Synthetic Data and Significance Tests: Why t-tests are Inappropriate and What to Do Instead
You should not use standard t-test testing with synthetically boosted data. In this post I explain why and list three alternatives.
You should not use standard t-test testing with synthetically boosted data. In this post I explain why and list three alternatives.
Are you using Notebook LM yet? If not, I think you should be using it; it is frankly quite mind-blowing. To illustrate the power of Notebook LM I took the YouTube link for my presentation “How should you plan for AI and its impact on you?” from the April NewMR AI Webinar and uploaded it to Notebook LM.
Earlier this week, I discussed the use of Digital Twins in research; you can read that post here. Today, I am sharing a concept piece that illustrates one approach to Digital Twins, using ChatGPT.
Over the last year, there has been a growing interest in Digital Twins, which are virtual participants based on real individuals. In this note, I will outline what is happening, why it is happening, and share some key concerns that need to be considered.
Currently, I am spending four weeks in Japan, a mix of work, including workshops and presentations, and leisure activities (such as hiking and running). Today I checked into an AirBNB in central Tokyo and washed some clothes, after spending the weekend running a marathon on the West coast of Japan. The apartment is tiny, so I hung the clothes in the combined bedroom and living room. I have some standard photos I use to demonstrate using ChatGPT for qual, but I thought I would add a new one, so I took the photo below and asked ChatGPT to analyse it.
Last week, I had the honour to be invited to attend the QRCA International Qualitative Conference in Berlin on behalf of ESOMAR. It was a fantastic event with leading-edge, innovative, and sometimes challenging presentations from North America, Africa, India and Europe. I also had the honour of being allowed to share my thoughts on The Future of Qual. I will share my message in this note and add a bonus insight I could not squeeze into my presentation.
One key variable that differentiates one large-language model (LLM) from another is the size of its context window. In this post, I explain what a context window is and why it matters.
I think Deep Research is likely to replace quite a few types of research, some of them in the market research area. To investigate more, I tried two simple experiments. The first was to forecast the results of the recent Canadian Federal Elections and the second was to forecast what the closing share price for Tesla would be in two weeks from the forecast. Both forecasts turned out to be interesting, as I will show below.
On the evening of 28 April, I requested that Deep Research forecast Tesla’s share price for 12 May and provide me with its reasoning.
It has forecast $300 (compared to the current price of $285.88), in the post I show you its full report.
Here is a post that shows how you can use custom GPTs to create better deliverables for your clients. Let them leverage the power of LLMs to bring your work to life.
By continuing to use the site, you agree to the use of cookies. more information
The cookie settings on this website are set to "allow cookies" to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click "Accept" below then you are consenting to this.