Capabilities
GOLDMineR gives you innovative, patented graphical displays so you can easily interpret your effect estimates and visually assess your model. Output features both regression and loglinear statistics, including model summary R-square and goodness of fit chi-square statistics. A table window displays observed or expected counts, probabilities, odds or odds ratios. And an advanced search feature delivers automatic predictor variable selection, so you can easily select important predictors from your database. Plus, you can easily import data into GOLDMineR, since it reads a variety of file types, including the SPSS� system file format.
GOLDMineR� is an acronym for Graphical Ordinal Logit Displays based on Monotonic Regression. With it, you can:
- Use innovative graphical displays and charts to better visualize and assess you model
- Use the table window to access various counts, odds and residual tables
- Use the search facility for automated predictor variable selection
- Update your results immediately for changes in contrast coding of qualitative variables
- Model and predict dichotomous and ordered categorical dependent variables
- Generate code for scoring external files
- View GOLDMineR's logit model graphically vs. a competing linear model applied to the same data
- Explore and assess competing models through visual displays and statistical measures of fit
- Use different scoring systems for your categorical variables
- Assess the relative impact of individual predictors on the response variable
- Include both categorical and continuous predictors into the model
- Build regression models for dependent variables containing ordered outcome categories (where the ordering can be prespecified or determined by the model)
Use The Best Approach for Ordered Categorical Outcomes
GOLDMineR� delivers the right regression framework to create better models. For example, while linear regression is fundamental in research, its measurement level requirements are not always met. Linear regression is not appropriate if a dependent variable is dichotomous or consists of ordered categories. For lack of good software alternatives, researchers often use it anyway for ordinal outcome variables, such as:
Rating scales ("Likelihood of purchase") | Medical treatment outcomes |
4. Very Likely | -1. Worse |
3. Somewhat Likely | 0. Stationary |
2. Somewhat Unlikely | 1. Mild Improvement |
1. Very Unlikely | 2. Moderate Improvement |
| 3. Well |
Discretized variables, such as educational attainment | Partially ordered variables, such as grouped income |
1. Less than eight years of schooling | 1. Less than $15,000 |
2. Eight - 11 years of schooling | 2. $15,000 - $30,000 |
3. 12 years of schooling | 3. $30,000 - $50,000 |
2. 13 or more years of schooling | 4. $50,000 and above |
| 5. Unknown |