Probability assignment (Assignment 1), Psych. 153, Fall 2009

To do the assignment, you must have your data from when you completed the questionnaire. In the email with your data (sent to you after you completed the questionnaire on the web, the two numbers in the first row are the probability you assigned to being male (around .5) and whether you yourself are male (1=male, 0=female).

Enter these here. p(male): Sex:

Then there are 5 rows corresponding to the 5 items:

love	prefer love stories to action/adventure movies
sports	choose to watch football, basketball, or hockey on TV
program	have programmed a computer
tall	am 67 inches tall or more (5 feet, 7 inches)
dress	spend 15 minutes or more getting dressed each day

In the following box, cut and paste your data from exacly those 5 rows from the email you received:

The following table shows the meanings of the items in each row:

me	whether the statement is true for you
p(y)	your judged probability of yes for a student in the class
p(y|m)	judged probability of yes for a male student
p(y|f)	judged probability of yes for a female student
p(m|y)	judged probability of being male given yes
p(m|n)	judged probability of being male given no

This assignment has two parts. The first part uses conditional assessment. The second uses Bayes's theorem.

For the conditional assessment, we will use a new variable, called p'(y). Like p(y), this also stands for the probability of a certain item being true for the class. But, p'(y) is different from p(y) because p(y) came from your direct judgment but you are going to calculate p'(y). You will calculate p'(y) using conditional assessment as described in chapter 6 of the text. You can then compare p'(y) to p(y).

Now compute p'(y) from p(y|m), p(y|f) and p(m), for each of the five items. You will need a pencil and paper for this. Enter the numbers here, with decimal points.
love:
sports:
program:
tall:
dress:

Now enter what you think are the best values for p(y), taking into account both your original answers and the conditional assessment. (You could decide that your original answers were best, or the calculated answers, or something in between, or something more extreme.)
love:
sports:
program:
tall:
dress:

For Bayes's theorem, we will use the variable p'(m|y). In the original web questionnaire, you estimated p(m|y). Again, the difference between these two variables is that p(m|y) was the result of judgment and you will calculate p'(m|y) using Bayes theorem. The relevant form of Bayes's theorem is equation 5.3:

p(H|D)= p(D|H)p(H) / [ p(D|H)p(H) + p(D|not-H)p(not-H) ] .

Now calculate p'(m|y) and enter the results here:
love:
sports:
program:
tall:
dress:

Now enter what you think are the best values for p'(m|y), taking into account both your original answers and the calculated values, as before..
love:
sports:
program:
tall:
dress:

Enter your full upenn email address:

Comments:

You should get an acknowledgement email shortly after you submit your answers. We suggest that you do not close this window until you get it. If you don't get it soon, then write down your answers and try again.