Methodology Podcasts

There are multiple papers that question the ethics of doing non-inferiority trials, because it’s probably going to end up with treatments being recommended from patients that are inferior to other treatments. And that’s where the controversies come out. The reason a lot of people liked them is that, you can get significant results with very small sample sizes. All I have to do to set it basic way down and set that criterion and way down there, and everything is going to come out significant. 

Three types of trials are conducted to compare a new treatment to the standard treatment:

• superiority trials seek to understand which is superior , the new treatment of the standard treatment
• non-inferiority trials seek prove that the new treatment is not inferior to standard treatment
• equivalence trials seek to explore if the new and the standard treatments are equivalent.

To learn more from Dr. Helena Kraemer listen to the podcast episode below.

Part 1

Part 2

Click here for more Research Methodology Podcasts

The survival curve, which is the basic tool of what essentially we’re going to get to in the Cox proportional hazards model, is a graph of the percentage of people who survive longer than each period of time. So it starts at 100% at the time you start this thing everybody is surviving. And then it’s the probability of surviving more than one day, one week, one month, one year, two years, three years, five years, ten years, et cetera.

In randomized clinical trials, for example, we’re comparing a treatment versus some sort of control or comparison. Time to remission is a great outcome measure. Or time to recovery, if there is such a thing as recovery in many of these illnesses, is a wonderful outcome measure, specifically because it is so important to the patients. You know we could talk about reduction of symptoms, we could talk about a lot of other outcome measures. But what the patient is really interested in is, “Am I going to get well?”

To learn more from Dr. Helena Kraemer listen to the podcast episode below.

Click here for more Research Methodology Podcasts

Linear models were the only things that were used for a very long period. But as it’s true of all statistical analysis, if you make assumptions that are not true, your conclusions aren’t going to be true. When you use a linear model in a moderate or mediator analysis, what it means is that for every value of the target, whether it’s a treatment or a risk factor, whatever, that the relationship between the outcome and the moderator, mediator is linear. Similarly, for every value of the moderator and mediator, if there are more than two targets, that’s also linear.

The moderators try to tear apart the population into subgroups where the response to treatment for example, or the effects are much the same. So it’s a process of dissecting the population. The mediators are dissecting the treatment. What components of the treatments seem to be the ones that account for the differences here? If we could do that, we could improve the treatment. So there are two different ways of dissection. But the proving of the causality is a new study in which you are randomly manipulating whatever causal factor you’re hypothesizing.

To learn more from Dr. Helena Kraemer listen to the podcast episode below.

Part 1

Part 2

Click here for more Research Methodology Podcasts

Last’s Dictionary of Epidemiology says that a covariate is a variable that is possibly predictive of the outcome under study. Even that is somewhat wrong because the word predictive means that the covariate has to occur in time before the outcome that is predicted, but covariates are frequently used when the covariate follows the outcome, when it’s coincident with the outcome as well as when it proceeds the outcome.

To learn more from Dr. Helena Kraemer listen to the podcast episode below.

Click here for more Research Methodology Podcasts

Every rule, that governs a randomized clinical trial originally came from some study that had a disastrous outcome. Somebody made a mistake and the results did not replicate or they turned out to be wrong and then some methodologist took a look at why this happened and thought about, well what can we do in the future to prevent this ever happening again? And all of these rules are based on real experiences with research and data and they are all meant to prevent consequences that they know about.

To learn more from Dr. Helena Kraemer listen to the podcast episode below.

Part 1

Part 2

Click here for more Research Methodology Podcasts