Statistical Analysis Research Paper

The census data of interest in the data tools and apps from the United States census bureau is the 2012 Economic Census. The title of the document is “All sectors: Core Business Statistics Series: Advance Summary Statistics for the U.S. (2007 NAICS Basis): 2012 and 2007.
The data will be instrumental in enabling us to establish the sector that had the highest sales in the year 2012. Other statistics that are of interest will include the sector that had the highest number of employees. Correlation analysis will be conducted to determine if there is a relationship between the sales and the number of employees. The strength of the relationship between these two variables will give an indication as to whether sales and employee number are correlated.
The mean of the value of revenue is 637,660,228.87, and the median is 225,562,195. The difference between these values is the presence of outliers and extreme values. There were four outliers and six extreme values and outliers had a tendency to exaggerate the mean. The mode of the variable is 522,282,839; this value is however not appropriate as a measure of central tendency in our data because we are considering numerous cases each with different value of revenue. The best measure of central tendency, in this case, is the median because it represents the middle value when our data is arranged in ascending order.
The mean number of employees is 2,224,238.89, and the median is 795,496. The mode of the number of employees is 655,358. The best representative of the measure of central tendency is the median. The data of the variable is highly dispersed as can be indicated by the standard deviation. The use of the mean will, therefore, not be appropriate as a measure of central tendency.
It would be expected that the amount of sales is dependent on the number of employees. Therefore, the number of employees is the dependent variable, and the value of revenue is the independent variable. A scatterplot indicates a weak linear relationship between these variables. The value of R2 is 0.328 which means that the variable number of employees predict the variable value of revenue by 32.8%.