Please enable JavaScript.

Coggle requires JavaScript to display documents.

Research methodology, Subject Selection - must be free of bias to remain…

- - - - the cause
      - Types
        
        Experimental independent variables
        
        Subject Variables
      - Its value is independent of other variables in the study
    - - the effect
      - The value depends on change in the independent variable
- - - - Single-system design:
        Type of quasi-experimental design in which only 1 subject is used to study the effects of an intervention
    - - Case-control design
        a type of retrospective design in which a group of individuals with the outcome of interest are compared to a control group
      - Cross-sectional study
        Studies a group of individuals at a single point in time
      - Longitudinal study
        Studies a group of individuals over a period of time
        
        Cohort study
        type of longitutinal design where a group of individuals who usually share a same characteristic is followed over time to observe the effectiveness of an intervention
  - - - Within-subjects design
        Compares repeated measures of an outcome within the same individuals
      - Between-subjects design
        Compares outcomes between two or more groups of subjects
- - - - quasi-experimental analysis
      - experimental analysis (pre-test and post-test)
    - - Numbers
        
        Standard deviation = measures the dispersion of a dataset relative to its mean
        
        Mean = average of a data set; found by adding all numbers in the data set and then dividing by the number of values in the set.
      - Bar Charts = typically used to display variables on a nominal or ordinal scale.
      - Tables = one of the most commonly used methods of displaying data in research.
      - Percentages = Compares a portion of a total to the total. Used when to assess how significant a portion or amount is to an established total
      - Line graphs = help show data variables and trends clearly. This format can help to make predictions about the results of data not yet recorded. Line graphs an also be used to display several dependent variables against one independent variable.
    - - the distribution = the frequency or range of values for a variable. Frequency Distribution = most common
      - the central tendency = an estimate of the “center” of a distribution of values
        
        Mean
        
        Mode - the value that appears most often in a set of data values
        
        Median - the middle value when a data set is ordered from least to greatest
      - the dispersion = the spread of the values around the central tendency
        
        Standard deviation = SD = a more accurate and detailed estimate of dispersion (an outlier can exaggerate the range). The Standard Deviation shows the relation that set of scores has to the mean of the sample.
        
        Range
  - - - Mean = average of a data set; found by adding all numbers in the data set and then dividing by the number of values in the set.
      - Standard deviation = measures the dispersion of a dataset relative to its mean
  - - - One-on-one interviews (most common). Good way to gather highly personalized information.
      - Open-ended surveys and questionnaires. allow participants to answer freely at length, rather than choosing from a set number of responses.
      - Observationallow participants to answer freely at length, rather than choosing from a set number of responses.
      - Focus groups = similar to interviews, except that you conduct them in a group format.
      - Case studies = helps analyze a combination of multiple qualitative data sources to draw inferences and come to conclusions. helps in exploration of a phenomenon within some particular context through various data sources, and it undertakes the exploration through variety of lenses in order to reveal multiple facets of the phenomenon
- - - - Confidence Intervals - refers to the probability that a population parameter will fall between a set of values for a certain proportion of times. Can be used to Generalize findings and explapolate to the larger population from a given sample
        
        A 95% confidence level indicates if we were to draw 100 random samples we would make 100 confiende intervals around the sample means, and 95 of them would contain the true population mean.
- - - - Purpose Statement
        
        Written based on the type of study design
        
        Ex: case report purpose statements are more detailed than systematic review purpose statements, which are more broad
        
        Examples:
        
        "The purpose of this study was to investigate the effects of..."
        
        "The main goal of this study was to examine the differences in..."
      - Problem Statement
        
        Uses similar phrasing as a purpose statement, but from the problem's perspective
        
        Also based on the type of study design
        
        Examples:
        
        "However, the long term effects of__ are still unknown"
        
        "There is currently a lack of research on..."
        
        "We still do not fully understand the physiological processes of..."
      - Question
        
        General research questions can help guide clinical focus
        
        Examples:
        
        Question:
        "What is the risk of___?"
        
        Clinical focus: Prediction about a future outcome
        
        Question: "What is the best way to determine if my patient has___?"
        
        Clinical focus: Usefulness of a Diagnostic Test
    - - Should be able to easily convey the general goal of the study to readers who are not familiar with the topic
      - Expected to be biologically plausible
  - - - Why an answer to their question is needed
      - How the study's results will contribute to the scientific community's knowledge & understanding of a topic or specific scenario
    - - Literature Review
      - Citations of Epidemiological Data
- - - - If the p-value is below your threshold of significance (typically p < 0.05), then you can reject the null hypothesis
        
        Based on the assumption that the null hypothesis is true, although it cannot be used to prove it.
      - Probability of finding an effect as big as the one observed when the null hypothesis is true.
      - Example: With a p = .02, even if there is no true difference, you would expect to observe this size effect 2% of the time.
        
        (if we performed 100 similar experiments, 2 of them would result in a difference this large, even if no true difference exists.)
    - - Identifies relevant population characteristics and partitions members of population into homogenous, nonoverlapping subsets
    - - Content Validity:
        
        Establishes that the multiple items that make up a questionnaire, inventory, or scale adequately sample the universe of content that defines the construct being measured.
      - Criterion-Related Validity:
        
        Establishes the correspondence between a target test and a reference or gold standard measure of the same construct.
      - External: Extent to which results can be generalized
      - Construct Validity:
        
        Establishes the ability of an instrument to measure the dimensions and theoretical foundation of an abstract construct.
  - - - Intrarater Reliability
        
        Variation between 2 or more raters who measure the same subjects
      - Extraneous variable
        
        Variable that you're not investigating that can potentially affect the dependent variable of your research study
      - Interrater Reliability
        
        The stability of data recorded by 1 tester across 2 or more trials
      - Confounding variable
        
        Present threats to internal validity because they offer competing explanations for the observed relationship between the independent and dependent variable
- - - - Probability Sampling
        
        Random Sampling
        
        Every member of the population has an equal chance of being selected
        
        Stratified Sampling
        
        Divides the population into subpopulations based on relevant characteristics and then you use random or systematic sampling to select a sample from each subgroup
        
        Systemic Sampling
        
        Individuals are chosen based on a regular interval
        
        Cluster Sampling
        
        Division of the population into subgroups, where each subgroups has similar characteristics to the whole sample. Clusters are chosen at random.
        Good for dealing with large and dispersed populations
      - Non-Probability Sampling
        
        Convenience sampling
        
        Inclusion of individuals who are the most accessible
        
        Purposive sampling
        
        Includes individuals that are hand picked by researchers based on how useful their data is.
        
        Snowball sampling
        
        Mostly used for hard to access populations. It is the recruitment through other participants
        
        Quota sampling
        
        The use of voluntary response to be included in the data
    - - Inclusion of all objects of interest
    - - Self Reports
      - Observation
      - Biophysiologic measures
    - - Advantages
        
        More objective and easy to analyze
      - Limitations
        
        Greater effort to develop and refine
    - - Advantages
        
        Allows for deeper, more thoughtful analysis
      - Limitations
        
        Data more difficult to analyze for subjects who can't express themselves verbally