Standard deviation is the number that tells you how spread out a set of data is. A small standard deviation means the values are close together, and a large one means they are spread far apart. It shows up in statistics class, in science labs, and in any problem where you need to describe how consistent a set of measurements is. Your TI-84 can work out standard deviation in seconds with 1-Var Stats, but you need to know which of the two standard deviations it gives you to use, and what the answer means. This guide explains both.
What standard deviation means
Imagine two sets of test scores. In the first set, everyone scores between 78 and 82. In the second set, the scores range from 40 to 100. Both sets might have the same mean, 80, but they are very different. The first set has a small standard deviation, because the scores are close to the mean. The second set has a large standard deviation, because the scores are spread out. Standard deviation is a single number that captures that difference.
Standard deviation is measured in the same units as the data. If your data is test scores out of 100, the standard deviation is in points. If your data is heights in centimetres, the standard deviation is in centimetres. A standard deviation of 5 points means the typical score is about 5 points away from the mean. That is a useful way to think about it, even if it is not exactly what the formula does.
Step 1: enter your data
Press [STAT] and choose 1: Edit. Move to L1 and type your data, pressing [ENTER] after each number. For our example, use the data 12, 15, 18, 21, 24. Type 12, press [ENTER], type 15, press [ENTER], and keep going until all five numbers are in L1. If L1 has old data in it, clear it first by moving to the top of L1, pressing [CLEAR], and pressing [ENTER].
Check your data before you go any further. A single typing error will make your standard deviation wrong, and the calculator will not warn you. Read the list through and compare it with the data in your question. If your data comes with frequencies, put the values in L1 and the frequencies in L2, and remember to tell the calculator about both lists when you run 1-Var Stats.
Step 2: run 1-Var Stats and find Sx and σx
Press [STAT], press the right arrow to move to CALC, and choose 1: 1-Var Stats. If your data is in L1, press [ENTER] to calculate. The calculator will show you a screen full of results. Look for Sx and σx. Those are the two standard deviations. For our data 12, 15, 18, 21, 24, Sx should be about 4.74 and σx should be about 4.24. They are different, and you need to know which one to use.
Sx is the sample standard deviation. It is the one you use when your data is a sample, a smaller group taken from a larger population, which is most of the time in school statistics. σx is the population standard deviation. It is the one you use when your data is the whole population, every value there is. Most school problems use Sx, the sample standard deviation, unless the question says population. If your teacher does not say, use Sx. If you are not sure, ask, because using the wrong one is a common way to lose marks.
What the numbers mean for your data
For our data, the mean is 18 and Sx is about 4.74. That means the values are typically about 4.74 away from the mean of 18. The values range from 12 to 24, which is 6 away from the mean in each direction, so a standard deviation of 4.74 makes sense. If the data were 17, 18, 18, 18, 19, the standard deviation would be much smaller, about 0.71, because the values are close to the mean. If the data were 0, 10, 20, 30, 40, the standard deviation would be much larger, about 15.81, because the values are spread out.
You can use the standard deviation to compare two sets of data. If one set has a standard deviation of 2 and another has a standard deviation of 10, the second set is much more spread out, even if they have the same mean. That comparison is the point of standard deviation. It is not just a number to work out. It is a way to describe data.
Standard deviation and the normal curve
Standard deviation is also the key to the normal distribution, which is the bell-shaped curve that shows up in statistics class. For data that is roughly normal, about 68% of the values are within one standard deviation of the mean, about 95% are within two standard deviations, and about 99.7% are within three. That is the 68-95-99.7 rule, and it is worth knowing, because it lets you estimate how many values are in a range without working it out exactly.
For example, if test scores have a mean of 70 and a standard deviation of 5, about 68% of the scores are between 65 and 75, and about 95% are between 60 and 80. You can work that out in your head once you know the mean and the standard deviation, and it is a good way to check whether a standard deviation makes sense. If the standard deviation is 5 and the scores range from 0 to 100, something is wrong, because a range that wide should have a much larger standard deviation.
Common mistakes
The most common mistake is using σx when you should use Sx, or the other way round. Read the question. If it says sample, use Sx. If it says population, use σx. If it does not say, use Sx, because most school problems are about samples. The second most common mistake is entering the data in the wrong list, or running 1-Var Stats on the wrong list. Always check that your data is in L1 and that you told the calculator to use L1.
Another mistake is forgetting to clear an old list, so your data has extra numbers at the bottom that you did not notice. Clear L1 before you start, every time. A fourth mistake is thinking that standard deviation can be negative. It cannot. It is a distance, and distances are never negative. If you get a negative standard deviation, you have read the wrong number, or you have made a mistake. The standard deviation is always zero or positive.
Try it yourself
Try these on your calculator. Enter the data 5, 10, 15, 20, 25 into L1 and run 1-Var Stats. Sx should be about 7.91 and σx should be about 7.07. Enter the data 100, 101, 102, 103, 104 into L1 and run 1-Var Stats. Sx should be about 1.58. Notice how much smaller the standard deviation is when the data is close together. If you can work out both sets and explain why the second standard deviation is smaller, you have the standard deviation skill down, and you can use it to describe any set of data you meet.