Postgraduate Course: Data Collection and Analysis for Food Security (PGGE11291)
Course Outline
| School | School of Geosciences |
College | College of Science and Engineering |
| Credit level (Normal year taken) | SCQF Level 11 (Year 1 Undergraduate) |
Availability | Not available to visiting students |
| SCQF Credits | 20 |
ECTS Credits | 10 |
| Summary | This course is designed for students wishing to work in a range of organisations addressing food security and agriculture challenges around the world, such as governments, international NGOs, international development and donor agencies, private enterprises and research organisations. The course will provide students with combined skills of statistical data analysis, computer literacy, and results¿ interpretation applied to real-world cases regarding food insecurity, malnutrition, poverty, food production and consumption. The course will complement the academic focus of other courses (e.g., Frameworks to assess Food Security ¿ MSc Food Security). |
| Course description |
The course will cover the following topics during the first semester:
Week 1 ¿ Introductory lecture
In this lecture, the students will be introduced to the topic of data processing and analysis. The importance of the knowledge that will be acquired from the course for their academic (e.g., MSc dissertation) and professional carrier (e.g., jobs) will be highlighted. In addition, the students will be provided with information on (1) the structure of the course, (2) a brief description of each lecture and the skills that will be learnt, and (3) a brief description of the case studies that will be discussed in the lectures as well the dataset that will be used for each case study.
PART I: DATA TYPES, THEIR COLLECTION AND PREPARATION FOR ANALYSIS
Week 2 - Data types and collection
In this lecture, the students will learn about:
types of data and what they are used for (e.g., secondary, data, primary data, and other classification such as cross-section data, time series, and panel data)
main methods of data collection for qualitative and quantitative research as well as their pros and cons.
how to design and conduct surveys
Activities in class:
Discussing examples of existing data (e.g., FAO data, World Bank data, and Eurostat data)
Discussing the topic and the structure of the survey that the students will use to collect data for the main assignment of the course.
Week 3 - Data preparation and visualisation
In this lecture, the students will learn:
How to prepare data for analysis, including data entry, cleaning (e.g., dealing with missing values, out-of-range values, nulls, outlier values), editing (e.g., types of variables, transforming variables, creating new variables), and formatting (e.g., labelling variables)
How to perform a descriptive analysis with examples in Excel and Rstudio:
Univariate analysis: this will mainly cover frequency distribution, central tendency (e.g., mean, median, mode), and dispersion (e.g., range, percentiles, variance).
Data visualisation: the student will be taught how to generate and use histograms, box plots, pie charts, and interactive charts. Other visualisation tools such as scatter plots and crosstabs will be taught in Week 4.
Activities in class:
use examples of datasets relevant to food security (e.g., FAO and World Bank data) to practice the knowledge gained on:
processing raw data and preparing them for descriptive analysis
compute basic food security indicators and visualise them (e.g., the prevalence of food insecurity, malnutrition, and poverty across countries and over time).
PART II: DATA ANALYSIS
All the lectures on data analysis will include computer lab sessions where participants are provided with data analysis software (e.g., Rstudio) to learn how to use real databases to estimate and test data analysis models taught in the lectures and gain hands-on experience in using new techniques for practical applications. By examining actual case studies, students will become familiar with problems of model formulation, estimation, testing, and forecasting.
Week 4 ¿ Understanding statistical association
Statistical association (not causality) is one of the simplest forms of statistical analysis used to find out if there is a relationship between two variables (e.g., income and diet quality), the degree of association if one does exist, and whether one variable may be predicted from another.
