wikiHow is a “wiki,” similar to Wikipedia, which means that many of our articles are cowritten by multiple authors. To create this article, 23 people, some anonymous, worked to edit and improve it over time.
wikiHow marks an article as readerapproved once it receives enough positive feedback. This article has 39 testimonials from our readers, earning it our readerapproved status.
This article has been viewed 1,779,998 times.
Learn more...
A Z score allows you to take any given sample within a set of data and to determine how many standard deviations above or below the mean it is. ^{[1] X Research source }. To find the Z score of a sample, you'll need to find the mean, variance and standard deviation of the sample. To calculate the zscore, you will find the difference between a value in the sample and the mean, and divide it by the standard deviation. Even though there are lots of steps to this method from start to finish, it is a fairly simple calculation.
Steps
Part 1
Part 1 of 4:Calculating the Mean

1Look at your data set. You will need certain key pieces of information to calculate the mean or mathematical average from your sample. ^{[2] X Research source }
 Know how many numbers are in your sample. In the case of the sample of palm trees, there are 5 in this sample.
 Know what the numbers represent. In our example, these numbers represent measurements of trees.
 Look at the variation in the numbers. Does the data vary across a large range, or a small range?

2Gather all of your data. You will need all the numbers in your sample to start your calculations. ^{[3] X Research source }
 The mean is the average of all the numbers in your sample.
 To calculate this you will add all the numbers in your sample together, then divide by the sample size.
 In mathematical notation, n represents the sample size. In the case of our sample of tree heights, n = 5 since there are 5 numbers in this sample.
Advertisement 
3Add all the numbers in your sample together. This is the first part of calculating the mathematical average or mean.^{[4] X Research source }
 For example, using the sample of 5 palm trees, our sample consists of 7, 8, 8, 7.5, and 9.
 7 + 8 + 8 + 7.5 + 9 = 39.5. This is the sum of all the numbers in your sample.
 Check your answer to make sure you did your addition correctly.

4Divide the sum by your sample size (n). This will provide the average or mean of the data. ^{[5] X Research source }
 For example, use our sample of tree heights: 7, 8, 8, 7.5, and 9. There are 5 number in our sample so n = 5.
 The sum of tree heights in our sample was 39.5. You would then divide this figure by 5 to figure out the mean.
 39.5/5 = 7.9.
 The mean tree height is 7.9 feet. The population mean is often represented by the symbol μ, therefore μ = 7.9
Advertisement
Part 2
Part 2 of 4:Finding the Variance

1Find the variance. The variance is a figure that represents how far your data in your sample is clustered about the mean. ^{[6] X Research source }
 This calculation will give you an idea about how far your data is spread out.
 Samples with low variance have data that is clustered closely about the mean.
 Samples with high variance have data that is spread far from the mean.
 Variance is often used to compare the distributions between two data sets or samples.

2Subtract the mean from each of the numbers in your sample. This will give you an idea of how much each number in your sample differs from the mean.^{[7] X Research source }
 In our sample of tree heights (7, 8, 8, 7.5, and 9 feet) the mean was 7.9.
 7  7.9 = 0.9, 8  7.9 = 0.1, 8  7.9 = 0.1, 7.5  7.9 = 0.4, and 9  7.9 = 1.1.
 Do these calculations again to check your math. It is extremely important that you have the right figures for this step.

3Square all of the answers from the subtractions you just did. You will need each of these figures to figure out the variance in your sample.^{[8] X Research source }
 Remember, in our sample we subtracted the mean of 7.9 from each of our data points (7, 8, 8, 7.5, and 9) and came up with the following: 0.9, 0.1, 0.1, 0.4, and 1.1.
 Square all of these figures: (0.9)^2 = 0.81, (0.1)^2 = 0.01, (0.1)^2 = 0.01, (0.4)^2 = 0.16, and (1.1)^2 = 1.21.
 The squares from this calculation are: 0.81, 0.01, 0.01, 0.16, and 1.21.
 Check your answers before proceeding to the next step.

4Add the squared numbers together. This calculation is call the sum of squares. ^{[9] X Research source }
 In our sample of tree heights, the squares were as follows: 0.81, 0.01, 0.01, 0.16, and 1.21.
 0.81 + 0.01 + 0.01 + 0.16 + 1.21 = 2.2
 For our example of tree heights, the sum of squares is 2.2.
 Check your addition to make sure that you have the right figure before moving on.

