tiểu luận kinh tế lượng FACTORS AFFECTING GPA OF FOREIGN TRADE UNIVERSITY STUDENTS IN 2019

FOREIGN TRADE UNIVERSITY FACULTY OF INTERNATIONAL ECONOMICS =====o0o===== ECONOMETRIC REPORT Topic: FACTORS AFFECTING GPA OF FOREIGN TRADE UNIVERSITY STUDENTS IN 2019 Group: Class: English - VJCC - K57 Members: Lê Thị Thu Phương - 1815520216 Nguyễn Hải Linh - 1815520191 Nguyễn Minh Trang - 1815520232 Instructor: Ph.D Từ Thúy Anh Hanoi, October 2019 Table of Contents ABSTRACT INTRODUCTION LITERATURE REVIEW I Questions of interest II Procedure and software used THEORETICAL BACKGROUND I Research history in the world II Research history in Vietnam III Econometrics Methodology Specifying the object for modeling Defining the target for modeling by the choice of the variables to analyze Econometric Model 10 Model specification 11 Estimation technique 11 DATA DESCRIPTION 13 I DATA OVERVIEW 13 II ESTIMATION OF ECONOMETRIC MODEL 14 Checking the correlation among variables 14 Regression model 16 III CHECK MULTICOLLINEARITY, NORMALITY OF RESIDUAL AND HETEROSCEDASTICITY Multicollinearity 20 20 Normality of residual 22 Heteroscedasticity 23 Statistical significance of model (using F – test) 25 Statistical significance of variables (using T-test) 25 CONCLUSION 27 REFERENCES 28 Exhibit 1: Summary statistics of variables in the GPA model 13 Exhibit 2: The - max - median value of each variable 14 Exhibit 3: Correlation matrix 15 Exhibit 4: Scatterplot of variables in GPA model 16 Exhibit 5: Ordinary Least Square Model 17 Exhibit 6: Ordinary Least Square Model Explanation 18 Exhibit 7: Multicollinearity test 21 Exhibit 8: Result of White’s test 24 ABSTRACT With the increasing diversity of students attending university, there is a growing interest in the factors predicting academic performance This study analyzes the effect of gender, working hours (part-time jobs), times absence, self-study hours, marital status (having boyfriend/girlfriend), extra activities participation hours on the total GPA of Foreign Trade University (FTU) students in 2018 We have conducted a survey with online questionnaire to collect data of 50 FTU students, their overall grade point averages were collected at semester completion - which were used to estimate multiple linear regression models The results showed some significant evidence for the hypothesis, concluding that the number of times absence is more likely to affect GPA with high significance The gender variable is shown to affect GPA less importantly Identifying the factors that influence academic performance (GPA scores in particular) can improve the targeting of interventions and support services for students at risk of academic problems INTRODUCTION Econometrics is the study of the social science in which the tools of economic theory, mathematics and statistical speculation are applied to analyze economic problems Econometrics uses the mathematical statistics methods to find out the essence of statistics, make conclusions about the collected statistics that can make predictions about economic phenomenon As much as Economy is a meaningful science that determines the social development in general and national growth in particular, Econometrics is the use of statistical techniques to understand those issues and test theories Without evidence, economic theories are abstract and might have no bearing on reality (even if they are completely rigorous) Econometrics is a set of tools we can use to confront theory with real-world data Since its inception, econometrics has provided economists with a sharp instrument for measuring economic relations As economics students, we recognize the need to study and learn about Econometrics in logical and problem analysis To better understand how to put the Econometrics into reality and to apply the Econometrics effectively and correctly, our team would like to develop the econometrics report to analyze the topic "Factors that affects Foreign Trade University students’ GPA in 2019" Our groups follows the methodology of econometric comprising eight steps to analyze the data Note that because of the lack of information on the data set, all inferences of abbreviations and others are based on assumptions and self-research As a result, we hope to have shown clearly our logic and reasoning of analysis To the extent of purpose and resources, there are still deficiencies in this report, but we look forward to providing readers with a decent view of the overall of the data set given and the knowledge that we have gained through Ph.D Tu Thuy Anh’s Econometrics course LITERATURE REVIEW Grade Point Average is a number representing the average value of the accumulated final grades earned in courses over time More commonly called a GPA, a student’s grade point average is calculated by adding up all accumulated final grades and dividing that figure by the number of grades awarded This