WELNS 670: Wellness Research Design Session 2. Review.

WELNS 670: Wellness Research Design

Session 2

Review

8 Characteristics of Research

Originates with a question or problem Requires a clear articulation of a goal Follows a specific plan of procedure Divides the principle problem into more manageable

sub-problems. Is guided by the specific research problem, question,

or hypotheses Accepts certain critical assumptions Requires the collection and interpretation of data in

an attempt to resolve the problem that initiated the research

Is cyclical, by nature… From Leedy and Ormrod (2001). Practical Research: Planning and Design.

The Research Cycle

From Leedy and Ormrod (2001). Practical Research: Planning and Design.

Research is not…

Information gathering by itself (information discovery, reference skills)

Transporting facts from one location to another (fact discovery, fact reporting)

Rummaging for information (self-enlightenment)

Catchword to get attention (sales-pitch)

From Leedy and Ormrod (2001). Practical Research: Planning and Design.

Thinking about research…

Describe an example of the word “research” being used inappropriately.

In the most rigorous tests of hypotheses, researchers set out to fail to support a hypothesis. Why might fail to support be a more rigorous test of a hypothesis than trying to support it?

As a Masters’ student, – Think of at least one personal benefit that the you would get

from completing a thesis– Think of at least one societal benefit that follows from your

completing a thesis

What would you study???????

Practical Example

Practical Example

Values of Journalist Added

Where does the Data Come From?

Always try to site the primary data collector.

Source: National Center for Education Statistics

Actual Source: US Department of Commerce, Bureau of the Census, Current Population Survey… by way of CPR, Series P-60.

In Class Activity (groups of 3-4)

Look through your group’s collection of articles.

How are these articles similar? How are they different? Which articles represent true research

articles as described in Chapter 1 of your text?

New Material

2 Primary Functions of Research Methodology

To control and dictate the acquisition of data To corral the data after their acquisition and

extract meaning

Research methodology – the general approach the researcher takes in carrying out the research project.

Tools of Research

Research tool – a specific mechanism or strategy the researcher uses to collect, manipulate, or interpret data.

– The library and its resources– The computer and its software– Techniques of measurement– Statistics– The human mind– Facility with language

The Library and its Resources

http://www.nlm.nih.gov/

Computer and It’s Software

Planning the Study Literature Review Study Implementation and Data Gathering Analysis and Interpretation Discussion Reporting

Question…

Do recent technological advances (WWW, electronic databases) assure that future research will be of higher quality, or of greater utility, than past research?

Measurement as a tool of research

“Measurement is limiting the data of any phenomenon – substantial or insubstantial – so that those data may be interpreted and, ultimately, compared to an acceptable qualitative or quantitative standard.”

Four Scales of Measurement

Nominal Ordinal Interval Ratio

The scale of measurement will ultimately dictate the statistical procedures used to analyze the data.

Nominal Measurement Scale

Divides data into discrete categories Has no values assigned to the various categories Examples: Boy/Girl, Red/White/Blue/Green,

None/Dial op/Cable/DSL/Other, Ball State/Purdue/IU/IUPUI, yes/no

Only a few statistics are appropriate for analyzing nominal data (mode, percentage, chi-square tests)

Usually described using frequency distributions

Ordinal Measurement Scale

Again, divides data into discrete categories However, this level of measurement allows us to

rank-order data in terms of one being greater or higher than another

Examples: small/medium/large, elementary/middle school/high school/college, 20-29/30-39/40-49/50+

Extends the range of statistical techniques (median, percentile rank, Spearman’s correlation)

Usually described using frequency distributions

Interval Measurement Scale

Has equal units of measurement and the “zero point” is established arbitrarily

Examples: Likert and Likert-type scales (strongly agree to strongly disagree), Fahrenheit and Celsius temperature scales

Again extends the statistical procedures available for analysis (means, standard deviations, Pearson Correlations)

Usually described using means and standard deviations

Ratio Measurement Scale

Has equal measurement units and an absolute zero such that the ) on the scale reflects a total absence of the quantity being measured

Examples: Age, distance, weight, velocity Allows you to conduct virtually any statistical analysis Usually described using means and standard

deviations

Summary: Measurement Scale

If you can say that… One object is different from another, you have a

nominal scale; One object is bigger or more anything than another,

you have an ordinal scale; On object is so many units more than another, you

have an interval scale; One object ti so many times bigger, brighter, heavier,

or as tall as another, you have a ratio scale.

Question Items Issues

Response categories should be mutually exclusive and exhaustive (for the audience).

Think carefully about “forced responses” and “neutral options” and overall, the number of options you will offer.

Validity and Reliability of a Measurement Tool

Validity and reliability influence… The extent to which you can learn something from

the phenomenon you are studying The probability that you will obtain statistical

significance in your data analysis The extent to which you can draw meaningful

conclusions from your data

“Psychometric measures”

Validity

“the extent to which the instrument measures what it is suppose to measure”

Face validity Content validity Construct validity

Reliability

“the consistency with which a measuring instrument yields a certain result when the entity being measured has not changed.”

Test-retest, internal consistency

Reliability is a necessary but insufficient condition for validity

Statistics as a Tool of Research

Statistics give information about the data and “help the human mind comprehend disparate data as an organized whole”

This information can be used to help give meaning to the data (interpretation)

Descriptive statistics – summarize the general nature of the data

Inferential statistics – help make decisions about the data (i.e., are the results statistically significant)

The Human Mind as a Tool of Research

The mind of a researcher must use all of the information available to them to interpret the data to arrive at logical conclusions to their meaning

Deductive Logic Inductive Reasoning Scientific Method (identifying a problem, positing a

hypothesis, gather data, analyze and interpret the data)

Critical thinking – evaluation information or arguments in terms of their accuracy or worth

Facility with Language as a Tool of Research

“Learning the specialized terminology of your field is indispensable to conducting a research study, grounding it in prior theory and research, and communicating your results to others.”

Group Work (small groups)

Find articles that include detailed information about measurement tools and identify the level of measurement of those items.

Explore whether and how information about reliability and validity of measurement tools is conveyed. If absent, what information is needed to convince readers that high quality measurement instruments were employed in the study.

Question (for next session)…

The authors include a relatively lengthy section on writing the research report. Why is it important that research results are carefully written up and made available to the scientific community?