How To Determine Sample Size For A Study

Contents:

What is a Sample Size?
How to Observe a Sample size:
- Function 1: Full general Tips.
- Cochran's Sample Size Formula
- Yamane's Sample Size Formula
- Known Conviction Interval and Width (unknown population standard divergence).
- Known Conviction Interval and Width (known population standard departure).
- Detect a sample size to approximate a population mean
- Apply Excel to discover a sample size.

Watch the video for an overview of how to find a sample size:

How to Find a Sample Size

Tin can't see the video? Click here.

What is a "Sample Size"?

A sample size is a part of the population chosen for a survey or experiment. For case, you might take a survey of dog possessor's brand preferences. Y'all won't desire to survey all the millions of dog owners in the country (either considering it's too expensive or fourth dimension consuming), so you take a sample size. That may be several thousand owners. The sample size is a representation of all domestic dog possessor's brand preferences. If you choose your sample wisely, it will exist a good representation.

When Error can Pitter-patter in

When you merely survey a small sample of the population, uncertainty creeps in to your statistics. If you can but survey a certain percentage of the true population, you lot can never be 100% sure that your statistics are a consummate and accurate representation of the population. This dubiety is called sampling error and is commonly measured by a confidence interval. For example, yous might state that your results are at a 90% confidence level. That means if yous were to repeat your survey over and over, 90% of the time your would get the same results.

A census is where every member of a population is surveyed, not just a sample.

Back to superlative

How to Observe a Sample Size in Statistics

A sample is a percentage of the total population in statistics. You lot can use the data from a sample to make inferences about a population equally a whole. For example, the standard divergence of a sample can be used to approximate the standard divergence of a population. Finding a sample size can exist i of the most challenging tasks in statistics and depends upon many factors including the size of your original population.

General Tips

Step 1: Conduct a census if yous accept a small population. A "small" population will depend on your budget and fourth dimension constraints. For example, it may take a day to take a census of a student body at a small private academy of 1,000 students just you may not take the time to survey 10,000 students at a large state academy.

Step two: Apply a sample size from a like written report. Chances are, your type of study has already been undertaken by someone else. You'll demand access to academic databases to search for a written report (usually your school or higher will have access). A pitfall: you'll be relying on someone else correctly calculating the sample size. Any errors they have made in their calculations volition transfer over to your study.

Step 3: Utilize a table to find your sample size. If you have a fairly generic study, then at that place is probably a table for it. For instance, if you have a clinical written report, y'all may be able to use a table published in Machin et. al's Sample Size Tables for Clinical Studies, Tertiary Edition.

Stride iv: Use a sample size reckoner. Various calculators are bachelor online, some unproblematic, some more complex and specialized. For example, this calculator is for group- or cluster-randomized trials (GRTs).

Stride 5: Use a formula. There are many different formulas you tin can employ, depending on what yous know (or don't know) well-nigh your population. If yous know some parameters about your population (similar a known standard departure), you can utilise the techniques beneath. If you don't know much nigh your population, use Slovin's formula..
Back to peak

Cochran's Sample Size Formula

Watch the video for an example:

Cochran'south Formula for Sample Size

Can't see the video? Click here.

The Cochran formula allows you to calculate an platonic sample size given a desired level of precision, desired confidence level, and the estimated proportion of the attribute present in the population.

Cochran'south formula is considered especially appropriate in situations with large populations. A sample of any given size provides more than information nigh a smaller population than a larger one, and then at that place's a 'correction' through which the number given by Cochran's formula can be reduced if the whole population is relatively small.

The Cochran formula is:

Where:

due east is the desired level of precision (i.e. the margin of error),
p is the (estimated) proportion of the population which has the attribute in question,
q is 1 – p.

The z-value is found in a Z table.

Cochran's Formula Example

Suppose we are doing a study on the inhabitants of a big boondocks, and want to find out how many households serve breakfast in the mornings. We don't have much information on the subject to begin with, and then we're going to assume that one-half of the families serve breakfast: this gives us maximum variability. So p = 0.five. At present let'due south say we want 95% confidence, and at to the lowest degree 5 percentage—plus or minus—precision. A 95 % confidence level gives united states Z values of one.96, per the normal tables, so we get

((one.96)^two (0.5) (0.five)) / (0.05)² = 385.

So a random sample of 385 households in our target population should be enough to give usa the confidence levels we need.

Modification for the Cochran Formula for Sample Size Calculation In Smaller Populations

If the population nosotros're studying is small, we can change the sample size we calculated in the above formula by using this equation:

Here n₀ is Cochran's sample size recommendation, N is the population size, and northward is the new, adjusted sample size. In our before instance, if there were just 1000 households in the target population, we would calculate

385 / (1 + ( 384 / yard )) = 278

So for this smaller population, all nosotros need are 278 households in our sample; a substantially smaller sample size.

Yamane'southward Formula

Yamane'southward formula is:
yamane's formula sample size

Where:

e = precision level
N = population size.

Watch the video for an case:

Yamane'southward Sample Size Formula

Can't run across the video? Click hither.

