NAME: ________________________

# ← Causal Forecasting: DemandTest

### Question Limit

of 28 available terms

### 5 Matching Questions

1. What are residual plots?
2. What is simple regression?
3. What are the two ways that you can use to cheak linear relationships?
4. How do remedy non-linear relationships?
5. The independent variablees must NOT be highly correlated, how do you check this?
1. a Correlation matrix. R<.90 is needed.
2. b 1. Scatter plots
2. Residual plots
3. c Eliminate offending independent variables from your analysis or transform your data.
4. d Plot residuals on the y-axis and independent variables on the x-axis. ( Data should exhibit a random pattern. NIce steady floor and ceiling.
5. e Assesses the mathamatical relationship between two variables. One of which the dependent variable (Y). is believed to be casused by the other indepedent variable (X). Alsio, known as Bivariate Regression. Simple Linear least squares regression.

### 5 Multiple Choice Questions

1. Represent unusually large or small observations/ values relative to others in the samle for a given variable.
2. Unstable regression coefficents
Inflated standard errors
3. Homocedasticity
4. Create a scatter plot of the residuals (y-axis) versus the predicted values (x-axis). The data should exhibit a random pattern with a relatively uniform variance.
5. Examine cases that are more than 3 or 4 standard deviations from the mean of the variable. (Another method involves standardized residuals (errors of the regression equation) Values +- 4 greater than indicated a potiential outlier.

### 5 True/False Questions

1. Non-independent residual pattern is characterized by?Residual (error) alternate between positive and negative signs. Also, exhibit a trend or pattern. Or exhibt a curved pattern.

2. What do you need to do if you have an outlier?Warrant additional scrunity

3. The residuals must be independent of each other, what are the problems that arise if they are not independent?Causes upward bias in t-tests of coefficients, leading us to accept some as statisically significant when they are not.

4. What if these hurdles are not met?If these assumptions are not met then we must take corrective action or use some other method.

5. Least squares regression...Assesses the mathamatical relationship between two variables. One of which the dependent variable (Y). is believed to be casused by the other indepedent variable (X). Alsio, known as Bivariate Regression. Simple Linear least squares regression.