P2RP-LP3M UB
Lecture Portfolio
UNIVERSITAS BRAWIJAYA
FACULTY OF MATHEMATICS AND NATURAL SCIENCES
DEPARTMENT OF STATISTICS /
UNDERGRADUATE STATISTICS STUDY PROGRAMME
Course Name: Advanced Econometrics
Course Code:
MAS62324
Laboratory:
Socio-economic Statistics
Semester : Even Lecturer Rahma Fitriani, S.Si., M.Sc., Ph.D
Introduction
This course is offered with the motivation that more advanced Econometrics topics cannot be discussed in the Econometrics course.
1 Purpose
General Purpose:
This course aims to study modeling and testing of economic theories empirically for more complex relationships between variables, including: involving more than one equation, accommodating dynamic properties with time series models, or accommodating dependency properties between locations with spatial models.
This course is taught to support the following Intended Learning Outcomes (ILO):
- ILO 1: The students are able to master basic scientific concepts and statistical analysis methods applied on computing, social science, humanities, economics, industry and life science.
- ILO 3: The students are able to manage, analyze, and complete the real case using statistical method on computing, social humanities, economics, industry and life science that helped by software, then present and communicate the results.
- ILO 4: The students are able to master at least two statistical software, including based on open source.
- ILO 5: The students are able to apply logical, critical, systematic, and innovative thinking independently when applied to science and technology that contain humanities values, based on scientific principles, procedures and ethics with excellent and measurable results.
- ILO 6: The students are able to take appropriate decisions to solve the problems expertly, based on the information and data analysis.
- ILO 7: The students are able to improve and develop a job networks, then supervise and evaluate the team’s performance they lead.
- ILO 8: The students are able to apply and internalize the spirit of independence, struggle, entrepreneurship, based on values, norms, and academic ethics of Pancasila in all aspects of life.
While the learning outcomes of the Mathematics Statistics II Course (Course Learning Outcome - CLO) are:
- CLO 1: Students are able to form empiric model based on economics theory in
P2RP-LP3M UB
the form of equation system for endogen and exogen variables
- CLO 2: Students are able to form dynamic regression model and analyze the causality among economics variables including time lag
- CLO 3: Students are able to forecast economic indicators based on time series data
- CLO 4: Students are able to form causality among economic variables in time series data
- CLO 5: Students know spatial econometric models to model causality among economic variables which involves locations dependency
- CLO 6: Students are able to present analysis results both written and oral, in the form of both individual or group assignments
Each Course Learning Outcomes (CLO) provide support for the Study Program Learning Outcomes (ILO) with a certain percentage, which details can be seen in the relationship matrix between CLO and ILO of Mathematics Statistics II, which is presented in Table 1.
Table 1. Relationship Matrix between CLO and ILO of Mathematics Statistics II
ILO1 ILO2 ILO3 ILO4 ILO5 ILO6 ILO7 ILO8
CLO1 0.25 0 0.3 0.3 0.1 0.05 0 0
CLO2 0.25 0 0.3 0.3 0.1 0.05 0 0
CLO3 0.25 0 0.3 0.3 0.1 0.05 0 0
CLO4 0.25 0 0.3 0.3 0.1 0.05 0 0
CLO5 0.25 0 0.3 0.3 0.1 0.05 0 0
CLO6 0 0 0.3 0 0.2 0 0.25 0.25
2 Teaching Strategy
This course is an elective course that requires the Econometrics course, where students learn how to apply Statistics models to solve problems in Economics. The material studied in the Advanced Econometrics course is models that use time series data and spatial data. Since this course raises many cases from economics, the delivery of lecture materials always begins with problems in economics and what kind of statistical model can provide solutions to these problems. Therefore, the following strategies are used::
- Provide access to material before lectures (in pdf/ppt files on the lecturer blog:
http://rahmafitriani.lecture.ub.ac.id/, and on the forums in Google Classroom).
- Explain at the beginning of the meeting about the economic problems involved and how the statistical model is used to answer the problem
- Explain the modeling concepts and statistical mathematical theory involved - Provide examples of interpretation of modeling
- Use Ms. Excel and Gretl as calculation tools.
- Ask students during the material presentation session regarding the need for the lecturer to re-explain or slow down the speed in explaining.
- Assign tasks that require deriving formulas from the basic model and interpretation
- Give assignments to practice skills using software.
3 Lecture Management
This course is a 3 credit points course. The scheduled meetings are once a week (3
P2RP-LP3M UB
times 50 minutes) for 14 weeks and 8 tutorial classes by the assistant (50 minutes each).
