D514

Multiple regression

The purpose of multiple regression is to determine the relationship between several independent or predictor variables and a dependent variable. Involves the use of more than one independent variable to predict the response or dependent variable. This approach allows for a more comprehensive analysis, considering the simultaneous impact of multiple factors on the outcome. Predicting a student's academic performance using multiple variables such as study hours, sleep quality, and attendance.

Autonomy

The right for a person to participate as a human subject or not. In healthcare, it refers to a patient having the right to make their own choices, unless they have been legally deemed unable to do so. Ex: Statement from physician to his nurse: "I think moving into assisted living would be best for Mr. Smith at this time, and so does his daughter, but I don't think he sees it that way. I'm concerned about his balance and how slowly he is walking now. "

Categorical variable

The value is in the name or label. Types of cancers (breast, skin, lung, etc) are categorical variables.

Analysis Plan

The what. What statistical test will be performed after the data is gathered to evaluate/analyze the data EX: Analysis Plan: Employing regression analysis to analyze the relationship between treatment variables and patient outcomes.

Disease Registries

These are a hybrid between transaction systems and data warehouses. They are designed for tracking explicitly defined data at a case-specific level. Some examples are trauma registries to track emergency department data, cancer registries, immunizations registries, and numerous others.

Data warehouses

These assimilate data from multiple transaction systems. Data warehouses can be used to distinguish larger trends in data from multiple sources. Used for advanced data mining. Hold huge amount of data. Mostly used where organizations join to share information (health exchange, etc). What you see in movies with huge server facilities.

Experimental Group

This group receives the treatment being studied with follow-up observation to determine the effect of the treatment.

Transactional database

Used for online transactions, such as retrieving real-time lab values for your patient. Has capacity to roll back to originally stored information due to power loss or hacking Ex: amazon

Nonparametric tests

Used when data are not normally distributed. Statistical tests that make no assumptions about the parameters of the population distribution(s) from which the data are drawn. Also known as distribution-free tests, non-parametric tests do not rely on specific distributional assumptions and are considered more robust when dealing with non-normally distributed data or ordinal variables. These tests are suitable when the requirements for parametric tests cannot be met. Example: Employing the Wilcoxon rank-sum test to compare the medians of two independent groups when the assumption of normality is questionable.

Methods section components

When analyzing the quality of a study, a careful evaluation of the research methods can reveal critical details about population and sample, covariables and hypothesis, data presentation, statistical analysis, and study limitations.

Factor analysis

a process in which the values of observed data are expressed as functions of a number of possible causes in order to find which are the most important. Example: I want to rank the reported reasons of nursing turnover in terms of frequency. In cardiovascular research, factor analysis might be applied to understand the key contributors to myocardial infarctions. Analyzing factors like smoking, overweight status, minimal exercise, and job-related stress could reveal which of these variables have the most substantial impact on the occurrence of heart attacks in a studied population.

Bayesian Approach

advanced mathematical process that applies probabilties to statistical problems. Provides the tools needed to update research beliefs in the evidence of new data or outcomes. Need a computer to run. Updating beliefs about the effectiveness of a medical treatment based on new clinical trial results.

Ordinal Data

can be measured as a frequency, and the mean of ordinal data is often calculated. Ordinal data in healthcare might include patient satisfaction surveys using a Likert scale. The word ordinal means to "put in order" Ordinal Data: data found in a Likert scale; pain scale; stages of cancer; trimesters of pregnancy. Ordinal Variable is a type of variable where the order or ranking of values matters, but the differences between values may not be uniform. In ordinal variables, the intervals between values are not consistent. An example is a pain scale where the order of pain severity matters, but the difference between a rank of "7" and "5" may not be the same as between "5" and "3".

