Since you have 8 independent variables and one dependent variable, logistic regression can be a suitable method for this analysis, especially when you have a binary outcome like customer acceptance (yes/no).

Here's a step-by-step guide on how to proceed:

1. Data Preparation:

- Ensure your data is cleaned and organized.

- Combine Likert scale questions to create composite independent variables if necessary.

- Encode your dependent variable as binary, where "Accepted" is 1 and "Not Accepted" is 0.

2. Data Exploration:

- Begin by exploring your data to understand its distribution and characteristics.

- Use descriptive statistics and data visualization techniques (e.g., histograms, box plots) to gain insights into your variables.

3. Assumptions Check:

- Logistic regression assumes that the independent variables are not highly correlated. Check for multicollinearity among your independent variables. If multicollinearity exists, consider addressing it through techniques like variable selection or dimensionality reduction.

4. Model Building:

- Split your data into a training set and a testing set (e.g., 70% training, 30% testing) for model evaluation.

- Fit a logistic regression model to your training data. You can use software like Python (with libraries like scikit-learn or statsmodels) or R for this.

- Interpret the coefficients of the model to understand the impact of each independent variable on customer acceptance.

5. Model Evaluation:

- Evaluate the performance of your logistic regression model using various metrics such as accuracy, precision, recall, F1-score, and the area under the ROC curve (AUC-ROC).

- Use the testing dataset to assess how well your model generalizes to new data.

6. Model Improvement:

- If the initial model doesn't perform well, consider feature selection or engineering to improve it. You may also experiment with different algorithms.

7. Interpretation:

- Interpret the results of your logistic regression model in the context of your study. Which independent variables have a significant impact on customer acceptance?

8. Validation and Deployment:

- If your model performs well on the testing data and meets your study objectives, you can consider deploying it for real-world predictions.

Remember that logistic regression assumes that the relationship between independent variables and the log-odds of the dependent variable is linear. If your data doesn't meet this assumption, you may need to explore other machine learning algorithms, such as decision trees or random forests, which can capture non-linear relationships.

Also, since you have Likert scale questions, you may want to convert them into numerical values before using them in the logistic regression model. This can be done through techniques like ordinal encoding or creating dummy variables.

Lastly, ensure that you have a sufficiently large and representative dataset for reliable model training and validation.

Gabriel Angelo Lomibao Rubia ok thanks for your information . I found similar answer using GPT. I need to know how i can deal with qualitative and quantative data in logestic regression

Mohammed Abdulaziz Abdulrasol Al-Romema I'm sorry if it looked like my responses resembled something automated like ChatGPT. I want to make it clear that I haven't used such tools because I understand they can potentially diminish the credibility and authenticity of research.

As for your question, I have experienced the same situation but in a different application.

So, when you've got numbers like ages or incomes, you can use them straightforwardly in logistic regression. But when you're dealing with categories, things get interesting. For simple binary choices like "yes" or "no," you just turn them into 0s and 1s, like 0 for "no" and 1 for "yes." When you have more options, say, different colors, that's when "one-hot encoding" comes into play. It's like creating little boxes for each category and marking a 1 in the box if that category applies and 0s in all the others. But watch out for multicollinearity when using one-hot encoding; it can get your model a bit tangled. If your categories have a clear order, you can assign numerical values based on that order. Just keep in mind that making sure your data and model speak the same language is the key to success in logistic regression.

Gabriel Angelo Lomibao Rubia thanks a much bro, I am appreciated your answer.

I misunderstand some points:

more one questions: IF I have this data:

********independent variables

* multible choice questions:

1.maximum distance are willing to

A. 0 m

B.100-500 m

C.More than 500 m

2.(overall travel time)

A.20 minutes

B.40 minutes

C.60 minutes

*LIKERT SCALE Questions :

3.Risk in payment

Q1.Risk of payment delay from customers

Q2.Risk of cancellation from customers

Q3.Risk in cash on delivery

Q4Risk in cash settlement

task stress

Q1.I feel tired of the long Participiting hours

Q2.task negatively affects my health

Q3.I feel insecure at task

********dependent variable

accepet the technology :

A.YEs

B.NO

could you please explain how i can solve this problem using spss or any tool? i would be thank for u for ur cooperation

Mohammed Abdulaziz Abdulrasol Al-Romema I don't know if this is also the same in your situation. But here's my suggestion based on your scenario. I hope this helps.

