Correlation and Regression Analysis – RTE Foods
Consumer Survey
Dataset Used
• Total responses analyzed: 122
• Project Type: Ready-to-Eat (RTE) Foods Consumer Survey
Variables Converted into Numerical Form for Statistical Analysis
Variable Coding Used
Frequency of Purchase Daily=5, Weekly=4, Occasionally=3, Rarely=2, Never=1
Monthly Spend Below Rs.500=1, Rs.500–1000=2, Rs.1000–2000=3, Above Rs.2000=4
Label Check Never=1, Sometimes=2, Always=3
Try New Products No=0, Yes=1
Satisfaction Original rating scale
Taste Rating Original rating scale
1. Correlation Analysis
Correlation measures the relationship between two variables.
• Positive value → both variables increase together
• Negative value → one increases while the other decreases
• Near 0 → weak or no relationship
Correlation Matrix
Monthly Label Try New
Variables Satisfaction Taste Frequency
Spend Check Products
Satisfaction 1.00 -0.13 0.06 -0.05 -0.16 0.13
Taste -0.13 1.00 -0.08 -0.06 -0.03 0.02
Frequency 0.06 -0.08 1.00 0.00 0.06 0.10
Monthly Spend -0.05 -0.06 0.00 1.00 -0.03 -0.05
1
Monthly Label Try New
Variables Satisfaction Taste Frequency
Spend Check Products
Label Check -0.16 -0.03 0.06 -0.03 1.00 -0.02
Try New
0.13 0.02 0.10 -0.05 -0.02 1.00
Products
Interpretation of Correlation Results
Key Findings
1. Satisfaction and Taste Rating (-0.13)
2. Very weak negative relationship.
3. Taste rating alone does not strongly influence overall satisfaction.
4. Satisfaction and Frequency of Purchase (0.06)
5. Very weak positive relationship.
6. Consumers purchasing more frequently are only slightly more satisfied.
7. Satisfaction and Monthly Spend (-0.05)
8. Almost no relationship.
9. Higher spending does not guarantee higher satisfaction.
10. Satisfaction and Trying New Products (0.13)
11. Weak positive relationship.
12. Consumers willing to try new products tend to be slightly more satisfied.
13. Satisfaction and Label Checking (-0.16)
14. Weak negative relationship.
15. Consumers who carefully check labels may be more critical in their evaluations.
2
2. Regression Analysis
Objective
To identify whether the following variables influence consumer satisfaction:
• Taste Rating
• Frequency of Purchase
• Monthly Spending
• Trying New Products
Regression Model
Dependent Variable:
Satisfaction
Independent Variables:
• Taste Rating
• Frequency of Purchase
• Monthly Spending
• Try New Products
Regression Equation
Satisf action = 4.327 − 0.125(T aste) + 0.044(F requency) − 0.040(M onthly Spend) + 0.261(T ry N ew)
Regression Results
Variable Coefficient Interpretation
Constant 4.327 Base satisfaction level
Taste Rating -0.125 Slight negative effect on satisfaction
Frequency of Purchase 0.044 Small positive effect
Monthly Spend -0.040 Negligible negative effect
Try New Products 0.261 Positive effect on satisfaction
3
Model Summary
Measure Value
R² (Coefficient of Determination) 0.039
Adjusted R² 0.006
F-statistic 1.176
p-value 0.325
Interpretation of Regression Output
1. R² = 0.039
2. Only 3.9% of the variation in satisfaction is explained by the selected variables.
3. This indicates a weak predictive model.
4. p-value = 0.325
5. The regression model is statistically not significant.
6. The selected variables do not strongly explain consumer satisfaction.
7. Try New Products has the strongest positive coefficient.
8. Consumers open to trying new RTE products tend to report higher satisfaction.
9. Taste and Spending show weak negative coefficients.
10. These factors do not significantly influence satisfaction in this dataset.
Final Conclusion
• The dataset shows weak correlations among the major consumer behavior variables.
• Consumer satisfaction cannot be strongly predicted using only taste, purchase frequency, monthly
spending, and willingness to try new products.
• Other variables such as:
• Brand trust
• Product availability
• Health perception
4
• Convenience
• Packaging
• Quality consistency may play a stronger role in influencing satisfaction.
Suggested Statistical Tools for Your Final Project
Additional Statistical Tools Included
1. Percentage Analysis
2. Frequency Distribution
3. Bar Charts and Pie Charts
4. Cross Tabulation
5. Chi-Square Test
6. Weighted Average Ranking Method
7. Correlation Analysis
8. Regression Analysis
9. Multiple Regression
10. ANOVA (Analysis of Variance)
11. Mean, Median and Mode
12. Standard Deviation
13. Factor Analysis
14. Consumer Satisfaction Index
15. Trend Analysis
16. Pivot Table Analysis
Applications in Your RTE Foods Project
• Identify consumer buying behavior
• Measure satisfaction level
• Compare spending patterns
• Analyze demographic influence
• Predict satisfaction using regression
• Identify hidden consumer preference factors
• Rank important purchase factors
• Study relationships among variables
You can additionally perform:
1. Percentage Analysis
2. Chi-Square Test
3. ANOVA
4. Weighted Average Ranking
5. Multiple Regression
6. Factor Analysis
7. Cross Tabulation
5
8. Consumer Preference Ranking
9. Trend Analysis
10. Pivot Table Analysis in Excel
Excel Steps to Perform Correlation and Regression
Correlation in Excel
1. Go to Data → Data Analysis
2. Select Correlation
3. Choose input range
4. Tick Labels in First Row
5. Select Output Range
6. Click OK
Regression in Excel
1. Go to Data → Data Analysis
2. Select Regression
3. Input Y Range = Satisfaction
4. Input X Range = Independent variables
5. Tick Labels
6. Click OK