STATISTICS, THE ART AND SCIENCE
OF LEARNING FROM DATA.
DATA - answer information we gather with experiments and surveys
STATISTICS - answer the art and science of collecting, presenting and analyzing data to
answer an investigative question objectively
THREE MAIN COMPONENTS OF STATISTICS - answer design, description, inference
DESIGN COMPONENT OF STATISTICS - answer stating the goal and/or statistical
question of interest. And planning how to obtain data to address this.
DESCRIPTION COMPONENT OF STATISTICS - answer summarizing and analyzing the
data that are obtained. Helps find patterns in data.
INFERENCE COMPONENT OF STATISTICS - answer making decisions and predictions
based on the data to answer statistical question and decide whether observed patterns are
meaningful. Also to draw a conclusion about the population, based on the sample.
PROBABILITY - answer “a framework for quantifying how likely various possible
outcomes are".
THE VARIABLE - answer refers to the characteristics being measured.
SUBJECTS - answer the entities measured in a study, which are usually people but can also
be other things such as schools, countries or days.
THE POPULATION - answer the set of all subjects of interest. However, we usually don't
have data for all of the subjects in the population.
SAMPLE - answer the subjects that we have data on, often randomly selected
DESCRIPTIVE STATISTICS - answer refers to methods for summarizing/ compressing the
collected data. The summaries usually consist of graphs and numbers such as averages and
percentages. Easy way to get overview of large quantities of data
INFERENTIAL STATISTICS - answer refers to methods of making decisions or predictions
about a population based on data obtained from a sample of that population, assessing
uncertainty about statements. Used when data are only available for a sample, but we want
to make decisions or predictions about the entire population.
, A PARAMETER - answer a numerical summary of the population, what we want to learn
about. Can’t be computed easily. Usually unknown but we use sample statistics to estimate
parameter values
A (SAMPLE) STATISTIC - answer a numerical summary of a sample taken from the
population. You can compute this: mean median standard deviation etc.
RANDOM SAMPLING - answer randomly selecting sample, designed to make the sample
representative of the population, by not favoring any part of the population with certain
characteristics. Random sampling allows us to make inferences about populations, it's also
crucial to performing experiments well.
VARIABILITY - answer how observations vary from person to person within a sample, and
how statistics computed from samples vary from one sample to the next, i.e., between
samples.
WITHIN SAMPLE VARIABILITY - answer the measurements we make on people vary
from person to person, not surprising because people are different from each other.
BETWEEN SAMPLE VARIABILITY - answer variation in results computed from samples.
The amount of variability in the results from one sample to another is quite predictable.
MARGIN OF ERROR - answer measure of the expected variability in the results from one
sample tot the next random sample
A MARGIN OF ERROR OF +3% - answer indicates that it is very likely that the population
percentage is no more than 3% lower or 3% higher than the reported sample percentage.
DIFFERING SIGNIFICANTLY - answer observed difference computed between the two
samples is larger than what would be expected from ordinary random sample-to-sample
variability
STATISTICALLY SIGNIFICANT - answer results of study would rarely be observed with
only ordinary random variation.
VARIABLE - answer characteristic observed in a study, height of a subject for example.
CATEGORICAL VARIABLE - answer each observation belongs to one of a set of distinct
categories. Key feature to describe it is the relative number of observations in the various
categories. Can be nominal or ordinal
NOMINAL CATEGORICAL VARIABLE - answer categories do not have an inherent
ordering. For example, gender or religious affiliation. Not one category is better than any
other category in any sense.
OF LEARNING FROM DATA.
DATA - answer information we gather with experiments and surveys
STATISTICS - answer the art and science of collecting, presenting and analyzing data to
answer an investigative question objectively
THREE MAIN COMPONENTS OF STATISTICS - answer design, description, inference
DESIGN COMPONENT OF STATISTICS - answer stating the goal and/or statistical
question of interest. And planning how to obtain data to address this.
DESCRIPTION COMPONENT OF STATISTICS - answer summarizing and analyzing the
data that are obtained. Helps find patterns in data.
INFERENCE COMPONENT OF STATISTICS - answer making decisions and predictions
based on the data to answer statistical question and decide whether observed patterns are
meaningful. Also to draw a conclusion about the population, based on the sample.
PROBABILITY - answer “a framework for quantifying how likely various possible
outcomes are".
THE VARIABLE - answer refers to the characteristics being measured.
SUBJECTS - answer the entities measured in a study, which are usually people but can also
be other things such as schools, countries or days.
THE POPULATION - answer the set of all subjects of interest. However, we usually don't
have data for all of the subjects in the population.
SAMPLE - answer the subjects that we have data on, often randomly selected
DESCRIPTIVE STATISTICS - answer refers to methods for summarizing/ compressing the
collected data. The summaries usually consist of graphs and numbers such as averages and
percentages. Easy way to get overview of large quantities of data
INFERENTIAL STATISTICS - answer refers to methods of making decisions or predictions
about a population based on data obtained from a sample of that population, assessing
uncertainty about statements. Used when data are only available for a sample, but we want
to make decisions or predictions about the entire population.
, A PARAMETER - answer a numerical summary of the population, what we want to learn
about. Can’t be computed easily. Usually unknown but we use sample statistics to estimate
parameter values
A (SAMPLE) STATISTIC - answer a numerical summary of a sample taken from the
population. You can compute this: mean median standard deviation etc.
RANDOM SAMPLING - answer randomly selecting sample, designed to make the sample
representative of the population, by not favoring any part of the population with certain
characteristics. Random sampling allows us to make inferences about populations, it's also
crucial to performing experiments well.
VARIABILITY - answer how observations vary from person to person within a sample, and
how statistics computed from samples vary from one sample to the next, i.e., between
samples.
WITHIN SAMPLE VARIABILITY - answer the measurements we make on people vary
from person to person, not surprising because people are different from each other.
BETWEEN SAMPLE VARIABILITY - answer variation in results computed from samples.
The amount of variability in the results from one sample to another is quite predictable.
MARGIN OF ERROR - answer measure of the expected variability in the results from one
sample tot the next random sample
A MARGIN OF ERROR OF +3% - answer indicates that it is very likely that the population
percentage is no more than 3% lower or 3% higher than the reported sample percentage.
DIFFERING SIGNIFICANTLY - answer observed difference computed between the two
samples is larger than what would be expected from ordinary random sample-to-sample
variability
STATISTICALLY SIGNIFICANT - answer results of study would rarely be observed with
only ordinary random variation.
VARIABLE - answer characteristic observed in a study, height of a subject for example.
CATEGORICAL VARIABLE - answer each observation belongs to one of a set of distinct
categories. Key feature to describe it is the relative number of observations in the various
categories. Can be nominal or ordinal
NOMINAL CATEGORICAL VARIABLE - answer categories do not have an inherent
ordering. For example, gender or religious affiliation. Not one category is better than any
other category in any sense.
