Domain I- Topic C: Research Flashcards
How many steps are there in research?
7
Step 1 in research
(1) Identify a relevant and important topic; literature review
Step 2 in research process
(2) Develop a well-considered research question.
Step 3 in research process
(3) Research ? leads to a hypothesis.
* hypothesis is a prediction of a relationship
* null hypothesis= no relationship
Step 4 in research process
(4) Prepare research protocol: methodology to solve the problem.
Step 5 in research process
Organize methods and materials
Step 6 in research process
Collect and analyze data
Step 7 in research process
Study results and make decisions
What are the parts of a research paper?
- Abstract
- General introduction
- Review of existing literature
- Methodology
- Results
- Discussion (interpretation of results)
- Conclusion
- Implications (applied in practice)
What type of research describes a state of nature at a point in time and establishes associations among factors, but does NOT prove cause/effect.
Descriptive research
Qualitative research, case report, and surveys are what type of research?
Descriptive research
Research designed to describe and quantify characteristics of a defined population and defined time frame; pinpoints problems.
Surveys
Type of research that tests hypotheses concerning the effects of specific factors of interest and allows cause/effect relationship to be determined.
Analytical research
Experimental model, Quasi-experiemental design, cohort studies, case control studies and cross-sectional studies are what type of research?
Analytical
The _______ model uses experimental and control groups. The control does not receive treatment or receives a placebo.
Experimental model
The Quasi-experimental design involves _____ _____, which is a series of measurements at periodic intervals before and after the program. It shows whether measurements before and after are a continuation of previous patterns or whether they indicate noteworthy change.
time series
This type of study follows a group through a time to see if they develop a specific disease. It’s sometimes called incidence studies tracking the frequency of new cases of a disease.
cohort studies
These studies focus on a specific disease. Those with the disease are compared to those without the disease, but have similar characteristics; studies how they differ.
case control studies
This study collects data ONE time. It is sometimes called prevalence study (ALL cases of a disease among a group in a specific time); gives a snap-shot look at one particular time period (present time, not past).
Cross-sectional study
The ability to measure phenomenon it intends to measure.
relevance or validity
______ validity tests whether the difference between the two groups is real (has the experiment group really performed differently).
Internal validity
______ validity tests whether or not a generalization can be made from the study to a large population.
external validity
ANOVA
Analysis of variance; tool used to evaluate validity (need >2 samples).
*used when several products compete against one another.
Consistency or reproducibility of test results
Reliability
Variables that fit into a category with no special order (gender, race, marital status)
Nominal variables (non-ordered)
variables that are compared with each other and put in order, perhaps from best to worst, state of disease from 1-4)
Rank order (ordinal scale)
______ variables are outcomes.
______ variables are what you manipulate in your study.
Dependent; Independent
*effect of cholesterol levels (independent) have on heart attacks (dependent)
Simple average of data
arithmetic mean
-total the values of all observations and divide the # of observations
Value at the midpoint
Median
- if there is an even amount of numbers, the median is the average of the 2 numbers closest in the center
- ex. 12 15 17 19 21 23 24 24 30 32 (median is 22)
Most frequent occurring value; prediction most likely to be right.
Mode
*if there is no # repeated, there is no mode.
Difference between the lowest and highest values in the distribution.
Range
*Subtract lower from higher value
Most significant measure of distribution; indicates degree of dispersion about the mean value of a distribution.
standard deviation
- has curve of normal distribution as it falls away from its peak on either side.
- distance between the mean and the point of inflection on either side is = to SD.
About 2/3 (68%) of all observations in a normal distribution lie within ___ SD of the mean.
1 SD
- 32% lie outside the range (16% below, 16% above the range)
- 95% lie within 2 SD either side of the mean
The closer the points to the line, the stronger the degree of ______ relationship. This is called ______ _______ ______.
linear relationship
linear correlation coefficient (r)
There is no linear relationship if r= ___.
0
Perfect positive correlation is ____. Perfect negative correlation is ____.
+1; -1
The lower the p value, the HIGHER/LOWER the significance of your results.
HIGHER
What does p < or = 0.05 indicate? <.0001?
significant difference, results are reliable
very, very significant difference, reliable results