Discussion Replies

1.What results in your departments seem to be correlated or related to other activities?    

My department is the machine gun section of our platoon. If I were to correlate prior data from years in the military (experience) and qualification scores on the weapons then it would be a strong application of this.

How could you verify this?

This could be verified by collecting data from multiple samples. Each sample could be calculated using Pearson’s correlation and then cross compared. Cross comparison will account for inconsistencies of manning and the potential for one group having significant experience over another.

What are the managerial implications of a correlation between these variables?

This could cause many effects if there is a direct correlation between these variables. Understandably with the career of being an Infantryman this could have a severe effect in bias for promotions which equate to pay raises. This could also cause an increased awareness for the importance of training inexperienced soldiers and the understanding of at what point they are efficient in their skill set.  Understanding these factors allow a leader to hammer out weaker skill sets to the best perfection levels possible.

Create a null and alternate hypothesis for one of these issues.

My null and alternative hypothesis for this would be:

Ho : military experience and qualification scores correlation is not statistically relevant

Ha : military experience and qualification scores correlation are statistically relevant


2.At times we can generate a regression equation to explain outcomes.  For example, an employee’s salary can often be explained by their pay grade, appraisal rating, education level, etc.  What variables might explain or predict an outcome in your department or life? 

Currently a hot topic that is separating those that are promotable over one another is their level of involvement in professional organizations.  This is a key indicator between those that are promotable.  “When variable have information in common, the measure of one can be used to predict the measure of the other” (Tanner & Youssef-Morgan, 2013).  Now, just as the books say there could be confusion because it could be a year where the Air Force reduced its personnel numbers making it more difficult to promote compared to normal. 

If you generated a regression equation, how would you interpret it and the residuals from it?

Since both correlation and regression are both based on the concept of association between variables, it could look a lot like a correlation.  Again a scatter plot could be used.  However, in the case above, you must satisfy the ordinary least squares regression providing a minimizing effect on error so that you can see just how much error there might be.  Because the sample population will be large, there will be less error assigned to the values therefore ensuring the regression line will predict equally.  This will give you a representation of how much promotes had been involved in professional organizations.