Showing Revision 4 created 06/27/2017 by Dejan Trajkovic.

1. Title:
   SD Social Networkers - Intro to Descriptive Statistics
2. Description:

3. 12 0:00 - 0:04
   >> I'm going to show you the answer to this, by doing it in a spreadsheet. You
4. 4197 0:04 - 0:09
   could do all of these calculations, without any technology. And if you did that,
5. 8949 0:09 - 0:13
   that's really great. It's always really good practice to calculate things
6. 13362 0:13 - 0:18
   without using any technology, but just for the purposes of figuring out the
7. 17709 0:18 - 0:23
   standard deviation, technology can really speed along this process. So I'm not
8. 22873 0:23 - 0:30
   going to use any shortcuts here. We're going to do it exactly as we would if we
9. 29985 0:30 - 0:39
   didn't have technology. So first we need to take the avearage of all of these,
10. 38639 0:39 - 0:47
    we're going to sum them up. So we're taking the sume of all of these. I could
11. 47458 0:47 - 0:55
    also just write equals a1 plus a2 plus a3 all the way to a10. And we'd get the
12. 55191 0:55 - 1:03
    same thing. But why would we do that if we can simply write this. Now to take
13. 62922 1:03 - 1:11
    the average all we do is divide by the number of values which is 10. So that's
14. 70884 1:11 - 1:19
    just going to be 51,511.1. Alternatively, the nice thing about technology is we
15. 78654 1:19 - 1:27
    can just do this. Take the sum, and divide by the total number. Do it all in 1
16. 87070 1:27 - 1:35
    step. So now we have the average. Now we're going to subtract the average from
17. 94563 1:35 - 1:41
    each 1 of these values. Not the opposite, where we subtract each of these values
18. 100776 1:41 - 1:46
    from the mean. That's an important distinction. In this case, it doesn't matter
19. 106216 1:46 - 1:51
    as much but in other statistical concepts that's an important distinction to
20. 111481 1:51 - 1:58
    make. So we'll write equals A1 minus. The mean. So I'm subtracting the mean from
21. 118227 1:58 - 2:06
    each of these values. Now I could just do the same thing here and write equals
22. 125630 2:06 - 2:13
    a2 minus the mean but that would be tedious. We can just drag this down. When
23. 133044 2:13 - 2:20
    you do that, remember that there has to be a little plus sign there. That means
24. 139621 2:20 - 2:26
    you're successfully dragging it down. If you went like this, it won't do
25. 145734 2:26 - 2:32
    anything. It'll just highlight the boxes. So here, we have the deviations from
26. 152486 2:32 - 2:39
    the mean. Here, in the next column We're going to square each deviation. Equals
27. 159383 2:39 - 2:45
    b1 squared. And again, we're going to drag it down. So we have the squared
28. 165394 2:45 - 2:52
    deviations for each of these values. Now remember that the variance is the
29. 171742 2:52 - 2:59
    average squared deviation. So we could just write. Average of c1 to c10. But I
30. 178709 2:59 - 3:06
    want to make sure we go through all the other steps in between. So let's again
31. 185996 3:06 - 3:14
    practice calculating the average just for clarity's sake. So the variants then
32. 193670 3:14 - 3:20
    would be the sum of c1 to c10. Remember that's how you start out taking the
33. 199829 3:20 - 3:26
    average, and then divide by 10. So here's the variance, and then the standard
34. 205637 3:26 - 3:32
    deviation is simply the square root of the variance. So we'll write equals SQRT.
35. 211794 3:32 - 3:38
    That's the shortcut for square root. And then we can just see C13. So we know
36. 217695 3:38 - 3:44
    that the standard deviation is 6557.16 approximately. Now I want to point out
37. 223730 3:44 - 3:50
    something really important before we finish this solution video. Here I simply
38. 229998 3:50 - 3:57
    said equals square root of this cell C13. Whereas here, I wrote out the
39. 236953 3:57 - 4:05
    whole average. The reason for that is because say I had but this all here, A13.
40. 245325 4:05 - 4:13
    Then, when we drag it down, we don't get the right deviations. And we can double
41. 252849 4:13 - 4:19
    click on it, and see what it did. Here, it took A4 minus A16, whereas here it
42. 259432 4:19 - 4:26
    took A1 minus A13, which is what we wanted. But we want it to always stay A13,
43. 266126 4:26 - 4:33
    which is why we have to make sure this is a constant. And the way to make sure
44. 272564 4:33 - 4:39
    it's a constant is by just writing it. Notice also that all of these values
45. 278507 4:39 - 4:44
    changed when these values changed because all these values are dependent of
46. 284267 4:44 - 4:51
    these values So when we change it back we should again get the correct standard
47. 290507 4:51 - 4:52
    deviation.