Science and technology play a great role in promoting the development of society. To promote the development of science and technology in Maoming, this paper employs econometric methods to carry out a quantitative analysis of the influencing factors of science and technology development in Maoming. In the regression analysis, all variables were tested, unreasonable variables were deleted, the model was modified, and tests such as heteroscedasticity a nd autocorrelation were performed on the modified model. The regression results show that: the number of people engaged in scientific and technological activities in Maoming is directly proportional to the number of students in ordinary colleges and universities, and there is a relatively stable positive correlation between them. Therefore, in order to promote the development of science and technology in Maoming, we should vigorously develop higher education in Maoming.
Scientific and technological resources are the precious wealth of human society, and have become the first resource of economic society. The development of science and technology represents innovation. Innovation is the soul of national progress and an inexhaustible driving force for the country’s prosperity. The key to innovation lies in scientific and technological personnel. How to strengthen the cultivation of scientific and technological innovation talents has become a strategic issue related to the national economy and people’s livelihood, and the key to solving this problem lies in the realization of education.
Liao et al. (2013) proposed that humanities education is of great significance to the cultivation of scientific and technological innovative talents. Humanistic education can effectively shape the independent personality of scientific and technological innovation talents, help them to establish correct values, noble moral quality and healthy psychological state; help to improve the innovative ability of scientific and technological innovation talents, stimulate innovative thinking and innovative spirit, and optimize innovative methods. Promote the comprehensive and healthy development of scientific and technological innovation talents. Tao & Meng (2014) also analyzed with the reform of German higher education in the 19th century. He believes that strengthening the comprehensive national strength depends on science and technology. The development of science and technology depends on the talents who master the science and technology. The cultivation of talents depends on education, especially higher education, which is in a dominant position and shoulders the task of cultivating high-quality and high-level talents.
At the same time, some scholars have proved through empirical research that the contribution rate of scientific and technological talents to economic growth generally shows an upward trend (Chen, Xiao, & Zhu, 2011) . For contemporary education, modern science education has developed into science and technology education, which plays an important role in cultivating students’ innovation and scientific inquiry capabilities. In terms of a relatively balanced level of education, the development of higher education is more urgent to accumulate a large amount of human capital, which has played a key role in economic development and reform and innovation. At the same time, some scholars have raised the issue of the quality view of higher education (Liao, 2012) . The development of science and technology must promote the process of popularization of higher education. It is necessary to establish a quality view of development, a diversified quality view, and an overall quality view. We must correctly handle the relationship between higher education development and economic growth, and increase investment in higher education (Chen, Fu, & Fu, 2008) . The purpose of education is ultimately to develop science and technology, to cultivate innovative ability and innovation awareness. The degree of development of scientific research technology directly affects the construction and development of the entire national innovation system, and is also the driving force to lead and support regional economic development.
Both for regional development and the development of a country, education and science and technology are two extremely important factors for development. Therefore, it is necessary to investigate the relationship between the two through different methods.
This article collects relevant data, establishes a model, and conducts an econometric analysis of the number of science and technology activities in Maoming and the number of people educated at different stages. After obtaining the relationship between the personnel engaged in scientific and technological activities and the number of people educated at each stage, according to the size of each factor coefficient in the model equation, analyze the main and secondary factors, so as to find the main starting point for the development of science and education in Maoming, and give some suggestions to develop science and education in Maoming.
Maoming is a prefecture-level city with a large population in Guangdong Province and a city with strong economic strength in the eastern and western regions of Guangdong. Its GDP has ranked first in eastern and western Guangdong for 14 consecutive years. At the same time, Maoming is the largest petrochemical base in South China, an important petrochemical production and export base in southern China, and an energy base in Guangdong Province. However, the current state of science and education in such a vibrant city is thought-provoking.
Through the above analysis we introduce 3 independent variables for analysis:
Y is said to engage in scientific and technological activities (person). Β indicates that the other explanatory variables remain unchanged Xi per unit of change, Y average changes. X1 is the number of students in ordinary colleges and universities (person). X2 is indicates the number of students in secondary schools (person). X3 is indicates the number of pupils in primary schools (person). µ is random error term.
According to the introduction of the variables set the following model.
Y = β 0 + β 1 X 1 + β 2 X 2 + β 3 X 3 + μ
Here are data of social science and technology information from 1995 to 2012 (
The estimation results are shown in
Model estimation can be got in the following.
