Appendix A & Chapter 1- Introduction Flashcards
Descriptive Statistic
Produces a number or a figure that summarizes or describes a set of data
Inferential Statistic
A method that uses sample evidence and probability to reach conclusions about unmeasurable populations
Population
All measurements of a specified group
Ex: If you were to have a study on Marian students, and you literally asked each and everyone of the Marian students. There are slim to none studies that are like this though.
Sample
A subset of a population, it may or may not be representative
Ex: If you were doing a study on college students in general and you used Marian students as a sample. They are a small amount of the overall picture of what you are trying to measure
Parameter
A numerical or nominal characteristic of a population
So if you have a study using population you took/have parameters of them
Statistic
A numerical or nominal characteristic of a sample
If you have a study using a sample you took statistics of them
Variable
Something that exists in more than one amount or in more than one form
Example: Height, IQ, dosage, gender, religion, income
What are the two different types of variables?
Quantitative and qualitative
Quantitative Variable
Variable whose levels indicate different amounts. The word quantity is in it. Has a numerical value.
Qualitative Variable
Variable whose levels are different kinds, not different amounts
Example: 1st, 2nd, 3rd doesn’t tell you how far apart, or by how much they are ranked. It’s qualitative
What are the different scales of measurement?
Nominal, ordinal, interval, ratio
Nominal
A scale in which numbers serve only as labels and do not indicate any quantitative relationship. If you have nominal data you are counting. You count the frequency of ‘oh, how many times do I have this number’. How many fives do I have, how many twos, or threes? You’re counting
Example: football uniform numbers, social security number, phone number
Ordinal
Scale in which numbers are ranks; equal differences between numbers do not represent equal differences between the things measured. Ordinal gives you order.
Example: Rank orders in a race; 1st, 2nd, 3rd place
Interval
Scale in which equal differences between numbers represent equal differences in the thing measured. The zero point is arbitrarily defined.
There’s not a legit zero defined.
I think celsius is ratio though??? Not sure…??
Example: Fahrenheit Temperature
Ratio
Scale with characteristics of interval scale; also, zero means that none of the things measured is present. A lot of psycho social studies do not have zeros, because, for example, if we measured self-esteem no one has a complete zero self-esteem, we all have something. This is not ratio.
Example: Weight, income, dosage
What is the only difference between interval and ratio data?
Ratio has a zero
What are the three different kinds of variables?
Independent, dependent, extraneous
Independent Variable
Variable controlled by the researcher; changes in this variable may produce changes in the dependent variable. What I assume has an effect on the dependent variable. Understand the direction of your experiment.
Dependent Variable
The observed variable that is expected to change as a result of changes in the independent variable in an experiment. What you are measuring, you don’t know what is going to happen with it.
Have to be careful with this one, because there may be things that have or are changing, but we need to make sure they meet the qualifications specified above.
What you assume is getting affected by the independent variable.
Extraneous/Confounding Variable
Variable other than the independent variable that may affect the dependent variable
Stuff that gets in the way of you have completely accurate results. Things that affect your data that you don’t want to, because they are controlled. Crappy designs have extraneous variables.
Vodka and Learning Example; Use all variables
You assume vodka has an effect on learning. Vodka is the independent variable. It changes and effects how you learn. Your learning is getting measured. But you can’t accurately predict what is going to happen. You could test people with completely different tolerances. And get completely different results so the data is messed up, main. Or if you get smart/dumb people grouped together on accident. One group does really well, because they’re smart not because you gave them three shots of vodka. And the other group who was given no alcohol does terrible, but it’s just because they’re all dumb.
