Lecture 1
Some definitions
- Population
• The set of ALL the individuals of interest in a particular study
• Vary in size, but can be quite large
• Populations are described by parameters
- Sample
• Aset of individuals SELECTED from a population
• Usually intended to represent the population in a research study
• Samples are described by statistics
- This distinction is very important in stats: the formulas change depending on whether you
are dealing with a population or a sample
Sampling error
- Asample is never identical to a population!
• People are all weird. Everyone is different
• This weirdness causes data to shift in random ways
- Sampling error
• The discrepancy, or amount of error, that exists between a sample statistic and the
corresponding population parameter
Sampling error (textbook example)
- Imagine a population of 1000 Carleton PSYC 2002 students
- Parameters:
• Average age= 21.3
• Average IQ= 112.5
• 65% female, 35% male
Sampling error
- Sample #1: Jen, Emily, Sue, Paul, Melissa
- Sample statistics:
• Average age= 19.8
• Average IQ= 104.6
• 80% female, 20% male
Sampling error
- Sample #1: Kermit, Fozzie, Gonzo, Piggy, Camilla
- Sample statistics:
• Average age= 20.4
• Average IQ= 114.2
• 40% female, 60% male
This is NOT surprising
- Small samples tend to have a lot of variability
- We should not be surprised if a small sample does not reflect the population
Variables and data
- Variable
• Characteristic or condition that changes • Either manipulated or observed
• Dependent or independent
Independent and dependent variables
- Independent variables (IVs)
• The variable manipulated by the researcher
• You choose the level of the manipulated variable
- Dependent variables (DVs)
• The variables measured by the researcher
• The levels of these variables tell you the effect of manipulating the IVs
Variables and data
- Data
• Measurements of a variable
- Data set
• Acollection of measurements
- A datum
• Asingle measurement or observation
• Commonly called a score or a raw score
Types of statistics Descriptive
- Descriptive statistics
• Summarize data
• Organize data
• Simplify data
- Familiar examples
• Tables
• Graphs
• Averages (aka means)
Types of statistics Inferential
- Inferential statistics
• Study samples to make generalizations about the population
• Interpret experimental data
• VERY USEFUL
- Unfamiliar (to some) examples
• Z tests
• T tests
• F tests
Types of studies
- Experiments:
• Carefully controlled, usually taking place in a laboratory
• IVs are directly manipulated to see if there is any affect on the DVs
• Well designed experiments let you make definitive statements about “cause-and-
effect”
- Quasi-experiments:
• When you can’t completely control one or more of the IVs • Example: non-equivalent groups
You compare groups, but you can’t control who goes into which group
• In these cases, the independent variable is quasi-dependent
- Correlational:
• When you observe a relationship between two variables, but can’t say with certainty
which is the IV and which is the DV
So no IV is actually required
• Example: I notice that the more comic books people read, t

More
Less