Marketing Research Ch. 14

Front 1

Associative analysis

Back 1

Determine where stable relationships exist between two variables.

(Business associated with customer satisfaction, demographics associated with buying products, sales training associated with performance, purchase intention associated with sales)

Front 2

Relationship

Back 2

A consistent, systematic linkage between the levels/labels of two nominal variables.

Front 3

Levels

Back 3

Characteristics of description for interval or ratio scales (level of temp, etc.)

Front 4

Labels

Back 4

Characteristics of description for nominal or ordinal scales (buyers vs non buyers, etc.)

Front 5

Nonmonotonic

Back 5

Two variables are associated, but only in a very general sense. No direction but relationship exists.

Don't know direction of relationship, but we do know that the presence or absence of one variance is associated with the presence or absence of another.

(Ex. Presence of breakfast...presence of coffee. Presence of lunch...absence of coffee.)

Front 6

Monotonic

Back 6

The general direction of a relationship between two variables is known. Can either be increasing or decreasing.

(Older children have a larger shoe size- direction increasing)

Front 7

Linear

Back 7

Straight line association between two variables. Knowledge of one variable will yield knowledge of another variable.

More precise than a monotonic or nonmonotonic relationship.

Front 8

Linear formula and what each letter stands for

Back 8

y= a + bx

y= dependent variable being estimated or predicted.

a= the intersect

b= the slope

x= independent variable used to predict the dependent variable.

Front 9

Curvilinear

Back 9

Some smooth curve pattern describes the association.

(Ex. Job satisfaction is high, then decreases, and later increases again.)

Front 10

3 ways to characterize relationships between variables

Back 10

1. Presence

2. Direction

3. Strength of association

*Asses in this order!!!

Front 11

Presence

Back 11

Whether any systematic relationship exists between two variables of interest.

(Statistical significance test)

Front 12

Direction

Back 12

Whether the relationship is positive or negative. Nonmonotonic looks for a pattern or a general relationship.

Front 13

Strength of association

Back 13

How strong the relationship is. Strong, moderate, or weak depending on correlation.

Front 14

6 steps for analyzing relationships

Back 14

1. Choose variable to analyze

2. Determine the scaling assumptions of the variable

3. Use correct relationship analysis

4. Presence

5. Direction

6. Strength of association

Front 15

Cross- tabulation

Back 15

Consists of rows and columns defined by the categories classifying each variable...Used for nonmonotonic relationships.

Front 16

4 types of numbers in each cell in a cross- tabulation table

Back 16

1. Frequency

2. Raw percentage

3. Column percentage

4. Row percentage

Front 17

Cross- tabs look for____________________________ among ______________________________.

Back 17

Nonmonotonic relationships among nominally- scaled variables.

Front 18

Commands to look for when using SPSS with cross- tabulation

Back 18

ANALYZE, DESCRIPTIVE STATISTICS, CROSSTABS.

Front 19

What to do when we have two-nominally scaled variables and we want to know if they are associated?

Back 19

Use cross- tabulations to examine the relationship and the chi-square test to test for the presence of a systematic relationship.

*We have 2 variables, both with nominal scales, so we test for a nonmonotonic relationship.

Front 20

Chi- square (x squared) analysis

Back 20

Examination of frequencies for two nominal- scaled variables in a cross- tabulation table to determine whether the variables have a significant nonmonotonic relationship.

Front 21

What is the null hypothesis in a chi- square analysis?

Back 21

That the two variables are not related.

Front 22

2 ways to determine the nature of the relationship of a significant relationship (no support for null hypothesis) in a chi- square test

Back 22

1. Column- percentage table

2. Raw percentage table

Front 23

Main purpose of the chi- square test?

Back 23

To tell us if monotonic relationships are really present.

Front 24

In SPSS, where to find STATISTICS, CHI- SQUARE?

Back 24

CROSSTABS dialogue box.

Front 25

Chi- square analysis

Back 25

Assesses nonmonotonic associations in cross- tabulation tables and is based upon differences between observed and expected frequencies.

Front 26

Observed frequencies

Back 26

Counts for each cell found in the sample.

Front 27

Expected frequencies

Back 27

Calculated on the null out of "no association" between the two variables under examination.

Front 28

The chi- square distribution's shape changes depending on what?

Back 28

The number of degrees of freedom.

Front 29

The computed chi- square value is compared to a table value to determine what?

Back 29

Statistical significance.

Front 30

Formula for chi- square degrees of freedom and what each letter means

Back 30

(r - 1) (c - 1)

r= number of rows

c= number of columns

Front 31

How to interpret the chi- square analysis?

Back 31

It yields the probability that the researcher would find evidence in support of the null hypothesis if he or she repeated the study many times with independent samples.

Front 32

What does it mean if the p value in a chi- square analysis is greater than or equal to .05?

