Quantitative Multiple Regression Analysis
About this set
Created by:
thomasrcusack on May 18, 2012
Subjects:
Log in to favorite or report as inappropriate.
Order by
14 terms
Terms | Definitions |
|---|---|
 Hypothesis | Research Question: For a study that includes A and B as 2 predictors of C: For the groups are the attributes of A and B predictive as an aggregate profile of C? Hypothesis: Treatment has no Impact or Treatment has an Impact |
| Model | Yij=βo+β1X1+β2X2+εij Yij= Int+(A)x1+(B)x2+Error |
| Level of Significance/ Risk | For this study the level of risk will be set at 0.05 (α=0.05). This will minimize the probability of committing a type I error. |
| Test Statistic | The test statistic that will be employed for this study is multiple regression. This will allow us to compare the relationship between the continuous dependent variable (A) and the n different continuous variables (B, C,...) |
| Variables | DV-criterion (continuous) and multiple IV's -predictors (continuous or if categorical they have been dummy coded) |
| Test Assumptions | *Homoscedasticity *Normal distribution (for each variable, the error variances, and the residuals) *No Specification errors *No Multicollinearity *Linear relationship |
| Descriptive Statistics | Measures of Center Measures of Spread Number of Observations Mean Differences for each group |
| Test Statistic Computed | Correlation matrix describes the relationship of each variable to each other variable in the model R (Pearson) is reported for each var Sig of each var N's for each var Model Summary indicates R, adj R2 (coefficient of determination - proportion of variance for the DV that is described by IV's (predictors) as a percent) ANOVA table Coefficient Table - tells that if all other vars were held constant, the predicted Y value would be higher or lower by the reported number of units |
| Critical Value | ... |
| Additional Statistics | ... |
| Results | Standard MR was employed to determine if IV's stat sig predicted DV. Tables x etc show the correlation between vars, the unstandardized reg coeff(B), intercept, standardized reg coeff(β), semi part corr, R, R2, adj R2. R for regression was stat sig diff from 0. F( ) = __ p=__R2 of _ (__adj) indicates that over _% of variability in the overall variability in DV is predicted by IV's |
| Decisions | ... |
| Limitations | ... |
| Problems for further study | ... |
First Time Here?
Welcome to Quizlet, a fun, free place to study. Try these flashcards, find others to study, or make your own.