27.10.2014 Views

Russel-Research-Method-in-Anthropology

Russel-Research-Method-in-Anthropology

Russel-Research-Method-in-Anthropology

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

54 Chapter 2<br />

Reliability<br />

Reliability refers to whether or not you get the same answer by us<strong>in</strong>g an<br />

<strong>in</strong>strument to measure someth<strong>in</strong>g more than once. If you <strong>in</strong>sert a thermometer<br />

<strong>in</strong>to boil<strong>in</strong>g water at sea level, it should register 212 Fahrenheit each and every<br />

time. ‘‘Instruments’’ can be th<strong>in</strong>gs like thermometers and scales, or they can<br />

be questions that you ask people.<br />

Like all other k<strong>in</strong>ds of <strong>in</strong>struments, some questions are more reliable for<br />

retriev<strong>in</strong>g <strong>in</strong>formation than others. If you ask 10 people ‘‘Do the ancestors<br />

take revenge on people who don’t worship them?’’ don’t expect to get the<br />

same answer from everyone. ‘‘How many brothers and sisters do you have?’’<br />

is a pretty reliable <strong>in</strong>strument (you almost always get the same response when<br />

you ask a person that question a second time as you get the first time), but<br />

‘‘How much is your parents’ house worth?’’ is much less reliable. And ‘‘How<br />

old were you when you were toilet tra<strong>in</strong>ed?’’ is just futile.<br />

Precision<br />

Precision is about the number of decimal po<strong>in</strong>ts <strong>in</strong> a measurement. Suppose<br />

your bathroom scale works on an old-fashioned spr<strong>in</strong>g mechanism. When you<br />

stand on the scale, the spr<strong>in</strong>g is compressed. As the spr<strong>in</strong>g compresses, it<br />

moves a po<strong>in</strong>ter to a number that signifies how much weight is be<strong>in</strong>g put on<br />

the scale. Let’s say that you really, truly weigh 156.625 pounds, to the nearest<br />

thousandth of a pound.<br />

If you have an old analog bathroom scale like m<strong>in</strong>e, there are five little<br />

marks between each pound read<strong>in</strong>g; that is, the scale registers weight <strong>in</strong> fifths<br />

of a pound. In terms of precision, then, your scale is somewhat limited. The<br />

best it could possibly do would be to announce that you weigh ‘‘somewhere<br />

between 156.6 and 156.8 pounds, and closer to the former figure than to the<br />

latter.’’ In this case, you might not be too concerned about the error <strong>in</strong>troduced<br />

by lack of precision.<br />

Whether you care or not depends on the needs you have for the data. If you<br />

are concerned about los<strong>in</strong>g weight, then you’re probably not go<strong>in</strong>g to worry<br />

too much about the fact that your scale is only precise to the nearest fifth of a<br />

pound. But if you’re measur<strong>in</strong>g the weights of pharmaceuticals, and someone’s<br />

life depends on your gett<strong>in</strong>g the precise amounts <strong>in</strong>to a compound, well,<br />

that’s another matter.<br />

Accuracy<br />

F<strong>in</strong>ally, accuracy. Assume that you are satisfied with the level of precision<br />

of the scale. What if the spr<strong>in</strong>g were not calibrated correctly (there was an

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!