Health disparities

differences in the incidence, prevalence, mortality, and burden of diseases. They are frequently seen in subpopulations based on socioeconomic status, geography, race, ethnicity, sexual orientation, or special needs

Ratio Data

divide one quantity by another, and you have a value. You will have a proportion, a percentage or a rate. UTI rates at a nursing home; male-female proportion of a disease; percentages of hospital readmissions; rates of MVA injuries compared to other E.D. admissions. Rates

Meta-analysis

easiest to think of this as a literature review with action. Reading about artificial intelligence in healthcare to create a new diagnostic tool. Literature review + verb

Outcome Evaluation

focuses on the end result of a specific program or initiative, generally clinically measured by improvements in morbidity, mortality, or vital measures of symptoms, signs, or physiologic indicators.

Independent variable

has an effect on dependent variable. It is what you are controlling. Investigating the effect of a new drug dosage (independent variable) on blood pressure (dependent variable) while keeping other factors constant.

Interval Data

includes units of equal size, such as IQ results. There is no zero point. An example of interval scale is time: Time is measured in 24 hours in each day; the time between each hour is the same, 60 minutes.

Risk adjustment

is essential for comparing data across systems, especially among patients with varying comorbid diseases and complex treatment modalities. Multivariate regression analyses can be used to analyze and adjust risk. This analysis model looks at each measured factor to the patient's risk of a particular outcome.

Pearson's Correlation

is used with the interval and ordinal scale data and determines the extent to which a change in one variable tends to be associated with a change in another. aka correlation coefficient As people age, their likelihood of having arthritic changes increases. (positive correlation) As people increase their exercise activity, their weight decreases. (negative correlation) Many research studies over the years have proven a strong correlation between cigarette smoking and lung cancer. (positive correlation)

U-test

known as the mann-whitney u-test, the mann-whitney-wilcoxon (MWW), the wilcoxon rank-sum test, or the wilcoxon two sample test. Used when we think we are comparing apples to apples but we arent sure. Patient surveys to determine preferences of where to see their doctor: in his hospital offices or at outpatient facility. Determining attitude of patients in using new patient portal. A non-parametric statistical test used to compare two sample means derived from the same population. It is employed when data is ordinal or when the assumptions of the independent sample t-test are not met. The Mann-Whitney U test is particularly useful for clinical trials, comparing the effectiveness of two treatments when the data does not meet parametric assumptions. In a clinical trial comparing the effectiveness of two medications, the Mann-Whitney U test could be used to analyze ordinal data related to patient outcomes. For instance, assessing pain levels on an ordinal scale between patients treated with Medication A and Medication B. The Mann-Whitney U test provides a non-parametric approach when the assumptions of a t-test cannot be met.

Literature review

learning for learning's sake. Example: reading about artificial intelligence and uses in healthcare.

Frequency

measure how often a particular value occurs to assess the importance of a value or check the variation of the values in a study.

Quality improvement

measured internally and externally using various benchmarks and indicators. These indicators are quantified by proportions, percentages, ratios, means, medians, and counts to measure processes, perspectives, and outcomes aligned with a certain initiative or decision.

Confounding variable

obscures the effect of another variable. An example is you find out that four research participants did not disclose that they are taking blood pressure medication. Or, another example is the individual who developed bell's palsy after the COVID vaccine. It was going to happen regardless. Variables that may obscure the effect of the independent variable on the dependent variable. These variables, often uncontrollable by the researcher, introduce additional factors that may impact the study's outcomes. In the exercise and weight gain example, food consumption, pain, and weather are potential confounding variables that can influence the relationship between exercise and weight gain.

Focus Group

research study of a demographically diverse group of people assembled to participate in a guided discussion about a particular product or process. An example would be a healthcare organization wants to ask its nurses their opinion on a new staffing policy. A healthcare organization holds focus groups with the first 100 patients who sign up for its patient portal, to determine their satisfaction with the portal and gather ideas for changes.

