POSC 202A: Lecture 1 Introductions Syllabus R Homework #1: Get R installed on your laptop; read chapters 1-2 in Daalgard, 1 in Zuur, See syllabus for Moore.

POSC 202A: Lecture 1

IntroductionsSyllabusR

Homework #1: Get R installed on your laptop; read chapters 1-2 in Daalgard, 1 in Zuur, See syllabus for Moore and McCabe

Today: why statistics? Where is the science?

Why Statistics?

Statistics: Uncertainty

The world is stochastic, not deterministic.

Stochastic

A process characterized by chance, randomness or probability.

In other words…

Stochastic

In other words….

SHIT HAPPENS!

Deterministic

A theory holding that, in nature, social phenomena are causally determined by preceding events.


Deterministic World View Stochastic World View


Deterministic World View Stochastic World View

The relationship between the cigarettes and death rate (i.e. the slope) is identical in both graphs.



Statistics provides a framework that allows us to account for this uncertainty.




Statistics is about guessing, or drawing inference.



Statistics is about guessing, or drawing inference.

But

There are many ways to guess:


Statistics provides a framework that allows us to explicitly account for uncertainty.

We can estimate how confident we should be in our guesses.

Political Science

Where is the science?

Political Science

Where is the science?

What make the study of politics scientific?

Political Science-

Empirical study of the political world:

the study of what is, not what should be.

What do political scientists do?

Describe, classify and explain events relating to the political world.



Try to distinguish the systematic from the non-systematic.



More specifically

We try to draw inference from what we see to what we do not.

What is Inference?

Inference

• Making statements about what we do not see from what we do see.

Examples?

How?

Develop and test hypotheses based on theory.

Hypothesis

a relational statement between two or more variables that is theoretically plausible and

empirically verifiable.

How?


What is Theory?

Explanations for how the world works based on experience and observation.

How?


How do we test theories and hypotheses?

How do we test theories and hypotheses?

For each hypothesis we make a list of all of the implications we can think of.

Implication

Implication

Some event or occurrence that must be true if the theory is true.

Hypothesis testing: the mechanics

1.

2.

3.

4.


1. Articulate a hypothesis

2.

3.

4.



2. Identify its implications• Make a list of all the things that must be true

if the theory is true.• As many as we can think of!

3.

4.



2. Identify its implications

3. Attempt to prove the implications stemming from theory false.

4.



2. Identify its implications

3. Attempt to prove the implications stemming from theory false.

4. Evaluate by looking at data

Data

Empirical evidence-information about the state of the world.

Ben Bishin

note that its not necessarily quantitative evidence

The same research principles always apply whether our data are qualitative or quantitative

Types of Evidence

Qualitative evidence: The collection and organization of evidence (data) using particular facts (or often cases).

Quantitative evidence: The collection and organization of evidence (data) using numbers usually through statistics.

What Makes the Process Scientific?

1.

2.

3.

4.


1. The goal is inference


The goal is inference:

Scientific research is designed to make descriptive or explanatory generalizations on the basis of empirical information.


The goal is inference (2 types)

Descriptive

A generalization about the state of the world based on the small part that we see.

Causal

A generalization about how the world works based on the small part that we see.



2. The procedures are public


The procedures are public

Scientific research uses explicit, codified and public methods to generate and analyze data whose reliability can therefore be assessed.


The procedures are public

Scientific research uses explicit, codified and public methods to generate and analyze data whose reliability can therefore be assessed.

Results should be replicable.




3. The conclusions are uncertain


The conclusions are uncertain

Inference is an imperfect process. Without an estimate of uncertainty a description of the world is not very meaningful.


Two types of uncertainty:

Fundamental uncertainty: Uncertainty inherent in the relationship between two things.

Estimation uncertainty: Uncertainty in our inference due to the methods we use to draw the inference.



Example: Probability of getting lung cancer

Smoker .34

Non-smoker .03

Not everyone who smokes gets lung cancer.


Two types of uncertainty:





Example: public opinion poll

The uncertainty in our estimates is a function of how large the sample is that we draw.

Sample size (N)

Margin of Error

100 10%

400 5%

900 3%




3. The conclusions are uncertain

4. The content of science is its (the) method


The content of science is its (the) method:

Scientific research adheres to rules on which its validity depends.

These rules can be applied to the study of any subject.


The content of science is its (the) method:

Scientific research adheres to rules on which its validity depends.

These rules can be applied to the study of any subject.

The possible subjects to be studied are endless but the principles (rules) for studying them are not.

POSC 202A: Lecture 1 Introductions Syllabus R Homework #1: Get R installed on your laptop; read chapters 1-2 in Daalgard, 1 in Zuur, See syllabus for Moore.

Documents

implication slide

uncertainty statistics

political world

political scientists

test hypotheses

hypothesis testing

preceding events

study of politics scientific