calculation results in a mathematical mean — or average—of all final grades The most common form of GPA is based on a to 4.0 scale (A = 4.0, B = 3.0, C = 2.0, D = 1.0, and F = 0), with a 4.0 representing a “perfect” GPA— or a student having earned straight As in every course GPA is the main criteria used to assess and rank students applied in most universities in Vietnam Today, in the context of fierce competition in the job market, the requirement for job seekers is increasing, so as soon as they enter colleges, students need to set themselves a certain goals to strive for In most universities including Foreign Trade University in particular, the average score is used as a main criterion to consider the type of diploma Some companies and employers also set a minimum average score as a way to decide the number of candidates who apply for a position In addition, many students desire to continue studying at higher levels or win scholarships to study abroad after graduation Therefore GPA is highly valued at the time because it is considered a factor that plays a important role in the achievement of these goals I Questions of interest Because this score is calculated by dividing the total score of the subjects, to achieve a high average, it is necessary to strive continuously throughout the university In fact, there are always students with high scores, and a lot of students not Most students think that focusing on studying will get good results, but there are some who find themselves studying hard but still not achieving the desiring grades From that fact, a question arose: “What is the student's average score determined by?” - which is the basic question to which this report targets to find the answer Understanding these factors can help students have a clearer direction when pursuing their target GPA II Procedure and software used ● Procedure Step 1: Questions of interest Step 2: Online questionnaire Step 3: Econometric model Step 4: Data collection Step 5: Estimation of econometric model Step 6: Check multicollinearity and heteroscedasticity Step 7: Hypothesis postulated Step 8: Result analysis ● Gretl software is primarily used to analyze the data and run the regression THEORETICAL BACKGROUND I Research history in the world According to Coleman’s (1961) zero-sum time-allocation model, working student’s GPA’s may be lower than GPA’s of students not working A Astin, 1977; Lunneborg et al., 1974 has indicated that women maintain higher GPAs than men Pantages and Creedon (1975) and Abbott-Chapman, Hughes, and Wyld (1992) found that students with poor study habits are more likely to withdraw from university or to have academic adjustment problems in the transition from high school to university Kirsten McKenZie & Robert Schweitzer (2001) identified full-time students with limited employment responsibilities will have higher GPA’s than full-time students with more demanding employment responsibilities According to Bratti and Staffolani (2002), student learning outcomes are largely determined by the student's learning attitude because the allocation of time for study depends on their decisions If Gi be the learning result of a student, depending on the time spent on self-study (Si), class time (who) and his ability (ei) then Gi = G (si, ai) ei Mussie T Tessema, Kathryn J Ready & Marzie Astani (2014) indicated work has positive effect on both satisfaction and GPA, when students did work fewer than 10 hours Thus, part-time job may not always be detrimental to students’ satisfaction However, when students work for more than 11 hours a week, students’ satisfaction and GPA were found to decline for each additional category of work, although the change is very small II Research history in Vietnam A number of studies in Vietnam have initiated this problem, such as Huynh Quang Minh (2002), a survey of factors affecting the academic performance of students at Ho Chi Minh City University of Agriculture and Forestry The study results (with significance level of about 10%) show that the average score of students in the second stage of semester is determined by the level of reading reference materials, class time, self-study time, average score whereas in the first stage is the number of drinks a month and the entrance examination scores Another study by Nguyen Thi Mai Trang, Nguyen Dinh Tho and Mai Le Thuy Van (2008) on the main factors affecting the learning knowledge of economic students The research results show that students' learning motivation has a strong impact on their acquired knowledge, faculty capacity has a high impact on learning motivation and learning knowledge of students Both elements: aim for studying and faculty capacity explain 75% of the variance of acquired knowledge Research gaps: Results of studies show that there are differences in academic results among different groups of students, resulting in