Chapter 13: Research and Data Analysis

Agency for Healthcare Research and Quality (AHRQ): Federal agency within HHS whose mission is to make healthcare safer, higher quality, more accessible, equitable, and affordable, and to work within HHS and with other partners to make sure that the evidence is understood and used 

1. Improving healthcare quality by accelerating implementation of patient-centered research (PCOR). This priority is being met through the Patient-Centered Outcomes Research Institute (PCORI) which provides funding to researchers to perform research that is patient-centered and patient-engaged

2. Makes healthcare safer by preventing healthcare-associated infections (HAI), accelerating patient safety in healthcare organizations, reducing harm associated with obstetrical care, improving safety and reducing medical liability, and accelerating patient safety in nursing homes

3. Increasing accessibility to healthcare

4. Improving healthcare affordability, efficiency, and cost transparency through improved data measures and public reporting strategies

Aggregate data: When individual, comparative, or other multiple sources of data are compiled and analyzed to draw conclusions about a specific topic or area

1. Ex: A focus group study, data, observation, and interview data were compiled into an aggregate format so that none of the individuals in the multiple healthcare organizations that participated could be identified

Bar chart: Simple chart used to describe qualitative, categorical, or discrete variables such as nominal or ordinal data—important to know the audience, keep it simple, and make it colorful, and concise

Box-and-whisker plots: visually summarize several main factors: median, range, and outliers—the line coming from the boxes are termed “whiskers” and illustrate the range of data values—can be used to provide a visual comparison of multiple data sets in a succinct way—provides information on the range of data results

1. Ex. The results of a patient satisfaction survey that had questions with a possible scaled response, such as highly agree, agree, neutral, disagree, and highly disagree

Bubble charts: a scatter chart except that it compares 3 data variables—can illustrate more data if that meets the needs and focus of the situation

1. Ex. Healthcare organization is reviewing the socioeconomic levels of its patients and the cost of their care during inpatient admissions, a bubble chart can show 3 data points: income, cost, and the relationship to the patient’s personal income—- The larger the bubble the more that group of patients had to pay for their hospital admission in relation to their income 

Centers for Disease Control and Prevention (CDC): US government agency whose mission is to collaborate with the public to create the expertise, information, and tools people and communities need to protect their health, through health promotion, prevention of disease, injury, and disability, and preparedness for new health threats 

Chart: generally display nonquantitative information such as the flow of subjects through a process 

Comparative data: when individual data is organized numerically and collated to evaluate against standards or benchmarks 

Confounding factors: those characteristics other than the characteristic of interest that may also be related to the disease under study 

Continuous variable: any numerical value that goes from one whole number to the next whole number— An example would be weight/patient’s height 

Correlational studies: similar to descriptive studies except that the correlational study determines if a relationship may exist between two variables—to determine which variables are connected in some way 

Descriptive statistics: include frequencies, percentiles, measures of central tendency (mean, median, mode) and measures variability (range, variance, and standard deviation)—used to give information on data and for organization and summarization—generally does not provide information on data relationships 

Descriptive studies:  include research that is exploratory in nature and generates new hypotheses from the data collected

1. Ex. A descriptive study approach was used to explore how the use of automated coding software (CAC) could be used to enhance anti-fraud activities

Ethnography Experimental study: a methodology where the researcher delves into a particular culture or organization in great detail in order to learn everything there is to know about them and to develop new hypotheses—not objective and includes opinions of the researcher 

Graph: data presentations that show the relationship of the included variable

Histogram: a graph that represents the frequency distribution of numerical data— a visual display of data that demonstrates where data falls— should be used with continuous data that is part of a frequency distribution

Independent variable: defined as a research element that is changed or controlled by the research environment or the researcher

Individual data: healthcare data that is housed within the EHR, or data collected from a case study, a focus group of individuals, or during the interview or survey— can be helpful in providing direct care to patients, and for quality improvement studies or for larger descriptive studies 

Inferential statistics: techniques that can be used to make deductions based on the evidence of the data and reasoning—the process of making deductions for a larger population based on the statistical results taken from a sample 

