Simon Blanchard
@blasimon.bsky.social
Professor of marketing at Georgetown university. Teaches research design and analytics. Interested in marketing research methods, fintech, and the Canadiens.
Thanks! Would love for you to try it out. It does require a bit of time to setup, but we think it’s not overly tedious.
May 29, 2025 at 2:37 PM
Thanks! Would love for you to try it out. It does require a bit of time to setup, but we think it’s not overly tedious.
Aaron Garvey and I would love to get feedback on toolkit or the paper
Garvey, Aaron G. and Simon J. Blanchard (2025). Generative AI as a Research Confederate: The LUCID Methodological Framework and Toolkit for Controlled Human-AI Interactions in Survey Research. papers.ssrn.com/sol3/papers....
Garvey, Aaron G. and Simon J. Blanchard (2025). Generative AI as a Research Confederate: The LUCID Methodological Framework and Toolkit for Controlled Human-AI Interactions in Survey Research. papers.ssrn.com/sol3/papers....
Generative AI as a Research Confederate: The LUCID Methodological Framework and Toolkit for Human-AI Interactions Research
As consumer interactions with Generative AI (GenAI) agents-such as ChatGPT-become increasingly common, marketing researchers face new methodological challenges
papers.ssrn.com
May 29, 2025 at 2:27 PM
Aaron Garvey and I would love to get feedback on toolkit or the paper
Garvey, Aaron G. and Simon J. Blanchard (2025). Generative AI as a Research Confederate: The LUCID Methodological Framework and Toolkit for Controlled Human-AI Interactions in Survey Research. papers.ssrn.com/sol3/papers....
Garvey, Aaron G. and Simon J. Blanchard (2025). Generative AI as a Research Confederate: The LUCID Methodological Framework and Toolkit for Controlled Human-AI Interactions in Survey Research. papers.ssrn.com/sol3/papers....
Step 3: Adapt to your use case
Once the backend is live and you’ve picked a template, you can:
• Edit the prompt wording
• Change when/where GPT is used in the survey flow
There’s a walkthrough in the guide on how these parts connect.
lucidresearch.io/Step3-Custom...
Once the backend is live and you’ve picked a template, you can:
• Edit the prompt wording
• Change when/where GPT is used in the survey flow
There’s a walkthrough in the guide on how these parts connect.
lucidresearch.io/Step3-Custom...
May 29, 2025 at 2:27 PM
Step 3: Adapt to your use case
Once the backend is live and you’ve picked a template, you can:
• Edit the prompt wording
• Change when/where GPT is used in the survey flow
There’s a walkthrough in the guide on how these parts connect.
lucidresearch.io/Step3-Custom...
Once the backend is live and you’ve picked a template, you can:
• Edit the prompt wording
• Change when/where GPT is used in the survey flow
There’s a walkthrough in the guide on how these parts connect.
lucidresearch.io/Step3-Custom...
Step 2: Choose a Qualtrics template
We’ve shared a few .QSF templates that show different ways GPT can be embedded into surveys:
• Simple conversational flow
• Between-subject manipulations
The goal is to give working examples that you can modify.
lucidresearch.io/Step2-Select...
We’ve shared a few .QSF templates that show different ways GPT can be embedded into surveys:
• Simple conversational flow
• Between-subject manipulations
The goal is to give working examples that you can modify.
lucidresearch.io/Step2-Select...
QSF Templates — LUCID
lucidresearch.io
May 29, 2025 at 2:27 PM
Step 2: Choose a Qualtrics template
We’ve shared a few .QSF templates that show different ways GPT can be embedded into surveys:
• Simple conversational flow
• Between-subject manipulations
The goal is to give working examples that you can modify.
lucidresearch.io/Step2-Select...
We’ve shared a few .QSF templates that show different ways GPT can be embedded into surveys:
• Simple conversational flow
• Between-subject manipulations
The goal is to give working examples that you can modify.
lucidresearch.io/Step2-Select...
Step 1: Deploy a backend to handle GPT
To keep OpenAI keys secure, we suggest deploying a small server (e.g. free on Vercel). This way, the GPT call happens outside of Qualtrics, and the key stays hidden.
