00:01
Which of these variables is not continuous? the height of nba players, time of a flight between atlanta and chicago, average temperature in orlando in july, or the number of heads you get when a fair coin is tossed 20 times.
00:17
Okay, so there are two main types of data we're looking at here.
00:21
Discrete and continuous.
00:28
Continuous data can take any value in an interval.
00:39
So, for example, the height of nba players can take any value.
00:45
We know it's not going to be zero or negative, but any positive value is possible.
00:53
Of course, some are more likely than others.
00:55
But if you were to take the interval of between about 1 .6 meters and 2 .2, you could have anything.
01:04
Whereas discrete have fixed values.
01:11
And as a result, with discrete data, you tend to count.
01:14
With continuous data, you tend to have to measure it.
01:21
So examples of continuous are height, because if you have somebody who is between 1 .6 and 1 .7 meters tall, they could fall anywhere in between that.
01:32
You can't say the probability of them being 1 .64 meters, because there are infinite possible values that their height could take.
01:42
Discrete would be d, but a number of obtained heads when you toss a fair coin.
01:48
Because you have to count that and you know there are only so many possibilities.
01:52
There will be zero or one or two or three up to 20.
01:58
There'll never be something between five and six.
02:02
Whereas with something like the time of a flight, there could be something between an hour and an hour and a second.
02:12
There's space in between that for an infinity of possibilities.
02:15
So that's continuous in nature.
02:22
That's the first question.
02:26
For the second question, frequency distributions are used to describe which of these types of data.
02:32
Nominal and ordinal, nominal and interval, nominal, ordinal and interval, nominal, ordinal, interval, and ratio.
02:41
So these are different data scales.
02:44
We have nominal, we have ordinal, interval, and ratio.
02:55
And as we go down this list, we have to add more rules to the data.
03:00
Nominal is typically for qualitative data.
03:03
You just have categories, you have no way of ranking them, no meaningful way of ranking them...