Case Study

researchers investigate one person, one group, or one institution in depth. Most often seen in professional journals and often focuses on a particular problem and how it was solved. Example: in future course you will study Sentara Health and how it managed to become one of the first integrated delivery systems. Example: A case study is performed at a nursing home which studies the impact that therapy dogs have on the emotional state and mood of its residents. Case study: investigates one person, one organization, one group in depth. Non-participant observational. Researcher does not interfere with the subject. Often in 'natural' setting. May include document or chart review.

Regression Analysis

statistical process for estimating the relationships among variables. Techniques for modeling and analyzing multiple variables at one time. For example, we know that age, sex, weight, and family hx are all associated with the likelihood of developing diabetes. However, considering only one of these predictors is not sufficient. It is the combination of them that produces the greatest predictive value. Tip: in the exam, look for scenario word clues such as "related to" "associated with" "linked" etc. The Framingham Calculator is an example of regression analysis applied in healthcare. It considers multiple factors (age, sex, cholesterol levels, smoking, blood pressure, etc.) to predict a patient's 10-year risk of a heart attack. Another example could be studying the relationship between various lifestyle factors (diet, exercise) and weight loss. The analysis would involve multiple predictors to understand how each contributes to the overall weight loss outcome.

Needs Assessment

the process of collecting and analyzing information about a specific population, enterprise, or cohort to gain stakeholder insight into cultural engagement. It may also identify coalition strengths, weaknesses, opportunities, issues, available resources, and constraints or barriers. The needs assessment supports clear direction for decisions involving development of a specific health initiative or program.

Mode

the value that occurs most frequently in the data. Think most

Control Group

this group of patients does not receive the treatment that is being studied

Cross-Sectional

type of research study, analyzes data collected from a population or subset at a specific point in time. The amount of data to be pulled is pre-determined and can be as big or small as warranted. Type of observational study, analyzes data collected from a population or subset, at a specific point in time, that is, cross-sectional data. AKA Prevalence study: analyzes data from a specific point in time

Risk stratification

used to classify patients into level of risk Example: fall risk- categories of high, medium, and low Strata is the root word of stratification and it means to layer. We want to subdivide (layer) the study population into categories related to risk. Allows us to determine disparities within groups or to allow us to monitor effectiveness of interventions. Used to estimate costs, gauge healthcare literacy, and overall resource usage.

z-test

used to determine whether two population means are different when the variances are known and the sample size is large (n >30). A statistical test utilized to assess whether there is a significant difference between two population means when the variances are known, and the sample size is large. The Z-test is based on the standard normal distribution and helps researchers make inferences about population parameters. Comparing the mean test scores of two different groups of students from large populations to determine if there is a significant difference in academic performance.

Dependent Variable

what is going to change (or not) as a result of research or intervention Example: you are researching whether a new exercise machine has an effect on lowering blood pressure. The independent variable is the exercise machine and blood pressure is the dependent variable.

Stratification Analysis

A process of dividing members of a population into homogenous subgroups before sampling. Example: comparing a new surgical intervention to conventional surgery. Place them into two groups. Note: strata in geography means layers. Hence, stratification is the process of layering (grouping) individuals. Separate out the gender. Dividing members of the population group into similar subgroups before doing any sampling. For research on patients who underwent cardiac rehabilitation, stratification analysis may involve dividing the population into subgroups based on gender. This approach enables a more detailed analysis of the rehabilitation outcomes and experiences, considering potential gender-specific factors that might influence the effectiveness of the rehabilitation program.

Hypothesis

A proposed explanation for an observation that leads to a prediction. Through investigation and the use of statistical data, those doing the study will either confirm or reject the hypothesis. Testing the hypothesis will show if there is a link (or not) between two or more variables.

Cohort Study

A study normally used to investigate the causes of disease or establishing links between risk factors and health outcomes. Forward looking, prospective study, planned in advance and carried over a future period of time (longitudinal study). Example: researchers want to follow 5000 individuals with a family history of dementia. They may send annual surveys to track lifestyle (diet, exercise, medications), work history, social history, over a period of 20 years to determine the effect that genetics has in developing disease or if certain lifestyle choices helped to mitigate development. Ex: a healthcare question you are going to ask over time. The method is longitudinal. establishing links between risk factors and health outcomes. Prospective or retrospective Example: First Responders who survived the 911 Terrorist Attack may be tracked over the years for the development of respiratory illnesses.