In this lecture, the students will learn how to analyse the relationship (association/dependence and not causal relationship) between different types of variables and how to select the most appropriate statistical test. The lecture will cover:
Probability distribution
Hypothesis testing
Testing association between two continuous variables (e.g., correlation test, Spearman Rank Correlation)
Testing association between two categorical variables (e.g., Chi-square test)
Testing association between a continuous variable and a categorical variable (e.g., One-sample t-test, One-sample Wilcoxon Signed-Rank Test, t-test for independent samples, Wilcoxon Rank-Sum Test, t-test for dependent samples, Wilcoxon Signed-Rank Test, one-way ANOVA, Kruskal-Wallis test, two-way ANOVA, Friedman test)
Selecting the right statistical test (parametric and non-parametric tests)
Example of a case study: Understanding the relationships between the determinants of the availability of healthy and sustainable food products in deprived areas: application of parametric and non-parametric tests
Understanding the drivers of food and nutrition security as well as the evaluation of interventions to mitigate food insecurity, poverty, and malnutrition require the study of more complex sets of data than what association analysis can handle. It requires, among others, examining how a response/outcome variable depends on one or more predictors or explanatory variables. This type of multivariate analysis is widely used to infer causal relationships and carry out prediction and forecasting. Depending on the type of the response/outcome variable (e.g., continuous, binary, multinomial), a different set of statistical methods is used.
In the remaining weeks of the course, students will learn quantitative tools that will allow them to understand causal relationships and make predictions and forecasting.
Week 5 ¿ Analysis of continuous outcome
This lecture will cover the commonly used regression models to determine the strength and character of the causal relationship between a continuous outcome/response variable (e.g., caloric intake) and one or multiple explanatory variables (e.g., age, gender, income, palatability, health status).
In this lecture, the students will gain knowledge on:
Requirements for testing causality
Regression and causality
Regression fundamentals
Manipulating variables in regression
Single linear regression analysis
Multiple linear regression analysis
Non-linear regression analysis
Interpretation and use of the analysis output
Example of a case study: Drivers of technology adoption for improved food security: application of multiple regression analysis
Week 6 ¿ Analysis of binary outcome
In this lecture, students will learn how to use the most commonly applied binary regression models to determine the strength and character of the effects on a binary outcome/response variable (e.g., household being poor) of one or multiple explanatory variables (e.g., widowhood, disability, illiteracy, low wages, household size).
In particular, the students will gain knowledge on:
Continuous versus binary regression
Fundamentals of logistic regression
Logit model versus Probit model
Specification and estimation of the Logit and Probit models
Interpretation and use of the analysis output
Example of a case study: Determinants of Malawians¿ decision to buy safer milk: application of logistic regression
Week 7 ¿ Analysis of choice behaviour I: assessing the drivers of individuals¿ choices
Understanding and predicting the choice behaviour of decision-makers when choosing among discrete products/services (e.g., different interventions, different crop management strategies, different food products with different environmental and nutritional qualities) is crucial to design and implement strategies to improve food and nutrition security and promote more sustainable and healthier food production and consumption.
In this lecture, the students will acquire knowledge on how to apply the commonly used behavioural choice models to determine the drivers of individuals¿ choices and quantify their effect. This lecture will cover:
Fundamentals of choice analysis
Binary choice models
Multinomial choice models
Specification and estimation of choice models
Interpretation and use of the analysis output
Example of a case study: Access to food security by beneficiaries of cooperatives: application of a multinomial logit approach
Week 8 ¿ Analysis of choice behaviour II: assessing the heterogeneity of individuals¿ preferences
In this lecture, students will be taught how to analyse and understand the heterogeneity of people¿s choice behaviour and decision making, for example, the variation of choice behaviour across different socio-demographic groups of decision-makers. Assessing the heterogeneity of individuals¿ choice behaviour is crucial if the outcome of the analysis is intended to help in designing effective policy and marketing strategies that are tailored to the needs of different stakeholder groups (e.g., rural consumers versus urban consumers, small farm holders vs. large farm holders). In this lecture, the students will learn about:
