Research 2

Front 1

A value, usually unknown (and which therefore has to be estimated) used to represent a certain population characteristic

ex. the mean ages

Back 1

Parameter

Front 2

Quantity calculated from a sample of data. Gives info about values in the corresponding population.

Back 2

Statistic

Front 3

2 basic types of inferential statistics

Back 3

estimation statistics & hypothesis testing

Front 4

Used to make statistical inferences about the data.

Based on statistical results, researcher can make an educated assumption concerning what the data means.

Back 4

Inferential statistics

Front 5

2 types of estimation statistics

Back 5

Confidence intervals & Parameter Estimation

Front 6

Used to describe or summarize data

- means

- ranges of scores

- percentiles

Back 6

Descriptive statistics

Front 7

Deal w/ the surety that the researcher has that the sample parameter is representative of the population parameter

Back 7

Confidence intervals

Front 8

Used to make inferences about how well a particular model might describe the relationship between variables in a population

ex. regression analysis

Back 8

Parameter estimation

Front 9

A single independent variable is used to predict the value of a dependent variable

Back 9

Simple Linear Regression

Front 10

2 or more independent variables are used to predict the value of a dependent variable

Back 10

Multiple Linear Regression

Front 11

Deals w/ the relationship between a set of independent variables and a dependent variable

Back 11

Nonlinear Regression

Front 12

Similar to techniques like ANOVA & multiple regression. Allows the researcher to specify the nature of the relationship.

Back 12

Nonlinear Regression

Front 13

The hypothesis of no change or effect

Ho

ex. there us no difference between those who receive a kind of speech therapy and those who don't.

Back 13

Null hypothesis

Front 14

The hypothesis of change or effect

H1

The RESEARCH hypothesis, states what researcher is looking for

ex. there is a difference between those who receive some kind of speech therapy and those who don't

Back 14

Alternate hypothesis

Front 15

Rejecting the null hypothesis when in fact it was true.

(We say therapy made a difference when it really didn't)

Back 15

Type I Error

Front 16

Failing to reject the null hypothesis when it is actually false.

(We say the therapy didn't make a difference when it really did)

Back 16

Type II Error

Front 17

A probability, w/ a value ranging from zero to 1.

Back 17

P-value

Front 18

A measure of how much evidence we have against the null hypothesis

Back 18

P-value

Front 19

Calculated to determine how secure researcher can be that the sample results do not reflect the population parameter

Back 19

P-value

Front 20

Rejecting the null hypothesis says that research results ______ _ ________.

Back 20

showed a difference

Front 21

Deals w/ the concept that research results are due to chance

Back 21

P-value

Front 22

______ p-value means results observed unlikely to be due to chance.

(What you are looking at really did result in a difference)

Back 22

Small

Front 23

_______ p-value means there is a strong possibility that the results are due to chance.

Back 23

Large

Front 24

Predetermined acceptance level for the p-value

Not calculated

Back 24

Alpha level

Front 25

Chosen by researcher prior to beginning of study &/or looking at the statistics - can be any number between 0 & 1

Back 25

Alpha level

Front 26

Alpha level is typically ___.

Back 26

.05

Front 27

Used to determine if results are statistically significant

Back 27

Alpha level

Front 28

If statistics _____ alpha level, results are significant.

Back 28

meet

Front 29

If statistics _____ alpha level, results are not significant.

Back 29

don't meet

Front 30

______ level is aka ______ ______ aka the probability of a ____ ___ error.

Back 30

Alpha level, significance level, aka type II error

Front 31

Used to compare difference between 2 proportions

Categorical data

Back 31

z-test

Front 32

Used to compare difference between 2 means

Numerical data

Back 32

t-test

Front 33

Used to compare independent groups

Back 33

Pooled variance t-test

Front 34

Used to compare related groups

-matched according to relevant characteristics

-repeated measures

Back 34

Paired t-test

Front 35

Used to compare differences in proportions between 2 or more groups

categorical data

Back 35

Chi-square tests

Front 36

Tests for

-the difference in proportion of successes in 2 or more groups

-a relationship between 2 categorical variables in a 2 way cross classification table

Back 36

Chi-square tests

Front 37

Analysis of variance

used to compare difference between means of more than 2 groups

numerical data

Back 37

One-Way ANOVA

Front 38

Tests for differences among means of more than 2 groups

Simultaneously compares the difference among the means of more than 1 group.

Doesn't really test variance

Back 38

One-Way ANOVA

Front 39

DIRECTIONAL hypothesis is used when either only positive or negative differences are of interest in an experimental study and you would use a ____ _____ test.

Back 39

one-tailed test

Front 40

NONDIRECTIONAL hypothesis is used to distinguish between no effect and an effect in the unexpected direction and a ___ _____ test would be used.

Back 40

two-tailed test

Front 41

_______ _______ are used to allow researcher to rule out chance as an explanation for the results observed.

Back 41

Statistical tests

Front 42

A main result of a correlation is called the ________ ________. or "r"

Back 42

Correlation coefficient (r)

Front 43

r= +1 means that every time one variable gets larger, the other _______ _____. This is a _______ positive correlation and does not typically happen.

Back 43

does too, perfect

Front 44

r= -1 means every time one variable gets larger, the other ______ ______. A ______ negative correlation also does not typically happen.

Back 44

gets smaller, perfect

Front 45

Only qualitative classifications

- gender

- race

Back 45

Nominal Variables

Front 46

Can measure in terms of which has less and which has more of the quality represented by the variable

- Quantitative

- can be rank ordered

Back 46

Ordinal Variables

Front 47

Can be rank ordered

sizes of differences can be quantified and compared between them

F and C

Back 47

Interval variables

Front 48

Very similar to interval variables

BUT have an identifiable absolute zero point

x times 2 is more than y

Back 48

Ratio variables

Front 49

When the null hypothesis is _________, the outcome is statistically significant.

Back 49

rejected

Front 50

When the null hypothesis is _______, the outcome is not statistically significant.

Back 50

not rejected