A randomized controlled trial is a special method of doing a scientific experiment which can reduce certain sources of bias. It is often used in the context of testing whether drugs are effective against a set of symptoms. When doing the test, the participants are randomly put into different groups. Each group is treated differently, and at the end the results are compared. A common case is that one group will receive a placebo drug, while the other will receive the real one. The trial is called blinded, if the participants, or those giving the drugs do not know what group a patient is in.
Controlled studies and trials have been done for a long time. In 1753, James Lind published a study that shows that scurvy could be treated by a diet including many lemons and oranges. Ignaz Semmelweis, a Hungarian doctor in Vienna, established the term "systematic controlled observation". Semmelweis is known today because he linked an increase in childbed fever to missing hygiene in hospitals. At the end of the 19th century, the first problem of not assigning people to test groups randomly became apparent. Austin Bradford Hill established the term "randomized controlled trial" in the 1940s. He did a study regarduing the treatment of tuberculosis with Streptomycin (an antibiotic) in the 1940s. This study is seen as thew first randomized controlled triall.[1]
- ↑ Medical Research Council Streptomycin in Tuberculosis Trials Committee: Streptomycin treatment of pulmonary tuberculosis. In: British Medical Journal. Volume2, 1948, pages 769–783.
|
---|
|
|
---|
Continuous data | |
---|
Count data | |
---|
Summary tables | |
---|
Dependence | |
---|
Graphics |
- Bar chart
- Biplot
- Box plot
- Control chart
- Correlogram
- Fan chart
- Forest plot
- Histogram
- Pie chart
- Q–Q plot
- Run chart
- Scatter plot
- Stem-and-leaf display
- Radar chart
- Violin plot
|
---|
|
|
|
---|
Study design |
- Population
- Statistic
- Effect size
- Statistical power
- Optimal design
- Sample size determination
- Replication
- Missing data
|
---|
Survey methodology | |
---|
Controlled experiments | |
---|
Adaptive Designs |
- Adaptive clinical trial
- Up-and-Down Designs
- Stochastic approximation
|
---|
Observational Studies |
- Cross-sectional study
- Cohort study
- Natural experiment
- Quasi-experiment
|
---|
|
|
|
---|
Statistical theory | |
---|
Frequentist inference | Point estimation |
- Estimating equations
- Unbiased estimators
- Mean-unbiased minimum-variance
- Rao–Blackwellization
- Lehmann–Scheffé theorem
- Median unbiased
- Plug-in
|
---|
Interval estimation | |
---|
Testing hypotheses |
- 1- & 2-tails
- Power
- Uniformly most powerful test
- Permutation test
- Multiple comparisons
|
---|
Parametric tests |
- Likelihood-ratio
- Score/Lagrange multiplier
- Wald
|
---|
|
---|
Specific tests | | Goodness of fit | |
---|
Rank statistics |
- Sign
- Signed rank (Wilcoxon)
- Rank sum (Mann–Whitney)
- Nonparametric anova
- 1-way (Kruskal–Wallis)
- 2-way (Friedman)
- Ordered alternative (Jonckheere–Terpstra)
|
---|
|
---|
Bayesian inference | |
---|
|
|
|
---|
Correlation | |
---|
Regression analysis |
- Errors and residuals
- Regression validation
- Mixed effects models
- Simultaneous equations models
- Multivariate adaptive regression splines (MARS)
|
---|
Linear regression | |
---|
Non-standard predictors |
- Nonlinear regression
- Nonparametric
- Semiparametric
- Isotonic
- Robust
- Heteroscedasticity
- Homoscedasticity
|
---|
Generalized linear model | |
---|
Partition of variance |
- Analysis of variance (ANOVA, anova)
- Analysis of covariance
- Multivariate ANOVA
- Degrees of freedom
|
---|
|
|
Categorical / Multivariate / Time-series / Survival analysis |
---|
Categorical |
- Cohen's kappa
- Contingency table
- Graphical model
- Log-linear model
- McNemar's test
- Cochran-Mantel-Haenszel statistics
|
---|
Multivariate |
- Regression
- Manova
- Principal components
- Canonical correlation
- Discriminant analysis
- Cluster analysis
- Classification
- Structural equation model
- Multivariate distributions
|
---|
Time-series | General |
- Decomposition
- Trend
- Stationarity
- Seasonal adjustment
- Exponential smoothing
- Cointegration
- Structural break
- Granger causality
|
---|
Specific tests |
- Dickey–Fuller
- Johansen
- Q-statistic (Ljung–Box)
- Durbin–Watson
- Breusch–Godfrey
|
---|
Time domain |
- Autocorrelation (ACF)
- Cross-correlation (XCF)
- ARMA model
- ARIMA model (Box–Jenkins)
- Autoregressive conditional heteroskedasticity (ARCH)
- Vector autoregression (VAR)
|
---|
Frequency domain | |
---|
|
---|
Survival | Survival function |
- Kaplan–Meier estimator (product limit)
- Proportional hazards models
- Accelerated failure time (AFT) model
- First hitting time
|
---|
Hazard function | |
---|
Test | |
---|
|
---|
|
|
Applications |
---|
Biostatistics | |
---|
Engineering statistics |
- Chemometrics
- Methods engineering
- Probabilistic design
- Process / quality control
- Reliability
- System identification
|
---|
Social statistics | |
---|
Spatial statistics |
- Cartography
- Environmental statistics
- Geographic information system
- Geostatistics
- Kriging
|
---|
|
|