We provide the code. No coding experience needed.
github.com/amgarv/LUCID...
To keep OpenAI keys secure, we suggest deploying a small server (e.g. free on Vercel). This way, the GPT call happens outside of Qualtrics, and the key stays hidden.
We provide the code. No coding experience needed.
github.com/amgarv/LUCID...
GitHub - amgarv/LUCID_TOOL_BACKEND
Contribute to amgarv/LUCID_TOOL_BACKEND development by creating an account on GitHub.
github.com
May 29, 2025 at 2:27 PM
Step 1: Deploy a backend to handle GPT
To keep OpenAI keys secure, we suggest deploying a small server (e.g. free on Vercel). This way, the GPT call happens outside of Qualtrics, and the key stays hidden.
We provide the code. No coding experience needed.
github.com/amgarv/LUCID...
To keep OpenAI keys secure, we suggest deploying a small server (e.g. free on Vercel). This way, the GPT call happens outside of Qualtrics, and the key stays hidden.
We provide the code. No coding experience needed.
github.com/amgarv/LUCID...
Define criticize? And in what format?
April 2, 2025 at 2:59 PM
Define criticize? And in what format?
Totally fair. I wrote too quickly.
The example used here was about the effect of income on education. But I have the same struggle: I don’t know how easy it’d be to convince myself and the reviewers that latent IV is appropriate.
link.springer.com/journal/11129
The example used here was about the effect of income on education. But I have the same struggle: I don’t know how easy it’d be to convince myself and the reviewers that latent IV is appropriate.
link.springer.com/journal/11129
Quantitative Marketing and Economics
Quantitative Marketing and Economics is a research journal focused on the intersection of marketing, economics, and statistics with an applied, quantitative ...
link.springer.com
February 19, 2025 at 8:55 PM
Totally fair. I wrote too quickly.
The example used here was about the effect of income on education. But I have the same struggle: I don’t know how easy it’d be to convince myself and the reviewers that latent IV is appropriate.
link.springer.com/journal/11129
The example used here was about the effect of income on education. But I have the same struggle: I don’t know how easy it’d be to convince myself and the reviewers that latent IV is appropriate.
link.springer.com/journal/11129
I’m wondering if we’re going to see some sort of reverse snowbirds effect: Canadian academics in the US seeking to reaffiliate with Canadian institutions/centers and attend Canadian conference more.
February 19, 2025 at 6:48 PM
I’m wondering if we’re going to see some sort of reverse snowbirds effect: Canadian academics in the US seeking to reaffiliate with Canadian institutions/centers and attend Canadian conference more.
Very nice table. It’s particularly striking to me that despite having fewer assumptions, my perception is that latent IVs still see so much less use. Do you discuss that in the chapter?
February 19, 2025 at 6:40 PM
Very nice table. It’s particularly striking to me that despite having fewer assumptions, my perception is that latent IVs still see so much less use. Do you discuss that in the chapter?
Have they appealed?
February 4, 2025 at 3:57 PM
Have they appealed?
If anyone really wants know, for my guesstimate of HSA annualized rate, I used data from Investopedia for 2022 onward. For 2017-2021, I extrapolated based on historical trends, accounting for the low-rate environment during that period. www.investopedia.com/best-high-yi...
Best High-Yield Savings Accounts for February 2025: Up to 4.75%
Compare the best high-yield savings account rates with our ranking of over 100 national banks and credit unions. Today's top savings rate is 4.75% APY, available from three banks.
www.investopedia.com
February 1, 2025 at 2:25 AM
If anyone really wants know, for my guesstimate of HSA annualized rate, I used data from Investopedia for 2022 onward. For 2017-2021, I extrapolated based on historical trends, accounting for the low-rate environment during that period. www.investopedia.com/best-high-yi...
I had to look this up! The price went from $0.49 in 2017 to $0.73 today - a 48% (~5% annual return).
