« What popular baby names teach us about data analytics | Main | More on the AA paper »


Feed You can follow this conversation by subscribing to the comment feed for this post.


My guess is that psychologists are having problems with things that people working with medical data have been aware of for a long time. Essentially ITT is correct because it reflects what happens to real patients. They get given a treatment and then there is some eventual outcome. They may switch treatments or whatever, but what matters is the initial choice of treatment. If we want to look at situations where we compare different alternative pathways through the various treatments, then we can define them as possible groups to be allocated to.

Where PP and other analyses may be useful is when we are interested in mechanisms and to see what may happen under different scenarios. We can try and estimate what will happen if we reduce dropouts, but that may not have a lot of relevance to the real world.

The comments to this entry are closed.


Link to Principal Analytics Prep

See our curriculum, instructors. Apply.
Kaiser Fung. Business analytics and data visualization expert. Author and Speaker.
Visit my website. Follow my Twitter. See my articles at Daily Beast, 538, HBR.

See my Youtube and Flickr.

Next Events

Jun: 5 NYPL Public Lecture on Analytics Careers, New York, NY

Past Events

Apr: 2 Data Visualization Seminar, Pasadena, CA

Mar: 30 ASA DataFest, New York, NY

See more here


Numbersense: Statistical Reasoning in Practice, Principal Analytics Prep

Applied Analytics Frameworks & Methods, Columbia

The Art of Data Visualization, NYU

Junk Charts Blog

Link to junkcharts

Graphics design by Amanda Lee


  • only in Big Data