Back 32

There is little support for the null hypothesis (no association).. Therefore we have a significant association.. we have the presence of a systematic relationship between the two variables.

Front 33

How to interpret a chi- square result?

Back 33

A significant chi- square result means the researcher should look at the cross tabulation row and column percentages to see the association pattern.

Front 34

What type of percentages can SPSS calculate?

Back 34

Row, column, or both. Located at the CELLS box at the bottom of the CROSSTABS dialog box.

Front 35

Do nonmonotonic relationships have direction?

Back 35

No, only presence and absence.

Front 36

2 instances in which you can use crosstabs and chi- square test:

Back 36

1. When you want to know if there is an association between two variables.

2. Both of those variables have nominal or ordinal scales.

Front 37

Correlation coefficient

Back 37

Index number, constrained to fall between the range of -1.0 and +1.0.

Communicates both the strength and direction of the linear relationship between two metric (interval or ratio) variables.

Front 38

The amount of linear relationship between two variables is communicated by what?

Back 38

The absolute size of the correlation coefficient.

Front 39

The direction of the association in a correlation coefficient is communicated by what?

Back 39

The sign of the correlation coefficient ( + or -).

Front 40

Covariation

Back 40

The amount of change in one variable systematically associated with a change in another variable.

Front 41

When measuring the association between interval or ratio scaled variables using SPSS, what commands are to be used?

Back 41

ANALYZE, CORRELATE, BIVARIATE.

Front 42

When looking at the presence of the p value, what does it mean if it is significant?

Back 42

If it is significant, there is a significant association, if it is not significant, there is no association.

Front 43

T/F: The closer the correlation is to 1 (+ or -), the stronger the association.

Back 43

True.

(1.0 and .81 are strong)

(.80 and .61 are moderate)

(.60 and .41 are weak)

(.40 and .21 are very weak)

Front 44

A correlation coefficient's size indicates ____________________ between two variables.

Back 44

The strength of association.

Front 45

The sign + or - indicates _________________.

Back 45

The direction of association.

Front 46

T/F: For different types of variables, different strengths become important.

Back 46

True.

Front 47

3 special considerations in linear procedures

Back 47

1. Correlation takes into account only the relationship between two variables, not interaction with other variables.

2. Correlation does not demonstrate cause and effect.

3. Correlations will not detect non- linear relationships between variables.

Front 48

When there is no association, the p value for the Pearson r will be ____________.

Back 48

Less than .05.

Front 49

What do we use to measure the linear association between interval or ratio scaled variables (1-5 scaled response questions)?

Back 49

Pearson Product Moment Correlation.

Front 50

When there is association, the p value for the Pearson r will be ___________.

Back 50

Greater than or equal to .05.

Front 51

How often will researchers test the null hypothesis of no relationship or no correlation?

Back 51

Almost always.

Front 52

What happens when the null hypothesis is rejected?

Back 52

The researcher may have a managerially important relationship to share with the manager.

Front 53

Testing a non- null hypothesis

Back 53

You may test whether they are less than, greater than, or not equal.

Front 54

What must happen for your alpha error to be in one tail?

Back 54

Your hypothesis must be less than or greater than (this makes the hypothesis easier to prove).

Front 55

Statistical vs. causal linkage

Back 55

Causal-a certain variable affected the other.

Statistical- no certainty, some other variable may have had some influence (relationship).

Front 56

4 basic types of relationships between two variables

Back 56

1. Nonmonotonic

2. Monotonic

3. Linear

4. Curvilinear

Front 57

Cross- tabulation cell

Back 57

The intersection of a row and a column.

Front 58

Frequencies table

Back 58

Contains raw numbers determined from the preliminary tabulation.

Front 59

3 sets of percentages that can be computed for cells in a table

Back 59

1. Raw percentages

2. Column percentages

3. Row percentages

Front 60

What does the computed chi- square value compare?

Back 60

Observed to expected frequencies.

Front 61

Chi- square distribution

Back 61

Skewed to the right and rejection region is always at the right hand tail of distribution. It's shape depends on the situation at hand and does not have negative values.

Front 62

Scatter diagram

Back 62

Plots the points corresponding to each matched pair of x and y variables.

Front 63

Correlation coefficient assumes that both variables share _________________ assumptions at minimum.

Back 63

Interval- scaling. If they had nominal scaling, cross- tabulation analysis would be used.

Front 64

T/F: The correlation coefficient takes into consideration only the relationship between two variables.

Back 64

True.

Front 65

Cause and effect relationship

Back 65

Condition of one variable bringing about the other variable. Correlation does not demonstrate this.

Front 66

Correlation coefficient in relation to the Pearson product

Back 66

Pearson expresses only linear relationships and is calculated from standardized data so the two variables must be identical. A correlation coefficient may not have a well defined pattern at all and will not detect nonlinear relationships.