Psych Stats Test 2

Front 1

Variability

Back 1

Opposite of consistency. Small variability indicates that similar behaviors are occurring. Larger variability indicates that scores were inconsistent.

Front 2

Measure of Variability

Back 2

Describes how far scores are spread out around the mean. The smaller the variability the less spread out from the mean the scores are. Two ways to calculate this is the variance and standard deviation.

Front 3

Range

Back 3

The distance between the two most extreme scores in a distribution.

Front 4

Variance

Back 4

The average of the squared deviations of scores around the mean. S2x. Also is the average error that you get when you predict that participants obtained the mean score.

Front 5

Standard deviation

Back 5

indicates the average deviation from the mean, the consistency in the scores, and how far scores are spread out around the mean. Sx

Front 6

Inflection points

Back 6

Points at which the curve changes its shape.

Front 7

Approximately ______% of the scores in a normal distribution are between the mean and the score that is 1 standard deviation from the mean

Back 7

34%

Front 8

For any roughly normal distribution, the standard deviation should equal about ______ of the range

Back 8

1/6

Front 9

Adding or subtracting a constant does/does not alter the variability of scores, but multiplying or dividing by a constant does/does not alter the variability

Back 9

does not; does

Front 10

Biased estimators

Back 10

S2x and Sx are biased estimators because the tend to underestimate the true population parameters. To fix this we divide by N-1.

Front 11

Degrees of freedom

Back 11

N-1. Number of scores in a sample that are free to reflect the variability within the population.

Front 12

Strength

Back 12

The scores in a given sample have a low variability between them thus representing a strong relationship. A weaker relationship has a greater variety in scores.

Front 13

Proportion of variance accounted for

Back 13

the proportional improvement that results from using the relationship to predict scores, compared to not using the relationship to predict scores.

Front 14

Z-transformation

Back 14

Used to compare and interpret scores from virtually any normal distribution of interval or ratio scores.

Front 15

Z-Score

Back 15

The distance a raw score deviates from the mean when measured in standard deviations. Will indicate exactly where on the distribution a score is located so that we can more precisely describe its relative standing. Sometimes called standard scores because you can compare scores on different variables. Has 2 components:
· Either a positive or negative sign that indicates whether it is above or below the mean
· Absolute value of a score indicates how far the score lies from the mean

Front 16

Z-distribution

Back 16

The distribution produced by transforming all raw scores in the data into z-scores. Three components:
· Has the same shape as the raw score distribution
· The mean is always 0
· Standard deviation is always 1

Front 17

Standard normal curve

Back 17

The perfect normal z-distribution that serves as our model of the z-distribution that would result from any approximately normal raw score distribution. Can be used to:
· Find simple frequency
· Find relative frequency
· Find a raw scores percentile
· Find the raw score at a certain percentile

Front 18

Standard error of the mean

Back 18

The average amount that the sample means deviate from the population means of the sampling distribution.

Front 19

Sampling distribution of means

Back 19

Frequency distribution of all possible sample means that occurs when an infinite number of samples of the same size N are randomly selected from one raw score population.

Front 20

Odds are expressed as ______ -

Back 20

Fractions or ratios

Front 21

Chance is expressed as________ -

Back 21

A percentage

Front 22

Probability is expressed as_______ -

Back 22

A decimal

Front 23

Inferential statistics

Back 23

Used to decide whether sample data represent a particular relationship in the population. Used because we will always have some uncertainty about whether the relationship in our sample is found in the population. The purpose of inferential statistics is to minimize the probability of committing type I and II errors.

Front 24

Probability

Back 24

Refers to the events relative frequency in the population of possible events that can occur. Also communicates confidence that a particular event will occur

Front 25

Probability distribution

Back 25

Indicates the probability of all events in a population. Can be made when we know the relative frequency of every possible event in a population.

Front 26

Independent event

Back 26

The probability of one event is not influenced by the occurrence of the other.

Front 27

Dependent event

Back 27

The probability of one event happening is influenced by the occurrence of another.

Front 28

Sampling with replacement

Back 28

Any previously selected individuals or events are replaced back into the population before drawing additional ones.

Front 29

Sampling without replacement

Back 29

previously selected individuals or events are not replaced in to the population before selecting again. The probability increases after each subsequent draw.

Front 30

Representative sample

Back 30

The characteristics of the individuals and scores in the sample accurately reflect the characteristics of individuals and score found in the population. To produce this type of results researchers use random sampling.

Front 31

Sampling error

Back 31

Occurs when random chance produces a sample statistic that is not equal to the population parameter is represents.

