# Lecture 2 MLOS 500_O

Views:

Category: Entertainment

## Presentation Description

No description available.

## Presentation Transcript

### MLOS 500A Online Lecture 2:

MLOS 500A Online Lecture 2 Types of Questions

### Three Basic Questions:

Three Basic Questions Descriptive: answers the question of “what is going on” or “what exists” What percentage of the population voted for a Democratic or a Republican presidential candidate? What is the distribution of Democratic versus Republican votes?

3 Some interesting descriptive answers Voting results by state in 2004

4 Some interesting descriptive answers Voting results by state population density in 2004

5 Some interesting descriptive answers Voting results by county in 2004

6 Some interesting descriptive answers Actual distribution between Republican (red) and Democrat (blue) expressed by scale in 2004

7 Some interesting descriptive answers States where the margin of difference was less than 5%

### The important point is. . . .:

9 The important point is. . . . What can you INFER from the distributions portrayed by the maps? NOTHING

### Three Basic Questions:

10 Three Basic Questions Relational: looks at the associations between two or more variables How do males and females say they would vote for a Democratic or a Republican presidential candidate? What is the relationship between study time and grades? What is the relationship between overtime and productivity in an organization?

### Three Basic Questions:

11 Three Basic Questions Causal: determines whether one or more variables (e.g., a program or treatment variable) causes one or more outcomes Did a recent political advertising campaign change voter preferences? Does a change in work schedule result in higher productivity or satisfaction?

### Three Basic Questions:

12 Three Basic Questions The three types = cumulative Relational assumes you can first describe (by measuring or observing) each variable you are trying to relate A causal study assumes you can describe the cause and effect variables and you can show they’re related Causal studies are the most demanding

### Variable:

13 Variable any trait that can CHANGE VALUES from case to case

### Questions Contain Variables:

Questions Contain Variables Questions help us identify the variables of interest Descriptive questions: Is there a relationship between overtime and stress? What kinds of behaviors do workers exhibit when stressed? What is the relationship between productivity and stress?

### Questions Contain Variables:

Questions Contain Variables Relational questions: Do people working overtime experience more stress when they have comp time or when they are paid overtime? Does productivity differ between workers who are given comp time versus overtime?

### Questions Contain Variables:

Questions Contain Variables Causal questions: Does changing a company’s policy on overtime reduce worker stress? Does the provision of on-site services reduce worker stress due to overtime?

### Creating a Problem Statement:

Creating a Problem Statement Think of something in your company that interests or intrigues you Think of a problem that needs to be solved Do a little research and find out what others may or may not have said about your problem (Emerald database) Your problem statement is an argument for studying your topic