Institutional Review Board (IRB): one that protects human subjects involved in research activities— determines whether research conducted on human subjects is appropriate and protects the participants’ rights—major focus is not whether the research is appropriate for the org or researcher to conduct, but that it contains all the appropriate protections for human subjects involved in the research 

Line graph: graphical device used to display continuous data and to show changes or trends of the data over time—x-axis from left to right, designates time and the y-axis shows the quantity of the plotted data—best to use when there are many different data points or more than one set of data to plot, multiple lines can be put on one graph for very useful comparisons

Mean: the average of a group of numerical values 

Measures of central tendency: include the mean, the median and the mode-defined as representing “the clustering of the majority of a data set’s values around its middle value” 

Measures of variability: examine the spread of different values around the measure of central tendency-include range, variance, and standard deviation 

Median: the value in which there is the same amount of numbers above and below; middlemost value when arranged in numerical order 

Mixed-methodology Mode: includes using both quantitative and qualitative data in a research study design; involves intentional collection of both quantitative and qualitative data in order to combine the strengths of both to answer the research question 

Nominal variables: those in which a number is assigned to a specific category such as 1=male and 2=female 

Normal distribution: if data follows a symmetrical or bell curve; the mean, median, and mode are equal

1. the appearance of a bell-shaped curve that is symmetrical about the mean and extends infinitely in both directions

2. the total area under the curve equals 1, to the area of one half of the curve is equal to 0.50 and the other area of the other half is equal to 0.50

3. being defined by two parameters: the mean, m, and the standard deviation 

Ordinal variables: ranked variables in which numbers are assigned to rank a category in an ordered series, but the numbers do not indicate the magnitude of the difference between any two data points

1. Ex. patient satisfaction the wait time to see your physician 1=strongly agree 2= agree 3= disagree and 4= strongly disagree 

Pareto chart: similar in appearance to a bar chart, but the highest ranking value is listed as the first column, the next highest ranking is second, and so on, to the lowest ranking—created by Vilfredo Pareto and is based on his theory that “the significant few things will generally make up 80 percent of the whole, while the trivial many will make up about 20 percent— show data in terms of arranging it into categories and then ranking each category according to its importance 

Percentile: is a measure used in descriptive statistics that shows the value below which a given percentage of scores in a given group of scores fall 

Pie chart: simple graphs that use slices of the pie to explain numerical proportion in relation to the whole, or 100%—- not the best format when comparing data elements or when using many data elements because the slices of the pie can become too small to interpret

Qualitative research: designs involve collecting types of data that reflect a participant’s perceptions, feelings, or attitudes about a certain subject  

Qualitative variables: categorical, meaning that the variable is from a specific category or group such as gender or age, eye color— given or assigned to items that are not numerical, cannot be subdivided into nominal or ordinal type

Quantitative study: research results that are numerical in nature and can be illustrated with descriptive or inferential statistics—include descriptive, correlational, retrospective, prospective, and experimental and quasi-experimental 

Quantitative variables: numerical variables that can be classified as discrete or continuous 

Quasi-experimental study: similar to the experimental study except that randomization of participants is not included in a quasi-experimental study-also the researcher may not manipulate the independent variable and there may be no control or comparison group—can be performed over time and may not include individual participants

Range: the simplest measure of variation to compute and is calculated by taking the difference between the highest and lowest values—quick and easy to do, but not that useful since it only considers extremes and not the entire sample of data values  

Regression equations: simple, multiple, logistic, multinominal, and multiple logistic— used to determine if there is a relationship between variables and to identify what type of relationship is present —can be used to find trends  

Research methodologies: can be used to perform research on healthcare and HIM topics  

Retrospective study: also called case control studies, by reviewing records and asking the subjects to recall past events in order to determine the presence or absence of the independent variable under study 

Scatter charts: scatter plot, scatter diagram, or scatter graph is used to demonstrate a relationship between two variables—  

Standard deviation: the measure of variability that is used most often and displays how data are related to the mean