DEV Community

Cover image for Ways to Collect Data
Dave Amiana
Dave Amiana

Posted on

Ways to Collect Data

Get the facts first, and then you can distort them as much as you please. (M. Twain)

Data collection is rudimentary for any research endeavor. Data is a significant component in all fields of study (Voung et al., 2018). The goal of data collection is to capture a shred of evidence that either proves or disproves an assertion subjected to the study. Along with statistical methods, raw data can be transformed into an insightful piece of information.

Data is everywhere, let's talk about the sorts of ways we can collect our data.

Irrespective of the fields of study, data collection must maintain research integrity. This article outlines five methods of data collection procedures.

  • Direct Method. Some forms of research need to get an in-depth examination with the interviewee. The direct method allows the researchers to provide follow-ups and clarification with their written form of questionnaires.

  • Indirect Method. In cases where the research calls for a large sample size, the Direct method is inconvenient for the researcher. Some forms of insights lie in the consensus drawn from a particular context. In return, the researcher may not expect that all distributed sets of questionnaires will be returned.

  • Registration Method. Some forms of data can be easily gathered by consolidating demographic and population statistics such as fetal deaths, marriages, divorces, judicial separations, adoptions, and the like.

  • Experimental Method. Some data can be gathered directly from an experimental setting where we can manipulate independent variable(s) in our attempts to moderate our investigations.

Your choice of data collection method will depend on the type of data you will be collecting, the precision required, and the research you are conducting.


Sampling Techniques

In most cases, gathering data from a population is infeasible. Sampling techniques rely on probability theory in gaining the confidence of the sample. For instance, random sampling uses the random chance to select sampling units from a population that permits generalizability if unbiased samples are obtained. Other techniques can be molded based on the context of our research problem.

  1. Simple Random Sampling. Simple random sampling obtains subjects by random numbers -- typically a pseudorandom number generator or games of chance are used to determine the samples.

  2. Systematic Sampling. Some research may want to select samples from a moving population. In such cases, systematic sampling is used where the researcher obtains the sample by selecting every k-th element of the population. Consider sampling from a population of N=15,000 people. A researcher may select every 10-th person for sampling or by an interval i.e. selecting samples every 10 hours.

  3. Stratified Sampling. Our research may permit us to divide our population by groups -- based on our particular characteristic of interest (variables). In these cases, we may administer our sampling for each group to gain a representative sample for our variables of interest. Consider this: our research needs to collate political opinions of different genders, we may want to group our population based on genders and gather our subjects within that strata(layer).

  4. Cluster Sampling. In other cases, our research may cluster our population wherein we may randomly select a cluster and subject all members of the cluster to our study. Consider this: an organization intends to survey the performance of their product across the Philippines. They can divide the entire county's population by cities (clusters) and select the highest population. Note that in this particular example, the researchers did not select the cluster by chance by formulating a criterion.

Determining Sample Size

To determine the sample size given the population of our study, we use the Slovin's Formula:

n=N1+Ne2n = \frac{N}{1+Ne^2}
  • nn - sample size
  • NN - population size
  • ee - margin of error

References:

  1. Vuong, Q. H., La, V. P., Vuong, T. T., Ho, M. T., Nguyen, H. K. T., Nguyen, V. H., ... & Ho, M. T. (2018). An open database of productivity in Vietnam's social sciences and humanities for public use. Scientific data, 5(1), 1-15.

  2. Directorate, O. E. C. D. S. (n.d.). OECD Glossary of Statistical Terms - Registration method Definition. https://stats.oecd.org/glossary/detail.asp?ID=3106.

  3. 6. DATA COLLECTION METHODS. (n.d.). http://www.fao.org/3/X2465E/x2465e09.htm.

  4. Bluman, A. G. (2013). Elementary statistics: A step by step approach: A brief version (No. 519.5 B585E.). McGraw-Hill.

Top comments (0)