Collecting Data

Data Collection Basics

Collecting data refers to the process of gathering information from a variety of sources to analyse and draw conclusions.
Data can be collected either primary (first-hand collection) or as secondary (using data already gathered).
Primary data is more reliable as it is collected specifically for your research, but it takes more time and effort.
Secondary data is less time-consuming to collect, but may not fully meet the requirements of your research.

Data is classified into qualitative (non-numerical) and quantitative (numerical).
Qualitative data involves descriptors that can’t be measured but can be observed, like colours or emotions.
Quantitative data involves numbers and can be subjected to statistical analysis. Quantitative data can be either discrete (countable) or continuous (measurable).

Observation: Involves watching and noting physical phenomena as it occurs naturally.
Interviews/Surveys/Questionnaires: Useful for gathering a large amount of information from participants through direct communication.
Experiments: Carried out in controlled conditions to measure the outcome of certain actions or interventions.
Records/Registers: Use of publicly available data to study the characteristics of a certain group.

Sampling refers to selecting a subset from a large population for the purpose of data collection.
Random sampling ensures that each individual has an equal chance of being selected.
Stratified sampling involves dividing the population into groups (stratas) based on a characteristic, and taking a proportional number from each.
Quota sampling is similar to stratified sampling, but with no concern to proportionality.
Cluster samplingselects certain groups (clusters) within the population, useful for geographical data.

Collected data should be reliable, accurate, and precise to be meaningful.
Data cleaning is the process of correcting or removing errors in the collected data. It can involve dealing with missing data, inaccuracies, or inconsistencies.
All data must be honestly and accurately represented to avoid biased interpretations.

Any data that can identify an individual (like names, address, etc.) must be handled with confidentiality and respect for privacy.
Accurate interpretation without bias or misuse of information is a vital part of ethical data handling.
Always obtain informed consent from participants before collecting data that relates to them.