Statistics - Exam 4 Flashcards
definition of statistics
the science of assembling, classifying, tabulating, and analyzing data of a numerical nature to present significant information about a given subject
definition of descriptive statistics
a way of summarizing data from population or sample
definition of statistical inference
comparison of data (outbound of objectives)
definition of data
a collection of information; a set of values of qualitative or quantitative variables
definition of qualitative data
non-numeric data
definition of quantitative data
numeric data
definition of measurement
assigning numbers to observations according to preset rules
definition of variable
a measured characteristic that can have various values or levels
definition of discrete variables
quantitative, can have only certain values (whole numbers)
definition of continuous variables
quantitative, can have any value (whole numbers or fractions)
definition of binary variables
have only 2 possible values (yes/no)
what are the 2 types of variables
qualitative and quantitative
what are the 3 types of qualitative variables
binary, nominal, ordinal
example of qualitative binary variable
death yes or no, presence of blood in urine
example of qualitative nominal variable
type of husbandry building in the farm
example of qualitative ordinal variable
score of judges at a dog show
what are the 2 types of quantitative variables
discrete & continuous
example of quantitative discrete variable
RBC count, parity of cattle, litter size of dogs
example of quantitative continuous variable
weight of calves at birth, girth of bulls, blood pressure of cats
definition of population
an entire group of observations that might have at least one characteristic in common
definition of sample
a group of elements selected from the total population
definition of parameter
a characteristic of a population
definition of statistic
a characteristic of a sample
descriptive statistics include
text & graphs
definition of absolute frequency
total number of observations/events (exact number of something counted)
definition of relative frequency
proportion of observations/events (percentage)
definition of tabular cumulative frequency distribution
frequency of the scores including the frequency of the previous scores, should be used for quantitative/ordinal variables only
definition of data distribution
graphical representation of the frequency distribution (i.e.: histogram)
the normal distribution is
Gaussian distribution, shaped like a bell, symmetric
quantitative data can be described with only 2
parameters (location- measure of central tendency & dispersion)
definition of a mean
the numerical average of a dataset
definition of a median
the middle value of a data set. It is the actual middle number with an odd number of data points, and it is the mean of the middle two numbers with an even number of data points
definition of a mode
the most frequent value in a dataset. can have more than one mode or no mode at all
3 main measures of variability
range, variance, standard deviation
definition of range
the range is the difference between the highest data value and the lowest value (difference with the book)
definition of variance
how far the distribution is spread out from the mean
definition of standard deviation
square root of the variance, variability of the variable distribution for the sample or for the population
standard deviation equation (SD) =
square root of sigma ^2
normal distribution (specificity) =
vertical symmetry, mean=median=mode, 50% greater than and 50% less than
definition of standard error
standard deviation of the variable “mean”; allows us to estimate the confidence interval of the mean
histogram used to represent
grouped frequency data
equation for variance (sigma^2) =
sum (x-mu)^2 / N
mu = mean
pie graph used to represent
a categorical variable; same data as a bar plot, plot frequency of 1 category
boxplot used to
plot difference of quantitative variables between several/different categories
scatter plot used to
plot 2 quantitative continuous variables (one point is one observation)
line plot used to
plot evolution of a quantitative variable in “time”, continuous