Simple random sampling has often been used by researchers when determining the sample. In this case, the researchers chose a random sample. Researchers who choose this technique must meet the required assumptions. Incidentally, on this occasion, I will discuss the topic of simple random sample selection techniques.

The simple random sampling technique is one of the sampling techniques grouped in the probability sampling group. For those who have studied research methodologies, that sampling can be grouped into probability sampling and non-probability sampling. “So, what’s the difference?”

The difference between the two is that probability sampling provides an equal opportunity for each member of the population to be selected as a sample. You can find out the non-probability sampling, right? Well, for non-probability sampling, it is the opposite, where this sampling technique does not provide equal opportunities for members of the population to be selected as samples.

Until this stage, you are expected to understand that simple random sampling is a sampling technique done by determining the same probability for each member of the population to be selected as a sample. Then, maybe you have a question “why do we need to determine the sample?”

Based on the theory, if we make observations, it would be better to observe all members of the existing population. However, there are limitations encountered. Generally, the boundaries of human resources, time and cost are the main considerations why researchers prefer to use samples rather than observe all population members. For example, if the population members are 100 to 200 respondents in survey research, it may not be a problem. What if it turns out that the population to be observed is 10,000 respondents?

Therefore, sampling is the answer to these obstacles. “Can we choose the number of samples we want?” certainly not. In selecting the sample, you must justify following scientific and statistical rules.

Researchers very often use simple random sampling. When choosing this technique, the researcher must already have a sampling frame. Suppose you already have data that there are 1000 members of the population; the next step is to make sure that the population members are homogeneous? If the population members are homogeneous, you are already on the right path. The next question is, what is the minimum number of samples that can be taken to be representative?

Before answering this question, you need to know what representative means here. So, a representative sample can represent the population. If it is representative, the conclusions from the research results using the sample can certainly represent the observed population.

Furthermore, there are several ways to determine the minimum sample to be representative. I happened to have made a video tutorial on determining the sample using the Slovin formula. You can use Slovin’s formula to determine the minimum number of samples to be representative. You can see the video tutorial below (video in Indonesian, please use subtitles):

Furthermore, based on the video, you have determined a representative minimum sample. “Does the number of samples have to be the same as the results of the Slovin formula?” Of course, the answer is no. As previously stated, the Slovin formula is the minimum number of samples. Suppose you could use a larger number of samples, even better. This will usually be linked to the time, cost, and human resources needed to conduct the research.

SAfter you have obtained the number of samples, you need to know how to choose a random sample in the next step. To make it easier to understand when selecting a sample at random, we can analogy mothers doing a social gathering. Usually, in social gatherings, in a shaker, the names have been written on a small piece of paper that is rolled up. Then when doing the draw, the mothers will shuffle several times and then issue a roll of paper to determine whose name wins. This analogy means that the mothers have chosen a sample at random.

The development of technology and science causes their method to take up quite a lot of time. We can easily do the random sampling method using Microsoft Excel. For those of you who already know, I say alhamdulillah. For those who don’t know-how, you can watch the video tutorial that I have prepared (video in Indonesian, please use subtitles):

Alright, I think our article this time has provided enough information. Let’s recap the results of our review this time. The first thing is that the simple random sampling technique offers equal opportunities for each member of the population to be selected as a sample. Furthermore, in using simple random sampling, you need to have a sample frame and the population members chosen as samples are homogeneous.

Hopefully, this article can provide value-added knowledge and benefits for those who need it. Wait for the update of the Kanda data article in the next week!

RioThank you, great!