Physics and Math - Reasoning about the Design and Execution of Research

MCAT Chp 11

Scientific method

set of steps that defines the appropriate order of events to structure and carry out an experiment

Hypothesis

Proposed explanation to our testable question

Basic Science Research

Conducted in lab, not on people

Independent Variable

The variable manipulated

Dependent Variable

The variable measured

Controls

correct for any influences of an intervention that are not part of a model

Positive controls

enfuse that a change in DV occurs when expected

Negative Controls

ensure no change in DV occur when none is expected

Accuracy

approximating true value

Precision

quality consistent in approximations

Binary variable

two options

Continous variables

values between a certain range

Categorical variables

Fixed amount outcomes

Randomization

method used to control for differences between subject groups in biomedial research

Blinded

subject do not have info waht group they are in

Single blind experiments

only the paitent or assesor is blinded

Double blind experiment

investigator, subject assessor do not know subjects group

Main effect

single ID individually affects the DV

Interaction effect

how one IV affects the relationship between different IV and DV

Observational Studies

often look for connections between exposure and outcomes, do not demonstrate causality

Cohort Studies

subjects are sorted into groups based on differences in risk factors and then assessed at various intervals to determine how many subjects in each group had a certain outcome

Cross Sectional Studies

Categorize paitents into dfiferent groups at a single point in time

Case Control Studies

identifying the number of subjects without or with a particular outcome, and then look backwards to asses how many subjects in each group had exposure to a particular risk factor

Survey

studies give predetermined questions to participants to answer, then used for statistical analysis to draw conclusions

Content analysis

Study looks at documents and communication artifacts to find theme and patterns in communication

In depth interviews

Qualitative method obtaining detailed info from individuals using open ended questions through individual interviews

Focus Groups

Groups of people assembled to participate in guided discussion of topic

Hill Criteria

describe component observed relationship that increase likelihood of causality in the relationshiup

Hill Criteria Components

temporality, strength, pose resonse relationship, consistency, plausibility, consideration of alternative explanation, experiment, specificty, coherence

Bias

result of flaws in data collection phase of an experimental or observational study

Confounding

error during analysis

Selection bias

subjects used for the study are not representative of target population

Detection Bias

results educated professionals using their knowledge in an inconsistent way

Response Bias

Tendency partipant to inaccurately respond to questions in research

Observation Bias

Behavior of study participants in altered because they recognize they are being studied

Social Desirability bias

participant answer questions in way make seem more socially fitting

Demand characteristics

participants change behavior or respones in a study in order to match what they think is expected of them from experiment

Cofounding variable

unmeasured, not controlled variables affect IV and DV

Mediating variables

sit in between two variables and provide a mechanism explain association

Moderating variables

variable changes strength of association between IV and DV

Control variables

Variables purposely held constant throughout an experiment ensure effects variable of interest are not influenced by flucuators in CV

What is the research ethics established by

Belmont report

Populations

all of individuals who share set of characteristics

Parameter

population data

Samples

subset of population that are used to estimate population data

Statistics

Sample data

Internal Validity

identification of causality in study between IV and DV

External Validity

ability of study be generated to population that it describes

Statistical significance

low likelhood of experimental finding being due to chance

Clinical significance

usefulness or importance of experimental findings to be paitent care or paitent outcomes