Design of Experiments (DOE) Checklist

Problem Definition & Objective Setting

1 of 8

Focuses on clearly defining the manufacturing problem and establishing measurable objectives for the DOE.

Describe the Manufacturing Problem

What are the initial observations and symptoms of the problem?

What is the current process capability (e.g., Cp, Cpk)?

What is the primary objective of the DOE? (Choose One)

Reduce Variation

Improve Mean

Reduce Cost

Improve Quality

Other (Specify)

Define specific, measurable, achievable, relevant, and time-bound (SMART) objectives for the DOE.

Target improvement percentage (e.g., reduce defect rate by 10%)

What are the key constraints limiting the improvement?

Cost

Time

Equipment

Material

Other (Specify)

Describe the current process control measures (if any).

Factor & Response Selection

2 of 8

Deals with identifying potential factors influencing the response and selecting the key responses to be optimized.

Describe the manufacturing process being studied.

What is the desired output metric (e.g., throughput, yield, defect rate)?

Select the units of measurement for the response variable (e.g., pieces/hour, %, parts per million).

Pieces/Hour

Percentage (%)

Parts Per Million (PPM)

Millimeters (mm)

Seconds

Other (Specify in LONG_TEXT)

List potential factors that could influence the response.

For each potential factor, briefly describe how it impacts the response (positive or negative).

Estimate the current average value of the response variable.

Which factors are considered the most critical to investigate (based on prior knowledge or experience)?

Describe any constraints on the factor ranges (e.g., equipment limitations, safety regulations).

Experimental Design Selection

3 of 8

Covers the process of choosing the appropriate experimental design (e.g., Full Factorial, Fractional Factorial, Response Surface Methodology) based on the problem and resource constraints.

Primary Design Type

Full Factorial

Fractional Factorial

Response Surface Methodology (RSM)

Mixture Design

Taguchi Design

Number of Factors to be Studied

Number of Levels per Factor

Central Composite Design (If using RSM)

Face-Centered

Circle

Incomplete Block

Justification for Chosen Design

Randomization Method

Latin Square

Random Order

Cyclical

Number of Replicates

Considerations for Interactions (if applicable)

Experimental Setup & Validation

4 of 8

Focuses on the physical setup, ensuring accurate data collection, and validating the experimental conditions.

Equipment Calibration Date

Standard Operating Procedure (SOP) Verified?

Yes

Describe Equipment Setup and Configuration

Measurement System Analysis (MSA) Score (e.g., % agreement)

Environmental Conditions Controlled?

Yes

Document any deviations from planned setup

Attach Photos/Videos of Setup (Optional)

Date of Setup Verification

Data Collection & Analysis

5 of 8

Addresses the procedures for collecting data and using statistical analysis tools to interpret results.

Number of Replicates per Run

Measurement Resolution (e.g., decimal places)

Calibration and Measurement System Analysis (MSA) Documentation Review

Statistical Software Used (e.g., Minitab, R, JMP)

Minitab

JMP

Other

Sample Size for Each Factor Level

Description of Data Validation Procedures

Analysis Method Used (e.g., ANOVA, Regression)

ANOVA

Regression

Other

Raw Data File (CSV, Excel)

Results Interpretation & Conclusion

6 of 8

Focuses on drawing meaningful conclusions from the experiment, identifying significant factors, and recommending actions.

Summarize the key findings of the DOE.

What is the R-squared value for the model? (Indicates model fit)

Which factors were found to be statistically significant (p < 0.05)?

Factor A

Factor B

Factor C

No significant factors found

Describe the interaction effects observed (if any).

What is the predicted optimal setting for the factors?

Does the model adequately explain the variability in the response? (Based on R-squared & Residual Analysis)

Yes, the model is a good fit.

The model needs improvement.

The model is not appropriate.

What conclusions can be drawn from the DOE results regarding the original manufacturing problem?

Which of the following recommendations are made based on the DOE?

Adjust factor settings

Modify process parameters

Investigate further

No action required

Implementation & Verification

7 of 8

Covers the steps involved in implementing the changes based on DOE results and verifying their impact.

Describe the proposed changes to the manufacturing process based on DOE findings.

Target improvement percentage for the response variable (e.g., yield, defect rate).

Planned start date for implementing the changes.

Planned completion date for implementation.

Number of production runs to monitor after implementation.

Method for initial verification (e.g., pilot run, gradual rollout).

Pilot Run

Gradual Rollout

Full Production Implementation

Describe the verification plan, including data collection methods and acceptance criteria.

Which key performance indicators (KPIs) will be monitored during verification?

Yield

Defect Rate

Cycle Time

Material Waste

Cost per Unit

Verification Result: Pass/Fail

Pass

Fail

Needs Further Investigation

Documentation & Reporting

8 of 8

Ensures proper documentation of the entire DOE process for future reference and auditing purposes.