Midterm Exam is scheduled after 7 meetings, while the Final Exam is scheduled after the 14th meeting.
Lecture:
a. Schedule: Meetings are scheduled every Thursday, 9.20 - 12.00 WIB.
b. Material that has been accessed by students before lectures. The first two credits (100 minutes) are used to explain the theory and use of the model to answer the corresponding economic problems. The last one credit is used to practice using software in modeling concepts.
c. Each meeting has specific learning outcomes according to the material presented. To measure the outcome, a post test and assignment was designed.
The results of the assignment are used for evaluation, to repeat the parts that are deemed necessary at the next meeting. As designed in the Semester Learning Plan, students do the following as a form of assessment:
- Assignment: Regression analysis review - Post Test: Dynamic Regression
- Post Test: Simultaneous Equation Models - Assignment: Forecasting
- Post Test: Error Correction Mechanism - Post Test: Causality and VAR
- Post Test: ARCH and GARCH - Post Test: Spatial Econometrics 4 Course Material
- Dynamic Econometrics Models - Simultaneous-equation Models
- Time Series Economic Models: Forecasting, Stationarity, Trend, Unit Root, Spurious Regression, Co-integration, ECM
- Time Series Economic Models: ARIMA Box Jenkins, VAR, ARCH & GARCH - Spatial Econometrics Models
The suitability between the course material designed in the curriculum and its practice can be seen in Appendix 1.
5 Lecture Participants
This course is a compulsory course that is participated by students of the Undergraduate Statistics Study Program of FMIPA UB, all students are in 6th semester (class 2017).
From two parallel class, this class (class A) contains 28 students.
6 Attendance Percentage
Of the 14 meetings planned, only 13 were realized (92%) due to the red date (national holiday) on Thursday, the schedule for this course meeting. Of the meetings that were realized, an average of 99% of the students attended.
7 System Evaluation
- Weekly evaluation through assignments and post-tests. The purpose of this evaluation is to explore students' understanding of whether it is in accordance with the course purpose in each week's meeting. The results of the post-test and assignments were used by the lecturer to discuss the material that they felt lacking in understanding.
- Evaluate some materials through Quizzes that measure the students'
P2RP-LP3M UB
understanding after 3 or 4 meetings. The types of questions are similar to midterm/final exam questions so that students have an idea of how to prepare for the midterm/final exam.
- Material evaluation up to mid-semester through the midterm exam, which is held on a scheduled basis.
- Material evaluation after mid-semester to the end of the semester through final exam, which is held on a scheduled basis.
- In midterm and final exam weeks, all lecture activities are closed so that students concentrate on midterm/final exam.
Questions for all types of evaluation are standardized / the same for parallel classes, which is the result of discussion from the teaching team. Material evaluation for each assessment and its weight can be seen in Table 2.
Table 2. Measured assessment and material, as well as the weighting of each assessment of the final score and Course Learning Outcome (CLO)
Assessm
ent Topic
Weight to Final Score
CLO1 CLO2 CLO3 CLO4 CLO5 CLO6
Assessment Weight to CLO (Course Learning Outcome) Post Test
1
Dynamic
Regression 0.035 0 0.9 0 0 0 0.1
Post Test 2
Simultaneo us-equation
Model 0.035 0.9 0 0 0 0 0.1
Post Test
3 ECM 0.035 0 0 0.1 0.8 0 0.1
Post Test 4
Causality
and VAR 0.035 0 0 0.1 0.8 0 0.1
Post Test 5
ARCH and GARCH
Model 0.035 0 0 0.1 0.8 0 0.1
Post Test 6
Spatial Econometri
cs 0.035 0 0 0 0 0.9 0.1
Assignm ent 1
Review of Regression
Model 0.06 0.45 0.45 0 0 0 0.1
Assignm ent 2
Forecasting
Model 0.06 0 0 0.9 0 0 0.1
Quiz 1
Simultaneo us
Equation and Dynamic
Model 0.15 0.5 0.5 0 0 0 0
Midterm Exam
Dynamic Model, Simultaneo us Model,
ECM 0.26 0.25 0.2 0.25 0.3 0 0
P2RP-LP3M UB Final Exam
Forecasting Model, Causality,
and VAR 0.26 0 0 0.5 0.5 0 0
8 Class Observation
Students generally participate actively in lecture activities. Lecturer provide motivation regarding the use of models in applied cases (in the field of Economics) and is considered effective enough to motivate and attract students. The practical/demo approach using software in front of the class has succeeded in attracting students' interest to try it themselves. In almost every meeting, there are always several students asking or clarifying explanations from previously accessible material.
