It is often useful to begin one’s examination of a set of data by looking at the distribution of scores

I feel like the author is talking about datasets in general. Scores? Does every entry in a dataset have a score? No, let’s just say these datasets have something called a score for each record and the score is numeric.

central tendency

I recall this. I’m a little rusty.

median … defined as the minimal score having at least 50% of the scores less than or equal to it.

Y

i to denote the score of the ith individual on the dependent variable

Y

bar sample mean

sample distribution … population distribution

Characteristics of samples are termed statistics, whereas characteristics of populations are called parameters.

Pretty sure I never knew that.

We will follow the convention of using Greek letters to denote population parameters and Roman letters to denote sample statistics.

Very clear! I feel like maybe this was always going on and I never noticed. lol

the expected value of Y is the sum of all values in the set times the probability of each.

Start here next pomo.

## Leave a Reply