All language subtitles for 06 - Calculate correlation among multiple pairs of columns

af Afrikaans
sq Albanian
am Amharic
ar Arabic Download
hy Armenian
az Azerbaijani
eu Basque
be Belarusian
bn Bengali
bs Bosnian
bg Bulgarian
ca Catalan
ceb Cebuano
ny Chichewa
zh-CN Chinese (Simplified)
zh-TW Chinese (Traditional)
co Corsican
hr Croatian
cs Czech
da Danish
nl Dutch
en English
eo Esperanto
et Estonian
tl Filipino
fi Finnish
fr French
fy Frisian
gl Galician
ka Georgian
de German
el Greek
gu Gujarati
ht Haitian Creole
ha Hausa
haw Hawaiian
iw Hebrew
hi Hindi
hmn Hmong
hu Hungarian
is Icelandic
ig Igbo
id Indonesian
ga Irish
it Italian
ja Japanese
jw Javanese
kn Kannada
kk Kazakh
km Khmer
ko Korean
ku Kurdish (Kurmanji)
ky Kyrgyz
lo Lao
la Latin
lv Latvian
lt Lithuanian
lb Luxembourgish
mk Macedonian
mg Malagasy
ms Malay
ml Malayalam
mt Maltese
mi Maori
mr Marathi
mn Mongolian
my Myanmar (Burmese)
ne Nepali
no Norwegian
ps Pashto
fa Persian
pl Polish
pt Portuguese
pa Punjabi
ro Romanian
ru Russian
sm Samoan
gd Scots Gaelic
sr Serbian
st Sesotho
sn Shona
sd Sindhi
si Sinhala
sk Slovak
sl Slovenian
so Somali
es Spanish
su Sundanese
sw Swahili
sv Swedish
tg Tajik
ta Tamil
te Telugu
th Thai
tr Turkish
uk Ukrainian
ur Urdu
uz Uzbek
vi Vietnamese
cy Welsh
xh Xhosa
yi Yiddish
yo Yoruba
zu Zulu
or Odia (Oriya)
rw Kinyarwanda
tk Turkmen
tt Tatar
ug Uyghur
Would you like to inspect the original subtitles? These are the user uploaded subtitles that are being translated: 1 00:00:00,005 --> 00:00:02,005 - [Instructor] In the previous movie, I showed you how 2 00:00:02,005 --> 00:00:05,005 to create a formula to calculate correlation 3 00:00:05,005 --> 00:00:07,006 between two sets of data. 4 00:00:07,006 --> 00:00:10,001 In this movie, I'd like to show you a quick way to set 5 00:00:10,001 --> 00:00:12,006 up a grid so you can analyze the correlation 6 00:00:12,006 --> 00:00:15,002 between multiple columns of data. 7 00:00:15,002 --> 00:00:18,008 My sample file is 05 06 Multiple Correlation, 8 00:00:18,008 --> 00:00:21,002 and you can find it in the chapter five folder 9 00:00:21,002 --> 00:00:24,000 of the exercise files collection. 10 00:00:24,000 --> 00:00:26,007 And as you can see on the left, starting in column A, 11 00:00:26,007 --> 00:00:28,007 I have four sets of data. 12 00:00:28,007 --> 00:00:33,002 Each of them contains 10 rows or 10 values. 13 00:00:33,002 --> 00:00:35,009 And then over on the right, starting with labels 14 00:00:35,009 --> 00:00:39,000 in column F, I have a grid setup so 15 00:00:39,000 --> 00:00:40,008 that we can examine the correlation 16 00:00:40,008 --> 00:00:43,000 between pairs of columns. 17 00:00:43,000 --> 00:00:46,003 You are always performing your correlation analysis 18 00:00:46,003 --> 00:00:49,002 between one set of values and another. 19 00:00:49,002 --> 00:00:53,009 So, let's start by creating a formula that we can copy 20 00:00:53,009 --> 00:00:58,005 to other cells and will let us set up the grid efficiently. 21 00:00:58,005 --> 00:01:00,002 I'll start in cell G6. 22 00:01:00,002 --> 00:01:02,007 So, I'll type an equal sign, 23 00:01:02,007 --> 00:01:06,000 and I want to find the correlation. 24 00:01:06,000 --> 00:01:10,008 So, that's the C-O-R-R-E-L, or correl, function, 25 00:01:10,008 --> 00:01:12,006 and I'll press Tab. 26 00:01:12,006 --> 00:01:16,000 And our first array will be in column A, 27 00:01:16,000 --> 00:01:19,009 so I'll select A3 through A12, 28 00:01:19,009 --> 00:01:24,006 and I want to make these references absolute or unchanging. 29 00:01:24,006 --> 00:01:27,008 So, I'll click in the middle of A3, press F4, 30 00:01:27,008 --> 00:01:28,008 that's on Windows. 31 00:01:28,008 --> 00:01:31,008 On the Mac, you would press Command + T, 32 00:01:31,008 --> 00:01:34,001 and I'll do the same thing for A12. 33 00:01:34,001 --> 00:01:38,007 So, I'll press F4, and then I'll click to the right 34 00:01:38,007 --> 00:01:41,007 of a cell reference, type a comma, 35 00:01:41,007 --> 00:01:45,007 and now I want to repeat A3 to A12, 36 00:01:45,007 --> 00:01:49,002 but make it a relative, or changing, reference. 