Interval/ratio measures of association

what is simple regression?

predict how someone will score on dv based on a specific score on iv

the regression line is the line of best fit

for the regression line if the question asks “calculate the percentage variation in the dependent that is explained by the independent variable” this is co-efficient so use pearson’s r

how to calculate the regression line

1) do the same calculations as for interval/ratio (x, y, xy, x², y²⁾ but add new columns for x² and (x)²

2) find the y-intercept (the y with the line means the average of y and the line above x is the average of x)

3) identify the regression line → the regression line is only y = a + bx and not the whole thing solved

4) use the regression line to determine the value for y for a specific value of x

how to solve for A?

so a has y with a line on top and x with a line on top → for each letter calculate the average

the finding for a is when x is 0; y is (the answer) the line regression starts at x = 0 and y = (answer)

what should be in the summary table?

N =

∑y =

∑x =

∑x² =

∑y² =

∑xy =

(∑x)²

(∑y)²

what is the finding for b

for every x, y will increase by b

what is a scatterplot?

it’s a visual representation of how changes in one variable affect changes in the other

1) title: type of graph of dependent by independent

2) label axes using the variable labels

3) plot the values of the iv (plotted on x axis) and dv (plotted on y axis)

4) each ordered pair is represented as a point on the graph showing the relationship between the two variables and if 2 have the same point just put 2 in brackets above it

5) determine the relationship - negative or positive

what is pearson’s r?

asymmetrical measure, used to determine strength, direction, and co-efficient of determination

co-efficient of determination: the percentage in variation (change) in the dv that is explained by the iv

what are the steps for pearson’s r?

1) determine x and y

2) create a frequency table with x, y, xy, x² and y²

3) make a little table with the sums of everything

use the formula

and square it → r² = the answer squared

the finding is: x% of the differences found in the dv is explained by the iv

x