Semester Offering: January
 
As shown by the needs expressed by alumni and managers working in both public and private organizations, it is extremely important for students to have basic understanding of and practical experience with selected techniques in quantitative methods, in particular, factor analysis that can establish causal relationship between independent variables and dependent variables. The objective of this course is to provide practical training to students so that they can examine their research questions and prove or disprove hypotheses through these tools. In particular, the course introduces a set of basic regression techniques, which enable the students to implement factor analysis while quantifying the effects of each factor. In fact, many students recognize at the time of writing their thesis that addressing the research questions in their thesis actually requires these skills. The course emphasizes hands-on practices in classroom and interpretation of analytical results, rather than deliberation on theories and concepts. Use of complicated equations including calculus is dispensedwith.

 

Upon successful completion of this course, students will be able to:
     Consider analytical methods at the stage of data collection and adjust the way of data collection accordingly;
     Select and apply basic but useful and relevant analytical methods using the open-access R software; and
     Interpret the output of the analysis in a quantitative manner in the context of development research, while noting the limitations

 

None

 

1.    Quality control in primary data collection
1)    Basic concept of CAPI
2)    Pros and cons in use of CAPI

2.    Introduction to R
1)    Installation of R and basic operations for data handling
2)    R codes for generating descriptive and inferential statistics

3.    Factor Analysis (Cross-sectional non-spatial models).
1)    Review of multiple linear regression (ordinary least squares method)
2)    The concept of ceteris paribus
3)    Some techniques within OLS:
i.    Dummy variables
ii.   Interaction terms
iii.  Quadratic terms
iv.   Logarithm
4)    Assumptions for OLS
5)    Basic ideas of estimation bias
6)    Selected models for limitation in dependent variables
i.     Censored and truncated variable (tobit model)
ii.    Binary variable (probit, logit, LPM)
iii.   Ordinal variable (ordered probit)
iv.   Categorical variable (multinomial logit)

4.    Principal Component Analysis
1)    Introduction to PCA

 

Classroom sessions involve lectures and hands-on exercise with students’ laptop computers. Lectures and practices go hand in hand. 

 

1.      Stock, JH and Watson, MW (2017) Introduction to Econometrics, 3rd edition, Addison-Wesley International.
2.      Gujarati, D. (1999) Essentials of Econometrics, 2nd edition, McGraw-Hill.

 

1.    Venables, WN, Smith DM, and the R Core Team (2017) Introduction to R: Notes on R: A Programming Environment for Data Analysis and Graphics. Manual for R version 3.4.3. R, Foundation for Statistical Computing. https://cran.r-project.org/doc/manuals/r-release/R-intro.pdf
2.    Wooldridge, JM (2003) Introductory Econometrics: A Modern Approach. 2nd edition, South-Western College Publishing.
3.    Kennedy, P (1998) A Guide to Econometrics. 4th edition, Blackwell.

 

1.    International Journal of Social Research Methodology (Taylor & Francis)
2.    The R Journal (The R Foundation)

 

Lecture: 22.5hours
Practices with own laptop computers in classroom: 15-22.5 hours
Self-study: 45 hours

 

Lectures and practices in the classroom. Selected quantitative techniques will be illustrated by using R software.


 

The closed-book mid-term exam carries 40% of the weight; assignments 10%; and the term paper 50%. Class attendance will not be taken into account, as the students are expected to decide which classes to attend based on their previous knowledge in statistics and expericen with R software.
 
Grade “A” would be awarded if a student demonstrates excellent understanding on topics covered in the course. Grade “B” would be awarded if a student shows an overall understanding of topics covered in the course. Grade “C” would be given if a student meets below average expectations on both understanding and application. Grade “D” would be given if a student does not meet basic expectations in analyzing or understanding issues covered in the course. Grade “B+” is positioned between Grade “A” and Grade “B”, while Grade “C+” is considered between Grade “B” and Grade “C”.