# Is median better than mean for reporting on website speed

Whilst I understand why median can be a better metric than mean in certain circumstances (e.g. you're creating/marketing a product, you want to use the median as it represents the biggest age group within your population and therefore real potential buyers, whereas mean age might be a number which doesn't correspond to anybody, or a very few people) I am wondering whether median is a good metric when it comes to measuring website performance.

Let's look at the below data representing page load time (in sec, the smaller the better):

Sample 1 and Sample 2 are identical, except for C4, meaning the website is only faster for 1 person. Yet, the median changes significantly between the 2 samples (nearly 40% improvement) whereas the mean is much more stable (less than 10% difference).

Accordingly my take on this is that mean is more accurate are representing the page load time.

Do you agree? / Is my observation biased because of the particular samples I have chosen or would mean be more representative than median no matter the samples?

• Median age need not represent the biggest age group. In statistics "changes significantly" would be best established by a formal test; changes that are big, striking or notable can be described informally using any simple word. That aside, the median can be unstable too in small samples. First, it must be a sample value or the average of two values. More importantly, you are rounding to seconds, so the median may easily jump by 0.5 s. In a larger dataset I would expect the mean for data like yours to be a bit larger than the median, but why not use both? Why do you feel you have to choose? – Nick Cox Dec 18 '13 at 12:29
• Thanks. Reason for wanting to choose one is that I like the idea of one number being more accurate than the other and that I get to use that number. Also, I'm gonna have to report this metric to management, and 2 different numbers with a whole explanation on statistics isn't going to cut it I'm afraid... What about the average value between the mean and median: does that make any sense? – Max Dec 18 '13 at 12:54
• The average of mean and median is just what it says; it doesn't have a special name or much of a following. If people want to compromise between mean and median they usually go for a trimmed mean or some other resistant or robust summary; if your management can't handle mean and median that is way too esoteric for them. My main recommendation is that you calculate both mean and median, work out for yourself what works better for your data and purposes, and report that to management. Note that means are natural if totals are. – Nick Cox Dec 18 '13 at 13:00