MATH1005 Lecture 3: Copy of MATH1005 lecture 3 (2)
25 Aug 2018
School
Department
Course
Professor
Document Summary
You cannot rely solely on the mean to understand the data, or make conclusions for other applications, ie buying a house. This is because we do not know if the data is skewed, and as a result, may be mislead. (recall: two sets of data can be drastically different, but have the same mean. ) You calculate the gap between the house and the mean. Mean gap = mean of (data-mean) == 0 (always 0, because it s the balancing point) Standard deviation measures the spread of the data. So basically, the rms of the gaps from the mean sd(data) You can adjust the way that r establishes sd, depending if your data is the population or a sample, but the sd() normally gets a sample version. Below provides a population version: sd(data) * sqrt(55/56) The squared standard deviation is called the variance: sd^2. You can tell the difference between a sample and population based on your dataset.
