Research methods in phonetics
Before you can begin to explain patterns in your data, you need to a) collect the data and b) analyze it appropriately. Methods for doing both abound, and several of my collaborative projects involve comparing or developing ways of dealing with data at various stages of collection and analysis.
For example, Paul De Decker and I have examined how different audio compression formats affect vowel formant measurements. Our work has found that while some compression algorithms and commonly-available recording devices may be used (with caution!) to source data for sociophonetic studies, others significantly distort the vowel space in ways that render the data unreliable for acoustic analysis.
Paul and I have also explored how novel methods of analysis may be incorporated into sociophonetic research. One such project is the application of smoothing spline ANOVA to the comparison of vowel formants; this method enables the researcher to compare whole formant trajectories rather than simple point measurements, which do not reflect the dynamic nature of vowel acoustics.
Lauren Hall-Lew and I wrote a paper which compares different methods for quantifying vowel difference, to support our individual research projects in vowel merger and distinction as well as those of the wider sociophonetics community.
Right now I'm working with Shannon Mooney to develop a fun new task for examining phonetic convergence among pairs of speakers.
De Decker, Paul & Jennifer Nycz. 2013. The technology of conducting sociolinguistic interviews. In Mallinson, Christine, Becky Childs & Gerard van Herk (eds.), Data Collection in Sociolinguistics, pg. 118-126.
De Decker, Paul & Jennifer Nycz. 2011. For the Record: Which Digital Media Can be Used for Sociophonetic Analysis? University of Pennsylvania Working Papers in Linguistics 17:2, Article 7.