Intro to Statistics

• Statistics is the study of data collection, organization, analysis, and interpretation.

Descriptive Statistics

• These present study results without generalizing to a larger group.
• The purpose is to present data characteristics and summarize them, including the average value for each variable and the amount of variation around the average.
• Include measures like range, central tendency, and standard deviations.

Inferential Statistics

• Used to draw conclusions about observed differences between groups.
• Used to extrapolate results to larger populations via statistical significance.

Statistical Significance

• Indicates whether results are meaningful or likely due to chance.
• Estimates the strength of associations between variables.
• A p-value of ≤.05 is generally considered statistically significant.
• Tests used depend on the type of data involved.

ANOVA (Analysis of Variance)

• Measures both statistical significance and the strength of association.
• Examines relationships among exposures, procedures or independent variables.
• Examines how exposures, procedures or independent variables affect outcome measures or dependent variables.
• Multiple analysis of variance (MANOVA) can be utilized when multiple outcomes are measured.

ANCOVA (Analysis of Covariance)

• Used to make groups comparable if demographic variables are unequally distributed between groups in a study.
• Analysis uses a cofactor to eliminate confounding effects on the outcome.

Power analysis

• Determines the number of participants needed for an 80% chance of achieving statistical significance.
• Typically done during the planning stages of a study.
• There should be at least 10 subjects per outcome measure.

Key Considerations for Research Novices

• Note whether a study performed tests of statistical significance.
• Ensure authors provide rationale for the statistical tests used.

Central Tendency

• Refers to a representation of the "middle" or "expected" value of a dataset.
• It is a central value for a probability distribution.

Mean

• The sum of all values in a list divided by the number of people in the sample.

Median

• A number dividing the higher half of a list of values from the lower half.
• It is found by listing data numerically and identifying the number in the exact middle.
• In an even-numbered data set, it's the mean of the two central numbers.

Mode

• The most frequent value assumed by a random variable.
• Usually different from the median and mean, especially in a skewed distribution.
• Can be bimodal, trimodal, etc.

Dispersion

• Measures statistical variability.
• Allows for analysis of how widely dispersed the data are around the middle.

Standard Deviation

• Measures the spread of numbers in a data set.
• A small standard deviation indicates data points are close to the mean.
• A large standard deviation indicates data points are far from the mean.
• A low standard deviation (+/-1) means there is little variability.
• A high standard deviation means there is a lot of variability.
• May serve as a measure of uncertainty.
• Data points in the tail ends of a standard deviation are outliers and atypical.

Range

• The difference between the highest and lowest values in a dataset.

External Validity

• Assesses the ability to apply research findings beyond the context of a study.
• Considered generalizable to a larger group or population.
• Considers whether animal studies can be replicated in humans.
• Considers whether the study sample is large and diverse enough to apply to the larger population.

Internal Validity

• Is the capacity of a study to link cause and effect, within the study itself.
• Excludes other hypotheses as possible explanations for the findings.
• Establishes a direct and absolute connection between cause and effect, differentiating correlation from causation.

Threats to Internal Validity

Confounding Variable

• Blurs or masks the effect of another variable.

Bias

• A systematic error in research.

Selection

• Results from choosing specific groups to survey or study.
• Can be limited by randomizing and including generalizable sample populations when selecting samples.

Statistical Validity

• Another potential threat to internal validity.
• Statistics can be misrepresentative or have errors.

Type I Error

• A "false positive" where a null hypothesis is rejected when it is actually true.
• Concluding a treatment works when it doesn’t.

Type II Error

• A "false negative" where one fails to reject a null hypothesis that is actually false.
• Concluding a treatment doesn’t work when it does.

Sample Size

• A small sample size can hinder significant observations.
• Low power (small sample size, many treatment outcomes) may lead to a Type II error.

Reliability

• Is dependability, consistency, and reproducibility of information obtained in a study.
• Is the probability that the same results would be obtained with different subjects, or generalizability.

Methods to Test Reliability

Test-retest

• Administering the same test/therapy/etc twice to the same group of subjects after a certain amount of time.

Equivalent-forms method

• Applying two different, but equivalent, therapies to the same group at the same time.

Internal-consistency method

• Measures the extent to which different researchers would be consistent in matching the same data and constructs.

Validity

• Is accuracy.
• Is the degree to which an instrument measures what it is supposed to measure.

Reliability

• Is consistency.
• Is the degree to which an instrument measures the same way each time it is used under the same conditions.

Peer Review Process

• Scientists study something and write about their results.
• A journal editor receives an article and sends it out for peer review.
• The editor may send reviewer comments to the scientists, who may then revise and resubmit the article for further review.
• Articles not meeting sufficiency high scientific standards, may be rejected.
• Peer reviewers read the article and provide feedback to the editor.
• If an article meets editorial and peer standards, it is published in a journal.

Transparency in Peer Review

• Journals should identify peer-reviewed articles.
• There should be access to the full text of peer reviews.
• Journals should disclose the peer review policy or guidelines.
• Journals should provide details like the average time from submission to decision, their average rejection or acceptance rate, etc.
• Details of the peer review process should be available.
• Journals should disclose publication ethics.
• Transparency should exist regarding the number of reviewers for the article, names of the editors, credentials of the reviewers, etc.

Ethics Review

• Ethics committees act to safeguard human rights and protect people who participate in health care research.
• Ethical principles and guidelines play an important role in advancing the pursuit of knowledge while protecting and respecting research participants.

Core Ethical Principles

Respect for Persons

• Recognizes the intrinsic value of human beings and the respect and consideration they are due.

Concern for Welfare

• The quality of a person's experience of life in all its aspects.

Justice

• The obligation to treat fairly and equitably.