Last Stats Test Before Final

Front 1

Normal Distribution

Back 1

very common and useful.

Describes many REAL variables:
height, weight, IQ, SAT.

Can be used to calculate probabilities

Front 2

Characteristics of the normal disribution

Back 2

Bell shaped; symmetrical; mean median and mode are equal; tail extends indefinitely; area under the curve equals 1.0

Front 3

You cannot directly compare scores when the mean and standard deviation are:

Back 3

different. The mean and SD have to be the same to directly compare.

Front 4

Standard scores

Back 4

scores with a set mean and standard deviation.
ex. IQ, GRE, t scores

Front 5

z score (one of the standard scores)

Back 5

States how many standard deviations the original score is above or below the mean of a distribution.

You calculate a z score to compare two distributions with different means and standard deviations.

Front 6

Characteristics of z scores

Back 6

The mean of any set of z scores equals 0.0
The standard deviation of any set of z scores equals 1.0
The shape of a distribution of z scores maintains the shape of the original score distribution from which the z scores were derived.

Front 7

z score calculation

Back 7

z=x + mean(or X bar)
----------- (divided by)
SD (stand. dev.)

Front 8

Random Sampling Distribution

Back 8

A relative frequency distribution of a sample statistic, obtained from an unlimited series of sampling experiments, each consisting of a sample size "n", randomly selected from the population.

Ex. Random Sampling Distribution of the mean

Front 9

Finding Areas Under the Curve

Back 9

For z scores distributions
Use z score to find area-use table in book

Front 10

Random Sampling Distribution of the Mean

Back 10

The relative frequency distribution of means, obtained from an unlimited series of sampling experiments, each consisting of a sample size "n", randomly selected from the population.

Basically: little "x bars" make a distribution...

Front 11

Central Limit Theorem

Back 11

The random sampling distribution of the mean approaches normal shape as the sample size increases, regardless of the shape of the population distribution.

It doesn't matter what the shape of the population is, the Random Sampling Distribution will always be normal in shape.

Front 12

The Logic of Hypothesis Testing: Modus Tollens

Back 12

Deductive argument of the form, "If P, then Q" Given -Q (not Q), you conclude -P(not P)

If it's raining then the streets are wet. (If P then Q)

The streets are not wet, (-Q)therefore its not raining. (-P)

Front 13

Null Hypothesis

Back 13

(H subscript 0) "Fake" hypothesis which is assumed to be true, tested directly, and either rejected or not rejected.

Front 14

Alternative hypothesis

Back 14

(H subscript 1)
The hypothesis believed to be true by the researcher

Front 15

Level of significance

Back 15

Probability that specifies how rare a sample result must be to reject null hypothesis as being true

Front 16

Establish region(s) of rejection

Back 16

Area under the curve where null hypothesis is rejected if the sample result should fall within the region (i.e. identifies sample results are to be considered -Q)

(See "Inferential Statistics" powerpoint Slide #10 for chart)

Front 17

When to Reject the null hypothesis

Back 17

When the calculated value of the test statistic equals or exceeds the critical value, our decision is to reject the null hypothesis.

Front 18

When to not reject the null hypothesis

Back 18

The calculated value of the test statistic is less than the critical value, we DO NOT accept the null hypothesis. Rather, we "do not reject" the null hypothesis.
There is insufficent evidence to reject the null hypothesis.

Front 19

To "accept" the null hypothesis would be to make a fallacious argument called:

Back 19

Affirming the consequent

Front 20

Statistical Significance

Back 20

Indicates the null hypothesis was rejected at a specified o- level

Front 21

Practical Significance

Back 21

refers to the real life importance of the result. That is, does the obeserved difference between the null hypothesis and alternative hypothesis really mean anything in practical terms?