Laboratory schedule: Wednesday | 13:00 - 16:00
Instructor: Christopher Llones
e-mail: christopher.llones@vsu.edu.ph
Pre-requisites: Stat21 or introductory statistics
Course credits: 3 units
Number of hours: 2 hrs lectures and 3 hrs laboratory per week
Course description
This laboratory course offers a practical, data-driven introduction to statistical methods used in economic research and policy analysis, with a particular focus on survey data. Students will engage with both foundational and advanced techniques for analyzing real-world datasets, emphasizing hands-on implementation, critical interpretation, and reproducible reporting.
Key topics include:
- Fundamentals of statistical inference and data exploration
- Survey design and measurement reliability
- Assumption testing and model diagnostics
- Correlation analysis and regression modeling (linear, logistic, and limited-dependent)
- Hypothesis testing for means and group comparisons
- Non-parametric statistical techniques
- Multivariate methods including exploratory factor analysis
Students will use R—a powerful statistical programming language—to clean and visualize data, conduct analyses, and generate publication-ready outputs. By the end of the course, students will be equipped to design surveys, analyze empirical data, and communicate findings with clarity, rigor, and policy relevance.
Course objectives
By the end of the course, students will be able to:
- Design and implement valid survey instruments
- Conduct exploratory data analysis (EDA) on survey datasets
- Evaluate statistical assumptions and model fit
- Apply correlation and regression techniques, including models for limited-dependent variables
- Perform parametric and non-parametric hypothesis tests
- Implement multivariate techniques such as factor analysis and clustering
- Use R for data wrangling, visualization, and reproducible reporting
- Interpret and communicate statistical findings in academic and policy contexts
- Critically assess empirical research for methodological soundness and relevance
Course outline
| Module 1: Introduction to R Programming |
- Installing R and RStudio
- R Basics
- Working with R scripts
- Importing data
- Basic data wrangling
|
- Learn to install and configure R and RStudio.
- Understand and apply basic R syntax including data types, vectors, and data frames.
- Develop proficiency in writing, saving, and executing R scripts.
- Import dataset and prepare them for analysis.
- Clean and transform data .
|
| Module 2: Introduction to data visualization using ggplot2 |
- Understanding grammar of graphics
- Dataset and mapping
- Geometries
- Statistical transformation and plotting distribution
- Position adjustment and scales
|
- Understand the grammar of graphics and its role in structuring visualizations.
- Create and customize basic plots including histograms, bar charts, boxplots, and scatterplot.
- Map variables to visual aesthetics such as color, shape, and size to enhance interpretability.
- Apply faceting techniques to produce multi-panel plots for comparative analysis.
- Modify plot themes and coordinate systems to improve clarity and accessibility.
- Export visualizations for use in reports, presentations, policy briefs, and others.
|
| Module 3: Reproducible report with Quarto in R |
- Introduction to Quarto
- Creating Quarto document
- Embedding R code
- Formatting Outputs
- Exporting reports
|
- Learn to create dynamic, reproducible documents using Quarto and markdown syntax.
- Embed R code and inline calculations within narrative text to integrate analysis and interpretation.
- Format outputs such as tables and plots for professional presentation.
- Render reports to multiple formats including HTML, PDF, and Word for diverse audiences.
- Develop the ability to produce transparent, replicable research outputs for academic and policy contexts.
|
| Module 1: survey research design |
- Methods of data collection
- Sampling design in surveys
- Measurement issues in survey research
- Questionnaire construction
- Basics of interviewing
- Creating a codebook
- Data entry
|
- Discuss the various methods of data collection including survey, observation and experimental methods.
- Discuss different ways for gathering a sample; random and non-random sampling. Discuss rudimentary formulas for sample size calculation.
- Discuss the issues in assigning numbers to represent quantities of attributes. Discuss the various scales of measurement. Discuss criteria in constructing good measurement of variables: reliablity and validity.
- Discuss the various advantages and disadvantages of interviews and questionnaire over other methods of data collection.
- Discuss the do’s and dont’s of an interviewer’s conduct.
- Discuss the importance of creating a codebook for survey data.
- Discuss rudimentary of data entry.
|
| Module 2: exploratory data analysis |
- Rudiments of EDA
- Charts and tables
- Measures of central tendency
- Dispersion, parameters, skewness and kurtosis
- Contingency tables and scatter plot
|
- Discuss EDA as the first step in data analysis.
- Discuss various techniques in summarizing and visualizing data.
- Discuss the various measures of central tendency and data location.
- Discuss the relevance of various dispersion, parameters, skewness and kurtosis.
- Discuss the relevance of contingency tables and scatterplots for summarizing and visualizing data.
|
| Module 3: test on means |
- Parametric test on means
- Non-parametric test on means
|
- Discuss the various t-tests and ANOVA and perform them on a sample data with R.
- Perform various non-parametric equivalent of the t-tests and ANOVA on sample data with R.
|
| Module 4: correlation and regression analysis |
- Correlation analysis
- Review of Regression analysis
|
- Discuss the various types of correlation analysis procedures. Interpret the correlation coefficient.
- Discuss the various aspects of regression model building.
|
| Module 5: limited-dependent variable models |
- Review of binary dependent regression
- Extension to the logit model.
- Censored and truncated regression models.
- Count dependent variable models.
|
- Discuss the various aspects of the logit and probit.
- Discuss the multinomial and ordinal logit models.
- Discuss the Tobit regression model for censored data and truncated regression models.
- Discuss Poisson and Negative Binomial regression models in the regression analysis of count-dependent variable models.
|
| Module 6: multivariate statistical analysis |
- Cluster analysis
- Principal component analysis
- Exploratory factor analysis
- Confirmatory factor anlysis
- Structural equation modelling
|
- Understand and apply different clustering methods. Analyze and evaluate the quality and effectiveness of different clusters in dataset.
- Learn to perform and interpret principal component analysis to reduce the dimensionality of dataset. Develop the ability to identify and retain significant components for simplifying data without losing critical information.
- Identify and estimate underlying factor structures within a set of observed variables.
- Understand model-based factor anlaysis and develop proficiency in evaluating model fit and making necessary adjustments to improve analysis.
- Apply SEM techniques to understand relationships among variables and construct theoretical models.
|