Studied by 0 people
Looks like no one added any tags here yet for you.
Blocking
Grouping already selected subjects into subgroups (blocks) and then randomly assigning each block to treatments.
Purpose of blocking
To reduce variability so that differences can be more easily seen.
Direct control
A method to reduce variability for clearer observation of differences.
Completely randomized experiment design
The most common type of experiment where subjects are randomly assigned to treatments.
Matched pairs experiment
An experimental design where either both treatments are given to a single individual or subjects are matched based on similar characteristics before randomizing treatments.
Point of matched pairs experiments
To reduce within-subject variability.
Control group
A group that receives no treatment, used for comparison against a treatment group.
Placebo
A treatment that appears identical to another but contains no active ingredients, serving as a secret control group.
Single blind
An experimental design where subjects do not know which treatment they are receiving, but the measurers do.
Double blind
An experimental design where neither the subjects nor the measurers know which treatment is being administered, although the experimenter does.
Dot plot
A chart used for displaying numerical data.
Bar chart
A chart used for displaying categorical data.
Mosaic chart
In this chart, each bar's width represents its frequency.
Random selection using random numbers
Choose two numbers at a time, where 01-30 represent people, ignoring 31-99 and repeats until three people are selected.
Number of classes for a histogram
Calculated as the square root of the number of observations.
Class width/intervals
Determined by the formula class width = (high - low) / number of classes.
Left skewed
Another term for negatively skewed data.
Right skewed
Another term for positively skewed data.
Fixing unequal intervals
Achieved by dividing the frequency by the width, known as density.
Bad graphing practices
Poor scaling, such as not starting at zero, can exaggerate differences in graphs.
Scatter plots
Used for displaying bivariate data (numerical data).
