Simple Random Sampling Example Calculation

Use this interactive calculator to estimate the sample size needed for a simple random sample. Enter your population size, confidence level, margin of error, and expected proportion to see the recommended sample, finite population correction, and a visual comparison chart.

Expert Guide to a Simple Random Sampling Example Calculation

Simple random sampling is one of the most widely taught and most practical methods in survey research, auditing, public health, education, and business analytics. The reason is straightforward: every member of the population has an equal chance of being selected. That feature makes the method easy to explain, statistically defensible, and highly useful when you want a sample that represents a larger group without introducing avoidable selection bias.

When people search for a simple random sampling example calculation, they usually want to answer one of two questions. First, how many observations do I need? Second, how does the math work in a realistic scenario? This page focuses on the first question and shows the exact sample size calculation commonly used for proportions. It also explains how finite population correction works, why confidence level matters, and when a 50% estimated proportion is the safest planning assumption.

What simple random sampling means

In a simple random sample, each unit in the population has the same probability of selection, and each possible sample of a given size is equally likely. Imagine you have a complete list of 10,000 customers and you want feedback on satisfaction. If you randomly assign each customer a number and use a random number generator to pick respondents, you are using simple random sampling.

This method differs from convenience sampling, where you only ask people who are easy to reach, or quota sampling, where you deliberately fill categories. Convenience methods are often faster, but they can seriously distort results. In contrast, a properly executed simple random sample supports valid confidence intervals and more reliable inference about the broader population.

The basic sample size formula

For a proportion, the initial sample size estimate for a large population is:

n₀ = (Z² × p × (1 – p)) / e²

Where:

• Z is the z-score tied to your confidence level, such as 1.96 for 95% confidence.
• p is the estimated proportion, expressed as a decimal. For example, 50% becomes 0.50.
• e is the margin of error, also expressed as a decimal. For example, 5% becomes 0.05.

If your population is not extremely large, the next step is to apply the finite population correction. That adjustment reduces the required sample size when the total population is known and relatively small.

n = n₀ / (1 + ((n₀ – 1) / N))

Here, N is the total population size. The result is usually rounded up to the next whole number because you cannot sample a fraction of a person, household, or record.

Step by step simple random sampling example calculation

Suppose a school district wants to estimate the proportion of parents who support a new after-school program. The district has a population of 10,000 families. It wants 95% confidence and a margin of error of 5%. Because it does not know the likely support rate in advance, it uses p = 0.50.

1. Set the inputs:
   • Population size, N = 10,000
   • Confidence level, 95%
   • Z-score, Z = 1.96
   • Margin of error, e = 0.05
   • Estimated proportion, p = 0.50
2. Compute the large-population sample size:
   • n₀ = (1.96² × 0.50 × 0.50) / 0.05²
   • n₀ = (3.8416 × 0.25) / 0.0025
   • n₀ = 0.9604 / 0.0025 = 384.16
3. Apply finite population correction:
   • n = 384.16 / (1 + ((384.16 – 1) / 10,000))
   • n = 384.16 / (1 + 0.038316)
   • n = 384.16 / 1.038316 = 370.00 approximately
4. Round up if needed. Recommended sample size: 370.

This is exactly the kind of result the calculator above produces. It shows both the unadjusted sample size and the finite-population adjusted size so you can see how much the population size changes the requirement.

Why researchers often use 50% for the estimated proportion

Many beginners wonder why so many sample size calculators default to 50%. The reason is statistical caution. The term p × (1 – p) reaches its maximum value at 0.50. That means the required sample size is largest when the expected proportion is 50%. If you choose 50% in advance, you avoid underestimating the sample needed. If you already have strong historical evidence that the true proportion is closer to 10% or 90%, you can enter that instead and often obtain a smaller sample size.

How confidence level changes the result

Confidence level reflects how strongly you want your interval estimate to capture the true population value over repeated samples. A higher confidence level means more caution and therefore a larger sample. Moving from 90% to 95% increases the z-score from 1.645 to 1.96. Moving to 99% raises it to 2.576. Because the z-score is squared in the formula, that increase can materially raise your required sample size.