Y = 4175.645 + 0.3979 X 1 − 0.0161 X 2 + 0.003 X 3 + μ ( 1.8930 ) ( 3.246 ) ( − 2.8102 ) ( 1.1445 )
R 2 = 0.5251 , F = 5.1591 , n = 18
| Index Year | Number of students in regular colleges and universities | Number of students in secondary schools | specialized middle school (ten thousand) | Secondary vocational schools (ten thousand) | Technical School (ten thousand) | Ordinary middle school (ten thousand) | Primary school students | Technologists |
|---|---|---|---|---|---|---|---|---|
| 1995 | 1512 | 275,100 | 0.95 | 0.45 | 0.19 | 25.92 | 753,900 | 1324 |
| 1996 | 1560 | 302,000 | 1.14 | 0.33 | 0.27 | 28.46 | 786,900 | 2057 |
| 1997 | 1162 | 324,800 | 1.06 | 0.29 | 0.38 | 30.75 | 817,400 | 1966 |
| 1998 | 1147 | 345,300 | 1.18 | 0.33 | 0.51 | 32.51 | 834,900 | 2154 |
| 1999 | 3078 | 368,500 | 1.14 | 0.42 | 0.40 | 34.89 | 852,300 | 3354 |
| 2000 | 7975 | 405,700 | 0.88 | 0.54 | 0.45 | 38.70 | 858,400 | 2744 |
| 2001 | 9512 | 439,900 | 0.85 | 0.62 | 0.66 | 41.86 | 925,300 | 3239 |
| 2002 | 10,170 | 479,700 | 0.77 | 0.68 | 0.68 | 45.84 | 928,800 | 3533 |
| 2003 | 11,471 | 537,600 | 0.89 | 2.58 | 0.98 | 49.31 | 923,800 | 4835 |
| 2004 | 14,376 | 583,500 | 0.76 | 3.00 | 1.36 | 53.23 | 959,400 | 3018 |
| 2005 | 14,954 | 626,300 | 0.63 | 4.00 | 1.44 | 56.56 | 948,900 | 2584 |
| 2006 | 15,968 | 672,600 | 0.57 | 4.96 | 1.41 | 60.32 | 932,400 | 2103 |
| 2007 | 19,244 | 712,600 | 0.78 | 6.01 | 1.78 | 62.69 | 878,700 | 2443 |
| 2008 | 19,782 | 752,700 | 0.99 | 7.75 | 1.94 | 64.59 | 801,100 | 2486 |
| 2009 | 23,151 | 785,300 | 1.25 | 9.09 | 2.84 | 65.35 | 724,500 | 2877 |
| 2010 | 26,967 | 810,100 | 1.35 | 14.49 | 3.65 | 65.52 | 666,600 | 2618 |
| 2011 | 27,256 | 834,700 | 1.53 | 13.85 | 3.58 | 64.51 | 624,100 | 3645 |
| 2012 | 30,180 | 774,200 | 1.50 | 11.87 | 3.12 | 60.93 | 598,000 | 6810 |
| Dependent Variable: Y Method: Least Squares Date: 11/27/15 Time: 21:26 Sample: 118 Included observations: 18 | ||||
|---|---|---|---|---|
| Coefficient | Std. Error | t-Statistic | Prob. | |
| C | 4175.645 | 2205.871 | 1.892969 | 0.0792 |
| X1 | 0.397900 | 0.122581 | 3.246016 | 0.0059 |
| X2 X3 | −0.016104 0.003029 | 0.005731 0.002647 | −2.810205 1.144530 | 0.0139 0.2716 |
| R-squared | 0.525057 | Mean dependent var | 2988.333 | |
| Adjusted R-squared | 0.423284 | S.D. dependent var | 1237.301 | |
| S.E. of regression | 939.6293 | Akaike info criterion | 16.72198 | |
| Sum squared resid | 12360645 | Schwarz criterion | 16.91984 | |
| Log likelihood | −146.4978 | Hannan-Quinn criter. | 16.74926 | |
| F-statistic | 5.159079 | Durbin-Watson stat | 1.634252 | |
| Prob (F-statistic) | 0.013082 | |||
1) β0 = 4175.645, that is when the number of people in different stages of education to maintain the original size, Maoming city engaged in scientific and technological activities have about 4175 people. This result is consistent with reality. It is reasonable.
2) β1 = 0.3979. In the case of other conditions unchanged, the number of ordinary colleges and universities in the number of students per 1, engaged in scientific and technological activities increased by 0.3979. The positive correlation between the two was in line with the economic reality.
3) β2 = −0.0161. In the case of other conditions unchanged, the number of students in secondary schools increased by 1, and the number of students in the middle school was reduced by 0.0161. The negative correlation between the two is not consistent with the reality. Should consider adjusting variables or deleting variables.
4) β3 = 0.003. In the case of other conditions unchanged, the number of primary school students increased by 1, the number of personnel engaged in scientific and technological activities increased by 0.003. The results are in line with reality, and it is reasonable.
1) Sample determination coefficient.
