HA535 Data Analytics for Health Care Managers - Units 1-4 Flashcards

Question

What research is based on a constructivist or naturalist approach and began as a countermovement to the positivist paradigm where, to the researcher, reality is subjective and seen through the eyes of the participants of the study?

Answer 1

Qualitative research. The process is inductive in nature, and patterns or theories are developed through the research process.

Answer 2

A3 B4 C1 D2

Answer 3

Combining the Two Methods [Information] Mixing of quantitative and qualitative methodologies is a possibility in any given study. Involve the use of observation to address research questions. Both methodologies "describe their data, construct explanatory arguments from their data and speculate about why the outcomes they observed happened as they did" (Sechrest & Sidani, 1995, p. 78) * Use techniques that are relatively analogous at some level of specificity, such as triangulation. * Try to discover meaning from the interpretation of data. * Use analytical techniques in an attempt to explain complex relationships in the social science world (Dzurec & Abraham, 1993; Sechrest & Sidani, 1995). * Utilize techniques to verify their data. * Use data reduction as an important part of the data analysis process. * Promote the role of theory by testing theory (quantitative methods) or initiating and building theory (qualitative methods). * Can use the same collection of data to get results (Onwuegbuzie & Leech, 2005, p. 380). There has been a growth in the mixing of quantitative and qualitative approaches in the twenty-first century, as researchers look to all available research techniques to address the research questions, rather than promote a preconceived bias toward one methodology or another

Answer 4

* One-third introduction and literature review that includes complex and important topics facing scholars and policymakers and the state of current knowledge about those topics, * One-third research procedures and findings, which includes the sampling design, research design, measurement, statistics, and the proper reporting of research evidence obtained, and, * One-third discussion and implications, which encompasses synthesis and integration of findings obtained from the present investigation within the context of existing knowledge (Smart, 2005, p. 463).

Answer 5

A literature review is a review of the literature that informs the research project. The literature review presents a theoretical background and a review of other studies that are closely related to the study that the researcher is developing; makes connections to the dialogue about the topic that may be appearing in literature; provides a framework for the researcher's study; and acts as a benchmark for findings that the research will reveal

Answer 6

Typical Quantitative Research Project Format (Informational) Creswell (1994) outlines a typical quantitative research project format, including the following segments: * Introduction: * Context (Statement of the problem) * Purpose of the study * Research questions or objectives or hypothesis * Theoretical perspective * Definition of terms * Delimitations and limitations of the study * Significance of the study * Review of the Literature: * Methods: * Research design * Sample, population, or subjects * Instrumentation and materials * Variables in the study * Data analysis * Appendices: * Instruments

Answer 7

Some researchers believe modern research lacks sound theory and does not significantly contribute to the field of knowledge. Smart (2005), for example, asserts that "reliance on strong theories is a rare attribute of higher education research manuscripts." He states that "the focus seems to be more toward development of our own distinct intellectual heritage and less toward reliance on the intellectual traditions of the more mature and advanced academic disciplines" (p. 468). He mentions three benefits to including sound theory in any research. Sound theories: * Provide a roadmap by identifying the important variables to be included in studies and the hypothesized relationships among those variables; * Incorporate extant empirical findings within a logical and consistent framework; and, * Offer a coherent potential answer to important issues facing the academic community (p. 467).

Answer 8

Advantages of Pragmatic Research Onwuegbuzie and Leech (2005) state that there are definite advantages to becoming a pragmatic researcher as opposed to a researcher who is wedded to either quantitative or qualitative research. They state that pragmatists who use a dual approach to research: * Are flexible in their investigative techniques, as they attempt to address a range of research questions that arise; * Promote collaboration among researchers; * View research as a holistic endeavor; * Can use quantitative research to inform qualitative research, and vice versa; * Can combine macro and micro approaches to viewing data; * Can merge two voices, the researcher and the participant (p. 383).

