 I think we'll start this out with the demo. We've got a Hilbert chain, as you're going to have eight passes. I'm going to drive a bit loud! You grab by the function fuller. We might be wrong. We're funny, but not always a joke. We're going to have to... So we're going to talk about replication today, because I've got replication on my mind. Alright, I don't know why, but I'm going to demonstrate some replication issues for you. Ba-doop, ba-doop, ba-doop, ba-doop. How well did I do? Was I pretty close to hit the same spots each time? I don't know, let's try it again. Ba-doop, ba-doop. Ba-doop, ba-doop. I'm not too far off, I can feel it on my feet, because it's squishy. Anyway, so that was like, you're going, why and what did you do it again? Ba-doop, ba-doop. Because I'm getting you to attend a salient stimulus. Ba-doop, ba-doop. And you will always remember, ba-doop, replication, replication by this video. Alright, so we have four different types of replication. We have intra-subject replication, which is what I've been demonstrating to you all day, or all videos so far. Intra-subject replication is putting forth the, or doing the experiment, or running the condition again with the same subject. Inter-subject replication would be if someone else was doing this. So this is someone else, because I don't have another actor up here with me. So there you go. And they had the same effect, right? So the intervention has the same effect, or it has an effect on different individuals. Inter-subject replication. So when we're doing single-subject logic, we get really cool things. We get lots of stuff, alright? We get, wow, I get excited. We get so much stuff, alright? Let's just do a little a-b-a design. So a-b-a, alright? Three conditions for our phase changes. So we have our phase changes in here. We get our a's, which is our baseline. And then we're going to do our intervention. And then we're going to go back to baseline. We're going to do five subjects. If I said three already alive, we're doing five. Alright, so we're going to study five subjects. And so we're going to do our baseline logic. Actually, let's do a full reversal. So a-b-a-b, alright? Makes the point a little easier. Inter-subject baseline for this person number one. So baseline, intervention phase, baseline. Back to intervention phase, alright? So the fact that they were the same spot during intervention one and intervention two demonstrates intra-subject replication. The fact that these patterns existed for all five people, roughly the same, we have inter-subject replication, which speaks to our external validity, which is what I've talked about in some other videos and why this is such a powerful tool. So those are the two types of replication inside of the experiment. So let's take it out a little bit bigger, alright? So Sidman also talks about systematic replication and direct replication. So for quality experimentation, we're going to need direct replication, alright? So that's the key to all science, it's the key to everything. We build replication into our experiments themselves, but we also need to replicate the broad experiments, alright? So sometimes what we do is just replicate everything. Identical! Run the experiment again. Completely over again, different lab, different subjects, different people. That's, you could argue that might be systematic, but I'm going to pretend that it's direct, alright? The most direct experiment would be the same subjects run again on a different day by the same experiment or in the same lab under just a different day. Just run the experiment over again so you can get the same effects, alright? That's the most strict definition of direct replication. So systematic replication is where we want to know, does the independent variable have an effect under slightly different conditions? With maybe slightly different people? Maybe with adults instead of with kids? Maybe with dogs instead of with rats? Or maybe with dogs instead of with humans? Or maybe with humans instead of with rats? I don't know, it's all pigeons and all. They're all the same. Behavior is behavior. Alright, so systematic replication. Let me give you an example, alright? So direct instruction is a great tool that you can use to teach kids how to read. It's an excellent intervention. So we have established that. We have done all sorts of replication experiments. There's something systematically different about it. Now that we've been doing this in the lab, let's see if we can do it in the classroom. Hmm, interesting, huh? Systematic replication. So we're doing the same experiment. We're just changing the context a bit to allow for more independent or more extraneous variables to come in and see if we still have that same effect that we got in the lab, alright? So if we do, then we know our intervention is pretty powerful, right? It's got strength, it's got power, alright? And I'll be darned. Direct instruction works for systematic replication. Instead of teaching kids to read, let's teach kids some math skills using direct instruction. So we're systematically changing one thing at a time about that experiment and we're replicating the experiment where changing one small thing about to see where that limit of that experiment is. How much can you teach using direct instruction and if we study that entire field, that DI field, if we completely study the whole thing and do all the possible systematic replications we can, now we know the limitations of direct instruction. That's the key. So there's our four types of instruction or replication. We have direct replication, running the experiment over again. Systematic replication, we could do things with different subjects, we could slightly different variation on the procedure, maybe not quite as intense, maybe a little bit less, knock off a couple of extra lessons here and there to see if you still get the learning out of it. Okay, so systematic replication, we're making some change to see what the limit of that independent variable is. We have intra-subject, which is what you see in the reversal designs where you have the A, B, A, B, the same individual changing repeatedly under the same conditions and showing the same effects. Then you have inter-subject, which is doing the comparisons that you see across the subjects in a particular experiment. All of this is part of the single subject logic and is what makes our field so darn awesomely sciencey. And that's an official thing now, we're sciencey. We're not soft science, we're hard sciencey. So there you go, hard sciencey people, that's us. If you like our videos and you have yet to figure out how we've organized them maybe you should go look at the playlist. It's kind of cool. They cover pretty much everything. In fact, we've got really probably a lot, maybe even too many playlists, but it's there for your organizational purposes. Use it, please.