Chapter 1
population – total set of subjects in which we are interested / sample – subset of pop. for whom we have data
descriptive statistics – methods for summarizing data (graphs, avgs, percentages, etc.)
inferential statistics – methods of making decisions / predictions about a population based on sample data.
design – planning how to obtain data / probability – helps to determine chances of an occurrence
random sampling – good and crucial for experiments and studies
subjects – entities that are measured in a study
parameter – numerical summary of a population / statistic – numerical summary of sample taken from a pop.
Chapter 2
variable – any characteristic that is recorded for subjects in a study
categorical variable – observation that belongs to one of a set of categories (college major, dating status, etc.)
quantitative variable – observation that takes on numerical value that represents magnitude of value (GPA, etc.)
discrete quantitative variable – a count; finite number of possible values (“the number of.
..”)
continuous “
“  form an interval; continuum of infinitely many possible values (time, height, dist., etc.)
frequency table – shows # of observations/values for variable; counts
percentage table – shows proportions x 100 (percentages and proportions are relative frequencies)
categorical variable graphs – pie charts, bar graphs (Pareto chart – bar graph ordered by highest to lowest freq., Pareto
principle – a small subset of categories often contains most of the observations).
quantitative variable graphs
dot plot
stemandleaf plot
histogram
dot & s&l plots good for small data sets; histograms good for large data sets
histograms more flexible in defining intervals than s&l plots
data values retained in s&l and dot plots but not histograms
bar chart – for categorical variables, histogram – for quantitative variables

 shape – symmetric
skewed to the right if
or skewed
if right tail > left tail
(highest pt
(pop. is
viceversa
 mode)
polarized)
time series – data set collected over time; graphically displayed by time plot; common pattern – trend
measures of center – mean and median
mean = sum of observations / number of observations; median – midpt. of obs. ordered from least to greatest
mean =
symmetric shape: mean = median, right skewed: mean > median, left skewed: mean < median
outliers – observations that fall well above/below overall bulk of data
mean can be highly influenced by outliers / median is resistant to outliers / mode – value that occurs most freq.
numerical summary of observations is resistant if outliers have little to no effect on its value
measures of spread – range and standard deviation
range: difference b/w largest and smallest observations
deviation: difference b/w observation and mean (xx); positive deviation + negative deviation = 0
variance: avg of squared deviations / standard deviation: square root of variance
standard deviation =
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview.
Sign up
to
access the rest of the document.
 Fall '08
 FRANKLIN
 Statistics, Inferential Statistics, explanatory variable, press enter

Click to edit the document details