Assignment 7

Question 1

Regression Line

Answer 1

The best fitting line through a scatter plot.

Question 2

Slope

Answer 2

The rate of change of a line. The slope describes how fast the line is rising or sinking. It is expressed as the change in y per unit change in x.

Question 3

Y-intercept

Answer 3

The point along the ordinate (the y axis) where a line cuts through when x = 0.

Question 4

Pearson Correlation Coefficient

Answer 4

A parametric measure of association, bounded by + or - 1 in which the observed covariance of two variables is divided by the maximum possible covariance.

Question 5

Homoscedasticity

Answer 5

One of the main assumptions of regression analysis which states that the variability of the y variable is constant across values of x.

Question 6

Heteroscedasticity

Answer 6

In regression analysis when the variability of the y variable is not constant across values of x.

Question 7

Least Squares Criterion

Answer 7

The rule for identifying the best fitting line in a scatterplot. The criterion states that the best fitting line is the one which minimizes the squared deviations of points around the line.

Question 8

Direct Relationship

Answer 8

A relationship in which two variables vary in the same manner. A direct relationship is observed when one variable increases and decreases as another variable does the same.

Question 9

Spearman Correlation Coefficient

Answer 9

A non-parametric measure of association, bounded by + or - 1 which is based upon the same concept of association in the Pearson Correlation, but is computed by way of ranks.

Question 10

Influence

Answer 10

The amount that the deletion of that datapoint would change the overall results of statistical analysis. (A highly influential data point would change the results significantly, where omission of a non-influential data point would not change the results much.)

Question 11

Coefficient of Determination

Answer 11

The square of the Pearson r which describes the proportion of variance in one variable that is explained by the variance in the other.

Question 12

Coefficient of Alienation

Answer 12

Alienation: 1 - the square of the Pearson r which describes the proportion of variance in one variable that is unrelated to the variance in the other.

Question 13

Scatterplot

Answer 13

A graph in which the values of one variable are plotted as a function of another.

Question 14

Standard Error of Estimate

Answer 14

The average error (in y units) when predicting y from x.

Question 15

Residuals

Answer 15

The difference between a measurement and the value of the measurement that is predicted by some mathematical model.

Question 16

Covary

Answer 16

The general term to denote that Variables vary together (i.e., height and weight covary).

Question 17

Inverse Relationship

Answer 17

A relationship in which two variables vary in opposition. As one increases, the other decreases.

Question 18

Fisher Transformation

Answer 18

A non-linear re-expression that is used in assessing the confidence interval of a population Pearson Correlation coefficient.

Question 19

Linearity Assumption

Answer 19

One of the main assumptions of regression analysis which states that a straight line adequately represents the relationship between x and y.

Question 20

Simpson’s Paradox

Answer 20

The change in the magnitude or direction of a relationship that is due to a confounding variable.