Databases

A well-designed healthcare database captures data to support the organization's analysis and comparison of safety, quality, effectiveness, timeliness, and efficacy of actual care and services delivered to the patient. Driven from the terms themselves relational database is able to maintain data according to relational paradigm while transactional database is one able to transform data within transactions. (ex: lab results). (ex: Amazon) Data Warehouse for storage and data mining for reports, different facilities. Disease Registry (Trauma registry): secondary data. Object-oriented database: text, audio, video, images

AHRQ

Agency for Healthcare Research and Quality: mission is to produce evidence to make healthcare safer, higher quality, more accessible, equitable, and affordable.

Qualitative Research Methods

Aimed at understanding perceptions, perspectives, interpretations, and opinions. Often includes questionnaires, interviews, and written documents, observations, and focus groups. Ex: Conducting interviews with participants to explore their perceptions and experiences of a particular health intervention. Involves the analysis of non-numeric data, describing observations, experiences, or phenomena. Qualitative research relies on methods such as interviews, observations, or content analysis to gather and interpret subjective information. The data is often categorized before summarizing, allowing for a deeper understanding of complex and context-specific phenomena.

De-identified

All participant information is removed. Used for anonymity when data reports need to be shared with external stakeholders. Ex: removing last names, ssn, addresses, etc.

Dichotomous variable

Also known as binary variable. It occurs in two possible states. For example, a patient is either diabetic or non-diabetic.

Continuous Variable

Also known as the interval variable. Meaningful difference between values. Temperature scales are an example. We all know what is meant by a 10-degree temperature change. A variable measured on the interval or ratio scales.

ANOVA

Analysis of variance (ANOVA) may be used in research studies where there are three or more groups to compare. Stands for analysis of variance. The ANOVA test is similar to the independent-samples t-test. It is used as a test to compare means between independent variables with similar variance and normality of distribution. Whereas the t-test compares just two means, an ANOVA test can be used to compare multiple groups. Example: Researchers are performing a randomized clinical trial evaluating the effectiveness of three distinct treatments for painful TMJ clicking. 60 patients were randomly assigned to 3 treatment options: (A) anterior positioning splint therapy; (B) physical therapy; (C) physical therapy and splinting. Similar to the t-test in that patients are all from same type of distribution (they have the same medical diagnosis) but there are more than 2 treatments in the experimental study.

Categorical Variable

Assume values that are names or labels. Eye color (e.g., green, blue, brown) or breed of dog (e.g. pitbull, shih-tzu, etc)

Parametric Tests

Based on probability distribution. Statistical tests that make assumptions about the parameters of the population distribution(s) from which the data are drawn. These tests are based on specific distributional assumptions and are used in inferential statistics. Parametric tests are sensitive to the underlying distribution of data and are applicable when certain conditions are met. Parametric: summarizes a population (the entire group you are interested in investigating) Using a t-test to compare the means of two groups when the data are assumed to follow a normal distribution.

Nominal data

Can be measured as a frequency or percentage, and the mean of these data cannot be calculated. Nominal data in healthcare might include demographic data about patients. The work nominal means "pertaining to name" Names (category) Nominal Data: various cancer types; different insurance companies; physician specialties offered at a clinic; types of medical units in a hospital (ICU, pediatrics, med-surg)

Multivariate regression analyses

Can be used to analyze and adjust risk. This analysis model contrasts each measured factor to the patients risk of a particular outcome.

CMS

Center for Medicare and Medicaid Services: division of DHHS. Develops healthcare policy and administers Medicare and the federal portion of Medicaid.