heterogeneity of the influence of factors on academic performance of students III Econometrics Methodology Specifying the object for modeling GPA score = f (x) As such, this report finds the relationship between GPA scores, which is the object for modeling, and each of relating factors including sex, time spending, class attendance and marital status Defining the target for modeling by the choice of the variables to analyze As mentioned above, there are four main categories that are expected to affect GPA scores: sex, time spending, and marital status Hence, the choices of would be such variables that constitute them After thorough research, factors have been narrowed down to six significant ones: (sex) gender, (time spending) part-time job hours per day, extra- activities hours per week, self-studying hours per day, (class attendance) times absence and (marital status) having boyfriend/girlfriend A brief description of each variable: Variable Definition gpa Grade Point Average of FTU students in 2019 (mostly 2nd-year students) gender Male=1, female=0 parttime Hours per day for part-time jobs absence Times absence from class study study Hours per day for self-study lover Have boyfriend/girlfriend=1; if not=0 acts Hours per week for extra activities Econometric Model To demonstrate the relationship between GPA scores and other factors, the regression function can be constructed as follows: (PRF): Y (gpa) = + + + + + + + (SRF): ̂ ̂ ̂ ̂ ̂ Y (gpa) = +1+2+3+4+5+ ̂ + 10 * We also get the table of min, max and median of independent and dependent variables in Exhibit 2: Exhibit 2: The - max - median value of each variable Variable Min Max Median GPA 1.8 4.0 3.0 Gender Parttime 20 2.1 Absence 10 Study Lover Acts 100 II ESTIMATION OF ECONOMETRIC MODEL Checking the correlation among variables First of all, the correlation of GPA and Gender, Parttime, Absence, Study, Lover, Acts are checked by calculating the correlation coefficient among these variables The correlation coefficient r measures the strength and direction of a linear relationship between two variables The result is shown in Exhibit 3: 14 Exhibit 3: Correlation matrix From the matrix above, we have the correlation coefficient r 10, the model has the possibility of multicollinearity The Exhibit shows the result 20 Exhibit 7: Multicollinearity test ⇒ Given the hypothesis that: - Ho: There is no multicollinear problem with this set of data - H1: There is multicollinear problem with this set of data From the Exhibit 7, we can see: - VIF(Gender) = 1.100 < 10 - VIF(Parttime) = 1.050 < 10 - VIF(Absence) = 1.114 < 10 - VIF(Study) = 1.065 < 10 - VIF(Lover) = 1.182 < 10 - VIF(Acts) = 1.257 < 10 21 ⇒ We have enough evidence to not reject Ho We have enough evidence to conclude that Multicollinearity is not too worrisome a problem for this set of data Normality of residual - Given the hypothesis that: Ho: The residual has normality H1: The residual does not have normality - Using normality of residual in Gretl: 22 Test for null hypothesis of normal distribution: Chi-square(2) = 0.095 with p-value 0.95352 * We can see Chi-square(2) = 0.095 with p-value 0.95352 > 0.05 → We have enough evidence not to reject Ho We have enough evidence to conclude that the residual of this data set has normality Heteroscedasticity Heteroskedasticity indicates that the variance of the error term is not constant, which makes the least squares results no longer efficient and t tests and F tests results may be misleading The problem of Heteroskedasticity can be detected by plotting the residuals against each of the regressors, most popularly the White’s test It can be remedied by respecifying the model – look for other missing variables In Gretl, the intest white command is used, which stands for information matric test Given the hypothesis that: - Ho: The model does not have heteroskedasticity problem - H1: The model has heteroskedasticity problem Exhibit shows the result of White’s test: 23 Exhibit 8: Result of White’s test We can see p-value = p(Chi-square(25) > 14.871928) = 0.944325 > 0.05 → We have enough evidence not to reject Ho → We have enough evidence to conclude that the model does not have heteroskedasticity problem 24 Statistical significance of model (using F – test) - Given the hypothesis that: Ho: R2 = H1: R2≠ - As we see, p-value (F) = 0.06% < 1%< α=5%  At 5% level of significance, we have enough evidence to reject H O => the model has statistical significance Statistical significance of variables (using T-test) const p-value 1.10e-0.23 *** gender 0.0948 * parttime 0.0043 *** absence 6.11e-05 *** study 0.0761 * lover 0.0495 * acts 0.0296 * Analyzing p-value, we can see that p-value of gender = 0.0948* < 10% At 5% level of significance, gender has statistic meaning p-value of parttime = 0.0043*** < 1% At 1% level of significance, parttime has statistic meaning p-value of absence