Scribd
Upload
40 views1 page

A Level Stats 5 Correlation - Regression

This document defines key terms related to correlation and regression analysis, including correlation, bivariate data, least squares regression line, independent and dependent variables, interpolation and extrapolation. It explains that the 'b' value of a regression line indicates the change in the dependent variable for each unit change in the independent variable. Hypotheses for correlation tests are outlined. It also notes that a regression line is only a valid predictive model when the data shows linear correlation, and predictions should only be made within the original data range.

Uploaded by

Alex Goldsmith
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
40 views1 page

A Level Stats 5 Correlation - Regression

This document defines key terms related to correlation and regression analysis, including correlation, bivariate data, least squares regression line, independent and dependent variables, interpolation and extrapolation. It explains that the 'b' value of a regression line indicates the change in the dependent variable for each unit change in the independent variable. Hypotheses for correlation tests are outlined. It also notes that a regression line is only a valid predictive model when the data shows linear correlation, and predictions should only be made within the original data range.

Uploaded by

Alex Goldsmith
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

What do I need to know

Key words & Definitions Interpreting ‘b’ of a regression line:


Refer to the change in the variable y for each
1. Correlation A description of the linear unit change of the variable x IN CONTEXT
relationship between two variables.
2. Bivariate data Pairs of values for two variables PMCC, r is the PMCC for a population sample
3 Causal relationship Where a change in a variable
causes a change in another. Not always true. PMCC,  is the PMCC for the entire population
4 Least squares regression line
A type of line of best fit which is a straight line in Range of PMCC, r: -1 ≤ r ≤ 1
the form y = a + bx
5 ‘b’ of a regression line Hypotheses for one tailed test on PMCC:
The gradient of the line; indicating positive H0:  = 0
correlation if it is positive and negative correlation H1:  > 0 or H1:  < 0
if it is negative..
6 Independent or Explanatory variable Hypotheses for two tailed test on PMCC:
The variable which occurs regardless of the other H0:  = 0
variable (e.g. time passing). Plotted on the x axis. H1:  ≠ 0
7 Dependent or Response variable
The variable whose value depends on the Check sample size is big enough to draw a valid
independent variable’s data points. conclusion and comment on it if not.
8 Interpolation Estimating a value within the range
of the data. Reliable. A regression line is only a valid model when the
9 Extrapolation Estimating a value outside of the data shows linear correlation.
range of the data. NOT reliable.
Only make predictions for the dependent
10 Product Moment Correlation Coefficient
variable using the regression line of y on x
A measure of the strength and type of
within the range of the original data
correlation.

Perfect positive Strong positive Weak positive No Weak negative Strong negative Perfect negative
correlation correlation correlation correlation correlation correlation correlation

r=1 r = 0.8 r = 0.3 r=0 r = -0.3 r = -0.8 r = -1


Exponential models
You can use logarithms and
If y = axn then logy = loga + nlogx
coding to transform graphs
and examine trends in If y = kbx then logy = logk + xlogb
non-linear data
@Lucyjc1612

You might also like