CDC

Centers for Disease Control: wealth of information related to morbidity and mortality. Numerous interactive database systems that contain updated data related to various topics; including chronic disease, global health, HIV, infectious disease, and vaccinations.

CLABSI

Central Line Associated Bloodstream Infection. Laboratory confirmed bloodstream infection that develops within 48 hours of central line placement.

Beneficence

Concerns the welfare of a research participant, but it can also apply to the treatment of patients. The opposite term, 'maleficence,' describes opposing the welfare of the research participant. You may also see a term, 'malfeasance,' which is intentional conduct outside the law. Helping the patient is the goal Ensuring that participants in a medical study receive the best possible care and protection of their well-being throughout the research process. Ex: The ethical concept emphasizing that researchers should prioritize the well-being of research participants in any clinical trial or research study. It advocates for actions that contribute to the welfare and improvement of the participants' conditions. The opposite term, maleficence, describes practices that harm the welfare of research participants, while malfeasance refers to intentional conduct outside the law.

Longitudinal Study

Data gathered on same subjects over a lengthy period of time. Can detect changes in the subjects to look for cause and effect Involves repeated observations of the same variables over long periods of time. It is often a type of observational study Ex: cohort study

Relational Database

Data stored in various tables where each table has a field that connects it to other tables. Example of student schedules (student list, course list, instructor room, etc. ) or address change in a system.

Multidimensional

Database: capable of processing large amounts of data quickly. Used for reports needed now. Stored viewed and analyzed from different perspectives. These perspectives are called dimensions. We can share this, we can have different users in there working on different components. Used to generate reports. Ex: WGU, insurance company (big companies)

Chi-Square Test

Determines if an association exists between two categorical variables. Qualitative in nature. Tests for relationships between categorical variables. Chi Square is used when you are comparing values you can observe with those you expect. • Chi square is a group of tests generally used with qualitative or non-normal data. There are chi-square tests that can be used to compare independent measures as well as tests to look for differences or for relationships Example: The owner of a laboratory wants to keep sick leave as low as possible by keeping employees healthy through disease prevention programs. Many employees get flu in the winter months, leading to productivity problems due to sick leave from the disease. There are many sources for flu vaccine today, and the owner believes that it is important to get as many employees vaccinated as possible. Due to a regional shortage, there was only enough vaccine for half the employees, last flu season. In effect, there are two groups; employees who received the vaccine and employees who did not receive the vaccine. The company sent a nurse to every employee who calls in sick with flu, to provide care if needed, and provide a nursing assessment. They kept track of the number of employees who contracted flu and the severity of symptoms.

Standard Deviation

Determines the amount of variance in a set of data and evaluates the degree to which each case deviates from the average, or mean. We're looking at the data and how far it is from the average (the mean).

Transaction Systems

Divide data according to individual operations. The data stored by transaction systems is granular and based on specialized systems.

Outcome evaluation

Focuses on the end result of a specific program or initiative, generally clinically measured by improvements in morbidity, mortality, or vital measures of symptoms, signs, or physiologic indicators.

Predictive Study

Forecasts outcomes, consequences, effects, costs. Analyzes existing data to make prediction.

HRSA

Health Resources and Services Administration. Agency within the DHHS (Department of Health and Human Services). Primary federal agency for improving healthcare to people geographically isolated, economically or medically vulnerable

T-Test

Helps the researcher to compare whether two groups have different average values. A paired t-test is used when each observation in one group is paired with a related observation in another. Compares the mean score of a sample to a known mean T test is used when we know we are comparing apples to apples. Example: comparing Hillcrest High School (in Utah) senior ACT scores to the national average. t-test: compares average (mean) of the score/result. sample size is small (n < 30) t-test looks for differences

HCAHPS

Hospital Consumer Assessment of Healthcare Providers and Systems. Patient satisfaction suvey required by CMS for all US hospitals. Contains 29 questions about recent hospital stay.

