Residuals Statistics Flashcards
LSRL
Residuals
Correlation
Terms : Hide Images [1]
| 3417189596 | X-variable | independent or explanatory variable | 0 | |
| 3417189597 | Y-variable | dependent or response variable | 1 | |
| 3417189598 | Y-hat | predicted y | 2 | |
| 3417189599 | B | slope; the amount by which the y increases when x increases by 1 unit | 3 | |
| 3417189600 | a | y intercept. It is the height of the line when x=0. | 4 | |
| 3417189601 | LSRL | least square regression line; line that gives the best fit to the data set; minimizes the sum of the squares of the deviations from the line | 5 | |
| 3417189602 | Slope interpretation statement | For each unit increase in x, there is an approximate increase/decrease of b in y. | 6 | |
| 3417189603 | Correlation coefficient interpretation statement | There is a direction, strength, type of association between x and y. | 7 | |
| 3417189604 | Extrapolation | Not knowing whether the pattern observed in the scatterplot continues outside the range. | 8 | |
| 3417189605 | Non resistant | affected by outliers | 9 | |
| 3417189606 | Correlation Coefficient (r) | a quantitative assessment of the stregnth and direction of the linear relationship between bivariate, quantitative data | 10 | |
| 3417189607 | Properties of (r) weak | 0-.5 | 11 | |
| 3417189608 | Properties of (r) moderate | .5-.8 | 12 | |
| 3417189609 | Properties of (r) strong | .8-1 | 13 | |
| 3417189610 | Value of r | a measure of the extent to which x & y are linearly related | 14 | |
| 3417189611 | Correlation does not imply causation | Correlation does not imply causation | 15 | |
| 3417189612 | Residuals | The verticle deviation between the observations & the LSRL | 16 | |
| 3417189613 | Sum of residuals | Always zero | 17 | |
| 3417189614 | Residual equation | residual=y-yhat | 18 | |
| 3417189615 | Residual plot | No pattern in residual plot then association is linear. Residual plots are the same no matter if plotted against x or y-hat | 19 | |
| 3417189616 | Coefficient of determination r^2 | gives the proportion of variation in y that can be attributed to an approximate linear relationship between x and y. remains same no matter which variable labeled x | 20 | |
| 3417189617 | Interpretation statement of r^2/ coefficient of determination | Approximately r^2% of the variation in y can be explained by the LSRL of x & y | 21 | |
| 3417189618 | Outlier | a date point with a large residual | 22 | |
| 3417189619 | Influencial point | A point that influences where the LSRL is located. If removed, it will significantly change the slope of the LSRL | 23 |