Meta analysis: Compare and contrast different research articles and studies in order to find patterns among the study results. Example: You will look at 5-7 articles on Constraint induced therapy to see if that is an intervention you want to use for your feeding group at the hospital.
Randomized Controlled Trials (RCT)/Randomized Assigned Trial: the gold standard for a clinical trial. RCTs are often used to test the efficacy or effectiveness of various types of medical intervention within a patient population. RCTs may also provide an opportunity to gather useful information about adverse effects, such as drug reactions. Example: In your feeding group of 10 patients, you will use constraint induced therapy on 5 patients. After the group is finished you can compare and contrast the results to see if constraint induced therapy made an impact on ROM and independence on feeding.
Longitudinal study: A correlational research study that involves repeated observations of the same variables over long periods of time — often many decades. It is a type of observational study.
The affect of smoking in the Los Angeles area for 10 years.
Cohort Studies:is a form of longitudinal study. It is an analysis of risk factors and follows a group of people who do not have the disease, and uses correlations to determine the absolute risk of subject contraction. Cohort studies are largely about the life histories of segments of populations, and the individual people who constitute these segments.
A group of graduate students who take the same classes together for 2 years.
Outcomes Research: refers to research (usually medically related) which investigates the outcomes of health care practices. It has been defined as the study of the end results of health services that takes patients’ experiences, preferences, and values into account—is intended to provide scientific evidence relating to decisions made by all who participate in health care
Case Studies/Case Series: “Case studies are analyses of persons, events, decisions, periods, projects, policies, institutions, or other systems that are studied holistically by one or more methods
Expert Opinion: who by virtue of education, training, skill, or experience is believed to have expertise and specialized knowledge in a particular subject beyond that of the average person
Evidence –Based Practice. Any time an entry level therapist or a therapist starting a new job is looking for interventions to incorporate into their new job, the therapist will look at evidence based practice.
A form of descriptive research that studies people, individually or collectively, in their natural social and cultural context.
A systematic, subjective approach to describe real life experiences that are meaningful.
It is rich in verbal descriptions of people and phenomena based on direct observation in naturalistic settings. Observations are unstructured and ever-changing according to the contexts and results of the observations.
Types of qualitative research:
Phenomenological: a study of one or more persons and how they make sense of their experience.
Phenomenological study: the collection of participant’s experiences through focus groups that contain open-ended interview questions.
Ethnographic: patterns and characteristics of a cultural group, including values, roles, beliefs, and normative practices, are intensely studied.
Extensive field observations, examinations of literature and materials, and cultural immersion are used.
Study of a nursing home.
Heuristic: complete involvement of the researcher in the experience of the subjects to understand and interpret a phenomenon.
Aim to understand human experience and its meaning.
Meanings can only be understood if personally experienced.
Case study: a single subject or a group of subjects is investigated in an in-depth manner.
Purpose can be description, interpretation, or evaluation.
Quantitative method/studies: the classic two-group design which includes random selection and assignment into an experimental group that receives treatment or a control group that receives no treatment.
Two levels of treatment (some and none) together constitute the independent variable being manipulates.
The cause and effect relationship between the independent and dependent variable is examined.
Observations are structured and formalized.
Types of Quantitative Research:
Grounded Theory Method involves the discovery of theory through the analysis of data. Grounded theory method is a research method which operates almost in a reverse fashion from traditional social science research. Rather than beginning with a hypothesis, the first step is data collection, through a variety of methods. From the data collected, the key points are marked with a series of codes, which are extracted from the text. The codes are grouped into similar concepts in order to make the data more workable. From these concepts, categories are formed, which are the basis for the creation of a theory, or a reverse engineered hypothesis. This contradicts the traditional model of research, where the researcher chooses a theoretical framework, and only then applies this model to the phenomenon to be studied. Example: when analyzing 100 surveys, I will code 60 male participants as (M), and the 40 female participants will be coded as (F).
Quasi-experimental: an independent variable is manipulated to determine its effect on a dependent variable but there is a lesser degree of researcher control and/or no randomization.
Used to study intact groups created by events or natural process.
A criterion-referenced test: is a style of test which uses test scores to generate a statement about the behavior that can be expected of a person with that score.
Non-experimental/correlational: there is no manipulation of independent variable; randomization and researcher control are not possible.
Used to study the potential relationships between two or more existing variables (e.g., attendance at a day program and social interaction skills).
Examples of correlational research
Retrospective: investigation of data collected in the past.
Prospective: recording and investigation of present data
Descriptive: investigation of several variables at once; determines existing relationships among variables.
Predictive: used to develop predictive models.
Levels of measurement
Nominal: The nominal type, sometimes also called the qualitative type, differentiates between items or subjects based only on their names or (meta-)categories and other qualitative classifications they belong to; thus dichotomous data involves the construction of classifications as well as the classification of items. Discovery of an exception to a classification can be viewed as progress. Examples of these classifications include gender, nationality, ethnicity, language, genre, style, biological species, and form.
