Changes

and intercept which provides a solvable pair of equations called normal equations.

and intercept which provides a solvable pair of equations called normal equations.

*Suppose there are <math> n </math> data points  <math> {y_{i}, x_{i}}</math>, where i = 1, 2, …, n.

*Suppose there are <math> n </math> data points  <math> {y_{i}, x_{i}}</math>, where i = 1, 2, …, n.

*To find the equation of the regression line:<math> a=bar(y)-b.bar(x)</math>.

*To find the equation of the regression line:<math> a=bar{y}-b.bar{x}</math>.

*This equation will give a "best" fit for the data points.  

*This equation will give a "best" fit for the data points.  

*The "best" means least-squares method. Here b is the slope.

*The "best" means least-squares method. Here b is the slope.

*The slope is calculated by:<math> b=\frac{\sum_{i=1}^{n} {(x_{i}-\bar(x))(y_{i}-\bar(y))}} {\sum_{i=1}^{n}{(x_{i}-bar(x))}^2}</math>.  

*The slope is calculated by:<math> b=\frac{\sum_{i=1}^{n} {(x_{i}-\bar{x})(y_{i}-\bar{y})}} {\sum_{i=1}^{n}{(x_{i}-bar{x})}^2}</math>.  

*In this formula<math> bar(x)</math> and<math> bar(y)</math> are the sample means  AVERAGE of <math> x</math>  and <math> y </math>.  

*In this formula<math> bar{x}</math> and<math> bar{y}</math> are the sample means  AVERAGE of <math> x</math>  and <math> y </math>.  

*In <math>INTERCEPT(y,x)</math> , the arguments can be numbers, names, arrays, or references that contain numbers.

*In <math>INTERCEPT(y,x)</math> , the arguments can be numbers, names, arrays, or references that contain numbers.

* The arrays  values are  disregarded when it is contains text, logical values or empty cells.  

* The arrays  values are  disregarded when it is contains text, logical values or empty cells.