How to Observe a Sample Size Given a Confidence Level and Width (unknown population standard deviation)

Role ii shows y'all how to find a sample size for a given conviction level and width (e.m. 95% CL, 6% wide) for an unknown population standard deviation .

Example question: 41% of Jacksonville residents said that they had been in a hurricane. How many adults should be surveyed to estimate the true proportion of adults who have been in a hurricane, with a 95% confidence interval 6% wide?

Stride 1: Using the data given in the question, figure out the following variables:

Step 2: Multiply past . Set this number bated for a moment.
0.41 × 0.59 =0.2419

Step 3: Divide Z_a/2 by E.
1.96 / .03 = 65.3333333

Stride 4: Square Step three:
65.3333333 × 65.3333333 = 4268.44444

Step 5: Multiply Footstep 2 by Stride 4:
0.2419 × 4268.44444 = 1,032.53671
= 1,033 people to survey.
Back to peak

How to Discover a Sample Size Given a Conviction Level and Width (known population standard difference)

Part three shows you lot how to determine the appropriate sample size for a given confidence level and width, given that yous know the population standard departure.

Instance question: Suppose nosotros want to know the boilerplate age of an Florida Country College student, plus or minus 0.5 years. Nosotros'd like to be 99% confident about our result. From a previous study, nosotros know that the standard deviation for the population is 2.9.

Pace 1: Detect z _a/twoby dividing the conviction level by 2, and looking that area up in the z-table:
.99/ii = 0.495. The closest z-score for 0.495 is 2.58.

Step ii: Multiply step one by the standard deviation.
ii.58 * 2.9 = seven.482

Footstep three: Divide Footstep ii by the margin of fault. Our margin of error (from the question), is 0.5.
7.482/0.5 = fourteen.96

Step iv: Square Step three.
xiv.96 * fourteen.96 = 223.8016

That'south it! Similar the explanation? Check out our statistics how-to book, with a how-to for every elementary statistics problem blazon.
Back to top

Observe a sample size to judge a population mean

Scout the video to find out how to notice a sample size if you want to estimate ways:

Sample Size for Population Hateful Confidence Level

Tin can't see the video? Click here.

How to find a sample size in Excel.

Picket the video or read the steps below:

How to select a sample using Data Analysis in Excel 2013

How to use Excel Sampling to find a Sample

If you have a set of data and you know your sample size, yous tin utilise Excel's Data Analysis toolpak to select either a periodic sample or a random sample. A random sample is but that — randomly selected from your data ready. A periodic sample (too called a systematic sample) is where Excel chooses the nth data detail to include in your sample. For example, if you wanted to choose every 5th number from the post-obit list: iv, five, 6, 7, 8, 9, 10, 11, 12, 13, fourteen, Excel would return 8 and xiii (the 5th and tenth numbers in order).

If you don't know what sample size you need, calculate it before using the Data Analysis tool (using the methods outlined at the meridian of this commodity). The Data Assay tool can help you excerpt a sample, but information technology can't assist you lot decide on the size. Why? There are many "human being" factors that become into selecting a sample size including budget, prior inquiry (you can use a sample size from previous enquiry) and tables synthetic from previous research.

How to utilize Excel Sampling to discover a Sample: Steps

Pace 1: Enter your data items into Excel. You lot can enter your data into rows or columns. Ensure the rows and columns are even; for instance, enter data into column A to jail cell 12 and cavalcade B to cell 12.

Step 2: Click "Data" and so click "Information Analysis." If you don't run into Information Analysis on your toolbar, load the Information Assay Toolpak.

Pace iii: Click "Sampling" and then click "OK."

excel sampling.

Data entered into a worksheet for Excel sampling: the rows and columns are even.

Step 4: Click in the Input Range box and then select your entire data fix.

Step five: Click either "Periodic Sampling" or "Random Sampling." If you cull periodic, enter the nth number (i.e. every 5) and if y'all choose random sampling, enter the sample size.

Step 6: Choose an output range. For example, click the "New Worksheet" button and Excel will return the sample in a new worksheet.

Step 7: Click "OK."

That's it!

Bank check out our YouTube channel for more Excel tips and help!
Back to top

Ways to Reduce Sample Size.
Effective Sample Size..
Unequal sample size.

References

Bartlett, J. et al. (2001). Organizational Research: Determining Appropriate Sample Size in Survey Research. Retrieved Jan 15, 2018 from: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.486.8295&rep=rep1&type=pdf.
Evans, K.; Hastings, N.; and Peacock, B. Statistical Distributions, third ed. New York: Wiley, 2000.
Israel, G. (n.d.) Determining Sample Size. University of Florida IFAS Extension. Article posted on Tarleton State University website. Retrieved Jan xiii, 2018 from https://world wide web.tarleton.edu/academicassessment/documents/Samplesize.pdf.

---------------------------------------------------------------------------

Need help with a homework or test question? With Chegg Study, you can get step-by-step solutions to your questions from an expert in the field. Your first 30 minutes with a Chegg tutor is free!

Need help with a homework or test question? With Chegg Study, you can become stride-by-pace solutions to your questions from an expert in the field. Your first 30 minutes with a Chegg tutor is costless!

Comments? Demand to mail a correction? Please post a comment on our Facebook page .