The value of R2 is close to 1, which indicates that the fitting degree of regression line to the observation value is better; otherwise, the value of R2 is close to 0, which indicates that the fitting degree of regression line is worse. The results obtained by the 1 parameter estimation can be obtained, and the sample decision factor R2 = 0.5251 can be seen that the model fit is poor.
2) Adjusted sample coefficient.
Because the explanatory variables are multivariate, the adjusted goodness of fit is used to eliminate the influence of explanatory variables on the goodness of fit. After adjusting the R2 = 0.4232, the fitting degree of the observed values of the regression line is poor.
1) Multiple linear test.
a) Test.
According to the output results of
From the data in the table, the correlation coefficient between X1 and X2 is higher, and there is a high correlation.
| X1 | X2 | X3 | |
|---|---|---|---|
| X1 | 1.000000 | 0.972687 | −0.492280 |
| X2 | 0.972687 | 1.000000 | −0.383061 |
| X3 | −0.492280 | −0.383061 | 1.000000 |
b) Fixed.
The use of stepwise regression method to remedy. Because the X1 linear relationship is strong and the fitting degree is good, the X1 is used as the basic variable, and then the other explanatory variables are brought into the X1 regression equation,
Y = 2126.201 + 0.0648 X 1 ( 4.7243 ) ( 2.3439 )
R 2 = 0.2556 , F = 5.4941
Y = 5978.372 + 0.3196 X 1 − 0.0130 X 2 ( 3 . 8318 ) ( 3 . 11 0 2 ) ( − 2 . 5492 )
R 2 = 0.4806 , F = 6.9402
After comparison, it can be seen that the model fit is improved with the increase of X2, and the variables are passed t test, but the parameters are not reasonable. Get rid of X3, the introduction of X2. It is shown in
Y = 2572.605 + 0.0620 X 1 − 0.0004 X 3 ( 0.9992 ) ( 1.8907 ) ( − 0.1763 )
R 2 = 0.2571 , F = 2.5962
Goodness of fit was decreased, and the parameters of the parameters were not consistent with the actual, and the F statistics were decreased. Remove X3.
| Dependent Variable: Y Method: Least Squares Date: 11/29/15 Time: 16:57 Sample: 118 Included observations: 18 | ||||
|---|---|---|---|---|
| Coefficient | Std. Error | t-Statistic | Prob. | |
| C | 2126.201 | 450.0607 | 4.724255 | 0.0002 |
| X1 | 0.064804 | 0.027648 | 2.343940 | 0.0323 |
| R-squared | 0.255608 | Mean dependent var | 2988.333 | |
| Adjusted R-squared | 0.209084 | S.D. dependent var | 1237.301 | |
| S.E. of regression | 1100.375 | Akaike info criterion | 16.94913 | |
| Sum squared resid | 19,373,204 | Schwarz criterion | 17.04806 | |
| Log likelihood | −150.5422 | Hannan-Quinn criter. | 16.96277 | |
| F-statistic | 5.494057 | Durbin-Watson stat | 0.981010 | |
| Prob (F-statistic) | 0.032321 | |||
| Dependent Variable: Y Method: Least Squares Date: 11/29/15 Time: 17:03 Sample: 118 Included observations: 18 | ||||
|---|---|---|---|---|
| Coefficient | Std. Error | t-Statistic | Prob. | |
| C | 5978.372 | 1560.216 | 3.831760 | 0.0016 |
| X1 | 0.319590 | 0.102754 | 3.110241 | 0.0072 |
| X2 | −0.012995 | 0.005098 | −2.549193 | 0.0222 |
| R-squared | 0.480618 | Mean dependent var | 2988.333 | |
| Adjusted R-squared | 0.411367 | S.D. dependent var | 1237.301 | |
| S.E. of regression | 949.2876 | Akaike info criterion | 16.70031 | |
| Sum squared resid | 13,517,203 | Schwarz criterion | 16.84871 | |
| Log likelihood | −147.3028 | Hannan-Quinn criter. | 16.72077 | |
| F-statistic | 6.940235 | Durbin-Watson stat | 1.351473 | |
| Prob (F-statistic) | 0.007348 | |||
Therefore, the final function expression is Y = f ( X 1 ) is the best. The fitting results are as follows:
| Dependent Variable: Y | ||||
|---|---|---|---|---|
| Method: Least Squares | ||||
| Date: 11/29/15 Time: 17:13 | ||||
| Sample: 118 | ||||
| Included observations: 18 | ||||
| Coefficient | Std. Error | t-Statistic | Prob. | |
| C | 2572.605 | 2574.540 | 0.999249 | 0.3335 |
| X1 | 0.061961 | 0.032771 | 1.890731 | 0.0781 |
| X3 | −0.000496 | 0.002816 | −0.176283 | 0.8624 |
| R-squared | 0.257147 | Mean dependent var | 2988.333 | |
| Adjusted R-squared | 0.158100 | S.D. dependent var | 1237.301 | |
| S.E. of regression | 1135.287 | Akaike info criterion | 17.05817 | |
| Sum squared resid | 19,333,151 | Schwarz criterion | 17.20657 | |
| Log likelihood | −150.5235 | Hannan-Quinn criter. | 17.07863 | |
| F-statistic | 2.596212 | Durbin-Watson stat | 0.978145 | |
