Changes

Jump to navigation Jump to search
3 bytes added ,  10:40, June 5, 2017
Line 76: Line 76:  
Suppose a polling firm was hired to talk to voters as they voted.  Each voter was asked "Are you a Republican?", "Are you a blue collar worker?", "Are you male?", "Do you live in West Virginia?", and "Did you vote for Donald Trump?"  We can record that data on a spreadsheet using one for yes and zero for no:
 
Suppose a polling firm was hired to talk to voters as they voted.  Each voter was asked "Are you a Republican?", "Are you a blue collar worker?", "Are you male?", "Do you live in West Virginia?", and "Did you vote for Donald Trump?"  We can record that data on a spreadsheet using one for yes and zero for no:
 
{| class="wikitable"
 
{| class="wikitable"
|Person||Republican?||Blue collar?||Male?||Wva?||Trump?
+
|Person||Republican?||Blue collar?||Male?||WVa?||Trump?
 
|-
 
|-
 
|A||1||1||1||1||1
 
|A||1||1||1||1||1
Line 95: Line 95:  
|}
 
|}
 
Whether the person voted for Trump is the independent variable, and each of the other questions are dependent variables.  The correlation coefficient can then be computed comparing the column of each dependent variable with the Trump column.  What this data tells us is that being blue collar is a perfect predictor of voting for Trump -- the correlation coefficient is 1.  The next best predictive factor would be whether the voter was a Republican, where they match 6 out of 7 times. Then comes gender and West Virginia residence.  Assuming that the data sample was large enough to be statistically significant, we could build a model to predict whether other voters would vote for Trump by asking the same questions and computing a score using the formula:
 
Whether the person voted for Trump is the independent variable, and each of the other questions are dependent variables.  The correlation coefficient can then be computed comparing the column of each dependent variable with the Trump column.  What this data tells us is that being blue collar is a perfect predictor of voting for Trump -- the correlation coefficient is 1.  The next best predictive factor would be whether the voter was a Republican, where they match 6 out of 7 times. Then comes gender and West Virginia residence.  Assuming that the data sample was large enough to be statistically significant, we could build a model to predict whether other voters would vote for Trump by asking the same questions and computing a score using the formula:
  .75*Republican + Blue collar + .73*Male + .42WVa
+
  .75*Republican + 1*Blue collar + .73*Male + .42*WVa
 
A perfect score would be 2.896, and someone with a 0 score would be most unlikely to vote for Trump.  Of course, the polling firm would be using many more questions and would experiment to fine-tune the questions to get the best predictive scores.  They would also use much larger data samples.
 
A perfect score would be 2.896, and someone with a 0 score would be most unlikely to vote for Trump.  Of course, the polling firm would be using many more questions and would experiment to fine-tune the questions to get the best predictive scores.  They would also use much larger data samples.
  
SkipCaptcha
3,995

edits

Navigation menu