QA Freling Chapter 1

Lecture notes

Data

facts and figures collected, analyzed, and summarized for presentation and interpretation

Elements

The things that we collect data on, aka, objects on which data are collected

Variables

Characteristics of the elements that we’re interested in

Observation

The set of measurements for a particular element. Can (will) contain multiple variables

Scales of measurement

Determines the amount of information contained in the data & indicates the most appropriate data summarization & statistical analysis

Four scales of measurement

* Nominal
* Ordinal
* Interval
* Ratio

Nominal

Data that has names, i.e., buckets.

* Can be coded numerically in a data set, e.g.:

\-- Undergrad student = 0

\-- Graduate Student = 1

Ordinal

Data for a variable exhibits nominal properties AND the data can be ordered in an objectively meaningful way.

ex:

* mostly sad
* sometime sad
* neither happy nor sad
* sometimes happy
* mostly happy

Interval

Data for a variable exhibit BOTH nominal and ordinal properties, AND the interval between values is expressed in terms of a fixed unit of measure, AND always numeric.

ex:

* 10 degrees
* 20 degrees
* 30 degrees
* 40 degrees

These have a meaningless zero. Holds no measures, aka is arbitrary. for example, zero degrees fahrenheight does not signify the lack of heat, it is simply a point on a scale that is temperature.

Ratio

Data for a variable exhibits:

* interval properties AND
* Ratio of two values is meaningful
* always numeric
* Zero - means ‘the absence of’ or nothing exists, aka, opposite of interval definition.

Categorical Data (Qualitative)

Grouped by specific categories (limited statistical analysis available)

Quantitative

Use numeric values to indicate how much or how many (arithmetic operations provide meaningful measures)

Cross-sectional data

Data collected at the same or approximately the same point in time.

Time series data

Data collected over several time periods

The largest experimental statistical study ever conducted is believed to be for:​

Polio

Observational

Data acquired by observing what is occurring in a particular setting and recording variables of interest

Descriptive Statistics

Data that is summarized and presented in a form that is easy for the audience to understand

* tables
* graphs
* numbers

Statistical Inference

The application of statistical processes to data collected from a *sample* to make estimates and test *hypotheses* about the characteristics of a population.

Population

The set of all elements of interest in a particular study

Sample

A subset of the population

Descriptive analytics

Describe what has happened in the past

Predictive analytics

the usage of analytical techniques that use models constructed from past data to predict the future or to assess the impact of one variable on another.

Big data

The volume of data collected by businesses today is immense - these large and complex data sets are referred to as Big Data.

* volume
* velocity
* variety
* veracity

Data Mining

The process of converting Big Data into useful information via the combination of statistics, mathematics, and computer science.

Proportion

The number of persons related to the certain group divided by the total number of persons in the sample

\
p = x/n

Frequency Distribution

Visual displays that organize and present frequency counts so that the information can be interpreted more easily.

* divide the frequency (f) by the total # of results (r) and multiply by 100.
* (f/r) x 100