5Divide the sum of squares by (n1). Remember, n is your sample size (how many numbers there are in your sample). Doing this step will provide the variance. ^{[10] X Research source }
 In our sample of tree heights (7, 8, 8, 7.5, and 9 feet), the sum of squares was 2.2.
 There are 5 numbers in this sample. Therefore n = 5.
 n  1 = 4
 Remember the sum of squares is 2.2. To find the variance, calculate the following: 2.2 / 4.
 2.2 / 4 = 0.55
 Therefore the variance for this sample of tree heights is 0.55.
Advertisement
Part 3
Part 3 of 4:Calculating the Standard Deviation

1Find your variance figure. You will need this to find the standard deviation for your sample. ^{[11] X Research source }
 Variance is how spread out your data is from the mean or mathematical average.
 Standard deviation is a figure that represents how spread out your data is in your sample.
 In our sample of tree heights, the variance was 0.55.

2Take the square root of the variance. This figure is the standard deviation. ^{[12] X Research source }
 In our sample of tree heights, the variance was 0.55.
 √0.55 = 0.741619848709566. You will often get a very large decimal figure when you calculate this step. It is ok to round to the second or third decimal place for your standard deviation figure. In this case, you could use 0.74.
 Using a rounded figure, the standard deviation in our sample of tree heights is 0.74

3Go through finding the mean, variance, and standard deviation again. This will allow you to make sure you have the correct figure for standard deviation.
 Write down all the steps you took when you did your calculations.
 This will allow you to see where you made a mistake, if any.
 If you come up with different figures for mean, variance, and standard deviation during your check, repeat the calculations looking at your process carefully.
Advertisement
Part 4
Part 4 of 4:Calculating Z Scores

1Use the following format to find a zscore: z = X  μ / σ. This formula allows you to calculate a zscore for any data point in your sample. ^{[13] X Research source }
 Remember, a zscore is a measure of how many standard deviations a data point is away from the mean.
 In the formula X represents the figure you want to examine. For example, if you wanted to find out how many standard deviations 7.5 was from the mean in our example of tree heights, you would plug in 7.5 for X in the equation.
 In the formula, μ stands for the mean. In our sample of tree heights the mean was 7.9.
 In the formula, σ stands for the standard deviation. In our sample of tree heights the standard deviation was 0.74.

2Start the formula by subtracting the mean from the data point you want to examine. This will start out the calculations for a zscore. ^{[14] X Research source }
 For example, in our sample of tree heights we want to find out how many standard deviations 7.5 is from the mean of 7.9.
 Therefore, you would perform the following: 7.5  7.9.
 7.5  7.9 = 0.4.
 Double check that you have the correct mean and subtraction figure before you proceed.

3Divide the subtraction figure you just completed by the standard deviation. This calculation will provide you with your zscore. ^{[15] X Research source }
 In our sample of tree heights, we want the zscore for the data point 7.5.
 We already subtracted the mean from 7.5, and came up with a figure of 0.4.
 Remember, the standard deviation from our sample of tree heights was 0.74.
  0.4 / 0.74 =  0.54
 Therefore the zscore in this case is 0.54.
 This zscore means that 7.5 is 0.54 standard deviations away from the mean in our sample of tree heights.
 Zscores can be both positive and negative numbers.
 A negative zscore indicates that the data point is less than the mean, and a positive zscore indicates the data point in question is larger than the mean.
Advertisement
Community Q&A

QuestionHow do I calculate the Z score for a 12 month old child who weighs 7 kg?Community AnswerYou would need to know the mean and standard deviation of weights from a large group of other 12 month old children. A doctor might have this information or you may be able to find it online. Then follow the steps in this article.

QuestionWhat is the Z score for a pulse rate of 69 beats per minute?Community AnswerZ score requires historical data. Assuming everyone was equally spread between 60100 bpm, the average is 80. Sample size is 41 (1 for each value between 60100, inclusive). Mean is 80, Standard Deviation is 11.98. So then (69  80) / 11.98, Z = 0.918. This answer is insignificant though, because you need data to calculate a Z score. Heart rate can be grouped by age, weight, habits, etc.