Answer 9

Best research evidence, clinical expertise, and the patient's unique values and circumstances.

Answer 10

Because they are out of date, frequently wrong, ineffective, or too overwhelming in their volume and too variable to their validity for practical clinical use.

Answer 11

Hierarchy of evidence and insufficiency of evidence alone

Answer 12

It is the hierarchy of evidence available that is used in clinical decision making and listed on its likelihood of freedom from error and strength. Meta-analyses of well conducted large RCTs Large multi-centric randomized trials Meta-analyses of well conducted small randomized trials Single centered randomized trials Observational studies Clinical experience or basic science research

Answer 13

Evidence-based health care (EBHC)

Answer 14

Because of the following factors: Information overload Rising patient expectations Introduction of new technologies and ageing populations In the past, health care managers tended to focus on cost and quality, thus “doing things right” and leaving “doing the right things” to other forces and chance. This situation is rapidly changing and everyone involved in decision making must use evidence to enable them to make decisions about “doing the right things” These skills are necessary for provision of health care in the 21st century. In situations where there is poor quality evidence, the decision maker will have to depend on his experience, available resources and patients expectations and values.

Answer 15

Evidence, experience and expertise, and expectations.

Answer 16

Producing evidence (research) Making evidence available especially at point of care, or the value of the new evidence can never be realized Evidence obtained can be used in two ways: firstly to improve clinical practice and secondly to improve health service management. Evidence-based clinical Practice One of the strategies used to implement this is the Physician-Patient Partnership Program (PPPP), which is based on the concept of patientcentred care and the idea of the physician and the patient being partners in problem solving. Evidence-based policy making, purchasing, and management for health services Decision makers and managers who are responsible for health care have to make policy decisions in order to allocate funds, purchase or manage resources. With increasing demand and limited resources these decisions will have to be based on evidence.

Answer 17

See photo.

Answer 18

Preparation and planning, searching the literature, going beyond the literature, and pulling it all together.

Answer 19

ACE Star Model of Knowledge Transformation The first star point, Discovery, represents the stage wherein new knowledge is generated. The knowledge is in the form of individual or primary research reports and in this form can be found in research journals, abstracts and/or conference proceedings. Kirchhoff (2009) referred to knowledge from a single or individual research study as a “brick” that when added to other “bricks” (e.g., other single studies) will be transformed into a wall of evidence. Evidence summary is the second star point, wherein the individual studies, that is, knowledge in the discovery form, are transformed through evidence synthesis and/or meta-analysis into a meaningful statement. This knowledge transformation is conducted by experts in their respective fields and the statements produced are often packaged as a systematic review. Translation is the third star point, wherein the synthesized knowledge of multiple systematic reviews is transformed in an evidence-based clinical practice guideline (CPG). In this stage of the model, our knowledge is transformed into a very user-friendly form for practice. Evidence-base CPG generally contains an evidence rating for each intervention listed. The most comprehensive set of open access CPGs, most of which are evidence-based, can be found via the National Guideline Clearinghouse, under the auspices of the Agency for Healthcare Research and Quality (AHRQ) of the U.S. Department of Health and Human Services. The fourth star point is Integration, wherein our knowledge has been transformed to the point at which it is usable by all clinicians and disseminated throughout our institutions. Frequently, systemwide change in practice is difficult, even change based on the best evidence and in the best possible form is difficult. Efforts to overcome barriers to EBP continue to be the focus of many outcomes by researchers. The last star point is Evaluation, wherein knowledge in the form we are using is evaluated from the perspective of its impact on outcomes. Possible EBP outcomes at this stage include patient satisfaction, safety, efficacy, efficiency, and health status of whole populations. Evaluation knowledge directs further issues to be researched in Discovery, and the cycle continues as knowledge is transformed into usable evidence at each star point.

Answer 20

Collection of the data of individual cases or subjects. Usually it is meaningless to present such data individually because that will not produce any important conclusions.

