Would You Like A Sample With That?

Yes please, a nice robust sample with a lovely rationale on the side. Easy to serve up right? But I’ve been reading some scary articles that tell me that if I don’t get the sample right, all that blood, sweat and tears agonising over evaluation questions and methodologies is all for nothing.   Apparently using a clunky fitting sample method is a bit of a death knoll.

As far as types of sampling goes, people who know about these things tend to like probability sampling This is because samples are randomized, which means samples are more likely to be able to be generalized to other groups.

But in our evaluation we’re not going to do that.  Instead we are going the non-probability route.  Non-probability sampling doesn’t involve randomization.  We’ve chosen this because we are interested in all of students enrolled in the course we are evaluating.  Having this common characteristic means it is a purposive sample in contrast to say accidental sample where you may selecting people who just happen to come along.  This path does have disadvantages however.  Part of the draw back of non-probability sampling is sometimes the sheer numbers involved, but as we will use survey monkey it takes care of that because of its ease of implementation and collation.  Another draw back is self-selection bias.  Even though all students can complete our survey, not all may choose to.  So the number of respondents and who responds (for instance will there be a subgroup such as all female respondents) will be important.  We will have to take this into account when we are analysing the results.

Have we got it right?  or will the bell begin to toll….


2 Responses

  1. Sandra I love your blogs and the way you add humour to what can be a very dry subject. I am interested in how you find the google.docs survey that we have ended up using in comparison to Survey Monkey. I’ve not used Survey Monkey so can’t compare.

    • Thanks Rosanne.
      Yes I am interested to see how google docs performs. I have found Survey Monkey easy to use but it is now restricted to 10 questions – any more and you have to pay. It also has the added advantage of compiling some information from the responses. It will be interesting to see if google docs has any features we can use to aid our analysis.
      Sandra H

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: