded from p-value which is less than significance level of 0.05.
• There is significant difference in means of number of employees of groups that are not ISO certified and that are ISO certified. This can be concluded from p-value which is less than significance level of 0.05.
• There is significant difference in means of RoA of groups that are not ISO certified and that are ISO certified. This can be concluded from p-value which is less than significance level of 0.05.
• There is significant difference in means of age of firms of groups that are not ISO certified and that are ISO certified. This can be concluded from p-value which is less than significance level of 0.05.

Hence, it seems that the ISO certification influences above factors as the groups with certification reported much higher average profits, number of employees, and firm age. However, firms with ISO certification reported lower average RoA.

Another ANOVA test was performed to check variance in means of operating profits of various types of firms categorized through classification codes.

Again, it was found that there is significant difference in means of operating profits between various classifications. However, in order to find which group has significantly different mean, post hoc tests will need to be performed. At a glance, the highest average operating profit was reported for classification code 60 that is for telecommunication industry. 

Correlation

The correlation matrix is available in Appendices. The Pearson’s correlation (r ) is measured on a scale of -1 to 1 with -1 indicating strongest inverse relationship and 1 indicating strongest direct relationship between any two selected variables.

Regression

Since the major objective of a firm is to maximize its profits and profit remains centric to all the efforts of a firm, the dependent variable was selected as operating profit. The independent variables included: certification, industry classification, number of employees, number of employees with master or doctor, number of employees with junior high school or below, revenue, Return on Assets, percentage of overseas investment in total investment, overseas investment dummy and age of the firm. The regression output is available in the Appendices section.

We can say that the Operating Profit is regressed on certification, industry classification, number of employees, number of employees with master or doctor, number of employees with junior high school or below, revenue, Return on Assets, percentage of overseas investment in total investment, overseas investment dummy and age of the firm.

From the output, we can interpret the least squares regression equation as follows:

y^{^} = 136.28 – 929.92 x₁ – 17.10 x₂ + 9.60 x₃ + 7.55 x₄ – 11.41 x₅ + 0.16 x₆ + 4025.05 x₇ – 2935.14 x₈ + 2343.72 x₉ + 17.37 x₁₀

where,

• Dependent variable, Operating Profit is represented as: y^{^} 
• Independent variable, Certification is represented as x₁ 
• Independent variable, Industry Classification is represented as x₂ 
• Independent variable, Number of Employees is represented as x₃ 
• Independent variable, Number of Employees with Master/Doctor is represented as x₄ 
• Independent variable, Number of Employees with Junior High School/Below is represented as x₅ 
• Independent variable, Revenue is represented as x₆ 
• Independent variable, Return on Assets is represented as x₇ 
• Independent variable, Percentage of Overseas Investment is represented as x₈ 
• Independent variable, Overseas Investment Dummy is represented as x₉ 
• Independent variable, Age of Firm is represented as x₁₀ 

The above equation has a constant of 136.28 which is also known as Y-intercept coefficient. It is the minimum value for y even when all x values are zero. It is the point where regression line crosses the vertical axis and is also known as ‘β₀’ or ‘constant’. 

x₃, x₄, x₆, x₇, x₉ ,and x₁₀ are greater than zero indicating that the relationship is positive such that x and y increase or decrease together. The remaining independent variables are lesser than zero indicating that the relationship is negative such that as x increases, y decreases and vice versa.

The output above provides coefficients as well some other statistically significant information, such as p-values for each of the coefficients. These values help in determining whether the variable has statistically significant relationship with the dependent variable or not.

Each of the p-value entails a null hypothesis that the variable has no correlation with the dependent variable. The alternative hypothesis is that the variable has correlation with the dependent variable. This null hypothesis can be rejected if the p-value for a coefficient is less than the significance level in consideration. Hence, in such a case, we can conclude that the particular variable has a correlation with the dependent variable. The assumed significance level is 0.05 for this research study. The p-values for various coefficients are:

• x₁ : 0.000, which is less than 0.05 Hence, the variable is statistically significant.
• x₂ : 0.076, which is greater than 0.05. Hence, the variable is not statistically significant.
• x₃ : 0.000, which is less than 0.05 Hence, the variable is statistically significant.
• x₄ : 0.531, which is greater than 0.05. Hence, the variable is not statistically significant.
• x₅ : 0.000, which is less than 0.05 Hence, the variable is statistically significant.
• x₆ : 0.000, which is less than 0.05 Hence, the variable is statistically significant.
• x₇ : 0.000, which is less than 0.05 Hence, the variable is statistically significant.
• x₈ : 0.009, which is less than 0.05. Hence, the variable is statistically significant.
• x₉ : 0.017, which is less than 0.05 Hence, the variable is statistically significant.
• x₁₀ : 0.047, which is less than 0.05. Hence, the variable is statistically significant.

The values of R and R² help in determining the degree of relationship between independent and dependent variables. These are also called as Coefficients of Determination.

In the given case, R value is 0.78 which indicates that there is high degree of correlation between the variables in consideration. R² is at 0.60 with adjusted R² being 0.60. The value of R² is nothing but the proportion of change in dependent variable that can be explained through the independent variables. As can be seen, at 60.0%, a high proportion of change in value of ‘Operating Profit’ can be attributed to change in independent variables, namely, certification, industry classification, number of employees, number of employees with master or doctor, number of employees with junior high school or below, revenue, Return on Assets, percentage of overseas investment in total investment, overseas investment dummy and age of the firm.

Limitations and Directions for Future Research

The above analysis indicates that ISO certification in fact, makes a difference to a firm particularly its key financial numbers. However, this analysis is based on a slice of limited informational data as extracted from Moodle.  It can be further expanded to include more classifications of industries as well as geographies to further validate the results. Additionally, the statisticall assumptions behind a statistical tool also need to be considered. If an assumption is breached, the results of the test may not be sensible or useful even when it is statistically significant. Hence, research can be expanded to test the assumptions. Further, more variety of statistical tools can be added to make it more comprehensive. Apart from the quantitative methods, qualitative methods will add much more value in terms of opinions of the people in these firms and their views regarding importance of ISO 9000 and its corresponding impact.

Appendices

Table: Variables, their descriptions and coding

Descriptive Analysis

ANOVA

Regression

Correlation