QMB Test 1 Word Scramble
|
Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.
Normal Size Small Size show me how
Normal Size Small Size show me how
| Question | Answer |
| One of the assumptions in regression analysis is that | the errors have a mean of 0 |
| a graph of the sample points that will be used to develop a regression line is called | a scatter diagram |
| when using regression, an error is also called | a residual |
| in a regression model, Y is called | the dependent variable |
| a quantity that provides a measure of how far each sample point is from the regression line is | the SSE |
| the percentage of the variation in the dependent variable that is explained by a regression equation is measured by | the coefficient of determination |
| In a regression model, if every sample point is on the regression line (all errors are 0), then | correlation coefficient would be -1 or 1 |
| when using dummy variables in a regression equation to model a qualitative or categorical variable, the number of dummy variables should equal | 1 less than the number of categories |
| a multiple regression model differs from a simple linear regression model because the multiple regression model has more than one | independent variable |
| the overall significance of a regression model is tested using an F test. The model is significant if | the significance level of the F value is low |
| A new variable should not be added to a multiple regression model if that variable causes | the adjusted R squared to decrease |
| a good regression model should have | a low R squared and a low significance level for the F test |
| The model that allows us to compare several populations | ANOVA tables |
| If the computed F is greater than the critical F | there is significant difference |
| If the computed F is smaller than the critical F | there is not significant difference |
| Residual is a synonym for | error |
| Df1 | Treatments/Regression |
| Df2 | Residual/Error |
| Correlation Coefficient | The strength of a relationship between two variables; R; always between 0-1; can have a positive or an inverse relationship |
| Coefficient of determination | shows what percentage of correlation the independent variable has on the dependent variable; R squared; always positive and always between 0-1 |
| Regression is a synonym for | treatments |
| Variables tend to be | WXYZ |
| Constants tend to be | ABCD |
| regression | is all about forecasting based on past data |
| B | slope (^Y/^X) |
| line of best fit | minimizes distance between points - regression equation describes this |
| y intercept | is equal to the A value |
| if X=O | Y=A |
| no matter what, there will always be associated | error, because the line of best fit isn't exact |
| N | # of observations |
| K | total number of variables |
| innocently assumed as | not correlated |
| null hypothesis | innocently assumed as not correlated |
| The tested hypothesis | differences exist |
| Coefficient of non-determination | 1-Rsquared; |
| to lower error | the only thing you can do is enlarge the sample size |
| computed t shows that the | variable is significant |
| computed F shows that the | model is significant |
| what is the meaning of least squares in a regression model | that the regression line will minimize the sum of the squared errors. no other line will give a lower sse |
| What is the SSE | Sum of Squares Error; the total sum of the squared differences between each observation and the predicted value |
| What is the SSR | Sum of squares regression; the total sum of the squared differences between each predicted value and the mean |
| What is the SST | Sum of Squares Total; the total sum of the squared differences between each observation and the mean |
Created by:
hopekn