Ordinal: The ordinal type allows for rank order (1st, 2nd, 3rd, etc.) by which data can be sorted, but still does not allow for relative degree of difference between them. Examples include, on one hand, dichotomous data with dichotomous (or dichotomized) values such as ‘sick’ vs. ‘healthy’ when measuring health, ‘guilty’ vs. ‘innocent’ when making judgments in courts, ‘wrong/false’ vs. ‘right/true’ when measuring truth value and, on the other hand, non-dichotomous data consisting of a spectrum of values, such as ‘completely agree’, ‘mostly agree’, ‘mostly disagree’, ‘completely disagree’ when measuring opinion..
Interval: The interval type allows for the degree of difference between items, but not the ratio between them.
Ratio: Ratio scale is the measurement is the estimation of the ratio between a magnitude of a continuous quantity and a unit magnitude of the same kind. A ratio scale possesses a meaningful (unique and non-arbitrary) zero value.
Null Hypothesis: a general or default position that there is no relationship between two measured phenomena,or that a potential medical treatment has no effect. Rejecting or disproving the null hypothesis – and thus concluding that there are grounds for believing that there is a relationship between two phenomena or that a potential treatment has a measurable effect.
Level/test of significance – level which you may be wrong (p value). p=.05 (5 out of 100 times you may be wrong). Null hypothesis is rejected if you reach a significance level of .05 or less.
Correlation coefficient also known as r, R, or Pearson’s r.: measure of the strength and direction of the linear relationship between two variables that is defined as the (sample) covariance of the variables divided by the product of their (sample) standard deviations.
The quantity r, called the linear correlation coefficient, measures the strength and the direction of a linear relationship between two variables.
The value of r is such that -1 < r < +1. The + and – signs are used for positive
linear correlations and negative linear correlations, respectively.
Positive correlation: If x and y have a strong positive linear correlation, r is close to +1. An rvalue of exactly +1 indicates a perfect positive fit. Positive values indicate a relationship between x and y variables such that as values for x increases, values for y also increase. Example: Using PasstheOT will have a positive effect on increasing your exam score.
Negative correlation: Values below zero express negative correlation. A perfect negative correlation has a coefficient of -1, indicating that an increase in one variable reliably predicts a decrease in the other one. An example would be yellow cars and accident rates or pages printed and printer ink supply.
No correlation: If there is no linear correlation or a weak linear correlation, r is close to 0. A value near zero means that there is a random, nonlinear relationship between the two variables
A perfect correlation of ± 1 occurs only when the data points all lie exactly on a
straight line. If r = +1, the slope of this line is positive. If r = -1, the slope of this line is negative.
A correlation greater than 0.8 is generally described as strong, whereas a correlation less than 0.5 is generally described as weak. These values can vary based upon the “type” of data being examined. A study utilizing scientific data may require a stronger correlation than a study using social science data.
Random Sample: individuals are selected through the use of a table of random numbers
Systematic Sample: individuals are selected from a population list by taking individuals at specified intervals (e.g., every 10thname)
Stratified Random Sample: individuals are selected from a populations identified subgroups based on some pre-determined characteristics (e.g., diagnosis) that correlates with the study
Purposive: individuals are purposefully and deliberately selected for a study (e.g. all consumers of a program for a CQI study)
Convenience Sample: individuals are selected who meet population criteria based upon availability to the researcher.
Snowball Sampling/Network: study subjects provide names of other individuals who can meet study criteria.
Reliability: the “consistency” or “repeatability” of research measures. If the reliability is low, then the test is not a reliable measure. If your score is inconsitent, then you need to do a test/retest.
Validity – face, content, criterion and construct. Test testing what it is intending to measure
Measures of central tendency: a determination of average or typical scores
Mean: the arithmetic average of all scores.
Median: the midpoint, 50% of scores are above the median and 50% of scores are below.
Mode: the most frequently occurring score.
Measures of variability: determine the spread of a group of scores
Range: the difference between the highest score and the lowest score
Standard deviation: a determination of variability of scores (difference) from the mean.
Normal distribution: a symmetrical bell-shaped curve indicating the distribution of scores, the mean, median, and mode are similar.
Inter vs. intra reliability
Inter-rater reliability:determines the extent to which two or more raters obtain the same result when using the same instrument to measure a concept. (think of interpersonal relationships). It gives a score of how much homogeneity or consensus. If various raters do not agree, either the scale is defective or the raters need to be re-trained. If you are testing a group of people and the scores are different, then the results will change based off of who is taking the test and what disability the patients have. A statistical measure ranging from 0 to 1.0. The larger the number, the better the reliability, values near or less than zero suggest that agreement is due to chance alone.
Intra-rater reliability: makes it possible to determine the degree to which the results obtained by a measurement procedure can be replicated. Lack of intra-rater reliability may arise from divergences between measurement instruments or instability of the attribute measured. This is a type of reliability assessment in which the same assessment is completed by the same rater on two or more occasions. These different ratings are then compared, generally by means of correlation. Since the same individual is completing both assessments, the rater’s subsequent ratings are contaminated by knowledge of earlier ratings.