For comparison, high-yield savings accounts over the same period returned about 2.3% annually. But, if that $0.49 had been in the S&P 500, it be $1.56 (15%). Still, not bad for stamps!
For comparison, high-yield savings accounts over the same period returned about 2.3% annually. But, if that $0.49 had been in the S&P 500, it be $1.56 (15%). Still, not bad for stamps!
February 1, 2025 at 2:21 AM
I had to look this up! The price went from $0.49 in 2017 to $0.73 today - a 48% (~5% annual return).
For comparison, high-yield savings accounts over the same period returned about 2.3% annually. But, if that $0.49 had been in the S&P 500, it be $1.56 (15%). Still, not bad for stamps!
For comparison, high-yield savings accounts over the same period returned about 2.3% annually. But, if that $0.49 had been in the S&P 500, it be $1.56 (15%). Still, not bad for stamps!
Those would have been great schools for me!
February 1, 2025 at 1:57 AM
Those would have been great schools for me!
What slowed adoption with first generation audio/video assistants is that they were largely ruled base and often "single turn" (i.e., no memory). It's now much easier to develop realtime voice chat agents that keep sessions in the context (e.g., platform.openai.com/docs/guides/...).
January 31, 2025 at 2:09 PM
What slowed adoption with first generation audio/video assistants is that they were largely ruled base and often "single turn" (i.e., no memory). It's now much easier to develop realtime voice chat agents that keep sessions in the context (e.g., platform.openai.com/docs/guides/...).
Sure, the LLM might be wrong, or perhaps it’s just demonstrating a bit of premonitory hallucination—seeing the Florida professor within before he does! ;)
January 31, 2025 at 1:59 PM
Sure, the LLM might be wrong, or perhaps it’s just demonstrating a bit of premonitory hallucination—seeing the Florida professor within before he does! ;)
Which deepseek were you running? Local or online? I’ve run ollama 70b locally, so I might try deepseek r1 70. I wouldn’t submit working or published papers to their GUI unless the paper is also on SSRN
January 24, 2025 at 8:17 PM
Which deepseek were you running? Local or online? I’ve run ollama 70b locally, so I might try deepseek r1 70. I wouldn’t submit working or published papers to their GUI unless the paper is also on SSRN
If you ran OLS on 0/1 and SPSS provided you estimates, would you be upset it didn’t stop you to say you should run a logistic regression?
Different models have different uses. o1 is complex reasoning. OA offers help & globe icon (enables search) is even disabled in o1. Seems like enough to me.
Different models have different uses. o1 is complex reasoning. OA offers help & globe icon (enables search) is even disabled in o1. Seems like enough to me.
January 23, 2025 at 5:17 PM
If you ran OLS on 0/1 and SPSS provided you estimates, would you be upset it didn’t stop you to say you should run a logistic regression?
Different models have different uses. o1 is complex reasoning. OA offers help & globe icon (enables search) is even disabled in o1. Seems like enough to me.
Different models have different uses. o1 is complex reasoning. OA offers help & globe icon (enables search) is even disabled in o1. Seems like enough to me.
o1 doesn’t have access to web search. Try 4o. help.openai.com/en/articles/...
What is the ChatGPT model selector? | OpenAI Help Center
Switch between different models in ChatGPT depending on your plan and your needs
help.openai.com
January 23, 2025 at 4:01 PM
o1 doesn’t have access to web search. Try 4o. help.openai.com/en/articles/...
Then we’ll see you on Red Note / the little red book? 😅
January 21, 2025 at 1:02 PM
Then we’ll see you on Red Note / the little red book? 😅
What a great game you chose to go to!
January 20, 2025 at 10:59 PM
What a great game you chose to go to!
Valid point! But it’s not just about the lack of shrinkage. It also requires well-balanced data between subjects, which is rare unless N is large. Plus, it risks a loss of power by discarding within-subject variability that multilevel models can leverage.
January 11, 2025 at 2:47 PM
Valid point! But it’s not just about the lack of shrinkage. It also requires well-balanced data between subjects, which is rare unless N is large. Plus, it risks a loss of power by discarding within-subject variability that multilevel models can leverage.