Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
26 Cards in this Set
- Front
- Back
Response Variable
|
the values of a set of variables
|
|
Study Conditions
|
measuring the values of a set of variables under a set of conditions
|
|
Explanatory Variable
|
Explaining the values of a response variable
|
|
Quantitative
|
Levels of an explantory variable are measured on an interval/ratio scale
|
|
Qualitative
|
Levels of an explanatory variable are measured on a nominal/ordinal scale
|
|
Nominal
|
When a type of ordering or ranking of the levels of a categorical variable is not appropriate(type of animal, favorite drink....)
|
|
Ordinal
|
When a type of ordering or ranking of the levels of a categorical variable makes sense (pain level 1-10...)
|
|
Interval
|
When the difference between levels of a quantitative variable is meaningful. However, the zero point is arbitrary and not a true zero. For example, the difference between 100 degrees and 90 degrees is the same as the difference between 90 degrees and 80 degrees (temperature). However, it does not make sense to say 50 degrees is twice as hot as 25 degrees.
|
|
Ratio
|
Has all of the properties of of an interval scale with the added property of a fixed zero point (weights, lengths, times). 10 inches is twice as long as 5 inches. The time between 5 minutes and 10 minutes = the time between 10 minutes and 15 minutes
|
|
Observational Units/Sampling Units
|
The smallest units of the study material for which responses are measured.
Subjects in a drug study are smallest units Individual plants studied are observational units Weight collected at multiple times, observatioanl unit is subject at each weigh time Chickens in a pen - each chicken is an observational unit |
|
Factor
|
An explantory variable whose effect on the response is a primary objective
|
|
Confounding Variable
|
An explanatory variable whose effect has the potential to mask (or enhance) the effect of a factor
Not taking amount of light into consideration for an experiment measuring the growth of plants |
|
Experimental Study
|
A study in which the investigator selects the levels of at least one factor
|
|
Experimental Factor
|
A factor whose levels are determined by the investigator
|
|
Observational Study
|
A design in which the levels of all the explanatory variables are determined as part of the observational process
Studying the effect of alcohol consumption on pregnant mothers - probably easier to simply find mothers who already drink rather than asking people to do it and classify alcohol consumption while observing |
|
Treatment
|
A combination of the levels of one or more experimental factor
|
|
Experimental Unit
|
The smallest unit of the study material sharing a common treatment
Study with multiple weight collections - each subject is experimental unit Chickens in a pen - the pen of chickens is the experimental unit Plants in a pot - the pot is the experimental unit |
|
Error Variation
|
Variation due to unidentified sources
|
|
Reasons for random allocation of treatments to experimental units
|
1. Allows observed responses to be regarded as random samples - many stats assumptions require random sample
2. Eliminates systematic biases |
|
Replications
|
The number of experimental units for which responses to a particular treatment are observed
20 pens of 5 chickens - 5 replications (the pens are the experimental units and each has 5 chickens) |
|
Blocks
|
Groups of experimental units sharing a common level of a confounding variable
|
|
Randomized Complete Block Design
|
Every treatment is applied to exactly one randomly selected experimental unit within a block
|
|
ANOVA Assumptions
|
1. Samples come from normal populations
2. Equal variances 3. Independent random samples from t populations |
|
Parameter vs. Statistic
|
Parameter = number that describes a characteristic of population (usually known)
Statistic = a number that describes a characteristic of the sample |
|
Contrast of sample means
|
Coefficients satisfy the condition that:
c1+c2+....+ct = 0 |
|
Mutually Orthogonal Contrasts
|
A set of k contrasts is mutually orthogonal if all the pairs in the set are mutually orthogonal
c1*d1 + c2*d2 +.....=0 |