Some readers of this newsgroup may remember a message i posted some
weeks back about analysing the data from some pilot tests concerning
dialling methods from a mobile phone (see: what test do i run?? help
for a novice please).

Well i have now done the main body of my research, and unsurprisingly
i am in somewhat of a muddle with my stats again. I do have tutors who
are SUPPOSED to help me, but they have made themselves both
unavailable and unintelligible. The details are below.

May i first though, thank profusely anyone who is taking the time to
read this and offer help. I cant express how much i greatly appreciate
and am utterly surprised by the amount of people who are willing to
offer help to complete strangers. Anyway, that out of the way, heres
the details (pared down as much as possible).....

I did a direct comparison of two methods of dialling a name from a
mobile phone 'look-free'.

The first was voice activated dialling which im sure most of you are
familiar with.

The second was a new method using text-to-speech technology (TTS):
Users press a button to start. The system then 'reads' the first name
in the users list. The user then scrolls through the names in their
list, whilst the system reads each one out. When the desired name is
reached, the user presses the dial button.

I was interested to know:

A) Which was faster on successful dials
B) Which had a higher error rate (either failed dial attempts or wrong
names dialled)
C) Which was faster OVERALL, once the errors had been included
D) Which ones performance was more affected detrimentally by
background noise

12 subjects took part. Each subject had their own 10 name phonebook.
Each subject had to dial every name in their phonebook (randomly
presented) under four different conditions (also randomised):

1) Voice dialling (VD) + quiet
2) VD + noise  
3) TTS dialling + quiet 
4) TTS dialling + noise

On the data i collected i did the following (all t tests):

1) speed of successful dials, VD vs TTS, with quiet
2) speed of succesful dials, VD vs TTS, with noise

etc... for aspects A, B, C listed above.

For D (effect of background noise) i did:

1) Speed of succesful dials, TTS in quiet vs TTS in noise
2) Speed of succesful dials, VD in quiet vs VD in noise
etc... for error rates and speed of dialling including errors

Phew! that was a lot of info... My question im afraid is somewhat
vague due to the fact that my tutors have confused me. Below is the
source of my confusion:

My tutors say that i cant produce these t tests without first running
a 2 way repeated measures ANOVA on all the data together to see if
there is a general effect first, only then can i parcel the analyses
into those for quiet and those for noisy. To quote them: "Start the
analyses with 2-way ANOVAs of the overall data from each
quiet/noisy/VAD/TST set and then go on to do the separate t-tests"

I just cant get my head round this. I guess my main problem is that i
dont know what an ANOVA does, and consequently when i do them i really
have no idea what the output means. To me it just makes no sense to
analyse the data with the noisy and quiet conditions taken together -
it is not interesting to know if there is an effect between VD Quiet
and TST noisy for example, because it is not a fair comparison. So
what do these tests actually tell me? Are my tutors misunderstanding
the point of my experiements?

I know this is vague, but because of my confusion im not really sure
of the exact question myself. Can anyone help?

thanks again, and sorry if i have wasted anyones time with a
non-answerable question

DN
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to