Object-oriented

In addition to text, can store audio, video, images, other 'objects' Ex: electronic health records

Quality Measures

In today's healthcare environment, administrators receive numerous quality reports on a regular basis. These reports are generated for internal quality improvement projects, for mandated external reports to government agencies, and for compliance with accrediting body requirements. As a value-based purchasing model evolves in healthcare, quality measures become pivotal operational "pulse checks" to administrators.

Errors

Incorrect application of a statistical test can result in a type 1 error, which occurs when a null hypothesis is rejected when it should have been accepted. A type II error is experienced with the alternative hypothesis is rejected when it should have been accepted.

Cancer Registry

Information system used to collect, analyze, and manage data on persons with malignant or neoplastic diseases. Used for public health and CDC.

Trauma Registry

Information system used to collect, analyze, and manage data on trauma patients. Used to improve emergency care, track trends. Also considered a disease registry

Misleading statistics components

Interpreting and presenting the results of data analysis affords many opportunities for accidental or deliberate misrepresentation of the data. Common examples include implying causation, extrapolating beyond the reasonable, relying on a biased or incomplete sample, and using inappropriate graphical representations.

Market Sementation

Market or population segmentation is used to divide the defined community, group, or cohort into aggregate domains of shared traits. The intent is to optimally understand specific needs and further customize care and services.

Measurement and decision support

Measurement is used to monitor quality improvement in systems and processes, analyze current trends, evaluate performance, and—when results are gathered—to place accountability. New knowledge is built on research. Decision support provides an information platform to evaluate leading, lagging, and real-time performance measures.

Measurement and decision support

Measurement is used within an organization to monitor improvements in systems and processes through analysis of current performance trends, identify key opportunities, and consider leading practices informed by new research-based knowledge. Decision support provides an information platform to evaluate leading, lagging, and real-time performance measures.

MEPS

Medical Expenditure Panel Survey: Large-scale survey of families and individuals, their medical providers, and employers. Most complete source of data on cost and use of healthcare and insurance coverage.

NPDB

National Practitioner Data Bank: web based repository of reports containing information on medical malpractice payments, and certain adverse actions related to healthcare practitioners, providers and suppliers. Used when on-boarding physicians or making injuries. ( it is a source of data)

Quantitative Data

Numeric (measurable, graphs, tables, etc), verifiable, accurate (value of the data is in the number). Examples are sample size (n), mean, median, mode, range, standard deviation Involves the analysis of numeric data, employing statistical methods to draw conclusions and make inferences. This type of research focuses on quantifiable variables and aims to measure and quantify relationships between variables, providing numerical insights. Analyzing survey responses with numerical ratings to understand the correlation between customer satisfaction and product features. Conducting a clinical trial to measure the effectiveness of a new drug by quantifying changes in patients' health metrics such as blood pressure, cholesterol levels, and heart rate.

Research identified

Participants normally identified through a number. Key system. Participants are numbered.

Justice

Pertains to the fair selection of research participants. The ideal distribution of risks and benefits when conducting clinical research and recruiting volunteer research participants to participate in clinical trials. One example of the principle of justice seen in the US is when citizens turn 65 years of age, they are eligible for Medicare, no matter who they are or their socioeconomic level. Ensuring that research participants in a clinical trial are selected without discrimination and that the risks and benefits of participation are distributed fairly among diverse populations.

Plagiarism Avoidance

Plagiarism is the uncredited use of someone else's words or ideas. A charge of plagiarism to a researcher may have serious consequences, including loss of a job or expulsion from a university, and will result in loss of standing in the professional community.

Reliability, Validity, and analysis of questionnaires

Questionnaires can be evaluated for reliability based ont heir consistency (stability) or repeatability over time; questionnaires are valid if they measure or record what they purport to measure. Data from questionnaires may then be grouped according to nominal, ordinal, or interval or ratio data.

