Do you still call it a t-test (therefore t-statistic) if you are calculating a sample mean to a population mean where the mean and std dev of the population are known, but...the size of the sample is n=1. i.e. the sample is just a single instance and therefore the mean of the sample is just the value of that one instance.What is being calculated is just the z-score but can you still call this a t-statistic?Since for t-statistic where the population standard deviation is known, the hypothesis is tested against the values on the normal distribution and not the t-distribution table. See hereThanks,lenni

Even if the sample size is 1 it is still a z test. T test is used when you don't know the population standard deviation so you have to use sample standard deviation instead.

The most common use of a t-test is to test whether your data is consistent with the unknown population mean ("true" mean, "underlying" mean) being some value you're interested in, often zero, when you don't know the population variance and you do know the data is normally distributed. So you might perhaps test a set of excess returns, (or excess log returns), against the hypothesis of their true mean being zero. Here you say you do know the population mean and have a sample size of 1, so I'm not sure you're doing a test in the way statisticians think of it. "z score" is fine as you're essentially measuring a distance on the standard normal distribution (the article you have referenced is too complex really for what you need to do). Tone.