Practise Karl Pearson’s correlation coefficient, coefficient of determination, regression equation and interpretation using a biological data problem.
In this question, the number of bacterial colonies destroyed is studied with respect to the amount of antibiotics. So antibiotics is taken as \(X\), and bacterial colonies destroyed is taken as \(Y\).
First calculate \(r\). Then use the sign and size of \(r\) to explain the direction and strength of the relationship.
The regression equation gives an approximate relationship between antibiotic amount and bacterial colonies destroyed for this given data.
\[ r=\frac{n\sum XY-\sum X\sum Y} {\sqrt{\left[n\sum X^2-(\sum X)^2\right]\left[n\sum Y^2-(\sum Y)^2\right]}} \]
\[ \text{Coefficient of Determination}=r^2\times100\% \]
\[ b=\frac{n\sum XY-\sum X\sum Y}{n\sum X^2-(\sum X)^2} \]
\[ \hat{Y}=a+bX \]
In trying to evaluate the effectiveness of antibiotics in killing bacteria, a research institute recorded the amount of antibiotics used and the corresponding number of bacterial colonies destroyed. Find the strength and direction of relationship between them. Also find a relationship between the variables.
| Antibiotics \(X\) | 12 | 15 | 14 | 16 | 17 | 10 |
|---|---|---|---|---|---|---|
| Bacterial Colonies Destroyed \(Y\) | 5 | 7 | 5.6 | 7.2 | 8.6 | 6.2 |
First find the required sums, then calculate \(r\), \(r^2\times100\%\), \(b\), \(a\), and write the regression equation.
Let antibiotics be \(X\) and bacterial colonies destroyed be \(Y\).
| \(n\) | \(\sum X\) | \(\sum Y\) | \(\sum X^2\) | \(\sum Y^2\) | \(\sum XY\) |
|---|---|---|---|---|---|
| 6 | 84 | 39.6 | 1210 | 269.6 | 566.8 |
Karl Pearson’s correlation coefficient:
\[ r=\frac{n\sum XY-\sum X\sum Y} {\sqrt{\left[n\sum X^2-(\sum X)^2\right]\left[n\sum Y^2-(\sum Y)^2\right]}} \]
\[ r=\frac{6(566.8)-84(39.6)} {\sqrt{\left[6(1210)-84^2\right]\left[6(269.6)-(39.6)^2\right]}} \]
\[ r=\frac{74.4}{\sqrt{204\times49.44}} \]
\[ r=0.741 \]
Interpretation of \(r\):
Since \(r=0.741\) is positive and greater than \(0.7\), there is a strong positive linear correlation between antibiotics and bacterial colonies destroyed.
This means that, in this data set, a higher amount of antibiotics is associated with a higher number of bacterial colonies destroyed.
Coefficient of determination:
\[ \text{Coefficient of Determination}=r^2\times100\% \]
\[ =(0.741)^2\times100\% \]
\[ =54.88\% \]
About \(54.88\%\) of the variation in bacterial colonies destroyed is explained by antibiotics according to this fitted linear model.
Now find the regression equation of bacterial colonies destroyed on antibiotics.
\[ b=\frac{n\sum XY-\sum X\sum Y}{n\sum X^2-(\sum X)^2} \]
\[ b=\frac{6(566.8)-84(39.6)}{6(1210)-84^2} \]
\[ b=\frac{74.4}{204} \]
\[ b=0.365 \]
Also,
\[ \bar{X}=\frac{84}{6}=14,\qquad \bar{Y}=\frac{39.6}{6}=6.6 \]
Method 1: Finding \(a\) first
Using \(a=\bar{Y}-b\bar{X}\),
\[ a=6.6-0.365(14) \]
\[ a=1.494 \]
Therefore, the regression equation is:
\[ \hat{Y}=1.494+0.365X \]
Method 2: Using the mean form of the regression line
After finding \(b\), we can also form the regression line directly by using:
\[ Y-\bar{Y}=b(X-\bar{X}) \]
Here,
\[ \bar{X}=14,\qquad \bar{Y}=6.6,\qquad b=0.365 \]
Substituting these values,
\[ Y-6.6=0.365(X-14) \]
Now simplify:
\[ Y-6.6=0.365X-5.110 \]
\[ Y=1.490+0.365X \]
This gives the same regression line, except for a small difference due to rounding. In final answer, we write:
\[ \hat{Y}=1.494+0.365X \]
Meaning of the regression coefficient:
The regression coefficient \(b=0.365\) indicates that for each additional unit of antibiotics, the predicted number of bacterial colonies destroyed increases by about \(0.365\) unit.