| front |
back |
revisions |
lasted changed by |
history |
| relative importance |
an attribute is its share of the total change in utility possible across all attributes |
0 |
jenmn2010 Thu, 10 Dec 2009 21:42:54 GMT |
 |
| importance weights |
-an attribute's importance is relative to the other attributes
-a move from its worst level to its best level is the maximum impact that an attribute can have on overall utility |
0 |
jenmn2010 Thu, 10 Dec 2009 21:42:54 GMT |
|
| part-worth utilities |
-the utility for a specific level of a particular attribute is called a respondent's part-worth (ex: how much is the "large" size box to me?)
-it designates how much that part of the product or service is worth (realtive to other levels and attributes) to the consumer |
0 |
jenmn2010 Thu, 10 Dec 2009 21:01:32 GMT |
|
| examples of attributes |
-price (experimentation and conjoint are two excellent way to assess brand equity
-brand name (conjoint analysis is one excellent way to asses brand equity
-size
-performance ro other quality measures |
0 |
jenmn2010 Thu, 10 Dec 2009 21:01:32 GMT |
|
| attributes |
an attribute may be any clrealy defined feature or characteristic |
0 |
jenmn2010 Thu, 10 Dec 2009 21:01:32 GMT |
|
| conjint procedures |
attempt to assign values to the levels of each attribute so that the resulting values or utilities attached to teh stimuli match, as closely as possible, the input evaluations provided by the respondents |
0 |
jenmn2010 Thu, 10 Dec 2009 21:01:32 GMT |
|
| conjoint analysis |
-attempts to determine the relative importance consumers attach to salient attributes and the utilities they attach to the levels of attributes
-the respondents are presented with stimuli that consistent of combinations of attribute levels and asked to evaluate these stimuli in terms of their desirability
|
1 |
jenmn2010 Thu, 10 Dec 2009 20:55:20 GMT |
|
| multi-collinearity |
is when your Xs are highly collinear with each other
-look at correlation matrix of Xs
-Regress on X on the other Xs (high R^2 indicates a problem)
-Solution: Do not include all of the Xs |
0 |
jenmn2010 Thu, 10 Dec 2009 20:53:00 GMT |
|
| correlation |
measure of association between any two interval or ration scaled variables --> correlation coefficient |
0 |
jenmn2010 Thu, 10 Dec 2009 20:53:00 GMT |
|
| comparing t-test and critical value |
if p-value < level of significance
--> reject the null |
0 |
jenmn2010 Thu, 10 Dec 2009 20:53:00 GMT |
|
| chi-square test (when to use) |
-test for statistical independence between two nominal variables (the two variables are unrelated)
-example: gender (males & female) and internet usage (heavy, medium and light) |
0 |
jenmn2010 Thu, 10 Dec 2009 20:38:53 GMT |
|
| more than two means: ANOVA |
-testing the mean for 3 or more for the same interval or ratio variable
-example: internet usage by different income levels/age groups/household sizes/marital status/edu levels/... |
0 |
jenmn2010 Thu, 10 Dec 2009 20:38:53 GMT |
|
| two sample means t-test |
-testing the mean for two different groups for the same interval or ratio variable
-example: men's internet usage and women's internet usage |
0 |
jenmn2010 Thu, 10 Dec 2009 20:38:53 GMT |
|
| paired means t-test |
-testing the mean for the same group for two different interval or ratio variables
-example: men's attitudes towards internet and men's attitude towards technology |
0 |
jenmn2010 Thu, 10 Dec 2009 20:38:53 GMT |
|
| single mean t-test |
-testing the mean of a single variable against a number
-example: people's average evaluation ofa product (1-5 likert scale) vs. score 3 |
0 |
jenmn2010 Thu, 10 Dec 2009 20:30:24 GMT |
|
| alternative hypothesis |
one in which some difference or effect is expected |
0 |
jenmn2010 Thu, 10 Dec 2009 20:30:24 GMT |
|
| null hypothesis |
a statement of the status quo, one of no difference or no effect. if the null hypothesis is not rejected, no changes will be made |
0 |
jenmn2010 Thu, 10 Dec 2009 20:30:24 GMT |
|
| chi square statistic formula |
x^2 = (ni - E(ni))^2 / E(ni)
ni = observed number of obs in cell i
E(ni) = expected number of obs in cell i under hypothesis |
0 |
jenmn2010 Thu, 10 Dec 2009 20:30:24 GMT |
|
| chi-square statistic definition |
a function of the squares of the deviation of the observed counts n form their expected values (under some null hypthesis), E(n), weighted by the reciprocals of their expected values |
0 |
jenmn2010 Thu, 10 Dec 2009 20:25:12 GMT |
|
| one-way chi-squared test |
The Chi Square (X2) test is undoubtedly the most important and most used member of the nonparametric family of statistical tests. Chi Square is employed to test the difference between an actual sample and another hypothetical or previously established distribution such as that which may be expected due to chance or probability. Chi Square can also be used to test differences between two or more actual samples. |
0 |
jenmn2010 Thu, 10 Dec 2009 20:25:12 GMT |
|
| in pairwise deletion |
intead of discarding all cases with any missing values, the researcher uses only the cases or respondents with complete responses for each calculation |
0 |
jenmn2010 Thu, 10 Dec 2009 20:25:11 GMT |
|
| in casewise deletion |
cases, or respondents, with any missing responses are discarded from the analysis |
0 |
jenmn2010 Thu, 10 Dec 2009 20:25:11 GMT |
|
| substitute an imputed response |
the respondents pattern of responses to other questions are used to impute or calculate a suitable response to the missing questions |
0 |
jenmn2010 Thu, 10 Dec 2009 20:25:11 GMT |
|
| substitute a neutral value |
typically the mean response to the variable |
0 |
jenmn2010 Thu, 10 Dec 2009 20:25:11 GMT |
|
| treatment of missnig values |
-substitute a neutral value
-substitute an imputed response
-in casewise deletion
-in pairwise deletion |
0 |
jenmn2010 Thu, 10 Dec 2009 20:25:11 GMT |
|
| consistency checks |
identify data that are out of range, logically inconsistent, or have extreme values |
0 |
jenmn2010 Thu, 10 Dec 2009 20:25:11 GMT |
|
