Most important things to know, Chapters 1-7:

Chapter 1:

How to make and read frequency tables & histograms

What distributions are, and how they differ in shape

Chapter 2:

How to calculate three common parameters used to describe populations of scores: Mean, variance, standard deviation

What a Z-score is, and how to go from raw scores to Z scores and back.

Chapter 3:

What a correlation is, how it is calculated, and that correlations differ in strength, linear vs curvilinear, positive vs negative

How to do bivariate regression: prediction using Z-scores of X and Y

[Advanced concept, from lecture: regression to the mean]

Chapter 4:

How to find proportions under the normal curve using the normal curve table

Relative frequency interpretation of probability; application of this interpretation to determine exact probabilities of scores in a certain range using a theoretically determined distribution like the normal curve

Difference between population parameters and sample statistics

Chapters 5-6:

Sampling distributions: what they are, how they differ from the underlying population distribution, and how we use them in hypothesis testing

Steps of hypothesis testing [see handout from class exercise--also on web]

How to calculate the standard error, and what it is

Significance levels and what they mean

The two kinds of estimation

[Advanced concept, from lecture: The central limit theorem and what it tells us about sampling distributions]

Chapter 7:

What Type I (alpha) and Type II (beta) errors are and how they are related

Advanced concepts [most of this chapter!]

What effect size is and how to calculate it using Cohen's d

What statistical power is, and its relation to beta

Five things that affect power: sample size, effect size, one or two-tailed test, alpha, sigma

The hardest things to understand/learn, Chapters 1-7 (my guesses)

Chapter 1:

Translating a list of numbers into a visual shape -- the frequency distribution

Chapter 2:

What variance and standard deviation mean, and why we calculate them the way we do (deviation scores, squaring, square root, etc.)

Getting comfortable with Z-score transformations

Chapter 3:

The formula for correlation -- why it works, and how to understand the number you get

The process of predicting one score from another, based on knowing the correlation

Multiple regression

Variance as a "substance" that we divide up: why the correlation squared is a measure of a "proportion of variance" in one variable accounted for by another variable

Regression to the mean--what it is, why it occurs

Chapter 4:

Learning to use the normal curve table

Chapters 5-6:

Sampling distributions: what they are, how (and why) they differ from the underlying population distribution, and how we use them in hypothesis testing

Steps of hypothesis testing --very confusing! Especially:

* Emphasis on null hypothesis

* Use of sampling distribution of mean

* What critical values are and how to connect them to both the sampling distribution and the decision about the null hypothesis

* Peculiar business of mixing and matching information generated from the sample (sample mean, sample size) with information generated from the comparison [NULL] population (mu, sigma-squared, sampling distribution)

How the standard error differs from the population standard deviation (sigma)

Chapter 7:

Keeping Type I and Type II errors straight

Understanding what effect size and statistical power mean

Learning how sample size, sigma, effect size, one or two-tailed test, alpha all affect statistical power (and, especially, understanding why).