9 Learning Outcomes
The learning outcomes of each student are reflected in the scores in each assessment.
These scores, with their respective weights, are processed into final grades, which later, in accordance with the conversion rules, are converted into numerical scores that are printed on the Study Result Card / transcript. Besides being processed into the final score, the scores in each assessment, taking into account the percentage of CLO contributions to each ILO (Table 1) and the weight of each assessment of CLO (Table 2), are processed with the help of OBES software, so each student also has a score in each CLO and ILO.
The description of the score of each CLO can be seen in Table 3 and Figure 1. Figure 1 (a) presents the student average outcome index for each CLO. Figure 1 (b) presents the percentage of students with an outcome score above 60. In both figures, each corner of the pentagon represents each CLO, and the trajectory of the outer pentagon shows the highest outcome. The outer the position of the blue line, the higher the outcome index of CLO.
In accordance with the outcome category presented in Table 4, it can be concluded that:
- Of the six CLO, two of them have achieved a satisfactory outcome category on average, namely CLO 1 (Students are able to form empiric model based on economics theory in the form of equation system for endogen and exogen variables) and CLO 2 (Students are able to form dynamic regression model and analyze the causality among economics variables including time lag), which reflects that these two CLOs have not been achieved perfectly, even though almost all students get outcome scores above 60 (HIGH category).
- 4 CLOs are achieved optimally (CLO 3, CLO 4, CLO 5, and CLO 6), with average results in the excellent category. These results reflect that these outcomes have been optimally obtained by students. Almost all students get an outcome score above 60 (HIGH category)
Table 3. Score Description and Outcome Category for Each CLO of Advanced Econometrics
CLO1 CLO2 CLO3 CLO4 CLO5
Average 74.36 72.8 75.52 76.3 82.67
Outcome SATISFACT SATISFACT SATISFACT SATISFACT EXCELLEN
P2RP-LP3M UB
Category ORY ORY ORY ORY T
Number of Students with
CLO>60 37 36 42 41 44
Percentage of Students with
CLO>60 84.09 81.82 95.45 93.18 100
Percentage
Category HIGH HIGH HIGH HIGH HIGH
Table 4. CLO/ILO Score Category and Percentage Category of Students with CLO/ILO
>60
CLO/ILO Score Category Percentage Category of Students with CLO/ILO >60
Score ≥ 80 EXCELLENT Percent ≥ 70 HIGH
65 ≤ Score <80 SATISFACTORY 60 ≤ Percent < 70 MEDIUM 50 ≤ Score <65 DEVELOPING 50 ≤ Percent < 60 LOW
0 ≤ Score <50 UNSATISFACTORY Percent < 50 VERY LOW
Figure 1.Visualization (a) outcome index and (b) presentation of students with an outcome>60 in each CLO of Advanced Econometrics
In addition to the scores for course learning outcomes (CLO), it can also be analyzed the scores of each ILO. The description of the ILO outcomes of this course is presented in Table 5 and Figure 2. Figure 2 (a) presents the average student outcome index for each ILO. Figure 2 (b) presents the percentage of students with an outcome score above 60. In both figures, each corner of the octagon represents each ILO, and the trajectory of the outer octagon shows the highest outcome. The outer the position of the blue line, the higher the outcome index of ILO.
Several things can be concluded from the support of this course for the Study Program Learning Outcomes (ILO):
- There are three ILOs in Satisfactory category, namely:
ILO 1: The students are able to master basic scientific concepts and statistical analysis methods applied on computing, social science, humanities, economics, industry and life science.
(a) (b)
P2RP-LP3M UB
ILO 4: The students are able to master at least two statistical software, including based on open source.
ILO 6: The students are able to take appropriate decisions to solve the problems expertly, based on the information and data analysis.
These three ILOs are actually a practical matter needed in the world of work.
Although the support from this course on the ILOs has been satisfactory, the efforts of the lecturer can be increased so that this course can better support the three ILOs.
- There are four ILOs in Excellent category, namely:
ILO 3: The students are able to manage, analyze, and complete the real case using statistical method on computing, social humanities, economics, industry and life science that helped by software, then present and communicate the results.
ILO 5: The students are able to apply logical, critical, systematic, and innovative thinking independently when applied to science and technology that contain humanities values, based on scientific principles, procedures and ethics with excellent and measurable results.
ILO 7: The students are able to improve and develop a job networks, then supervise and evaluate the team’s performance they lead.
ILO 8: The students are able to apply and internalize the spirit of independence, struggle, entrepreneurship, based on values, norms, and academic ethics of Pancasila in all aspects of life.
