Primary and secondary data
Primary data are collected first-hand for your own study. Secondary data were collected earlier by someone else and are reused, such as NFHS reports.
Primary vs secondary data
| Point | Primary data | Secondary data |
|---|---|---|
| Collected by | The researcher, for this study | Someone else, for another purpose |
| Nature | Original, first-hand | Already available, second-hand |
| Cost and time | High | Low |
| Fit to the problem | Fits the objectives exactly | Definitions, units or area may not match |
| Accuracy | Known, because you control the method | Depends on the original collector |
| Methods or sources | Observation, interview, questionnaire, schedule, measurement | Published reports, records, journals, websites |
| Nutrition example | 24-hour diet recall of 100 students | Anaemia figures from NFHS-5 |
Methods and sources
Most good studies use both: secondary data to plan and compare, primary data to answer your own question.
Before using secondary data, check (Kothari)
- Reliability: who collected it, by what method, when (is it recent enough?), and was there any bias?
- Suitability: do the definitions, units and area match your study? (NFHS counts girls aged 15-19 as adolescents.)
- Adequacy: does it cover enough of your area, period and group?
A dietitian uses secondary data (NFHS-5 anaemia rates, IFCT 2017 nutrient values) to plan, and collects primary data (weight, Hb, 24-hour recall) to assess her own group. A study of anaemia in college girls can compare its own figures with NFHS-5.
2 marks: “Define primary data.” Primary data are original data collected first-hand by the researcher for the specific purpose of the study, e.g. through a questionnaire or measurement.
5 marks: “Differentiate between primary and secondary data.” Compare who collects, originality, cost, time, fit to the problem and accuracy, with one nutrition example each; add Kothari's three checks for secondary data.
10 marks: “What are primary and secondary data? Explain their sources and the precautions in using secondary data.” Definitions, methods of primary data, published and unpublished secondary sources, a comparison table, and reliability, suitability and adequacy.
Primary = Personally collected. Secondary = Someone else collected it.