A couple months ago I was leaving Lowe’s with a bunch of plywood for my rattlesnake “arena”, and I reached the exit just as another older gentleman did. We both kind of stopped, and I said “Oh, sorry.” He said “Go ahead, Mr. Cougar.” Wondering why he called me that, I glanced down at my shirt. Sure enough, I was wearing a Washington State shirt (I rarely pay attention to the way I dress, I just grab whatever shirt is first in the drawer, without paying much attention. It makes for some interesting outfits). I said thanks and walked out first.
The conversation continued outside:
guy at Lowe’s: “Washington State, that’s in Seattle, right?”
me: “No, the University of Washington is in Seattle, Washington State is in the opposite side of the state, near the Idaho border.” (This confusion commonly happens, much to the chagrin of all Cougar alumni, who hate being confused with those pretentious purple bastards).
guy at Lowe’s (thinking for a second): “Oh. Well Washington State is where Mike Price came from, right?”
guy at Lowe’s (suddenly extremely excited): “Oh! Mike Price is the best football coach UTEP has ever had! He turned the program around!!”
me: “Yeah, he had success at both schools, it was a good hire for UTEP.”
He then said some less-than-flattering things about Sean Kugler, and also added that he used to drink at local bars with Don Haskins.
After we parted ways, I began thinking: Is Mike Price really the best football coach UTEP has ever had? That is very debatable. I started thinking further: I wonder how Sean Kugler’s four years here at UTEP compare to Price’s first four years.
So, I decided to do some research. I have for you a chart comparing the two coaches’ records. Price’s first four seasons were from 2004-2007; Kugler’s from 2013-2016 (bowl games included). Here is how they stacked up:
We can see that Price clearly has a better winning percentage than Kugler. But, is there atrue difference here? In science, we sometimes get two groups of data that look similar or different, but upon further analysis, are not. To analyze such datasets we use what is called a t-test. This type of test determines if there is a true difference between two groups. The main thing we are looking for is the p-value. Essentially, a p-value determines whether or not your results are strong enough to be accepted. The threshold used in science in 0.05.
What this means is that if we say Price is a better coach than Kugler (more wins than Kugler through four seasons), and our p-value is less than 0.05, then we can be confident that this is the case. If the p-value is greater than 0.05, then there is no difference between the two coaches’ seasons, in terms of wins.
So, when running a t-test, is there a difference between Kugler and Price’s first four years?
*Note – I swear I did not know what the outcome would be
Answer: Statistically speaking, at least in science, there is no difference between Price’s first four seasons and Kugler’s, when it comes to wins. For all the scientists reading this, here is a screen shot of the data, computed on Minitab 17:
We can see that the p-value is 0.277, which is pretty high. Although Price averaged 6.25 wins per season, compared to Kugler’s 4.5., statistically speaking there is not enough of a difference to be significant. Not even close.
I would like to add that I am not railing for or against Sean Kugler here, nor am I trying to compare him to Mike Price. I am simply evaluating his performance through his first four seasons, compared to Price’s, who I think most Miner fans will agree had some successful seasons at UTEP (although mostly early on).
Furthermore, Price took the Miners to a bowl game his first two seasons; Kugler in his second season.
Also, if the guy from Lowe’s is reading this, thanks for the idea for this article. And, if my doctoral advisor is reading this, I promise I’ll get back to work on my dissertation real soon.