Of the four ILOs, ILO 5, ILO 7, and ILO 8 are not directly related to econometrics, but more towards attitudes and behavior. Only ILO 1 is closely related to econometrics.
- Of all the ILO supported by Advanced Econometrics, 100 percent of students obtained an outcome score above 60
Table 5. Score Description and Outcome Category for Each ILO of Advanced Econometrics
ILO1
ILO 2
ILO 3
ILO
4 ILO5 ILO6
ILO
7 ILO8
Weighte d
Average 79.92
80.1 3
79.9
2 80.32 79.92
86.2
1 86.21
Outcome Category
SATISFACTO
RY
EX CE LL EN T
SA TIS FA CT OR Y
EXCELLE NT
SATISFACTO RY
EX CE LL EN T
EXCELLE NT Number
of Students with
ILO>60 28 28 28 28 28 28 28
Percenta ge of Students with
ILO>60 100 100 100 100 100 100 100
Category HIGH
HIG H
HIG
H HIGH HIGH
HIG
H HIGH
P2RP-LP3M UB
Figure 1.Visualization (a) outcome index and (b) presentation of students with an outcome>60 in each ILO of Advanced Econometrics
10 Obstacle
- Students' insights are lacking about the background of cases in economics, so they are not optimal in interpreting the model.
11 Grade Distribution
The final score is obtained from the weighting of all components of the assessment as presented in column three in Table 2, while the descriptive statistics of the final score can be seen in Table 6. The mean of the students' final score is 80.18, with less and more than 5.8 points from the mean. There is one student with the lowest score (65.78) and one student with the highest score (89.94).
Table 6. Descriptive Statistics of Final Score of Advanced Econometrics 2019/2020
Mean 80.18
Standard Deviation
5.8
Range 24.16
Minimum 65.78
Maximum 89.94
After being converted into letter grades under the assessment conversion standards, the distribution of letter grades can be seen in Figure 3. The figure shows that there are more than half of the students with grades above C, even the highest percentage is grade A.
(a) (b)
P2RP-LP3M UB
Figure 3. Grade Distribution of Advanced Econometrics 2019/2020 12 Conclusion
- With all the obstacles and basic abilities of students who have been given, the final score obtained still reflects that the strategies and learning methods are well accepted by the majority of students.
- There needs to be a change in the delivery technique in the Simultaneous Model (CLO1) and Dynamic Model (CLO2), to increase the outcome score of both.
- Other learning outcomes are as expected.
- The support of this course for the outcomes of study programs related to practical matters in the world of work is still not optimal.
13 Recommendation
- Try other approaches in the delivery of material, especially in the simultaneous and dynamic model.
- Retrain software utilization skills for real cases
30% 27%
14% 14%
9% 7%
A B+ B C+ C D
Pencentage of Letter Grade
P2RP-LP3M UB
Appendix 1
Wee
k Topic
Implementation in Week
1 2 3 4 5 6 7
8 and 9
10 11 12 13 14 15 16 17
1 Class Contract Econometric analysis stages based on data types
Class Contract, reviewing economet rics
2 Distributed Lag Model, Autoregressive Model
Dynamic models, Distribute d Lag Model, and Autoregre ssive Model
3 Simultaneous equation models, Endogenous, exogenous variables, Order identification, Indirect Least Square, Two Stages Least Square
Simultane ous models
4 Identify time series trend, Moving Average Autoregressive Model, Exponential Smoothing
Simulta neous models and quiz
5 Time
series and forecasti
P2RP-LP3M UB
Wee
k Topic
Implementation in Week
1 2 3 4 5 6 7
8 and 9
10 11 12 13 14 15 16 17
ng 6 Autocorrelation,
Random-walk concept, Stationarity, Integration
Forecast
ing
7 Co-integration concept, Spurious regression
Co- integrati on concept, Spuriou s regressi on, ECM
8 and 9
Midterm Exam Mi
dte rm Ex am
10 Co-integration Detection Error Correction
Model ECM
11 ACF and PACF concepts Estimation of ARIMA model ARIMA forecasting
ARIMA
P2RP-LP3M UB
Wee
k Topic
Implementation in Week
1 2 3 4 5 6 7
8 and 9
10 11 12 13 14 15 16 17
12 The concept of one-way and two-way causality VAR modelling
Grang er Causal ity and VAR 13 The concept of
volatility ARCH modelling GARCH modelling
VAR and ARCH/
GARCH 14 Introduction to
spatial heterogeneity An introduction to the
coordinate system The concept of distance in spatial data analysis
ARC H/GA RCH and Spatia l Data
15 Distance Weighted Matrix Contiguity Matrix
Spatia l Econo metric s 16 Various types of
spatial regression (SAR, SEM, SLX, etc.)
