exam review Flashcards
name three different types of populations
target, sample, accessible
Define target, accessible and sample pops
The target population is the overall group you wish to study.
○
The accessible population is the group available to you, the researcher, within your study.
○
The sample population is the refined population selected for the study from the accessible population and should accurately represent the target population.
what are the different types of sampling
probabilistic and nonprobabilistic
when is probabalistic sampling used
Probabilistic sampling (used in quantitative studies with the aim to generalize results)
when is nonprobabalistic sampling used
Non-probabilistic sampling (used in qualitative studies with the aim to represent phenomena)
subtypes of probabilistic sampling
simple random, systematic, stratified (proportional and non proportional), cluster
subtypes of nonprobablistic sampling
convenience, snowball, quota, reasoned chocie, theoretical
define simple random sampling
Simple random sampling: Each element in a population has an equal chance of being selected.
define systematic sampling
Systematic sampling: Elements are selected at regular intervals from a randomly determined starting point.
define stratified sampling, name and define its two subtypes
Stratified sampling: Divides the population into subgroups (strata) with common characteristics and samples are selected from each strata.
subtypes:
proportional: The sample size for each strata reflects its proportion in the total population.
nonproportional: Over-represents certain strata.
define cluster sampling
Randomly selects heterogeneous groups (clusters) instead of individuals.
define convenience sampling
Selection based on easy accessibility.
define snowball sampling
Participants recruit others they know who meet study criteria.
define quota sampling
Selection based on pre-determined proportions of subgroups in the population.
define reasoned choice
Combination of quota and convenience sampling, considering availability and knowledge about the topic.
define theoretical sampling
Iterative selection based on emerging themes from data analysis in grounded theory.
what determines sample size in quantitative contexts? what factors influence it?
the number of variables needed for statistical significance
factors: statistical power, homogeneity vs. heterogeneity, magnitude of effect, error types, power level, purpose of study
explain the factors that influence sample size in quantitative studies
Statistical power: probability of correctly finding an effect
Homo/heterogeneity: population=uniform or diverse
Magnitude of effect: is the measured difference/relationship small or large
Error types: type one (rejecting null hypothesis when true) or two (accepting null hypothesis when false)
Power level: 80% in most studies
Purpose: is the goal exploring, describing or predicting relationships?
what determines sample size in qualitative contexts? what factors influence it?
Not predetermined, based on data saturation - the point at which no new themes are emerging from the data.
Factors: scope, nature, data quality
explain the factors that influence sample size in qualitative studies
scope: whether the research question is broad or narrow
nature: is this study complex or sensitive?
data quality: level of ease in collecting complete and rich data
name the principles underlying measurement
operationalization and levels of measurement (nominal, ordinal, interval, ratio)
define measurement
measurement involves assigning numbers or symbols to events, objects or characteristics according to rules.
types of data collection instruments
questionnaires, structured observations, physiological measurements
define each data collection instrument and possible advantages
Questionnaires: Written sets of questions used to collect information from respondents. Advantages: low cost, efficient, allows anonymity, no interviewer bias.
○
Structured observations: Collecting data by systematically watching and recording behavior or events.
○
Physiological measurements: Objective measurements of bodily functions (e.g., BMI, blood pressure).
Define and name the two subtypes of measurement error
Measurement Error: Discrepancy between observed scores and true scores. Subtypes: random and systematic
What causes random error vs systematic error?
Random Error: Due to unpredictable factors, subjective influences, or instrument issues.
○
Systematic Error: Due to predictable and consistent factors.
Define relibaility versus validity and how they differ
Reliability: Consistency of measurements.
Validity: Accuracy of measurements, whether the instrument measures what it intends to measure.
name and define the constituents of relibaility
Temporal stability: Consistency over time.
■
Equivalence: Consistency between different versions of the instrument.
■
Inter-rater reliability: Consistency between different observers.
■
Internal consistency: Consistency of items within the instrument.
Name and define the constituents of validity
Content Validity: Whether the instrument covers all aspects of the concept being measured.
■
Construct Validity: Whether the instrument accurately measures the underlying theoretical concept.
■
Face Validity: Whether the instrument appears to measure what it claims to measure
How do you assess reliability and validity using statistical methods? List and explain the two methods
Correlation Coefficient: A statistical measure of the strength and direction of association between two variables.
