statistics

True. A scatter diagram is used to identify whether there is a relationship between two different quantities (variables).

The type of correlation shown is negative correlation. The data points follow a general trend from the top left of the graph to the bottom right.

False. The data points in a strong correlation closely follow a straight line. If the points only follow a straight line loosely, then they show a weak correlation.

Because the quantities A and B are positively correlated, if quantity A increases, then quantity B will also increase. E.g. the number of ice creams sold by a café is positively correlated with the air temperature. As the air temperature increases, so does the number of ice creams sold by the café.

The phrase "correlation does not imply causation" means that although a correlation may be noticed between two different quantities, it does not necessarily mean that a change in one quantity causes the other to change. E.g. the number of ice creams sold by a cafe and the number of bottles of suncream sold by a shop may be positively correlated. More ice creams being sold does not cause more bottles of sun cream to be sold, but both quantities may increase because of a third related variable, such as as an increase in the number of hours of sunshine.

False. A line of best fit does not have to go through every point in the data set, nor does it have to go through any specific points. The line must follow the general trend of the points and it should have roughly the same number of data points on each side of it.

You can use a line of best fit to predict values that lie within the region covered by the data points: E.g. to estimate the value of y when x = 7, draw a line up from 7 on the x-axis until it meets the line of best fit, then draw a horizontal line back to the y-axis and read off the value.

Interpolation is the method of predicting values that lie within the region covered by the data points. You can use your line of best fit to do this.

False. A line of best fit should not be used to predict values that lie outside of the original data set. This is called extrapolation and values predicted in this way may be unreliable.

When drawing a line of best fit, you should ignore any extreme values that do not fit the general trend of the rest of the points.