I need a coorelation data to work on a project. eg a data of study time and the marks getting. please help me.

Question

we have a project that we have to find a data like lets say students studying time and their marks and than from that i have to do hypothesis and the correlation study and have to go in depth so please someone help me get a data that will help me do this project please.

Answer 1

You're going to have to get your own data, but if I were you, here's how I'd do it.

First, I'd recognize that grades ought to be a function of study time, not the other way around. In other words, if I study longer, I ought to get a higher grade; if I get a higher grade, then I ought to study longer.

That has to do with dependent and independent variables. Here, we're saying that grades (the dependent variable) depend on study time (the independent variable).

Your hypothesis, then, is that grades depend on study time; the longer you study, the higher your grade will be. You can write this as

y = a + bx

where y is the grade, x is the time spent studying, and a and b are the regression coefficients.

Next, you need to gather data, preferably for at least 30 students. For each one, you need the grade obtained (y) and the time spent studying (x).

The time might be in hours or minutes. The grade might be on a 0 to 100 scale, or it might be letter grades A through E. If you use letter grades, let A be 4, B be 3, and so on. If plusses and minuses are used, e.g., C+ or B-, you can, for example, use a 12-point grading scale where A+ is 12, D- is 1, and a fail (E) is 0.

You tabulate these data pairs, and you can also make a "scatter diagram" where time studying is on the x-axis and the grade obtained is on the y-axis.

Now you want to do the regression and the correlation of the data. To get the regression coefficients a and b, use the formulas

b = (n sumxy - sumx sumy) / (n sumx2 - sumx^2)

a = (sumy - b sumx) / n = ybar - b xbar

where n is the number of students, sumxy is the sum of the xy products, sumx and sumy are the sums of the x and y data columns, sumx2 is the sum of the x-squared terms, xbar and ybar are the averages of the x's and y's.

This gives you your regression equation y = a + bx.

Now you want the correlation coefficient. Use the formula

r = (n sumxy - sumx sumy) /
sqrt[(n sumx2 - sumx^2) (n sumy2 - sumy^2)]

The correlation coefficient has a value between -1 and +1. When it's close to zero, you have little or no relationship between study time and grades; when the absolute value of r is closer to 1, you have a more significant relatiionship.

One other thing you'd like to look at is r^2, the "coefficient of determination." This tells you what percentage of the grade is due to the amount of time studying.

For example, suppose r = 0.7. Then r^2 is about 0.5, and 50% of the grade is determined by the amount of time studying.