Designers thrive when they have a working concept of what makes people tick, a context that allows them to shape their ideas by considering what people covet and use, and somewhere to focus all their creative energy. Research can provide the fuel for new ideas. To Ben's point, design research isn't a scientific endeavor aimed at finding truths. Our clients typically can't afford the large sample sets and extended time frames necessary for such a "scientific" process.
And sometimes design teams don't have the patience to see the value in dragging out a study in an effort to make it scientifically or statistically significant. We're just not wired that way; we prefer to make and experiment and then analyze later. So what is research good for?
1. Learning about people's behavior
Behavior is fertile ground for design. Not just human behavior, but systems behavior: social, technical, environmental, political, and economic systems.
2. Understanding and analyzing culture
...Culture is another important system when it comes to understanding design because it deals with the relationships we build between each other, our things, our routines, our view of the the world, and our beliefs.
3. Defining context
Context includes the physical and virtual settings that behavior occurs in and that culture shapes and emerges from. Identifying touch points—the decisive moments where a customer and a business intersect—is an important part of defining context.
4. Setting focus
Ill-defined problems, short project schedules, and a lack of patience are common conditions in design, and these can often lead to poor solutions. Doing research demands being comfortable with ambiguity in the early stages of a project in order to attain eventual clarity.
...Even the legendary Charles Eames expressed a similar sentiment when asked about the boundaries of design. He responded, "What are the boundaries of problems?"
Design research is not "a science" and is not necessarily "scientific." It gives designers and clients a much more nuanced understanding of the people for whom they design while providing knowledge that addresses some of the most fundamental questions we face throughout the process. What is the correct product or service to design? What characteristics should it have, and is it working as intended? "The research" won't necessarily provide cold hard answers. But it will generate some good and feasible ideas.
The above is taken from the longer full article The Art of Design Research (and Why It Matters). I think it's important to consider particularly while having the sentiment expressed by Faris in mind, in a piece called All Market Research Is Wrong. If you're interested in research both the above piece and Faris's thoughts are worth reading in full, because they both express the sentiment that research is of course valuable, but in a way that we often overlook.
The phrase is "research is often used like a drunk uses a lamppost - not for illumination but for support." The idea at hand here requires a bit of long-term thinking - research that matters isn't the means to an end, rather it's a way to frame the beginning (#4 above).
Hence, the research that is important is often what takes place before and after you're actively researching. The first is something more like observation and filtering; the latter we call prototyping and iteration.