○
Reliability Coefficient: A statistical measure of the consistency of scores from an instrument.
name and define the subtypes of qualitative data analysis
Non-statistical: Focuses on interpretation, description, and exploration of themes and patterns.
○
Iterative: Involves a cyclical process of data collection, analysis, and interpretation.
what are the key steps involved in qualitative data analysis? explain them
Data Cleaning: Review data, remove irrelevant information, and refine the research question.
○
Data Reduction: Organize and categorize data into meaningful units, identifying recurring themes and patterns.
○
Data Analysis/Interpretation: Coding data, developing and refining themes, and connecting them to the research question and theoretical framework.
○
Data Display: Presenting the findings in a clear and compelling way using text, tables, figures, or diagrams.
how do you differentiate between descriptive and inferential statistics?
Descriptive Statistics: Used to summarize and describe data.
Inferential Statistics: Used to make inferences and generalizations about a population based on sample data.
explain measurement tools involved in assessing descriptive statistics
Frequency Analysis: How often different values occur.
■
Central Tendency: Measures of the average or typical value. (mean, median, mode)
■
Dispersion: Measures of the spread or variability of data. (range: difference between the highest and lowest values.,
variance: average squared deviation from the mean.,
standard deviation: square root of the variance.)
explain the measurement tools involved in assessing inferrential statistics
Hypothesis Testing: Evaluating whether there is enough evidence to reject a null hypothesis.
■
Relationships Among Variables: Exploring associations and correlations between variables.
How do you select appropriate statistical tests based on variable types and the research question?
according to OUTCOME X predictor. consult the following.
DICHOTOMOUS x dichotomous: chi^2 or fisher-exact
DICHOTOMOUS x categorical: chi^2 or fisher-exact
DICHOTOMOUS x ordinal: wilcoxon
DICHOTOMOUS x continuous: t-test, wilcoxon, logistic regression
CATEGORICAL x dichotomous: chi^2
CATEGORICAL x categorical: chi^2
CATEGORICAL x ordinal: kruskal-wallis
CATEGORICAL x continuous: anova, class prediction
ORDINAL x dichotomous: wilcoxon
ORDINAL x categorical: kruskal wallis
ORDINAL x ordinal: spearman correlation
ORDINAL x continuous: anova, class prediction
CONTINUOUS x dichotomous: t-test, wilcoxon
CONTINUOUS x categorical: anova
CONTINUOUS x ordinal: anova
CONTINUOUS x continuous: correlation, linear regression
Define statistical and clinical significance
Statistical Significance: The probability that observed results are not due to chance.
○
Clinical Significance: The practical or meaningful importance of the results.
How do you interpret results of statistical analyses?
Hypothesis Testing: Determine whether the null hypothesis can be rejected.
○
Effect Size: Determine the magnitude of the effect or relationship.
○
Confidence Intervals: Provide a range of values within which the true population parameter is likely to lie.
What is epidemiology?
The study of the distribution and determinants of disease frequency in human populations.
What are the key components of epidemiology?
Distribution: How diseases are spread across different populations.
■
Determinants: Factors that influence the risk of disease (exposures).
What are prevalence and incidence? name and describe their subtypes
Prevalence: The proportion of individuals in a population who have a disease at a specific time. Subtypes: point and period prevalence
Point Prevalence: Measured at a single point in time.
Incidence: The rate at which new cases of a disease occur in a population over a specific time period. Subtypes: cumulative incidence and incidence rate.
Cumulative Incidence: The proportion of individuals who develop the disease during a specific time period.
Incidence Rate: The number of new cases per unit of person-time at risk.
How do you calculate prevalence? what about point prevalence?
number of existing cases/total population
this concept, but at a specific point in time (specified in explanation, not as units), often represented as a percentage
How do you calculate cumulative incidence?
of new cases / # of the population at risk at the start of the time period
over a range of time but only analyzes cases that are active (time is specified in the explanation, not denominator)
How do you calculate the incidence rate?
of new cases / total person-time of observation
at a specific point in time but time is shown as a unit of PT or person-time (population that is not immune and can still get the disease: people - those already known to be affected or vaccinated * the time they were observed for)
Differentiate between ratios, proportions, and rates.
