Regression Analysis can be identified as providing a "best-fit" mathematical equation for the values of the two variables that you chose to analyze. From this we get two types of analysis, one being Simple Linear Regression Analysis, which we have been working with. This type of analysis can be defined as a regression model that uses one independent variable to explain the variation in the dependent variable. From the data given we have chosen to look at the affect experience (in years) has at this given company on annual salary. From gathering the data it is my hypothesis that there will be a positive linear relationship between experience and annual salary. Now lets see if the data supports or contests this.
The first thing done when using the mini-tab program is to put all your data into the columns. Once you have done that you can start to look at your regression analysis. Because I inserted the data by hand, the columns are as follows: C1: Annual salary in dollars, C2: Experience in years, C3: Gender, C4: Age (years), C5: Training level (A=1, B=2, C=3). From the regression analysis the first thing we get is B1. The B1 value is located on the computer print out under the coefficient column and the horizontal column C2. The B1 value tells us that for every unit change in X, it will contribute to the Y by 1833.9 units. Since we have a positive slope, a one-unit increase in X will lead to an increase in Y by 1833.9 units. After we find out what B1 is we then can find out what B0 is which is also located under the coefficient column horizontally in the constant column. This value is 34,620 which to us means that when X is zero then Y(hat)=34620. The fundamental equation for our regression analysis is Y(hat)= 34620+ 1833.9X. From this equation we can now predict what our annual salary will be using a value of X or the years of experience. .
There are three important terms the Sum of the Squared Error, the Sum of Squared Regression and the Sum of Squared total variation.