Chapter 12

A study was conducted to evaluate shivering in the postoperative patient. The study measures subjects' weight in pounds and temperature in centigrade degrees. What should the reader consider about the level of measurement of these two parameters? 1. Temperature is measured at ratio level. 2. Weight is measured at the ratio level. 3. Both of these measurements are at interval level. 4. Additional information is needed before any determination of level of measurement can be made.

Correct Answer: 2 Rationale 2: Weight is generally considered to be measured at ratio level, which is the highest level of measurement. Ratio level of measurementincludes data that can be categorized and ranked; in addition, the distance between ranks can be specified, and a "true" or natural zero point can be identified.

The nurse researcher has spent several days choosing an instrument to gather study data. What is the researcher's next step? 1. Collect the data. 2. Determine the level of measurement desired. 3. Conduct a trial run of the instrument. 4. Convert the instrument to collect interval data.

Correct Answer: 3 Rationale 3: A trial run of the instrument will help the researcher determine if it will serve the purposes of the study. A trial run can save time and trouble in the long run.

A study used a multiple choice exam with point ranges from 0-10 to measure subject knowledge of diabetic care. The exam score is an example of what level of measurement? 1. Ratio. 2. Interval. 3. Ordinal. 4. Nominal.

Correct Answer: 1 Rationale 1: Ratio level data have categories that are mutually exclusive and exhaustive, can be rank ordered, with equal distance between rank and no absolute zero.

The nurse researcher administered a questionnaire to a group of subjects six weeks ago. Today, the researcher administered the same questionnaire to the same subjects. Select the type(s) of reliability the researcher is testing using this technique. Standard Text: Select all that apply. 1. Test-retest. 2. Parallel forms. 3. Stability. 4. Alternate forms. 5. Interrater.

Correct Answer: 1,3 Rationale 1: The technique described tests stability, reliability, or test-retest reliability. By testing a group and then retesting them with the same instrument, the researcher is testing the instrument's consistency over time. Rationale 3: The technique described tests stability, reliability, or test-retest reliability. By testing a group and then retesting them with the same instrument, the researcher is testing the instrument's consistency over time.

While reading a research report, the nurse discovers that the researcher used a study instrument that has an established correlation coefficient of .54. How should the reader interpret this information? 1. This information is not pertinent to the critique of the study. 2. This instrument is not very reliable. 3. This is a very valid instrument. 4. The instrument is very reliable.

Correct Answer: 2 Rationale 2: Correlation coefficients can range between -1.00 and +1.00 and are a measurement of reliability. It is risky to use an instrument with reliability lower than .70.

According to the research report, the nurse researcher tested a study instrument's validity using the technique of factor analysis. What other test could the researcher have used to test the same type of validity? 1. Test-retest. 2. Known-groups procedure. 3. Scale homogeneity. 4. Interrater.

Correct Answer: 2 Rationale 2: Factor analysis and know-groups procedure both test construct validity.

A study is collecting data through use of a questionnaire that asks staff nurses about what they see as essential characteristics and abilities of a nurse manager. The nurses were asked to complete the questionnaires at the beginning or at the end of their shift and place them in a box located in the nursing unit. What is the most likely source of error in this data collection procedure? 1. Instrument inadequacies. 2. Transitory personal characteristics. 3. Environmental variations during the data-collection process. 4. Instrument administration bias.

Correct Answer: 2 Rationale 2: Having nurses fill out the questionnaires both before and after the shift could influence responses-nurses at the end of their shifts could be more fatigued. Events that occurred during their shifts also influence their answers.

A researcher is developing a data collection instrument to measure nurses' attitudes about their working conditions. A draft copy of the instrument is sent to 20 nurse clinicians to critique and provide feedback. What is the researcher attempting to establish by using this strategy? 1. Face validity. 2. Construct validity. 3. Content validity. 4. Criterion validity.

Correct Answer: 3 Rationale 3: Content validity for an instrument is concerned with the scope or range of items used to measure the variable. Content validity can be determined by a panel of experts.

Which term means the extent to which a measurement tool consistently measures a variable? 1. Stability. 2. Equivalence. 3. Internal consistency. 4. Precision.

Correct Answer: 3 Rationale 3: Internal consistency (homogeneity) examines the extent to which all items on an instrument measure the same variable.

A study is conducted to measure the effect of specific nursing interventions on the oxygen saturation of infants. Oxygen saturation is an example of what level of measurement? 1. Nominal scale. 2. Interval scale. 3. Ratio scale. 4. Ordinal scale.

Correct Answer: 3 Rationale 3: Ratio scale of measurement is the highest form of measurement. Categories are mutually exclusive, mutually exhaustive, can be rank ordered, have equally spaced intervals, and have an absolute zero point. Oxygen saturation levels meet each of the preceding characteristics.

Which statement most accurately describes the relationship between reliability and validity of a measurement instrument? 1. A measure cannot be reliable unless it is valid. 2. As reliability increases, validity decreases. 3. A measure cannot be valid unless it is reliable. 4. As validity increases reliability decreases.

Correct Answer: 3 Rationale 3: Reliability of a measure is always considered first because reliability is a necessary condition for validity. An instrument cannot be valid unless it is reliable

The nurse researcher is using the Mental Measurement Yearbook published in 2010. What portion of the research process is this researcher completing? 1. Review of the literature. 2. Selection of a measurement level. 3. Instrument choice. 4. Data collection.

Correct Answer: 3 Rationale 3: The Mental Measurement Yearbook is a source of research instruments. To be reviewed by MMY, a test must be commercially available; be published in the English language; and be new, revised, or widely used since it last appeared in the MMY series.

Which statement regarding construct validity of a measurement instrument is accurate? 1. It is established by complex statistical procedures. 2. It is used to determine that items on the tool adequately represent conceptual definitions of variables in the study. 3. It is concerned with the ability of an instrument to predict behavior of subjects in the future. 4. It is the measurement of a variable that is not directly observable.

Correct Answer: 4 Rationale 4: Construct validity is an abstraction derived from observable behavior.

The nurse is completing a questionnaire that asks for the nurse's area of specialization in nursing (Peds, OB, Med-Surg). On which scale is this data measured? 1. Ordinal scale. 2. Ratio scale. 3. Interval scale. 4. Nominal scale.

Correct Answer: 4 Rationale 4: Data measured by a quantitative difference between categories that are mutually exclusive and mutually exhaustive is nominal level data.

The researcher asks another nurse to use a study instrument to score a questionnaire completed by study participants. The researcher has previously used the instrument to score the questionnaire and will compare the two results. Which type of reliability is this researcher trying to establish? 1. Internal consistency. 2. Stability. 3. Homogeneity. 4. Equivalence.

Correct Answer: 4 Rationale 4: This scenario describes interrater or interobserver reliability. Equivalence reliability is established by the comparison of two observers measuring the same event for equivalence.