Database Reference
In-Depth Information
OK; so, for the example in the previous section, we computed Yc to be 91.135,
which is our best estimate of the time it would take a person to complete the Major
Task, given he/she required 80, 100, and 100 seconds, respectively, for the three com-
ponent tasks. That, of course, does not mean that an individual person with compo-
nent task times 80, 100, and 100 seconds, will require
exactly
91.135 seconds for the
Major Task. After all, we have sampled and based our estimate on a random sample
of
n
= 25, not a sample of a
zillion
.
More importantly, even if we had ininite data, which would make 91.135 the
true
mean time
for the Major Task for people with component task times of 80, 100,
and 100 seconds, the fact is: if we examined a bunch of people with component task
times of 80, 100, and 100 seconds, they would all have different times to complete
the Major Task!! Hence, there is the need for a conidence interval for how long it
would take an individual person with these component task times to complete the
Major Task. A 95% conidence interval for that time is
91
.
135±2* (7
.
205)
or
76
.
725to105
.
545
In other words, there is a 95% chance (or, equivalently, probability 0.95) that the
interval, 76.725-105.545 seconds will contain the time an individual person requires
to complete the Major Task, if his/her time for the component tasks are 80, 100, and
100 s, respectively.
10.5
BACK TO BEHEMOTH.COM
Now, let's get to our Behemoth.com data.
In an unmoderated usability test, 180 recruiters used the Behemoth.com candidate
search engine to search for job candidates. All the respondents were tasked with ind-
ing good candidates for the same three requisitions: (1) A Java Developer with at least
5 years experience, a bachelor's degree from MIT, a maximum salary requirement of
$95,000 per year, willing to relocate, who is looking for a full-time position; (2) A Web
Designer with skills using Axure, Photoshop, and Illustrator within 25 miles of San
Diego, with an Active Conidential Security Clearance; and (3) A Business Analyst
who has previously worked at Oracle, an average length of employment of no less than
1 year, with a resume dated no earlier than 2013, willing to travel up to 50% of the time.
After completing the tasks of inding candidates for the three positions, the
respondents were asked how likely they are to adopt the search engine. In addition,
they are speciically asked to rate their perception of usefulness for each of the ields
in the search engine, on a scale of 1-5, where 1 = not at all useful and 5 = extremely
useful.
Table 10.3
shows the 15 speciic search engine components respondents are
asked to rate (this table is listed also in Chapter 9).
These 15 variables are now our 15 X's (independent variables) in a multiple regres-
sion analysis, with the dependent variable, Y, being the
likelihood the respondent
would adopt the search engine
. (The actual question was, “Imagine that this search
Search WWH ::
Custom Search