911 Flashcards
Week 1-4
What is the definition of statistics according to Davidian and Louis?
Statistics is the science of learning from data, measuring, controlling, and communicating uncertainty. It is essential for controlling the course of scientific and societal advances.
What are the main types of statistical paradigms?
Bayesian Statistics
Classical (Error) Statistics
Likelihood-Based Statistics
Akaikean-Information Criterion-Based Statistics
Frequentist Statistics
What defines a research question?
A question that defines what a study hopes to learn, addressing how, why, when, and what.
What are the types of research questions?
Descriptive: Describes what is going on or what exists.
Relational: Examines relationships between variables.
Causal: Determines if a variable affects one or more outcomes.
What are characteristics of a researchable question?
Narrow and specific.
Can be answered by observable evidence (data).
Has significant relevance for guiding policy, theory, or practice.
What is a hypothesis?
A specific, concise statement predicting the outcome of a study, indicating variables and the relationship to be examined.
What are the types of hypotheses?
Null hypothesis
Alternative hypothesis
Hypothesis of difference
Hypothesis of point-prevalence
Hypothesis of association
What is operationalization?
Defining a concept by specifying the activities or operations needed to measure it.
What is the difference between independent and dependent variables?
Independent Variables (IV): Variables that predict or cause the dependent variable.
Dependent Variables (DV): Variables that are explained or predicted.
What are levels of measurement in data?
Continuous data (Quantitative)
Categorical data (Qualitative)
What are the types of data in research?
Primary Data: Data collected by the researcher (e.g., surveys, interviews).
Secondary Data: Data previously collected for other purposes (e.g., administrative records).
What are the advantages and disadvantages of primary data?
Advantages: Collect the exact data needed, define and measure variables directly.
Disadvantages: Expensive, time-intensive, labor-intensive.
What are the advantages of secondary data?
Less expensive
Large quantities available
Depth (multiple years) and breadth (many data elements)
Easy to access (some)
What are some disadvantages of secondary data?
May not be collected for research purposes
May have data entry errors or omissions
May not measure the exact variables needed
Barriers to linking datasets (e.g., HIPAA)
What is the difference between Missing Completely at Random (MCAR) and Missing at Random (MAR)?
MCAR: Missingness has no relationship with any observed or missing data.
MAR: Missingness is related to some observed data.
What are the three types of statistical tests based on the purpose of analysis?
- Tests of Differences (e.g., T-test, ANOVA)
- Tests of Associations (e.g., Chi-square, correlation, regression)
- Parametric and Nonparametric tests (dependent on distribution and sample size)
What are the main types of descriptive statistics?
- Measures of Frequency (e.g., Count, Percent, Frequency)
- Measures of Central Tendency (e.g., Mean, Median, Mode)
- Measures of Dispersion/Variation (e.g., Range, Standard Deviation, Variance)
- Measures of Position (e.g., Percentile Ranks, Quartile Ranks, Z-scores)
What are the three measures of central tendency?
Mean: The arithmetic average.
Median: The middle score in a distribution.
Mode: The most frequently occurring score.
What is the range in descriptive statistics?
The range is the difference between the highest and lowest values in a dataset.