| Prob (F-statistic) | 0.107590 | |||
| Heteroscedasticity test: White | |||||||
|---|---|---|---|---|---|---|---|
| F-statistic | 3.338013 | Prob.F(2,15) | 0.0632 | ||||
| Obs*R-squared | 5.543842 | Prob.Chi-Square(2) | 0.0625 | ||||
| Scaled explained SS | 6.008799 | Prob.Chi-Square(2) | 0.04 | ||||
| Test Equation: | |||||||
| Dependent Variable: RESID^2 | |||||||
| Method: Least Squares | |||||||
| Date: 11/29/15 Time: 19:38 | |||||||
| Sample: 118 | |||||||
| Included observations: 18 | |||||||
| Coeffcient | Std. Error | t-Statistic | Prob. | ||||
| C | 774824.9 | 872394.2 | 0.888159 | 0.3885 | |||
| X1 | −120.5674 | 144.3419 | −0.835291 | 0.4167 | |||
| X 1 2 | 0.007191 | 0.004817 | 1.492622 | 0.1563 | |||
| R-squared | 0.307991 | Mean dependent var | 1,076,289 | ||||
| Adjusted R-squared | 0.215723 | S.D. dependent var | 1,834,411 | ||||
| S.E. of regression | 1,624,543 | Akaike info criterion | 31.59036 | ||||
| Sum squared resid | 3.96E+13 | Schwarz criterion | 31.73876 | ||||
| Log likelihood | −281.3133 | Hannan-Quinn criter | 31.61083 | ||||
| F-statistic | 3.338013 | Durbin-Watson stat | 1.947175 | ||||
| Prob (F-statistic) | 0.063217 | ||||||
Y = 2126.201 + 0.0648 X 1 ( 4.7243 ) ( 2.3439 )
R 2 = 0.2556 , F = 5.4941
2) Heteroscedasticity test (
This shows that the model has no heteroscedasticity.
3) First-order autocorrelation test.
It can be judged that the model does not have autocorrelation.
So, it can be got as following.
Y = 2126.201 + 0.0648 X 1
Through the study of this model and the analysis of different test results, it can be seen that education is important for scientific research, especially in higher education. We should regard the development of higher education as the main means of revitalizing the country and increase investment in scientific research in higher education institutions in order to better absorb talents. At the same time, correct the thinking of teachers and students. Teachers are not only disseminators of knowledge, but also scholars who lead students to explore unknown fields. Students are not only to receive knowledge, but also to learn how to freely and creatively explore the frontiers of knowledge. Only in this way can we create a good research atmosphere. The development of Maoming technology must first promote the construction of basic education, especially increase the popularization of higher education, and lay a good foundation for the scientific research development of Maoming. Only in this way can more technological talents serve the development of the economy and society.
This research was financially supported by Scientific Research Project of Lingnan Normal University. The project is Research on Economic Growth in Underdeveloped Areas (Xu Yanli, Grant No. ZW1807).
It is a pleasure to acknowledge the support of the project from Xu Yanli being selected in the introduction of shortage top talent of “Yangfan (Sailing up) project” in Guangdong Province in 2014. The project is Leading Industry Development Strategy Research in Emerging Areas in Western Guangdong for Accelerating the Economic Development of Western Guangdong.
It is also a pleasure to acknowledge the support from the talents introduction project of universities in Guangdong Province.
It is also a pleasure to acknowledge the support from the following projects: 1) Excellent Course “Macroeconomics” in Teaching Quality and Teaching Reform Project in Lingnan Normal University in 2017 (Grant No. 114961700227); 2) Comprehensive reform experiment of International Economics and Trade major in Guangdong University of Petrochemical Technology; 3) International Education Department in Guangdong University of Petrochemical Technology. The project is Research on Teaching Quality Evaluation for the major International Economics and Trade in English in the Background of International Education (Grant No. 2014GDUPTGJ-07).
This research is supported by Guangdong Coastal Economic Belt Development Research Center, Lingnan Normal University (Grant No. 20223L08, Grant No. 20191L01).
The authors declare no conflicts of interest regarding the publication of this paper.
Xu, Y. L., Huang, F., Dai, Z. R., & Liu, D. (2023). Econometric Analysis on Education and Technology in Maoming. Modern Economy, 14, 1610-1619. https://doi.org/10.4236/me.2023.1411084