Quantitative research focuses on things you can count. It is the process of collecting numerical data through standardised techniques, then applying statistical methods to derive insights from it.
The goal of quantitative research methods is often to collect numerical data from a group of people, then generalise those results to a larger group of people to explain a phenomenon.
Quantitative data is numerical and can be collected in the form of :
- Units: number of students enrolled
- Prices: amount of money spent on a vaccine
- Proportions/percentages: proportion of the community that has access to a well
- Rates: percentage change in average income over one year
- Ratios: of midwives to families in a region
- Scoring and ranking: out of ten or 100
Statistical data can often be represented in the form of graphs, tables, pie-charts or bar charts
Advantages and Disadvantages of Quantitative Techniques
- They help to produce more accurate, objective and conclusive results
- They can help you to quantify the progress of your project and assess whether or not you have met the indicators outlined in your log frame
- They are useful in establishing baseline data at the start of a project (eg. Proportion of pupils aged 12 to 16 passing end of year exams in mathematics)
- They can enable you to generalise on the basis of your findings. With statistically significant sample sizes, the results can sometimes even be generalized to an entire target group
- They can allow you to draw comparisons and correlations (e.g. is the percentage of girls aged 14 passing science exams lower than boys of the same age and, if so, could this be linked to differences in the school syllabus followed by boys and girls?
- They are particularly important where there is a need for accurate, concrete answers (e.g. on improved literacy rates, increased annual yields, percentage of population vaccinated)
- They can also be particularly appreciated by donors who put a premium on the demonstration of success (e.g. DFID)
- They can be used with hard and soft data
- They can be used to display data visually in meaningful tables, graphs, pie-charts, and other formats. See the example below from Development Initiatives.
- Quantitative techniques can lead to misleading results, not least if you use them incorrectly. If, for example, you count the number of children sitting an exam rather than the percentage of those passing it or if you focus only on the past three months when the yield was high and ignore the 21 months before where the yield was extremely low
- They are not good at capturing feelings
- They can be open to misrepresentation or misinterpretation. Graphs can suggest sharp or slow increases depending upon the variables used in the X and Y axes
- They may require a certain skill set or level of numeracy if they are to be drawn on effectively and accurately
- They can lead to over-generalisation: for example if you make claims that your findings apply to an entire country when they relate to a sample of only two towns or regions
Where to next?