Fidelity

Requires loyalty, fairness, truthfulness, advocacy, and dedication to patients (and others). It involves an agreement to keep promises, to keep a commitment, and is based on the virtue of caring. This principle would include patient advocacy. Keeping a promise to a patient about a specific treatment plan and advocating for the patient's rights and well-being during the healthcare process. The ethical principle that demands loyalty, fairness, truthfulness, advocacy, and dedication to patients. Fidelity involves the commitment to keeping promises made to patients, and it is rooted in the virtue of caring. This principle also encompasses patient advocacy, ensuring that the healthcare provider acts in the best interests of the patient.

Research Components

Research Design (How) Study Population (Who) Data Collection (Where) Analysis Plan (What)

Integrity

Research always makes some assumptions, depending on the type of method used. Research assumptions must be identified to determine possible breaches of integrity.

Time-Series

Research study method for analyzing a sequence of data taken at pre-determined points in time. Does not always need to be "neat." We use multiple cross-sectional data pulls to achieve our analysis. Examples: weekly for 12 weeks, quarterly for 3 years, or weeks 1, 7, 10, 13, 18, 22 For example, a QI team pulls quarterly reports, over a period of three years, to compare the number of patients with asthma who were treated in the emergency department.

Healthy People 2030

Sets data-driven national objectives for a variety of factors. Covers health disparities, social determinants of health, and a vast amount of tools and resources

Flat File

Single table database. Multiple users cannot access and view simultaneously. Doesn't support large amounts of information. Very simplistic, almost like a notepad or spreadsheets

Measuring effectiveness of treatment

Statistics are necessary to measure and compare treatment outcomes. Statistically analyzing the effectiveness of treatments is the optimal method to determine validity for adoption.

F-test

The F-test is designed to test if two population variances are equal. The ratio of the two variances is compared. If they are equal, the ratio of the variances will be 1. For equality of variance: It is most often used when comparing statistical models that have been fitted to a data set, to identify the model that best fits the population from which the data were sampled. Ensuring two samples are 'not statistically different'. Two population variables are equal. Rules for tests F, z and t: dependent variable must be measured on the interval scale; samples must come from normally distributed population; for tests z and t, the variance of the samples must be equal.

Research Design

The How. The type of study that is being done. How the research is constructed. Plan to achieve the researcher's purpose. Ex: - Research Design: Choosing a longitudinal study to assess the long-term effects of a medication on a specific patient group.

Data Collection

The Where. Where is data coming from to support the research? Sources of data - Data Collection: Utilizing patient records and disease registries to gather information on treatment outcomes and medical histories.

Study Population

The Who. Who is being studied - Study Population: Researching patients with diabetes between the ages of 50 and 70 to examine the impact of a new treatment.

Mean

The arithmetic average. Divide the sum of all scores by the total number of scores.

Statistical testing and treatment

The basis of statistical testing is whether or not the study results have a proven relationship to a change in processes or care modalities. Results that are statistically significant do not automatically indicate clinical significance.

Sample size

The design of the study provides insight into an appropriate number and volume of each variable. The calculation of statistical confidence factors informs the validity testing of the study sample size. Is usually expressed as a count and often includes the total number of subjects in a study The number of subjects in each group, and other counts (such as the number of males and females, the number within each age group, etc.

Variables

The independent variable is the factor that is directly manipulated by the researchers. The dependent variable is the measurable variable that depends on the independent variable.

Median

The midpoint of the distribution of values, or the point above or below which 50 % of the values fall.

Statistical significance

The observation is statistically significant if the null hypothesis is rejected. In a research study, the null hypothesis states there is no association between the independent and dependent variables in a study.

p-value

The probability level which forms basis for deciding if results are statistically significant (not due to chance). The p-value is the level of probability. In research, the lower the p-value, the less probability that the results of your research occurred 'by chance'. You want low probability.

Forecasting

The process of predicting outcomes and needs to create systems and models with the highest financial and operational safety and efficiency; it can be used to determine the potential use of services and patient demand, or to expand service lines and markets.