Multiple Choice

1		Measurement is:
			A)	the operationalization of a variable.
			B)	describing something in a standardized form.
			C)	an interpretive device.
			D)	everything the researcher does to arrive at the numerical estimate.
2		A variable measured with discrete data means that the data identify participants as:
			A)	belonging to one of at least two categories of a variable.
			B)	belonging to several categories of a variable.
			C)	having some position on a continuum of scores.
			D)	being rank and compared to others.
3		The categories of discrete data should:
			A)	be anonymous and confidential.
			B)	be ranked in importance or value to one another.
			C)	be mutually exclusive, exhaustive, and equivalent.
			D)	always include one category for zero or none of that characteristic.
4		Continuous level data:
			A)	reflect different categories of a variable.
			B)	reflect differing degrees, amounts, or frequencies.
			C)	are only produced from participants' answers to items on a questionnaire.
5		A Likert-type scale:
			A)	is a discrete measurement.
			B)	has a true zero.
			C)	is an interval measurement that has a response set which must be balanced at the ends of the continuum.
			D)	is a ratio measurement.
6		A semantic differential scale:
			A)	asks participants to locate the meaning they ascribe to a stimulus.
			B)	is a form of continuous level measurement.
			C)	has a response set anchored by two opposite or bipolar adjectives.
			D)	does not include descriptors for the intermediate positions on its response set.
			E)	all of the above.
7		A measure is said to have face validity when:
			A)	one measurement can be linked to some other external measurement.
			B)	the measuring items reference the construct we want to measure.
			C)	the measuring items represent the full range of characteristics associated with the construct.
			D)	the measure is stable, trustworthy, and dependable.
			E)	a respondent responds similarly to all of the items.
8		Internal reliability:
			A)	is also known as Cronbach's alpha.
			B)	can be affected by how the items are worded.
			C)	should be .70 or greater.
			D)	should be reported for each variable composed of multiple items.
			E)	all of the above.
9		Interrater reliability for categorical data:
			A)	is also known as interrater agreement.
			B)	is generally associated with content analysis.
			C)	is also known as intercoder reliability.
			D)	can be calculated with Cohen's kappa or Scott's Pi.
			E)	all of the above.
10		Unitizing and categorizing reliability are used with:
			A)	Likert-type scales.
			B)	ordinal data.
			C)	content analysis.
			D)	ratio data.
			E)	continuous data.
11		Measurement should have:
			A)	reliability.
			B)	validity.
			C)	reliability and validity.
12		A threat to validity or reliability is:
			A)	any data-related problem that could lead you to draw a false conclusion from the data.
			B)	not really an issue if you're a student researcher.
			C)	generated by research participants only.
			D)	generated by researchers only.
			E)	generated only when participants drop out of a study that collects data over a long period of time.