Karteikarten
Stats Part 4
Karten in diesem Stapel (20)
- 1What is the advantage of the coefficient of correlation over the covariance?It has a lower and upper set of limits, which allow us to determine the strength of the linear relationship- which couldn't be completed in the covariance
- 2How to determine the strength of association of the covariance?- difficult to judge
- 3Definition of the Coefficient of Correlation- the covariance divided by the Standard Deviation of the variables
- 4Coefficient of Determination- measures the amount of variation in the dependent variable that is explained by the variation in the independent variable
- 5What does a coefficient of determination of 0.3000 represent?30.00% of the variation in the dependent variable (Y) is caused by the independent variable (X)
- 6Required Condition for the Error Variable- the probabilty distribution of e is normal
- the mean of the distribution is 0, E(e)=0
- the SD of e is constant regardless of the value of x
- value of e associated with any particular value of y is independent of e associated with any other value of y - 7probabilistic model- realistic probability model that takes into account the randomness error
- 8deterministic model- equations allow us to determine the value of the dependent variable
- 9What does observational regressional data allow us to infer?- correlation data, but not which variable is dependent or independent
- 10What does experimental data allow us to infer?- determine if correlation
- which value is dependent, which value is independent - 11Which two pieces of information can we extract from the covariance?- sign of the covariance- which tells us the nature of the relationship
- magnitude- describes the strength of the association - 12What is a drawback of the coefficient of correlation?- except for 1,0 and -1, we can't interpret the correlation
- 13Least Squares Method Definition- an objective method of producing a straight line
- produces a straight line drawn through the points, so that the sum of the squared deviations between the points and the line is minimized - 14Regression Analysis- allows us to predict the value of one variable on the basis of other variables
- 15SSE- sum of squares for error
- the minimized sum of squared deviations - 16First-Order Linear Model- relationship between an independent and dependent variable
- 17What is the condition of the distibution being normal called?- normality
- 18Why is auto-corellation bad?- involves patterns, which means an absense of randomness
- 19Definition of Auto-Correlation- when two errors are dependent of each other
- when the data is time series, errors often involve auto-correlation - 20—
Informationen
- Beschreibung
- Karteikarten am Stats Part 4, erstellt von Chanel Elenbaas am 07/11/2018.
- Erstellt von
- Chanel Elenbaas
- Aufrufe
- 2
- Bewertung