Intro to Research Chapter 1-6

Research

The search for knowledge, or any systematic investigation, to establish novel facts, solve new or existing problems, prove new ideas, or develop new theories, usually using scientific method

Clinical research

Patient-based research, medical training

Basic research

Patient or non-patient-based, outside the clinic and animal research

Industry Research

Profit-based research, basic or clinical depending on “stage of development”

Cross-sectional study

A group examined at one point in time

Cohort study

A group (usually without the outcome) identified at the beginning of the study and followed over time

Case-control study

Two groups selected based on the presence or absence of an outcome

Randomized blinded trial

Two groups created by a random process and a blinded intervention

External validity

The fidelity of with which conclusions happen apply to people and events outside the study; the planning phase, generalizability, design and infer

Internal validity

The degree to which the study’s results reflect what happened in our study, implement, analyze, and interpret

Infer

General appeal

Random error solution

Improve precision of measurements, increase sample size

Systematic error solution

Improve accuracy and validity of measurements and choose a better design

Random and systematic error solution

Quality control

Research question

The uncertainty the researcher wants to investigate

Population

Complete set of people with a specified set of characteristics

Study sample

Subset of accessible population that participates

Convenience samples

Easily accessible

Consecutive sample

Everyone that meets criteria consecutively

Probability samples

Random process to ensure general application

Simple random sample

Number everyone and pick a sample

Systematic sample

Every other person (ie; Framingham Study)

Stratified random sample

Dividing the population into subgroups according to characteristics: age, sex, etc.

Cluster sample

Natural groupings: city blocks, retirement centers

Precision

The degree to which a variable has nearly the same value when measured several times

Observer variability

Due to the observer and includes such thing as choice of words in an interview and skill in using a mechanical instrument

Instrument variabiltiy

Due to the instrument and includes changing environmental factors, differences between batches of reagents, and so on

Participant variability

Due to intrinsic variability in characteristics of study participants unrelated to variables under study that may influence the measurement, such as variability in measurements of strength, dur to time of day, time since last food intake, or effort

Accuracy

The degree to which a variable approximates the true value

Content validity

The degree to which an instrument or measurement covers the full domain of the specific construct or variable being studied

Operations manual

Described the method for conducting and recording the results of all the measurements made in the study

Research hypothesis

Specific version of the research question

Simple hypothesis

One predictor and one outcome variable

Complex hypothesis

2 predictors and 1 variable, or 1 predictor and 2 variables

Null hypothesis

A doubtful hypothesis

Ex: There is no association between regular exercise and mean fasting blood glucose levels in middle-aged women with diabetes

Alternative hypothesis

There is an association between regular exercise and mean fasting blood glucose levels in middle-aged women with diabetes

Standard for rejecting null hypothesis

Level of statistical significance

Type I error

“False-positive,” falsely assume and association, comparable to convicting an innocent person

Type II error

“False-negative,” falsely assume no association, comparable to acquitting a guilty person

P value

Statistical value, probability of ‘seeing’ an effect vs. chance

Random error

A mistake due to chance-there is no known cause or predictable pattern to the error

Translational research

Studies that translate basic science discoveries into clinical practice or that expand clinical research findings into broad-scale public health or community-based programs

Systematic review

A thorough search of published literature in the areas pertinent to the research question and read important papers critically

FINE

Feasible, Important, Novel, Ethical

Study plan

Describes the importance of the study, the design, the study participants, and how they will be selected

Inclusion criteria

Define the main characteristics of the target population that pertain to the research question and study design

Exclusion criteria

Define limited exceptions to the broad brushstrokes of the inclusion criteria and should be used parsimoniously

Non-probability sample

Do not involve a random selection process

Consecutive sample

Enrolls potential participants who meet the entry criteria in some sort of order

Convenience sample

Consists of participants who were selected because they were easy for the investigator to identify and enroll

Dichotomous

Two categories, chi-squared test, ex: dead or alive

Nominal

Unordered categories, ex: blood type, straightforward to measure

Ordinal

Ordered categories with intervals that are not quantifiable, ex: degree of pain

Continuous

Infinite number of values, weight/hemoglobin level

Short-Form (SF)-36

A standardized questionnaire for assessing quality of life that produces discrete numerical ratings of eight dimensions

Standard deviation

Helps researchers understand the variability or consistency of their data

-Standardizing the measurement methods

-Training and certifying the observers

-Refining the instruments

-Automating the instruments

-Repetition

Minimizing random error and increasing precision

Observer bias

A distortion, conscious or unconscious, in the perception or reporting of the measurement by an observer

Instrument bias

Can result from faulty function of a mechanical instrument

Participant bias

A distortion of the measurement by the study participant

Gold-standard

A reference measurement carried out by a technique that is believed to best represent the true value of the characteristic

-Standardizing the measurement methods

-Training and certifying the observers

-Refining the instruments

-Automating the instruments

-Making unobtrusive measurements

-Calibrating the instrument

-Blinding

Increasing accuracy