37 00:01:49,002 --> 00:01:54,003 So, A3 colon A12 right parenthesis, and enter, 38 00:01:54,003 --> 00:01:56,002 and I get a correlation of one, 39 00:01:56,002 --> 00:01:58,004 and that is exactly what I want. 40 00:01:58,004 --> 00:02:01,006 I am correlating a column with itself. 41 00:02:01,006 --> 00:02:05,007 So, of course, the values move exactly as one would expect. 42 00:02:05,007 --> 00:02:07,009 So, the correlation is one. 43 00:02:07,009 --> 00:02:11,002 If you get a different value, you did something wrong. 44 00:02:11,002 --> 00:02:14,005 Now, I want to create another version of that formula 45 00:02:14,005 --> 00:02:16,002 for column B. 46 00:02:16,002 --> 00:02:21,005 So in G7, I'll type an equal sign, correlation, 47 00:02:21,005 --> 00:02:27,003 and it'll be B3 to B12. 48 00:02:27,003 --> 00:02:30,009 And again, I want to make the references absolute. 49 00:02:30,009 --> 00:02:32,009 F4, not four. 50 00:02:32,009 --> 00:02:34,005 There we go. 51 00:02:34,005 --> 00:02:37,007 Then a comma and A3 52 00:02:37,007 --> 00:02:40,000 through A12 because we're comparing column two 53 00:02:40,000 --> 00:02:41,001 to column one. 54 00:02:41,001 --> 00:02:45,002 So, A3 to A12, and again, we want to make this changing. 55 00:02:45,002 --> 00:02:47,004 Right parenthesis, and enter, 56 00:02:47,004 --> 00:02:50,004 and we have a small negative correlation. 57 00:02:50,004 --> 00:02:59,004 Same in G8, so, equal correlation C3 to C12, 58 00:02:59,004 --> 00:03:05,000 make those references absolute. 59 00:03:05,000 --> 00:03:11,005 Then comma and A3 to A12, and enter. 60 00:03:11,005 --> 00:03:17,004 And last one, equal correlation, I'm working in cell G9. 61 00:03:17,004 --> 00:03:25,004 That will be D3 absolute to D12 absolute, pressing F4, 62 00:03:25,004 --> 00:03:29,008 comma A3 to A12, and enter. 63 00:03:29,008 --> 00:03:30,008 Great. 64 00:03:30,008 --> 00:03:35,003 So, I have my formulas, and now I can copy them over 65 00:03:35,003 --> 00:03:39,000 to column two, three, and four, H, I, and J 66 00:03:39,000 --> 00:03:41,007 of the worksheet so that I can calculate correlations 67 00:03:41,007 --> 00:03:44,003 between each pair of columns. 68 00:03:44,003 --> 00:03:48,003 So, I'll select cells, G6 through G9, 69 00:03:48,003 --> 00:03:52,009 and drag the fill handle over, and the first thing I note, 70 00:03:52,009 --> 00:03:57,003 and this is a good sign, is that anytime I compare a column 71 00:03:57,003 --> 00:04:00,005 with itself, I get a correlation of one. 72 00:04:00,005 --> 00:04:04,000 So, between column one and column one, 73 00:04:04,000 --> 00:04:07,005 column two and column two, three and three, four and four, 74 00:04:07,005 --> 00:04:10,002 I get correlations of one. 75 00:04:10,002 --> 00:04:14,000 So, along the main diagonal of this grid 76 00:04:14,000 --> 00:04:17,004 I see that I have the correlations that I'm looking for. 77 00:04:17,004 --> 00:04:21,001 Another way that I can check my values is to ensure 78 00:04:21,001 --> 00:04:24,002 that column one and column two, 79 00:04:24,002 --> 00:04:26,002 when column one is a row header 80 00:04:26,002 --> 00:04:29,008 and column two is a column header, 81 00:04:29,008 --> 00:04:30,007 I need to make sure 82 00:04:30,007 --> 00:04:35,000 that produces the same result as when I have column two 83 00:04:35,000 --> 00:04:39,001 as the row header and column one as the column header. 84 00:04:39,001 --> 00:04:43,001 So, it looks like my values, even though they're duplicated 85 00:04:43,001 --> 00:04:46,005 within this grid, they are accurate. 86 00:04:46,005 --> 00:04:49,006 So, if I want to compare column two to column three, 87 00:04:49,006 --> 00:04:53,008 I can do it here, or I can do it here, 88 00:04:53,008 --> 00:04:58,000 and I will get a correct result based on my calculations. 6916

Can't find what you're looking for?
Get subtitles in any language from opensubtitles.com, and translate them here.