Front 32

Region of rejection

Back 32

The part of a sampling distribution containing means that are so unlikely that we reject that they represent the underlying raw score population. Samples with means in the region of rejection are usually representative of some other population.

Front 33

Criterion

Back 33

The probability that defines samples as too unlikely for us to accept as representing a particular population. Researchers usually use .05 as their criterion probability.

Front 34

Critical value

Back 34

Zcrit. Marks the inner edge of the region of rejection and thus defines the value required for a sample to fall into the region of rejection. If a sample lies beyond the critical value it is considered to be in the region of rejection.

Front 35

When using a two tailed distribution and a criterion of .05, we use the critical values of ______

Back 35

+/- 1.96

Front 36

When using a one tail distribution and a criterion of .05, we use the critical values of_____

Back 36

+/- 1.645

Front 37

Parametric statistics

Back 37

Procedures that require specific assumptions about the characteristics of the populations being represented. Two assumptions are:
· The population of dependent scores forms a normal distribution
· The score are interval or ratio scores

Front 38

Nonparametric statistics

Back 38

Inferential procedures that do not require assumptions about the populations being represented. Used with nominal or ordinal data.

Front 39

Robust procedure

Back 39

Parametric procedures are robust. The data does not need to meet the assumptions of the procedure perfectly and it can still be correct because the amount of error possibly is negligible.

Front 40

Experimental hypotheses

Back 40

Describe the predicted relationship that we may or may not find. Usually composed of two hypotheses. One states that we will demonstrate the predicted relationship and the other that we will not demonstrate that relationship.

Front 41

Two-tailed test

Back 41

Used when we predict a relationship but do not predict the direction in which the scores will change. Used when we predict that that one group will produce different dependent scores that the other group without saying which group will score higher or lower.

Front 42

One-tailed test

Back 42

Used to predict the direction in which the scores will change.

Front 43

Statistical hypotheses

Back 43

Describe the population parameters that the sample data represent if the predicted relationship does or does not exist. Two branches: The alternative hypothesis and the null hypothesis.

Front 44

Alternative hypothesis

Back 44

Describes the population parameters that the sample data represent if the predicted relationship exists. It is always the hypothesis of a difference; it says that changing the independent variable produces the predicted difference in the populations.

Front 45

The null hypothesis

Back 45

Describes the population parameters that the sample data represent if the predicted relationship does not exist. It is the hypothesis of no difference, saying that changing the independent variable does not produce the predicted difference in the population.

Front 46

Z-test

Back 46

Procedure for computing a z-score for a sample mean on the sampling distribution of means. Used only if standard deviation of the population is known. The z-test has four assumptions:
· We have randomly selected on sample
· The dependent variable is at least approximately normally distributed in the population, and involves an interval or ratio scale
· We know the mean of the population of raw scores under some other condition of the independent variable
· We know the true standard deviation of the population as described by the null hypothesis

Front 47

Criterion is the same as____

Back 47

alpha. Usually .05.

Front 48

Significant

Back 48

Indicates that our results are unlikely to occur in the predicted relationship does not exist in the population. It is assumed to be a real relationship found in nature and that it was not produced by a sampling error. Reject the null hypothesis and believe that the data reflect a relationship found in nature. If z obtained is beyond the z crit.

Front 49

Nonsignificant

Back 49

Indicates that the results are likely to reflect chance, sampling error, without there being a relationship in nature. Failed to reject the null hypothesis and are thus likely to occur when there is no real relationship in nature.

Front 50

Type I error

Back 50

Rejecting the null hypothesis when the null hypothesis is true. We conclude that the independent variable works when it really doesn’t. There is so much sampling error that we are fooled into concluding that the predicted relationship exists when it really does not.

Front 51

Type II error

Back 51

Retaining the null hypothesis when the null hypothesis is false. We fail to identify that the independent variable really does work. The sample mean is so close to the population mean that we are fooled into concluding that the predicted relationship does not exist when it really does.

Front 52

Power

Back 52

The probability that we will reject the null hypothesis when it is false thus correctly concluding that the sample data represent a relationship. It is the probability of not making a type II error. We seek to maximize power so that if we retain the null hypothesis we are confident we are not making a type II error.

Front 53

Beta

Back 53

the probability that a type II error has been committed.

Front 54

Degrees of freedom

Back 54

The number of scores in a sample that are free to vary, and thus the number that is used to calculate an estimate of the population variability.

Front 55

Central limit theorem

Back 55

A statistical principle that defines the mean, standard deviation, and shape of a theoretical sampling distribution.

Front 56

Relative standing

Back 56

A description of a particular score derived from a systematic evaluation of the score using the characteristics of the sample or population in which it occurs.