In this week’s episode Greg and Patrick take advantage of a recent expiration of a statute of limitations that legally allows them to talk about the multilevel model: what it is, when we might use it, and extremely cool extensions that it allows. Along the way they also discuss hostile federal judges, McNeish, airing of …
In today’s episode Greg and Patrick talk about that sweet spot between panel designs and time series designs, intensive longitudinal data, both the logistical and analytical challenges but more importantly its tremendous potential. Along the way they also discuss camp fire face-plants, fear of horses, your spare eyelid, polishing your Nobel Prize, ripples in a pond, …
S4E09 Intensive Longitudinal Data: Be Careful What You Wish For Read More »
In today’s episode, Greg and Patrick talk about the rich array of models for testing hypotheses about mutual influences between people within a dyadic relationship. Along the way they also discuss bones to pick, red herrings, bad influences, cow nutrition, playing both sides of the ball, Deion Sanders, the mind’s eye, it’s not me it’s …
Patrick and Greg talk about the potential advantages and disadvantages of alternative approaches to analyzing two time-point data. They discuss traditional models for raw and residualized change scores, and describe how each of these remains baked into the soul of contemporary models for repeated measures data. Along the way they also mention: 24 inch pizza …
Greg and Patrick talk about how, although textbooks almost exclusively talk about simple random samples, in practice they almost never actually occur. To try to sort this out, they enlist the help of Dr. Laura Stapleton from the University of Maryland, who lived a prior life as an economist and knows a thing or two …
S2E32: Lies, Damned Lies, and Random Samples with Laura Stapleton Read More »
Greg and Patrick explore the many interesting issues related to centering predictor variables prior to analysis, both in the standard regression model and in the multilevel model. Along the way they also discuss honking Diet Coke through your nose, rashes, hostage negotiation, reading at seven months of age, dealer’s choice, Coors Light, Galapagos tortoises, friendly …
S2E30: ‘Always Center Your Predictors!’ And Other Sh*t My Advisor Says Read More »
Patrick and Greg fulfill a legal obligation to interview the unnecessarily ubiquitous Dr. Dan McNeish of Arizona State University about why you probably don’t need to use multilevel modeling even when you have multilevel data. Along the way they also mention MacNair, safety schools, the Green Monster, driving a Corvette across the country, Compensation Club, …
S2E29: Multilevel Models — The Often Unnecessary Green Monster Read More »
In this episode Greg and Patrick attempt to resolve long festering relationship issues that arise between the multilevel modeling and structural equation modeling approaches to growth curve analysis. Along the way they also discuss first dates, Jets and Sharks, Cubs and Cardinals, Montagues and Capulets, Tsingtao Beer, Thunderdome, stupid LISREL tricks, pressure math, dirty secrets, …
Patrick and Greg talk about variability — both within individuals and within groups — as a source of really interesting and often overlooked research questions, to complement our well-developed skillset for studying means. Along the way, they also mention: Natatoriums, finding your spot, picking at a scab, the Polkaholics, Location Scale models, high-fiving statisticians, Inception, …
In this episode Greg and Patrick wander semi-drunkenly around the topic of model-based inference and discuss how this perspective can help move us forward as a scientific discipline. They also somehow manage to discuss explosives, sniffing glue, homemade 787s, catfish noodling, the Ikea helpline, Calvinball, Ludwig Beethoven, Rube Goldberg, hell’s half acre, denouements, and intolerable …