Confidence level	Z-score	Interpretation in practice	Impact on sample size
90%	1.645	Useful for exploratory work or early-stage analysis	Smallest of the three common options
95%	1.96	Standard choice for most academic, market, and policy studies	Balanced precision and feasibility
99%	2.576	Used when higher certainty is required	Largest required sample

How margin of error affects sample size

Margin of error has an even stronger effect than many users expect. Because it appears in the denominator as a squared term, a tighter margin of error can substantially increase your sample. For example, reducing the margin of error from 5% to 3% does not merely increase the sample a little. It can more than double it. That is why feasibility, budget, and timeline matter so much in sample design.

Example population	Confidence level	Margin of error	Estimated proportion	Approximate adjusted sample size
10,000	95%	5%	50%	370
10,000	95%	3%	50%	965
10,000	99%	5%	50%	623
5,000	95%	5%	50%	357

These figures illustrate the relationship between precision assumptions and sample requirements for a simple random sample of a finite population.

Real-world survey statistics that show sampling at scale

To understand why sample design matters, it helps to look at actual large survey programs. These organizations rely on rigorous statistical methods because policy and funding decisions depend on the quality of the estimates they produce.

Program	Organization	Reported scale	Why it matters
American Community Survey	U.S. Census Bureau	About 3.5 million addresses sampled each year	Shows how large, probability-based sampling supports national and local estimates
Behavioral Risk Factor Surveillance System	CDC	More than 400,000 adult interviews each year	Demonstrates the scale needed for state-level health estimates
National Assessment of Educational Progress	NCES	Nationally representative student samples across grades and subjects	Illustrates how sampling supports education benchmarking without testing every student

Although these programs often use more complex designs than pure simple random sampling, they still depend on the same core statistical logic: probability-based selection, transparent weighting, and careful management of sampling error. For many business and classroom applications, simple random sampling is the ideal starting point because the principles are easy to understand and implement correctly.

Common mistakes in simple random sampling calculations

• Using percentages instead of decimals in the formula. A 5% margin of error must be entered as 0.05 in the math.
• Ignoring the finite population correction. For a small or moderate population, the corrected sample can be noticeably smaller than the large-population estimate.
• Confusing population size with sample size. The population is the full group. The sample is the subset you actually survey.
• Relying on convenience responses after planning a random sample. If selection stops being random, the calculation no longer matches the fieldwork.
• Forgetting nonresponse. If you need 370 completed responses and expect only a 50% response rate, you may need to contact about 740 sampled units.

When a simple random sample is the right choice

A simple random sample works best when you have a complete list of the population, no strong need to oversample subgroups, and a goal of estimating an overall proportion or mean. It is especially useful for:

• Customer satisfaction surveys with a full customer database
• Student opinion polling within a school or university roster
• Quality control spot checks on a complete inventory list
• Internal audits where every record can be numbered and randomly selected

It may be less efficient if your population includes very different subgroups and you must guarantee representation for each one. In that case, a stratified sample can be better. Still, simple random sampling remains the conceptual foundation for understanding more advanced methods.

How to interpret your calculator result

If the calculator says your recommended sample size is 370, that does not mean exactly 370 responses will guarantee perfect accuracy. It means that under the assumptions of random selection, the chosen confidence level, and the specified margin of error, a sample of about 370 completed observations is statistically sufficient for estimating a proportion. Real-world conditions such as nonresponse bias, frame coverage error, and data quality problems can still affect the final result.

That is why good survey practice combines proper sample size planning with disciplined execution. You need a complete sampling frame, a reliable randomization method, consistent data collection, and documentation of who responded and who did not. Statistical design and field procedures must work together.

Recommended authoritative references

For deeper study, these official and academic sources are excellent starting points:

• U.S. Census Bureau: American Community Survey overview
• Centers for Disease Control and Prevention: BRFSS
• Penn State STAT 500: Applied Statistics

Final takeaway

A simple random sampling example calculation becomes much easier once you break it into four inputs: population size, confidence level, margin of error, and estimated proportion. Start with the large-population formula, apply the finite population correction when needed, and round up to the next whole number. If you are uncertain about the expected proportion, use 50% for a conservative plan. Then adjust for likely nonresponse so your final number of completed responses still meets the target.

The calculator above automates the arithmetic, but the underlying logic remains important. The better you understand the assumptions behind simple random sampling, the more confidently you can design a survey, justify your sample size, and explain your results to clients, teachers, managers, or stakeholders.