Chapter 13: Implementing Basic Differences Tests

Market Segmentation

Based on differences between groups of consumers

Null hypothesis

Refers to the hypothesis that the difference in the population parameters is equal to zero

ANOVA will:

"Signal" when at least one pair of means has a statistically significant difference, but it does not tell which pair

Market segmentation is the discovery of differences that are the following:

1. Statistically significant 2. Meaningful 3. Stable 4. Actionable differences

Paired samples test for the differences between two means

A test to determine if two means of two different questions using the same scale format and answered by the same respondents in the sample are significantly different

Ha

Alternative hypothesis

Testing the Difference Between Means

Differences between two means from independent samples Differences between three or more means from independent samples Differences between paired means

Statistically Significant

Differences found in the sample(s) truly exist in the population(s) from which the random samples are drawn

Use the SPSS command _________________ to produce the percentages you need

Frequencies

Behavioral Segmentation

Grouping potential customer by their attitude towards, use of, likes/dislikes of, or response to a product, service, promotion, or brand

Geographic Segmentation

Grouping potential customers by country, state, region, city or even neighborhood

Demographic Segmentation

Grouping potential customers by ethnicity, age, gender, income, religion, family makeup, and education

Psychographic Segmentation

Grouping potential customers by hobbies, interests, and lifestyle choices

Do female teens and male teens drink different amounts of sports drinks?

H0: μF = μM vs. Ha: μF≠ μM

Researcher needs to consider other factors in a study like:

How to adequately select/identify the research study participants (and how large the sample would be)

Green light procedure

If at least one pair of means has a statistically significant difference, ANOVA will signal this by indicating significance

ANOVA advantages

Immediately notifies researcher if there is any significant difference Arranges the means so the significant differences can be located and interpreted easily

Z-score

Indicates how many standard deviations an element is from the mean

Alternative hypothesis

Indicates that there is a true difference between the population means (at least, there is a significant and meaningful difference between the population parameters)

ANOVA is an:

Investigation of the differences between the group means to ascertain whether sampling errors or true population differences explain their failure to be equal

Absolute value of the computed z-value is greater than 1.96:

Is not likely that the null hypothesis of no difference is true. Rather, it is likely that there is a real statistical difference between the two percentages.

If the null hypothesis is true, we would expect there to be:

No differences between the two percentages

Ho

Null hypothesis

Meaningful

One that the marketing manager can potentially use as a basis for marketing decisions

Stable

One that will be in place for the foreseeable future

Post hoc tests

Options that are available to determine where the pair(s) of statistically significant differences between the means exist(s)

Example of the population "parameters":

Population "means" - Average sport drinks consumed by male teenagers vs. average sport drinks consumed by female teenagers)

Differences Between Means with Two Groups

Procedure is identical to the procedure for testing two percentages

Duncan's multiple range test

Provides output that is mostly a "picture" of what means are significantly different

If your z-score falls in ______________________ you will reject the null.

Rejection region

Independent Samples

Representing two potentially different populations

A z-score of 0

Represents an element equal to the mean

A z-score that is less than 0

Represents an element is smaller than the mean

A z-score that is equal to 1

Represents an element that is 1 standard deviation greater than the mean

Small Sample Sizes and IBM SPSS

SPSS eliminates the need to determine the appropriate statistical test, since it is programmed to select the most adequate (correct) statistic

Any given study, differences may be expected due to:

Sampling error

Z-Test

Statistical inference test to be used when the sample size is 30 or greater

T-test

Statistical inference test to be used with small sample sizes Ex: N ≤ 30

Actionable

The marketer can focus various marketing strategies and tactics, such as product design or advertising, on the market segments to accentuate the differences between segments

Differences Test

The null hypothesis states that there is no difference between the percentages being compared; or there is no difference b/t the group means

Most computer statistical programs, including IBM SPSS, report only the t value because it is identical to the z-value with large samples. True or False

True

SPSS does not perform tests of significance of the difference between the percentages of two groups. True or False

True

Analysis of Variance (ANOVA)

Used when comparing the means of three or more groups

What does VALs stand for?

Values, Attitudes, Lifestyles

If the null hypothesis were true:

We would expect 95% of the zscores computed from 100 samples to fall between -1.96 and +1.96 std. dev.

Statistical tests are used:

When researcher wants to compare the means or percentages of two different groups or samples