QuestionHow can I find the mean?Community AnswerAdd all the numbers, for example; 23+75+80+260=438. Divide the sum with the number of numbers you added up; in this case here, the numbers 23, 75, 80, and 260. There are four numbers in total, so with the sum (438) divide it by 4. 438/4=109.5.

QuestionWhere did you get 7.5 from?Community Answer7.5 was chosen from the tree heights in Part 1  Step 1 to compare to the rest of the data set. It was only chosen as an example for how to find the zscore.

QuestionHow do I find the Z score for my salary?Community AnswerFind out the mean and standard deviation of salary of your organization/state/country (depending upon your research area), and use this formula: z = X  μ / σ.

QuestionWhat is the percentile Z score for a score that is 1.3 standard deviation below the mean?Community Answer[(mean1.3(st.dev))mean]/st.dev=z score. Use appropriate zscore table to find the percentile or refer to your calculator's normalCDF.

QuestionWhat if I am only given a mean of 84 and two zscores of 0 and 0.8? I can't figure out how to find the data points the zscores come from. Can anyone at least explain how to solve for the variable of x in this situation?Community AnswerA value of zero zero score mean the first z score is the average which is 84 which is 0 sigma or in the first sigma. 0 = (x  84)/sigma 0.8 = (x mean)/sigma 0.8 = (x  84)/sigma not on the second

QuestionCan I compare Zscores obtained from two different data sets even though the distributions are different?Community AnswerThe Z score will simply tell you how far away from the mean you are. It shows performance relative to the average. So if two students score z=+2.1 on their tests, regardless of class average or their actual mark, they both are getting A's.

QuestionI want to ask for a raise at work, and want to see what percentile my pay ranks. The minimum hourly pay is $14.33, median is $19.62, and maximum is $24.90. What percentile is my pay of $16.66?Community AnswerYou are being paid 16.26 % more than the lowest, only receiving 84.9% of the median, and receiving a measly 66.9% of the highest.

QuestionHow can I use a Z score to find outlier data from a data set?Community AnswerAny zscore greater than 3 or less than 3 is considered to be an outlier. This rule of thumb is based on the empirical rule. From this rule we see that almost all of the data (99.7%) should be within three standard deviations from the mean.
Video
Tips
References
 ↑ http://www.statisticshowto.com/howtocalculateazscore/
 ↑ http://www.mathsisfun.com/data/standarddeviation.html
 ↑ http://www.mathsisfun.com/data/standarddeviation.html
 ↑ http://www.mathsisfun.com/data/standarddeviation.html
 ↑ http://www.mathsisfun.com/data/standarddeviation.html
 ↑ http://pirate.shu.edu/~wachsmut/Teaching/MATH1101/Descriptives/variability.html
 ↑ http://pirate.shu.edu/~wachsmut/Teaching/MATH1101/Descriptives/variability.html
 ↑ http://pirate.shu.edu/~wachsmut/Teaching/MATH1101/Descriptives/variability.html
 ↑ http://pirate.shu.edu/~wachsmut/Teaching/MATH1101/Descriptives/variability.html
 ↑ http://pirate.shu.edu/~wachsmut/Teaching/MATH1101/Descriptives/variability.html
 ↑ http://pirate.shu.edu/~wachsmut/Teaching/MATH1101/Descriptives/variability.html
 ↑ http://pirate.shu.edu/~wachsmut/Teaching/MATH1101/Descriptives/variability.html
 ↑ https://statistics.laerd.com/statisticalguides/standardscore2.php
 ↑ https://statistics.laerd.com/statisticalguides/standardscore2.php
 ↑ https://statistics.laerd.com/statisticalguides/standardscore2.php
About This Article
To calculate a Z score, start by calculating the mean, or average, of your data set. Then, subtract the mean from each number in the data set, square the differences, and add them all together. Next, divide that number by n minus 1, where n equals how many numbers are in the sample, to get the variance. Once you have the variance, take the square root of it to find the standard deviation. Finally, subtract the mean from the data point you're examining, and divide the difference by the standard deviation. To learn how to calculate the mean of your sample, read on!
Reader Success Stories

"Until I discovered this wikiHow, I had been completely lost in my statistics class. This is the first time that I actually grasp the formulas, what they are, and how they are related to each other. The pictures, language, and stepbystep instructions has made these impossibletolearn concepts possible!"..." more