Step 1: Get Your Data Ready

• First things first, make sure your data is neatly organized in a spreadsheet. Each question should have its own column, and answers should be converted into numbers. For example, for "maximum distance," you could use 1 for "0 m," 2 for "100-500 m," and 3 for "More than 500 m." Do the same for Likert scale responses, using a scale like 1 for "Strongly Disagree" and 5 for "Strongly Agree."

Step 2: Import Your Data into SPSS

• Open up SPSS and bring your dataset in. SPSS should recognize the type of variables you have (nominal or ordinal), but you may need to tweak this manually.

Step 3: Define Your Variables

• In SPSS, go to the "Variable View" tab. Here, you can define your dependent variable, which is "accept the technology" in your case. Make sure it's set as nominal since it's binary (Yes/No).
• Define your independent variables too, including the multiple-choice and Likert scale questions. Set the variable types appropriately (nominal or ordinal).

Step 4: Time to Analyze

• Head over to the "Data View" tab and check that your data is properly loaded.
• Now, go to the "Analyze" menu, pick "Regression," and then "Binary Logistic."

Step 5: Setting Up the Logistic Regression

• In the "Binary Logistic Regression" box, drag your dependent variable ("accept the technology") to the "Dependent" box.
• Move your independent variables to the "Covariates" or "Predictors" box. SPSS can handle the different types of variables you have (binary and ordinal).

Step 6: Customize Your Model (Optional)

• You can tweak your analysis further if you want. For instance, you can choose between "Forward" or "Backward" for variable selection, define categorical variables if needed, and check for multicollinearity.

Step 7: Run the Analysis

• Click "OK" to start the logistic regression analysis.

Step 8: Making Sense of the Results

• SPSS will generate a bunch of stats and coefficients. Pay attention to those coefficients; positive ones suggest a positive link with accepting the technology, while negative ones imply the opposite.

Step 9: Check for Significance

• Look at the p-values linked to each coefficient. If they're below your chosen significance level (typically 0.05), that variable is considered significant.

Step 10: Evaluate How Well Your Model Fits

• Use statistics like the Wald chi-square test and the Hosmer-Lemeshow test to gauge how well your model matches the data.

Gabriel Angelo Lomibao Rubia OK Thanks . your information is valuable.

if i add dimographic variables like:

A. What is your gender?

📷 Male 📷 Female

B. Which age group do you belong to?

📷 18- 25years. 📷 26- 30years. 📷 > 30 years.

how i can deal with them by logistic regression. i mean how i can handle with them? put them in an independent variable(covariate)box or categorical box or something else?

Mohammed Abdulaziz Abdulrasol Al-Romema Based on your scenario, here's how I understand it as it applies.

Let's discuss how to handle demographic variables like gender and age group in a way that's more like a friendly conversation:

Gender (Categorical Binary Variable):

• Think of gender as a simple "Male" or "Female" choice.
• In our logistic regression analysis, we treat it as a categorical binary variable. So, you can pop it into the independent variable box.
• For SPSS or similar software, you can use 1 for "Male" and 2 for "Female," just to give the computer a clear signal.

Age Group (Categorical Nominal Variable):

• Age groups like "18-25 years" or "> 30 years" are a bit different. They don't follow a natural order, so they're considered nominal categorical variables.
• You can also add age group as an independent variable, but here's the twist: since we've got more than two categories, you need to do something called "one-hot encoding."
• Imagine creating little boxes for each age group, like "18-25 years," "26-30 years," and so on. If a person falls into a particular age group, you put a 1 in that box, and 0s in all the others.

By doing this, you're making sure that your logistic regression considers the influence of both gender and age group on how people feel about accepting the technology. When you run your analysis, keep an eye on the coefficients for these variables to see how they're affecting the technology's acceptance.

Adding demographic variables can make your analysis richer, as it lets you explore how different groups within your data might have different attitudes toward the technology. It's like adding extra layers to your research!

Gabriel Angelo Lomibao Rubia thanks for your interests. i am appreciated for your response. best friend,

Mohammed Abdulaziz Abdulrasol Al-Romema You're very welcome, my Friend! Feel free to reach out anytime you need assistance in the future. I'd be delighted to collaborate with you on any research publications or journals as well. Thanks for considering it!