Ratio: A comparison of two numbers.
○
Proportion: A ratio where the numerator is a subset of the denominator.
○
Rate: A measure of frequency that includes a unit of time in the denominator.
Define a systematic review vs. meta-analysis
Systematic Review: A comprehensive and rigorous review of existing research on a specific question, following pre-defined methods to minimize bias.
○
Meta-Analysis: A statistical technique that combines data from multiple studies to provide a quantitative summary of the overall effect.
What are the steps of a systematic review? explain them
- define question: use PICOS (population, intervention, comparison, outcome, study design)
- Develop research strategy: identify keywords so you can systematically search databases
- screen and select studies: apply pre-defined inclusion/exclusion crtieria to identify studies that meet it
- extract data: collect from chosen studies
- assess the risk of bias: evaluate methological quality of studies
- analyze and synthesize data: summarize findings and assess strength of evidence
How do you interpret a forest plot?
horizontal lines represent confidence intervals (wider the lines, the greater the uncertainty)
square in the middle represents point estimate (study’s effect size; larger squares = studies with larger effects on a meta-analysis)
vertical line represents the null effect; studies that cross this line have no statistical significance (odds ratio: line at 1, mean difference line: at 0)
diamond represents the overall confidence interval and effect size; if not touching the null effect line, pooled effect is statistically significant
I2 statistic: level of heterogeneity (<25% = low heterogeneity and more consistent studies, >50% = high heterogeneity and studies are less consistent) or p-value over 0.05
What are the different types of bias that affect reviews and meta-analyses?
Publication Bias: The tendency to publish studies with positive findings more often than studies with negative findings.
○
Language Bias: The tendency to include studies published in certain languages.
What components increase the clarity and effectiveness of a presentation? Explain
Use tables and figures: Present numerical data and illustrate trends.
○
Highlight key findings: Emphasize the most important results and their implications.
○
Consider the audience: Tailor the presentation to the specific audience.
list examples of formats that can be used to disseminate research results
posters, scientific articles, presentations
how do you interpret the p-value?
p-value represents the probability of obtaining observed results if the null hypothesis is true
statistical significance: p<0.05 so we reject the null
What are the subtypes of qualitative studies?
Phenomenology: Explores lived experiences of individuals.
○
Ethnography: Studies the culture and social practices of a group.
○
Grounded Theory: Aims to develop theories based on data.
○
Case Study: In-depth investigation of a single case or small group.
what are the subtypes of quantitative studies?
Descriptive: Describe characteristics of a population or phenomenon.
Analytical: Test hypotheses about relationships between exposures and outcomes.
what further sections can descriptive quantitative studies be broken into? explain them
Case Report: Detailed description of a single case.
■
Case Series: Description of a group of individuals with similar characteristics.
■
Ecological Studies: Examine relationships between exposures and outcomes at a population level.
■
Cross-Sectional Studies: Collect data on exposures and outcomes at a single point in time.
■
Longitudinal Studies: Follow a group of individuals over time.
what further sections can analytical quantitative studies be broken into? explain them
Case-Control Studies: Compare individuals with a disease (cases) to individuals without the disease (controls) to identify risk factors.
■
Cohort Studies: Follow a group of individuals with and without exposure over time to see if they develop the disease.
■
Randomized Control Trials (RCTs): Experimentally test the effectiveness of an intervention by randomly assigning participants to treatment and control groups.
■
Quasi-Experimental: Similar to RCTs, but participants are not randomly assigned to groups.
list the 3 measurements of risk
absolute risk, relative risk and odds ratio
define and explain how to calculate absolute risk (AR)
Absolute Risk: Probability of an event happening (e.g. developing a disease) in a specific group of people.
○
Formula: Number of instances of an event in a group / Total number of people in that group.
define and explain how to calculate relative risk (RR)
Relative Risk: Ratio of the risk of an event in the exposed group to the risk of an event in the unexposed group.
○
Formula: Absolute risk in the exposed group / Absolute risk in the unexposed group.
define and explain how to calculate odds ratio (OR)
Odds Ratio: Ratio of the odds of an event in the exposed group to the odds of an event in the unexposed group.
○
Formula: (Odds of event in exposed group) / (Odds of event in unexposed group)