Design of Experiment

Design of Experiment case studies:

In this case study that I am doing with my associate (Andrew), we role-played as the CEO (team leader) and CFO (Chief Financial Officer) to find the ranking of the factors that affected the number of inedible unpopped kernels that remained in popcorn.

3 factors were identified, namely:

1. Diameter of bowls to contain the corn, 10 cm and 15 cm.
2. Microwaving time, 4 minutes and 6 minutes.
3. Power setting of microwave, 75% and 100%.

8 runs were performed with 100 grams of corn used in every experiment and the measured variable is the amount of “bullets” formed in grams and data collected are shown below. This data will be used for full factorial data analysis.

Run order

A

B

C

Bullets (grams)

1

+

-

-

3.5

2

-

+

-

1.6

3

-

-

+

0.7

4

+

+

-

1.2

5

+

-

+

0.7

6

+

+

+

0.3

7

-

+

+

0.5

8

-

-

-

3.1

 

I have sorted the data into their respective run orders in this table below as shown in excel:



Factor A was the Diameter of bowls to contain the corn, 10 cm and 15 cm.
Factor B was the Microwaving time, 4 minutes and 6 minutes.
Factor C was the Power setting of microwave, 75% and 100%.

After tabulating all the results into the excel table as seen above, I have acquired the data plots for the average weight of the bullets for high and low levels of the corresponding factors. The graph obtained is shown below:



Effects of factor C is the greatest, followed by B and lastly A.

Interaction effects of each factor:

I have deduced that the weight of bullets is affected the greatest due to change of level of factor C, followed by factor B, and lastly factor A.

Conclusion of the data analysis

When the power setting of the microwave is at 75%, there is a greater number of inedible unpopped kernels.
When the microwaving time is at 4 minutes, there is a greater number of inedible unpopped kernels.
When the Diameter of bowls to contain the corn is 10 cm, there is a greater number of inedible unpopped kernels.

 

To use subsequent data for fractional factorial data analysis, I will be using runs 1, 2, 3 and 6. The sorted data in their respective run order is in this table below as shown in excel:



After tabulating all the results into the excel table as seen above, I have acquired the data plots for the average weight of the bullets for high and low levels of the corresponding factors. The graph obtained is shown below:



Effects of factor C is the greatest, followed by B and lastly A.


Interaction effects of each factor:

I have deduced that the weight of bullets is affected the greatest due to change of level of factor C, followed by factor B, and lastly factor A.

Conclusion of the data analysis

When the power setting of the microwave is at 75%, there is a greater number of inedible unpopped kernels.
When the microwaving time is at 4 minutes, there is a greater number of inedible unpopped kernels.
When the Diameter of bowls to contain the corn is 10 cm, there is a smaller number of inedible unpopped kernels.

 

The data file for the fractional factorial data analysis can be found in the link below:

https://docs.google.com/spreadsheets/d/1iKVY0SWdHeOscCj2Kk3ebnQWT26l9LST/edit?usp=sharing&ouid=109141842767507540525&rtpof=true&sd=true

The data file for the full factorial data analysis can be found in the link below:

https://docs.google.com/spreadsheets/d/1mJ7Z4-UwK8l55WmxnHiyEWOfClZznyAa/edit?usp=sharing&ouid=109141842767507540525&rtpof=true&sd=true





Comments