Statistics Flashcards
list the 3 reasons why we study statistics
- objective evaluation of numbers
- population description
- estimate unknown value
what is breeding value?
the actual genetic worth of an animal
what is variation?
the raw material that a breeder has to work with
list the 2 kinds of variation
- discontinuous
2. continuous
describe discontinuous variation
involves quaLitative traits, where few, discrete genes determine the phenotype, and the phenotype is not greatly influenced by the environment
describe continuous variation
involves quaNtitative traits, or economically important traits, where many genes control the phenotype, which has many small gradations that are almost imperceptible to one another, and are highly complex
what does a random sample represent?
inferences from a population
what is a population parameter?
a numerical descriptive measure for a population, number that describes a population
what is a sample statistic?
numerical descriptive measures for a sample, estimate of population parameter
what is central tendency?
the values clustered at the midpoint, thinning out symmetrically toward both extremes
what are the 3 measures of central tendency?
- mean
- median
- mode
what is the most useful statistic for estimating central tendency of most populations?
mean!
describe the formula of mean
the sum of all values divided by the amount of values
what is variance?
a measure of the distribution (deviation around the mean)
describe the formula for variance
defined as the average squared deviation of observations from their mean
list the 4 steps to compute variance
- subtract the mean from each observation in the sample
- square results of #1
- add squared results
- divide sum by n-1
what is standard deviation?
“typical” deviation, in absolute value, of an observation drawn at random from the population from its mean
how can standard deviation be used?
to describe variation in a population
what does standard deviation help us picture?
how much variation actually exists for a trait
what is standard error?
how accurately the mean has been estimated
what are correlation and regression? and what are they not?
they are measures of association, NOT predictions
what is correlation?
measures the strength of the relationship between 2 variables, a population measure
when asking, is one trait of an animal associated with another? what are you referring to?
correlation
what does the correlation coefficient measure?
the degree of association between 2 variables (traits) in a sample from a population, the degree of tightness of the relationship
what is the range of the correlation coefficient?
-1.0 to +1.0
what does a correlation of 1.0 indicate?
that for each standard unit increase in one variable, there is a standard unit increase in the correlated trait
what does a significant correlation indicate?
that there is a high probability that there is a real association between the traits
what unites is correlation measured in?
none, it’s unitless
what can’t correlation be used for? why?
to predict the level of one variable based on the second, because there is no basis for cause and effect determination
what are the 3 types of correlation?
- phenotypic correlation
- genotypic correlation
- environmental correlation
describe phenotypic correlation
measures the strength of the relationship between performance (a phenotypic value) in one trait and performance in another trait
give the variable for phenotypic correlation
rp
describe genetic correlation?
measures the strength of relationship between breeding value for one trait and breeding value for another trait
give the variable for genetic correlation
rg
why is genetic correlation important?
because of the concept of correlated response to selection (selection for one trait leads to selection on another trait)
describe environmental correlation
measure of the strength of the relationship between environmental effects
give the variable for environmental correlation
re
what does regression coefficient measure?
measures the change in Y response per unit change in X
how good is regression at predicting values?
the greater the slope, the closer the association between 2 traits
what units is regression expressed in?
the original units of measure of the values
what is the regression of y on x?
byx
of x and y in regression, which is the cause and which is the effect (assumed)?
x is cause, y is effect
when is regression used?
when we want to predict the numerical value of one trait from the phenotypic value of another, when it may be difficult or expensive to measure y