Red Date / Natio nal Holid ay 17 Final Exam
Fina
l
P2RP-LP3M UB
Wee
k Topic
Implementation in Week
1 2 3 4 5 6 7
8 and 9
10 11 12 13 14 15 16 17
Exa m
P2RP-LP3M UB
Appendix 2. List of Grade Details
STUDENT ID NAME
PT1 Dynamic Regressio
n
TG1 Review
of Regressi
on Model
PT2 Simultaneou
s Equation
PT3 ECM
Assignment:
Forecasting Model
PT4 Causality and VAR
PT5 ARCH
and GARCH
PT6 Spatia
l econo metric s
Quiz 1 Midt
erm Exa
m
Final Exam
Final Score
'175090500111012 APRILIA NURUL AZIZAH 97 80 100 100 90 80 95 85 66 72.5 90 81.61
'175090500111013 RIZKI NURANI AISHA 95 93 100 100 90 80 100 80 64 68 90 80.71
'175090500111015 CHANDRA MALIK
SYAMASY 90 84 100 100 90 80 95 90 78 81 100 88.25
'175090500111026 TAMARA REZTI
SYAFRIANA 85 100 100 100 90 80 95 85 83 85.5 90 88.38
'175090500111030 NI MADE AYU ASTARI
BADUNG 50 91 100 100 95 70 100 75 100 79.5 93 88.11
'175090500111033 ALIFYA AL ROHIMI 80 97 100 100 85 70 95 80 88 84 95 88.81
'175090500111036 MAMLU`ATUL
MARCHAMAH 80 98 100 97 85 70 60 70 70 72 79 77.15
'175090501111003 YULI ROCHMAWATI 95 94 100 93 90 80 95 90 88 83.5 95 89.94
'175090501111004 ROSI DWI LESTARI 80 80 100 93 90 70 90 80 75 74 83 80.06
'175090501111005 NAJUNDA ZUKHRUFIAH
SYAHDU FIRDAUS 70 92 100 100 90 80 65 75 51 85.5 81 78.81
'175090501111011 IRSYAD MAULANA
KHAIRONI 95 80 100 85 85 70 70 60 67 93 89 83.47
'175090501111012 FIFI ADINDA PUTRI 95 97 100 100 85 80 100 90 69 73.5 76 79.79
'175090501111014 DENISA LAUVIL MAULIDIA 75 80 100 100 90 80 95 90 49 74 76 75.45
'175090501111020 KUSHARTANTI ALIFAH 70 96 100 100 90 80 95 85 49 78 90 80.64
'175090501111023 SEPTIKA NINGRUM RISKI
IRAWATI 95 80 100 100 90 80 90 85 70 64 76 76.15
'175090501111026 EVA FADILAH RAMADHANI 50 97 0 100 90 70 100 85 77 76 83 81.26
'175090501111031 RENICA ANGGUN
PUSPACANDRA 70 80 90 75 95 80 77 85 64 78 84 79.08
'175090501111036 WULAIDA RIZKY FITRILIA 100 80 100 100 90 80 100 80 88 62 90 82.12
'175090507111008 ENGELBERTA VANIA 0 86 100 78 90 70 77 75 49 74.5 79 74.445
'175090507111009 DIAH AYU MAYLIANA SARI 80 80 100 93 90 70 93 95 75 60 70 74.03
P2RP-LP3M UB
'175090507111010 LAKSMI ADLINA
YUDIHARTIN 60 86 100 75 90 80 72 80 45 57 91 72.2
'175090507111011 NATASHA DEBORA THO 55 87 100 70 60 60 90 65 69 48 73 65.78
'175090507111017 BESTARI ARCHITA SAFITRI 80 89 100 93 90 70 60 90 59 67 64 71.14
'175090507111022 NABILA AZARIN BALQIS 85 97 95 100 90 80 98 70 66 79 100 85.6
'175090507111031 GREIS ULLY DAMAIYANTY
GULTOM 80 86 100 100 90 70 60 55 74 73 82 77.56
'175090507111034 FATMA INAS ZAKIYA 95 100 100 100 90 70 97 85 69 65 85 79.71
'175090507111037 NEFRANITA HALEVI 60 86 90 75 90 90 80 85 74 66.5 86 78.26
'175090520111001 MUHAMMAD NUR DZAKKI 100 81 100 85 90 65 100 100 81 89 83 86.63
