Just a screen cap of me recreating the effect. I don't talk, so if you see new items show up on the timeline, it's me hitting CTRL-D and duplicating the selected item. Also, I sped up some areas where it's repetitive.
If you have specific questions, feel free to shoot me a message.
Used After Effects. The sound is a little low for the talking, but it's not really that important anyways. He just says "get me a drink" and then "that's not mine."
Video from the tutorial. I added the run effect on my son, too, which the tutorial doesn't show (sorry--limited to 10 minutes.)
You Tube's converter threw the audio synch off a bit. I'll have to try to re-encode with a diff codec and re-upload.