Importance of analysing heterogeneity
Use of the split-sample approach
Use of the Interaction approach
Use of the latent class model
Interpretation and use of the analysis output
Example of a case study: Kenyan farmers¿ preferences and willingness to pay for the use of a new variety of drought-tolerant potatoes: application of the latent class model
Week 9 ¿ Behaviour change analysis: the role of attitudes and perceptions
In addition to being influenced by socio-demographic and economic factors, people¿s behaviour is also affected by their attitudes, perceptions and views. In this lecture, the students will learn about data analysis methods that are widely used to quantify the role played by stakeholders¿ attitudes, perceptions, and views in shaping their behaviour. This lecture will cover:
Fundamentals of behaviour change analysis
Path analysis
Exploratory factorial analysis
Confirmatory factorial analysis
Example of a case study: The role of social supermarkets in reducing food waste and food insecurity: application of confirmatory factorial analysis
Week 10 ¿ Evaluation of food and nutrition programmes I
In this lecture, the students will learn how to use impact evaluation methods to assess the effectiveness of food security and nutrition-related programmes/interventions. The impact evaluation establishes whether the intervention/programme had a welfare effect on individuals, households, and communities and whether this effect can be attributed to the concerned intervention/programme. Impact evaluation serves both objectives of evaluation: lesson-learning and accountability, which, in turn, provide policy-relevant information for scaling up or redesigning existing programmes and designing future programs.
The students will learn about the most widely used methods to evaluate the impact of food and nutrition programmes. This lecture will cover (more in the next lecture):
Theory of change and measurement
Randomisation method
Propensity score matching method
Example of a case study: Food and agricultural approaches to reducing malnutrition¿application randomisation method
Week 11 ¿ Evaluation of food and nutrition programmes II
This lecture is a continuation of the previous lecture (week 10). The students will gain knowledge on the use of other impact evaluation methods. In particular, the lecture will cover the following methods:
Instrumental variables method
Difference-in-difference design
Regression discontinuity design
Example of a case study: The effect of income-supplementation on food insecurity - application of the difference-in-differences approach
|
Entry Requirements (not applicable to Visiting Students)
| Pre-requisites |
|
Co-requisites | |
| Prohibited Combinations | |
Other requirements | None |
Course Delivery Information
| Not being delivered |
Learning Outcomes
On completion of this course, the student will be able to:
- Understand key features of common approaches methods used for data-driven (empirical) analysis in food security/development/agricultural economics
- Have acquired foundational skills in the analysis of datasets relevant to food security/development/agriculture in R
- Understand how the approaches covered in class can be applied to address real-world problems related to food security/development/agriculture
- Have developed mini-research proposals, demonstrating analytical, problem solving and team working skills
- Have a solid basis for understanding methods and data needs for undertaking empirical socio-economic food security research
|
Reading List
Tutorial book/class text book that will be prepared by the course organisers and the lecturers. The book will include a detailed and easy to fellow description of the content that will taught in each of the eleven weeks (e.g., background of the methods, theory, use of the methods with examples, software codes).
Babu, S., Gajanan, S., & Sanyal, P. (2014). Food security, poverty and nutrition policy analysis: statistical methods and applications. Academic Press.
Khandker, S. R., Koolwal, G. B., & Samad, H. A. (2009). Handbook on impact evaluation: quantitative methods and practices. World Bank Publications.
Hanck, C., Arnold, M., Gerber, A., & Schmelzer, M. (2019). Introduction to Econometrics with R. University of Duisburg-Essen, 1-9. |
Additional Information
| Graduate Attributes and Skills |
Design tools for data collection
Collecting data
Use of qualitative and quantitative tools to analyse the data
Interpreting the outcome of the analysis
Using the results to understand the ¿problem¿ and propose solutions
Write up the findings and present them (e.g., reports, essays, oral presentations, blogs) |
| Keywords | Type of data,data collection,data cleaning and editing,descriptive analysis,quantitative analys |
Contacts
| Course organiser | |
Course secretary | Ms Jennifer Gumbrell
Tel:
Email: Jennifer.Gumbrell@sruc.ac.uk |
|
|
University Homepage