Index > Toolbox > Analysing Data

Toolbox: Analysing data

Coding and analysis

The researcher can choose how to analyse output of the focus group discussions. This might be qualitative, ethnographic, or based on systematic content coding.

Political analysis

Political science uses a number of broad theoretical approaches and methodologies.

Quantitative analysis

  • Testing and adjusting for attrition in Household Panel Data
    This note describes the use of a simple procedure to correct for attrition due to observables in household panel survey: inverse probability weights. The procedure involves estimating two probit regressions, one with and one without variables that are significantly associated with attrition, and using the ratio of predicted probabilities from these regressions to reweight the observations. The procedure is illustrated in Stata using data from part of the CPRC-DATA-IFPRI panel in rural Bangladesh. 

Creating and Interpreting Contour plots using DASP and GNUPLOT

This notes describes how contour plots, which are two dimensional representations of welfare distributions that can be regarded as a continuous analogue to transition matrices, can be creating using the Stata package DASP and the graphics package gnuplot. The procedure is illustrated with panel data from the Vietnam Household Living Standards Survey from 2002 to 2006. Also related source data:

 

Search

What is the methods toolbox?

This toolbox provides a guide to the variety of approaches and methods available and how they can be mixed to produce both rigorous and policy relevant research.

 

The toolbox should be considered as a set of resources to draw upon within the context of particular research requirements. It is divided into short sections that introduce each topic such that readers are able to get a sense of the materials and approaches included.

 

The toolbox is a work in progress. Any comments or queries you have about its content or organisation, and any other resources you feel we should include, would be most welcome.