The correlation coefficient, denoted as 'r', measures the strength and direction of the linear relationship between two quantitative variables, ranging from -1 to +1. A positive value indicates both variables increase together, while a negative value indicates one increases as the other decreases; a value of zero indicates no association. Caution is advised when using correlation coefficients in non-linear relationships, in the presence of outliers, or when variables are measured across distinct groups.
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
0 ratings0% found this document useful (0 votes)
5 views11 pages
Correlation Coefficient
The correlation coefficient, denoted as 'r', measures the strength and direction of the linear relationship between two quantitative variables, ranging from -1 to +1. A positive value indicates both variables increase together, while a negative value indicates one increases as the other decreases; a value of zero indicates no association. Caution is advised when using correlation coefficients in non-linear relationships, in the presence of outliers, or when variables are measured across distinct groups.
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 11
CORRELATION
COEFFICIENT Dr. HAMOOYA • Correlation coefficient simply summarizes the strength of the relationship between two quantitative variables.
• Correlation coefficient is denoted by a letter “r”
• Apart from summarizing the strength of the relationship,
correlation coefficient test the null hypothesis that the population correlation coefficient (p) is zero.
• The quantity for correlation coefficient ranges from -1 to
+1 • Positive correlation is one in which both variables increase together
• Negative correlation is one in which one variable increases
as the other decreases.
• When variables are linearly connected/related, the correlation
coefficient will either be -1 or +1.
• Correlation coefficient is not affected by the unit of
measurement. Say you want to ascertain the relationship cholesterol (mmol/l) and age (years), despite different units of measurement, correlation coefficient remains the same Correlation coefficient, r =1 Correlation coefficient, r = -1 Correlation coefficient, r = 0 • When correlation coefficient, r=0, then it means there is no association.
• Correlation coefficient , r=1, indicates a perfect positive
relationship/association i.e as one variable increases even the other one increases.
• Correlation coefficient , r=-1, indicates a perfect inverse
relationship/association i.e as one variables increases, the other one decreases
• Correlation coefficient is used when the basic relationship
between the two variables is linear. • Existence of a correlation between two variables does not necessarily imply causation
• Correlations may arise because;
• one variable is the partial cause of another • or the two correlated variables have a common cause
• Factors such as sampling, variation in the two populations
e.t.c affect the size of the correlation coefficient When not to use correlation coefficient • Correlation coefficient should not be used when the relationship is non-linear • Correlation coefficient should be used with a caution in the presence of outliers • Correlation coefficient should be used with a caution when variables are measured over more than one distinct group • Correlation coefficient should not be used in situations where one of the variables is determined in advance. • Assumption underlying the test of significance correlation coefficient is that observation are random samples and that one of the two variables is normally distributed • When the assumption of normality is fulfilled, Pearson correlation coefficient is used. • When the assumption of normality is not fulfilled, Spearman correlation coefficient is used. Reference • Biostatistics and epidemiology : a primer for health and biomedical prefessionals / by Sylvia Wassertheil-Smoller.— 3rd ed (2003).