For the following scores:

\begin{tabular}{|c|c|}
\hline [tex]$X$[/tex] & [tex]$Y$[/tex] \\
\hline 7 & 6 \\
\hline 9 & 6 \\
\hline 6 & 3 \\
\hline 12 & 5 \\
\hline 9 & 6 \\
\hline 5 & 4 \\
\hline
\end{tabular}

a. Sketch a scatter plot showing these six data points.

b. Describe the correlation in terms of direction and strength by just looking at the scatter plot.

c. Compute the Pearson correlation for these data. (Please show all work)



Answer :

Let's break down the solution step-by-step for each part of the question:

### Part (a): Sketch a Scatter Plot

To create a scatter plot, we plot each pair [tex]\((X, Y)\)[/tex] on a coordinate system where [tex]\(X\)[/tex] values are on the horizontal axis and [tex]\(Y\)[/tex] values are on the vertical axis. Here are the pairs to plot:
- [tex]\((7, 6)\)[/tex]
- [tex]\((9, 6)\)[/tex]
- [tex]\((6, 3)\)[/tex]
- [tex]\((12, 5)\)[/tex]
- [tex]\((9, 6)\)[/tex]
- [tex]\((5, 4)\)[/tex]

Though I cannot directly draw a scatter plot here, you can visualize the points on a graph:

1. Draw your horizontal axis (X-axis) and label it with values from 5 to 12.
2. Draw your vertical axis (Y-axis) and label it with values from 3 to 6.
3. Plot the points on the graph accordingly.

### Part (b): Describe the Correlation

Looking at the scatter plot:

- Direction: You may observe a positive correlation, meaning as [tex]\(X\)[/tex] increases, [tex]\(Y\)[/tex] also tends to increase. However, it's not perfectly linear.

- Strength: The points are somewhat scattered but there is a noticeable pattern that suggests moderate positive linear association. The correlation is not extremely strong but it's not weak either.

### Part (c): Compute the Pearson Correlation

To calculate the Pearson correlation coefficient [tex]\( r \)[/tex], use the formula:

[tex]\[ r = \frac{n(\sum XY) - (\sum X)(\sum Y)}{\sqrt{[n\sum X^2 - (\sum X)^2][n\sum Y^2 - (\sum Y)^2]}} \][/tex]

Where [tex]\( n \)[/tex] is the number of data points (here [tex]\( n = 6 \)[/tex]).

Given the values:
[tex]\[ X = [7, 9, 6, 12, 9, 5] \][/tex]
[tex]\[ Y = [6, 6, 3, 5, 6, 4] \][/tex]

We'll sum the necessary components:
- [tex]\( \sum X = 7 + 9 + 6 + 12 + 9 + 5 = 48 \)[/tex]
- [tex]\( \sum Y = 6 + 6 + 3 + 5 + 6 + 4 = 30 \)[/tex]
- [tex]\( \sum XY = (76) + (96) + (63) + (125) + (96) + (54) = 42 + 54 + 18 + 60 + 54 + 20 = 248 \)[/tex]
- [tex]\( \sum X^2 = 7^2 + 9^2 + 6^2 + 12^2 + 9^2 + 5^2 = 49 + 81 + 36 + 144 + 81 + 25 = 416 \)[/tex]
- [tex]\( \sum Y^2 = 6^2 + 6^2 + 3^2 + 5^2 + 6^2 + 4^2 = 36 + 36 + 9 + 25 + 36 + 16 = 158 \)[/tex]

Now plug these values into the Pearson correlation formula:
[tex]\[ r = \frac{6(248) - (48)(30)}{\sqrt{[6(416) - (48)^2][6(158) - (30)^2]}} \][/tex]

[tex]\[ r = \frac{1488 - 1440}{\sqrt{[2496 - 2304][948 - 900]}} \][/tex]

[tex]\[ r = \frac{48}{\sqrt{192 \cdot 48}} \][/tex]

[tex]\[ r = \frac{48}{\sqrt{9216}} \][/tex]

[tex]\[ r = \frac{48}{96} \][/tex]

[tex]\[ r = 0.5 \][/tex]

So, the Pearson correlation coefficient is approximately [tex]\(0.5\)[/tex], which indicates a moderate positive correlation between [tex]\(X\)[/tex] and [tex]\(Y\)[/tex].