The Arizona Desert Lamp

Kings of Convenience

Posted in Campus by Evan Lisull on 24 March 2009

SSF Survey Results, 2009

The Office of Student Affairs released the latest results for the democratically-rejected Student Services Fee survey, and it’s the same it ever was. The same biases previously discussed at length here are still at play, and Student Affairs still doesn’t care. One comes across a paragraph like this

Students living in off-campus housing and those living in Greek housing were the least enthusiastic. Students living in Greek Housing were the least satisfied with three out of the four changes with significant differences, with those in off-campus housing the least satisfied with the fourth. Additionally, students living in Greek Housing were the least enthusiastic group for 8 of the 19 initiatives, and students living in off-campus housing were the least enthusiastic in 9 of the 19 initiatives.

and can’t even pretend to be surprised. You, do, however, have to love truth revealed through footnotes:

 

Note: Prices for each of the initiatives were not listed for the Spring 2009 assessment.  

 

In other words, we supply all of the pertinent information – except when it inconveniences our prerogatives. What’s more, Student Affairs still stands defiantly behind its ‘convenience sampling’ method:

 

This research relied on a convenience sample, as a link was advertised via e-mail to all enrolled students. This type of sample is based on availability and accessibility, and can often produce samples that are quite similar to the population of interest when conducted properly.

 

For the sake of comparison, some thoughts from actual statistics Ph.Ds:

 

Estimates of population characteristics based on convenience samples are affected by selection bias. Since the interviewers choose respondents that they want to interview or respondents decide whether or not to participate, there is a potential for selection bias. If the respondents in the survey are systematically different from the general population being measured, then estimates of characteristics will be different on average from what they would have been with a controlled probability-sampling scheme. Probability sampling refer to a collection of survey sample designs in which the survey planner or researcher controls which units are in the sample and selects the sample using known probabilities of selection. The probabilities of selection can be used to produce estimates of population characteristics without the problem of selection bias. Probability sampling is the standard methodology for large-scale surveys intended to support scientific studies and decision making for government policy. That is not to say that convenience sampling should never be done. Sometimes it is very helpful to get some feedback and suggestions from people especially concerned with a problem or issue. One should careful, however, about the limitations of general statements about a large population based on convenience samples. [emphasis added – EML]

-Larsen, Michael D. “Convenience Sampling.” Encyclopedia of Measurement and Statistics. ed. Neil J. Salkind. Sage Publications, Thousand Oaks, CA, 2007. p. 186-87

 

More pithily:

 

Convenience Sample  A sample of subjects selected for a study not because the are *representative but because it is convenient to use them — as when college professors study their own students. Compare *accidental sample, *bias

-Vogt, W. Paul. Dictionary of Statistics and Methodology. Sage Publications, Newbury Park, CA, 1993. p. 48

 

From On Thinking Statistically:

 

When it comes to choosing a sample which will be a reliable cross-section of the larger group, this will only be achieved if selection is not biased in any way, if it is random. Each individual in the main group must have an equal chance of getting into the sample. This is a crucial requirement and guarantee against the dangers of bias. 

Brodie, Morris. On Thinking Statistically. Crane, Russak, & Company, Inc. New York, 1972

 

Presciently, from an older textbook:

 

Sometimes a sample is taken in a more or less haphazard fashion. Or, the investigator may include the data which are convenient or readily available, after which he will trustingly announce that the sample so taken is doubtless representative of the population which he is studying.

Croxton, Frederick E., Dudley J. Coweden, and Sidney Klein. Applied General Statistics, Third Edition. Prentice-Hall, Inc. Eaglewood Cliffs, NJ, 1967. p. 29

Advertisements

3 Responses

Subscribe to comments with RSS.

  1. Jimi Alexander said, on 24 March 2009 at 11:44 pm

    Why are the proud affiliates of Greek Life opposed to the initiatives? I can understand off-campus students being less-than-enthusiastic, but our numerous Greek-alphabet-soup-wearing colleagues live on campus.

    Any idea?

    • Evan Lisull said, on 25 March 2009 at 9:27 am

      This is a good question, especially since it was a trend that was observed in the earlier survey. I would hypothesize that the benefits that come with paying Greek dues make the benefits of the SSF irrelevant. While the SSF may have provided $3 lunches, many Greek houses have in-house chefs and buffets for free. I’d suspect that Greek houses have their own legal services, and the conflict between drunk Greeks and the SafeRide system is never-ending.

  2. […] by Evan Lisull on April 5th, 2009 As if the litany of other absurdities associated with the Student Services Fee weren’t enough, recipients of SSF money must use some of the funds to pay for […]


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 )

Twitter picture

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

Facebook photo

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

Google+ photo

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

Connecting to %s

%d bloggers like this: