Intro to Biostats

Descriptive Statistics (data analysis)

The branch of statistics concerned with organizing, summarizing, and analyzing data to describe its features.

Inferential statistics

The process of reaching decisions or drawing conclusions about a large body of data (a population) by examining only a small part of it (a sample).

qualitative variables (categorical variable)

conveys information about an attribute. We count the number in each category, which is called the frequency.

Examples: Eye color, medical diagnosis, and ethnic group.

Data

the "raw material" of statistics. It is information obtained through observation, measurement, or counting.

What are the two primary ways numeric data is obtained?

1. Measurement: Used for continuous data like weight (lbs/kg), height (in/cm), or temperature. 2. Counting: Used for discrete data like the number of phone calls per hour.

Give examples of non-numeric data

Eye color, Yes/No answers to a survey, and Gender or blood type

What are the two main pillars of the field of Statistics?

The collection, organization, summarization, and analysis of data (Descriptive). 2. Drawing inferences about a large body of data when only a small part is observed (Inferential)

Biostatistics

It is the term used when data is derived from the biological sciences or medicine. This is distinct from fields like business, education, psychology, or sports.

What are the four primary sources of data?

Routinely kept records, Surveys, Experiments, and External sources.

Variable

A characteristic that takes on different values in different persons, places, or things (e.g., height, weight, or eye color).

Quantitative Variable

A variable that can be measured, has units, and conveys information about an amount. It makes sense to take the average of these values.

• Examples: Weight, height, GPA, and salaries.

Variable

A characteristic that takes on different values in different people, places, or things (e.g., blood pressure, height).

Value

The specific result found when measuring or observing that characteristic in an individual.

Random Variable

A variable whose values arise due to chance factors and cannot be exactly predicted. (The adult height of a newborn or the result of a coin toss.)

Discrete Variable

A variable characterized by gaps or interruptions in the values it can take.

Continuous Variable

A variable that can assume any value within a specified interval. It does not have gaps.

Entities

The individual "things" about which we take measurements.

Population

The collection of all entities for which we have an interest at a particular time.

What is a Population of Values?

The largest collection of values for a random variable generated by measuring every entity in a population.

Finite

Contains a fixed number of values or entities

Infinite

Contains an endless number of values or entities

Parameter

An exact, fixed value calculated from a population. We usually use a Greek letter as shorthand to label it.

Measurement

the assignment to numbers, objects, or events according to a set of rules.

Sample

part of a population

statistic

a value calculated from a sample

Nominal Scale

The simplest level of measurement used for qualitative data. It involves naming or classifying observations into categories

Ordinal Scale

A scale that involves ranking observations according to specific criteria. Numbers are assigned to order or rank observations from lowest to highest, but the "distance" between ranks isn't necessarily equal.

Interval Scale

A true quantitative scale that orders observations and has a known, meaningful distance between any two measurements. It has a unit distance and a zero point, but the zero is not "true" (it doesn't mean a total absence of the variable).

Ratio Scale?

The highest level of measurement. Like the interval scale, distances mean the same thing, but it also features a true zero point. This allows you to say one value is "twice as much" as another (ratios are meaningful).

Statistical inference

the procedure which we reach a conclusion about a population based on the information taken from a sample of a population

representative

A sample that resembles the population

Sample Random sample

A specific way of picking a sample where every single entity in the population has an equal chance of being selected

sampling with replacement

every entity (number) of the population is available at each draw

sampling without replacement

We would not record the height of anyone already selected.

research study

a scientific study of a phenomenon of interest.

Experiment

A special type of research study in which observations are made after specific manipulations of conditions have been carried out.

scientific method

a process by which scientific information is collected, analyzed, and reported in order to produce unbiased and replicable results in an effort to provide an accurate representation of observable phenomena.

experimental design 

one in which study subjects are randomly assigned to an experimental group (or treatment group) and to a control group that is not directly exposed to a treatment.