Answer 21

Statistics. Providing summary statistics of data sets present in a easily absorbable form for the audience. Descriptive and inferential statistics.

Answer 22

To summarize a set of observations, in order to communicate the largest amount of information as simply as possible.

Answer 23

Inferential statistics. In these statistics, most predictions are for the future and generalizations about a population by studying a smaller sample.

Answer 24

You use statistical methods have assumptions including normality of the continuous data like numerical and visual methods (which have their pros and cons). Descriptive and inferential statistics both are employed in scientific analysis of data and are equally important in the statistics.

Answer 25

Measures of frequency (frequency, percent), measures of central tendency (mean, median, and mode), and measures of dispersion or variation (variance, SD, standard error, quartile, interquartile range, percentile, range, and coefficient of variation (CV)), provide simple summaries about the sample and the measures.

Answer 26

Because it helps in further statistical analysis because many techniques like correlation, t-test, ANOVA test are calculated using values of measures of central tendency. A representative value (measures of central tendency) is considered good when it was calculated using ALL observations and not affected by extreme values because these values are used to calculate for further measures.

Answer 27

Mean, median, and mode.

Answer 28

Measures of Dispersion like variance, SD, standard error, quartile, interquartile range, percentile, range, and CV.

Answer 29

It measures how spread out values is from its mean value. Called SD because we have taken a standard value (mean) to measure the dispersion.

Answer 30

A variable can collect either qualitative or quantitative data. A variable differing in quantity is called a quantitative variable (e.g., weight of a group of patients), whereas a variable differing in quality is called a qualitative variable (e.g., the Fitzpatrick skin type)

Answer 31

The subtraction test. if you can subtract one variable to another and get a meaningful result, then you are dealing with a quantitative variable.

Answer 32

Discrete or continuous. Discrete variables are variables in which no values may be assumed between the two given values (e.g., number of lesions in each patient in a sample of patients with urticaria). Continuous variables can take any value in between the two given values (e.g., duration for which the wheals (hives) last in the same sample of patients with urticaria).

Answer 33

Use the "mid-way" test. If, , for every pair of values of variable, a value exactly mid-way between them is meaningful, the variable is continuous.

Answer 34

Nominal/categorical and ordinal variables.

Answer 35

Nominal/categorical variables. (Qualitative)

Answer 36

Ordinal/ranked variables (Qualitative)

Answer 37

Dependent variable is known as the outcome variable and is linked to the primary outcome of the study. The independent variable is also known as the explanatory variable and is something which is not affected by the experiment itself but which can be manipulated to affect the dependent variable. Confounding variables are extra variables, which can have an effect on the experiment and can cause spurious associations. Moisturizer use during an experimental study on a topical ointment for psoriasis may be a confounding variable.

Answer 38

Descriptive statistics give a summary about the sample being studied without drawing any inferences based on probability theory. These will always be needed even if inferential statistics are the goal. To make these statistics inferential, it would involve a specific statistical test, like the mann-whitney u-test, to compare the mean scores.

Answer 39

Descriptive statistics. These can help in summarizing data in the form of simple quantitative measures such as percentages or means or in the form of visual summaries such as histograms and box plots.

Answer 40

They are statistics used to describe a single variable, two variables, or multiple variables.

Answer 41

Sorting/grouping (frequency distribution tables, like a stem and leaf diagram) and illustrations/visual displays Summary statistics

Answer 42

Frequency diagrams, bar charts (for discrete variables) and histograms (for continuous variables) Composite bar charts (see image) Pie charts help show how total quantity is divided among its constituent variables. Scatter diagrams can be used to illustrate the relationship between two variables. (see image)

Answer 43

Measures of central tendency and measures of dispersion and variation.

