Problem Statement: African Americans have the highest population of people diagnosed with hypertension.
Research Question: Does the development of community programs and providing health education, reduce Disparities in Hypertension in predominately African American Communities versus a more diverse community?
By Saturday, October 14, 2017 write a 2–3-page paper addressing the sections below of the research proposal. Citation/References within 5 years.
Extraneous Variables (and plan for how controlled).
Instruments: Description, validity, and reliability estimates, which have been performed (on a pre-established measure). Include plans for testing validity and reliability of generating your own instrument(s).
Description of the Intervention
Data Collection Procedures
Assignment 2 Grading CriteriaMaximum Points
Identifies extraneous variables and plan for how controlled.5
Instrument is appropriate to address research question.5
Includes description of the selected instrument(s), validity, and reliability estimates.5
Description of the Intervention is fully addressed.5
Data Collection Procedures are clear and succinct.5
Followed APA guidelines for writing style, spelling and grammar, and citation of sources.5
Measurement Theory Concepts
Measurement is the process of assigning numbers to objects (or events or situations) in accord with some rule. Numbers assigned can indicate numerical values or categories.
Instrumentation, a component of values or categories is performed consistently from one subject (or event) to another and, eventually, if the measurement strategy is found to be meaningful, from one study to another. Begins by clarifying the object, characteristic, or element to be measured.
Directness of Measurement: can be a person’s height or BMI—this is a concrete form of measurement
Indirect measurement: Aimed at abstract concepts, such as pain, depression, self-care
The instrument used in the study must match the conceptual definition.
There is no perfect measure. Error is inherent in any measurement strategy.
Measurement error is the difference between what exists in reality and what is measured by a research instrument.
Two types of measurement error:
Random error: causes individuals’ observed scores to vary around their true score. For example, one’s observed score may be higher than the true score.
Systematic error: This is error that is not random. For example, use of a weight scale that weighed subjects 2 lb. more than their true weights. All of the body weights would be higher and thus, the mean would be higher than it should be.
Levels of Measurement
Nominal: lowest level, used when data is organized into categories.
Ordinal: Data that is assigned to categories of an attribute that can be ranked. Categories (as in nominal) must be exclusive. Example: Degrees of coping, intensity of pain, daily amount of exercise.
Interval: Distances between intervals of the scale are numerically equal. Must be mutually exclusive, and rank ordered. Assumed to be a continuum of values. Fahrenheit temperatures are an example.
Ratio: This is the highest level of measurement and meets all rules (mutually exclusive categories, rank ordering, equal spacing between intervals, and continuum of values) and adds an absolute zero point. Weight, length, and volume are common examples. Each has an absolute zero point, at which a value of zero indicates the absence of the property being measured.
Reference of Measurement
Norm-Referenced Testing: Test performance standards that have been carefully developed over years with large, representative samples using a standardized test with extensive reliability and validity.
Criterion-Referenced Testing: Comparison of a subject’s score with a criterion of achievement that includes the definition of target behaviors. When behaviors are mastered, the subject is considered proficient in the behaviors.
What is reliability?
Reliability is concerned with how consistently the measurement technique measures the concept of interest. Reliability testing is usually expressed as a form of correlation coefficient.
Types of Reliability
Stability—is concerned with the consistency of repeated measures or test-retest reliability
Equivalence—is focused on comparing two versions of the same instrument (alternate forms reliability) or two observers (interrater reliability) measuring the same event.
Homogeneity—addresses the correlation of various items within the instrument or internal consistency; determined by split-half reliability or Cronbach’s alpha coefficient.
What is validity?
The extent to which an instrument reflects the concept being examined.
Types of Validity
Content-Related Validity: supports the extent to which the instrument measures all relevant dimensions of the construct, often referred to as the universe or domain of the construct.
Criterion-Related Validity: supports the relationship between scores on the research instrument and another measure, known as the criterion.
Construct Validity: refers to the degree to which scores obtained from the use of an instrument are related to the concept of interest to the researcher.
Physical Measurement Methods
Pulse, Blood Pressure
Involves spontaneously observing and recording what is seen with a minimum of planning.
Defines carefully what is to be observed. Concern is directed toward how the observations are made, recorded, and coded.
Used primarily in descriptive and qualitative studies. May be initiated by asking a broad question such as, “Describe for me your experience with….”
This includes strategies that provide increasing amounts of control by the researcher over the content of the interview. Questions are designed before initiation of data collection.
Unstructured or Open ended:
Tell me about…..
What has been your experience with….?
What was it like to hear you have cancer?
Structured or Closed ended:
Response alternatives fixed
Which would you rather do, x or y?
In person/on phone
Rating Scales: crudest form of measurement which lists an ordered series of categories of a variable that are assumed to be based on an underlying continuum. A numerical value is assigned to each category. Commonly used by the general public. “On a scale of 1 to 10, I would rate that . . . “
Likert Scales: designed to determine the opinion or attitude of a subject and contains a number of declarative statements with a scale after each statement.
Semantic Differentials: consists of two opposite adjectives with a seven point scale between them. Hot – – – – – – – Cold
Visual Analog Scales: used to measure mood, anxiety, alertness, craving, quality of sleep, etc. Stimuli must be defined in a way that is understandable to the subject. Only one major cue should appear for each scale. The scale is a line 100 mm in length with right-angle stops at each end.
No pain I——————————————————————–I Pain as bad as it possibly can be
Best to use existing instruments.
Buros Mental Measurement Institute: http://www.unl.edu/buros
There are several large volumes of test reviews. The reviews cover critical evaluation of the test (e.g., validity, reliability, etc.), and provide information on cost and publisher.
FAQ on Psychological Tests: http://www.apa.org/science/faq-findtests.html
Information on testing considerations from the APA.