Thursday, August 11, 2016

Fifth Annual Cinnamon Roll DOE

This week, I taught another class on experimental design concepts. Time for another cinnamon roll DOE! Each year, I have a different theme. Recall the themes from past experiments:


This year's theme was Maple Bacon! It seems bacon is especially popular right now for many foodies:  bacon milkshakes, bacon pancakes, bacon you-name-it. One of our local bakeries sells maple bacon doughnuts that are extremely popular. That's what prompted this theme.

Here are the new questions I wanted this experiment to answer:

1. Does roll size matter? Usually I make rather large cinnamon rolls. What if I made them more like Burger King's cini-minis?


2. Does freezing the starter make a difference? My starter is 27 years old, which is quite unusual. Not surprisingly, I've always nurtured it. When my friend Nancy shared that she froze the starter I gave her because of her two-week trip to Australia, I seriously wanted to gasp. No way! I am so grateful she was so bold to do this because I certainly wouldn't have been so daring. Currently, I have to "feed" the starter every two weeks, so if freezing the starter didn't affect the rolls, that would be a huge find. I would be able to take a break from this type of baking for extended periods of time, if desired.

3. Does freezing the rolls make a difference? I tested freezing the rolls twice before: in the Second Annual Cinnamon Roll DOE as well as the Third Annual Cinnamon Roll DOE. In both of those experiments, I learned that freezing actually hurt. Darn. I still don't want to give up. In these previous experiments, I froze the cinnamon rolls after I baked them. What if instead, I froze the rolls before I baked them? 

4. Is a maple icing better than the plain sugar glaze that I normally use?

5. Should I top the cinnamon rolls with bacon or not?

6. Do males have different cinnamon roll preferences than females?

As before, for those of you who just want to bypass the details and simply find the answers to these questions, simply scroll to the bottom of this post. For the rest of you . . .

Here is another way of listing the factors, or changes, that I wanted to try:

Factor:                   Current Condition:     Change to Try:
A:Roll Size                Large                          Small
B: Starter                  Refrigerated               Frozen
C: Rolls                     Fresh                          Frozen
D: Icing                     Plain                            Maple
E: Topping                No topping                 Bacon topping
F: Gender                 Female                       Male

I made 8 different batches of cinnamon rolls, each with differing combinations of above. (Nerd alert:  I conducted a resolution III,  2^6-3 fractional factorial design with 10 replicates.)

The following four batches were made fresh this morning (not frozen first):

Recipe 1: Small cinnamon rolls made with dough from a refrigerated starter. Topped with maple icing and bacon. Taste tested by a male.


Recipe 2: Large cinnamon rolls made with dough from a refrigerated starter. Topped with plain icing. Taste tested by a male. (This was status quo condition, or the control group.)


Recipe 3: Small cinnamon rolls made with dough from a frozen starter. Topped with plain icing and bacon. Taste tested by a female.



Recipe 4: Large cinnamon rolls made with dough from a frozen starter. Topped with maple icing. Taste tested by a female.



The following four batches were made last week and frozen before baking:

Recipe 5: Small cinnamon rolls made with dough from a refrigerated starter. Topped with maple icing. Taste tested by a female.



Recipe 6: Large cinnamon rolls made with dough from a refrigerated starter. Topped with plain icing and bacon. Taste tested by a female.



Recipe 7: Small cinnamon rolls made with dough from a frozen starter. Topped with plain icing. Taste tested by a male.



Recipe 8: Large cinnamon rolls made with dough from a frozen starter. Topped with maple icing and bacon. Taste tested by a male.



As before, I asked each student/co-worker who wanted to participate in this experiment to taste a particular batch (or batches) of cinnamon rolls. (A big thanks to all who participated!) Then, each was asked to provide a "likeability" score (using a 1-5 scale) by completing the following survey:



My plan was to collect 10 surveys for each batch, for a total of 80 observations. However, one batch only yielded 7 surveys and another one only had 9. So, admittedly, there were a few missing observations. After analyzing the results, I learned that only the topping (Factor E) significantly affected the likeability score. This is depicted in the chart below by the very long bar.



Even though most of the responses were very favorable, I learned that the topping (Factor E) had the most significant negative effect on the likeability score. Adding the bacon on top actually hurt. What? This surprised me! 



In fact, one of my buddies Brian said, "If you wrap bacon on a shoe sole, I'll eat it."  I would have thought most people would have agreed! :) But this leads me to another significant find. Scores were all over the place when evaluating the bacon topping. However, answers were more in agreement without the bacon topping.



The remaining factors didn't significantly affect the likeability score. I've said more than once that some of the most significant findings in an experiment are those things that are actually insignificant. (Yes, it sounds like a Yogi Berra quote.)
  • Roll size doesn't matter. Make cinni-minis if you'd like!
  • Freezing the starter doesn't matter. Yeah! Nancy was right. If I want to take a sabbatical from baking, I'll be able to do it now. 
  • Freezing the rolls before baking them doesn't matter. This will be so convenient! I'll be able to make many to freeze, then pull out only a few for baking at one time as opposed to baking a whole pan.
  • The type of icing in this case didn't help or hurt. The maple icing was more expensive to make, so now I know this additional investment isn't worth it.
  • Males didn't have significantly different preferences than females. This surprised me, too. I speculated that males would prefer bacon, but females would not. (Insert your best Tim the Toolman Taylor grunt here.) That just wasn't the case.
Once again, these results were more like the very first cinnamon roll DOE. It looks like I should simply "leave well enough alone." Until next year. . . . 


Brian: "If you wrap bacon on a shoe sole, I'll eat it."



No comments:

Post a Comment

Pin It button on image hover