Scribd
Upload
32 views19 pages

Introduction, Sampling, and Measurement

This document provides an introduction to key concepts in statistics, including data, variables, levels of measurement, populations and samples, descriptive and inferential statistics, and types of sampling. It discusses how variables can be quantitative or qualitative, and the different levels of measurement from nominal to ratio. It also distinguishes between populations and samples, parameters and statistics, and explains the goals of descriptive and inferential statistics.

Uploaded by

kaliman2010
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
32 views19 pages

Introduction, Sampling, and Measurement

This document provides an introduction to key concepts in statistics, including data, variables, levels of measurement, populations and samples, descriptive and inferential statistics, and types of sampling. It discusses how variables can be quantitative or qualitative, and the different levels of measurement from nominal to ratio. It also distinguishes between populations and samples, parameters and statistics, and explains the goals of descriptive and inferential statistics.

Uploaded by

kaliman2010
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 19

Introduction, Sampling,

and Measurement

Why Statistics?

Behavioral revolution.
This is how many of us communicate.
Not the only approach, but the most common approach.

Data

Gather information about observations.


Collectively, observations are our data.

Whats a Variable?

A measurable characteristic of an observation.


Things vary and we want to explain why!

Qualitative vs. Quantitative

Quantitative variables have numerical values.


Qualitative variables have categories.

Levels of Measurement

Nominal: different categories.


Categories are exhaustive and mutually exclusive.
Makes the least assumptions about the phenomenon.
Ordinal: meaningful order.
Interval: intervals between categories have meaning.
0 is arbitrary.
Ratio: 0 means absence of the what were measuring.

Strong Democrat

Democrat

Leaning Democrat

Independent

Leaning Republican

Republican

Strong Republican

var2
2

More on Ordinal vs. Interval

Ordinal often treated as interval.

More on Ordinal vs. Interval

Source: Jacoby (1999)


8

Strong Democrat

Democrat

Leaning Democrat

Independent

Republican
Leaning Republican

Strong Republican

var2
2

More on Ordinal vs. Interval

Another Typology: Discrete and Continuous

Discrete: integers.
Continuous: an infinite continuum of possible values.

10

Populations and Samples

Population: all cases of interest.


A census.
Sample: a selected subset of the population from which

data is collected for study.


A random survey of 800 residents.

11

Parameters and Statistics

Measurements of population quantities are called

parameters.
Often represented with Greek alphabet.

Measurements of the sample quantities are called

statistics.
Often represented with Latin alphabet.

12

Descriptive Statistics

Descriptive statistics are a summary.


Often presented graphically.

13

Inferential Statistics

Make predictions (inferences) about population.


Were rarely just interested in our sample.

14

Kinds of Random Samples

Simple random sample.


Stratified random sampling.
Cluster sampling.
Multistage sampling.
Post-stratification.

15

Why Sample?

If you want to know the population values, why not just

measure them?
Too expensive.
Sampling can be more accurate less error.
Sample: fewer measurements, but each is more accurate.
Census: more measurements, but many are inaccurate.

16

Sampling Error and Bias

Error: bad luck.


Bias:
Sampling bias: under coverage (incomplete sampling
frame).
Nonresponse bias: inadvertently end up with
unrepresentative sample.
Response bias: inaccurate responses.

17

Experiments vs. Observational Studies

Another kind of randomization.


Control group and experimental group(s).

18

A Word of Warning

Software is now very easy to use.


It is essential you understand what youre doing.
Computers will do whatever you tell them to.

19

You might also like