Answer 44

Mean is the average of the data and can be skewed by outliers. The median is better to use since it divides the data set into equal halves, which is referred to as the 50th percentile (50% of the values are above it and 50% of the values are below it). In data sets with equal numbers, you take an average of the two values. The mode is the most common data point and this may or may not necessarily be in the center of the distribution.

Answer 45

In a symmetric distribution, all three are the same, whereas in skewed data the median and mean are not the same; lie more toward the skew, with the mean lying further to the skew compared with the median. See picture for example.

Answer 46

The range. Ex. 86 - 30 = 56 (range)

Answer 47

A quartile is one of the values which break the distribution into four equal parts. The 25th percentile is the data point which divides the group between the first one-fourth and the last three-fourth of the data. The first one-fourth will form the first quartile. The 75th percentile is the data point which divides the distribution into a first three-fourth and last one-fourth (the last one-fourth being the fourth quartile). The range between the 25th percentile and 75th percentile is called the interquartile range.

Answer 48

Variance. Subtracting each individual value from the mean and then adding them and finding the average would give a clue to the total dispersion, but the problem is that since the deviations are a mix of negative and positive values, the final total becomes zero. To calculate variance, this problem is overcome by adding squares of the deviations. So variance would be the sum of squares of the variation divided by the total number in the population (for a sample we use "n-1"). If we were to divide by n alone, we would always underestimate variance, and if we divided by n-2, we would always over estimate. N-1 is best for variance calculation. To get a more realistic value of the average dispersion, we take the square root of the variance, which is called the "standard deviation." Standard deviation is the spread of a group of numbers from the mean. The variance measures the average degree to which each point differs from the mean. While standard deviation is the square root of the variance, variance is the average of the squared difference of each data point from the mean. Example: For a class of students, the scores are 85, 90, 88, 92, and 82. To calculate the variance and standard deviation, find the mean: (85 + 90 + 88 + 92 + 82) / 5 = 87.4. Then, calculate the variance: [(85-87.4)^2 + (90-87.4)^2 + (88-87.4)^2 + (92-87.4)^2 + (82-87.4)^2] / 5 = 64.8 / 5 = 12.96. Finally, calculate the standard deviation, which is the square root of the variance: Standard Deviation = √12.96 ≈ 3.60.

Answer 49

It is a composite representation that portrays the mean, median, and mode, and the outliers.

Answer 50

The concept of skewness and when a distro curve is not symmetrical, it is considered skewed. Kurtosis is a representation of outliers. Distributions with high kurtosis tend to have heavy tails indicating a larger number of outliers, whereas distributions with low kurtosis have light tails, indicating lesser outliers. There are formulas to calculate both skewness and kurtosis.

Answer 51

A census. If you had all units, that'd be great but it is unrealistic. Having all samples would remove chances of sampling error (difference between the outcome characteristics in a random sample when compared with the true population values - something that is virtually unavoidable when you take a random sample).

Answer 52

Sample size. To have sufficient numbers, having a bigger sample size rather than a smaller one is needed to make a meaningful and accurate conclusions and reduce the effect of sampling error.

Answer 53

Probability and nonprobability sampling. For probability sampling, we have: Simple random sampling (each member in a population has an equal chance of being selected) Stratified random sampling (in nonhomogeneous populations, the population is divided into subgroups - followed by random sampling in each subgroup) Systemic sampling (sampling is based on a systemic technique - e.g., every third person is selected for a survey) Cluster sampling (similar to stratified sampling except the clusters here are preexisting clusters unlike stratified sampling where the researcher decides on the stratification criteria) Nonprobability sampling is where every unit in the population does not have an equal chance of inclusion into the sample. These methods include: Convenience sampling (e.g., sample selected based on ease of access) Purposive sampling (where only people who meet specific criteria are included in the sample)

Answer 54

A sample size that is too less may make the study underpowered, whereas a sample size which is more than necessary might lead to a wastage of resources.

HA535 Data Analytics for Health Care Managers - Units 1-4 Flashcards

(81 cards)