Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
57 Cards in this Set
- Front
- Back
A numerical representation of information is a
|
Statistic
|
|
Weight is an example of this type of variable
|
Continuous
|
|
List 2 types of quantitative variables
|
Discrete, continuous
|
|
These variables can not be directly measured, but are inferred
|
Latent
|
|
These variables can be observed and directly measured
|
Observable
|
|
These variables are numeric in nature
|
Quantitative
|
|
These variables are nonnumeric in nature
|
Qualitative
|
|
These numeric variables measure "how many" -- they cannot be subdivided
|
Discrete
|
|
These numeric variable measure "how much"
|
Continuous
|
|
List 4 scales of measurement
|
Nominal, Ordinal, Interval, Ratio
|
|
This type of scale of measurement has discrete, qualitative variables
|
Nominal
|
|
This scale of measurement has qualities including magnitude, equal intervals, and absolute 0
|
Ratio
|
|
This scale of measurement has qualities including magnitude and equal intervals
|
Interval
|
|
This scale of measurement only has the quality of magnitude
|
Ordinal
|
|
This scale of measurement has no special qualities, but includes things like names or lists of words.
|
Nominal
|
|
A Likert scale or rank ordered scale is an example of this type of scale of measurement
|
Ordinal
|
|
Temperature is an example of this type of scale of measurement
|
Interval
|
|
Age, height, and weight scales are examples of this type of scale of measurement
|
Ratio
|
|
You can multiply or divide items on this type of scale of measurement
|
Ratio
|
|
You can add and subtract items on this type of scale of measurement, but cannot multiply or divide
|
Interval
|
|
List 4 general ways in which researchers and test developers describe statistics
|
Frequency,
Central Tendency, Variability, Relationships |
|
This is a way to show a disorganized set of scores and place them in order, showing how many (people) obtained each of the scores
|
Frequency Distribution
|
|
This type of graph uses vertical lines and bars to portray the distribution of test scores.
|
Histogram
|
|
This variation of a histogram replaces bars with lines connecting the midpoint of each class interval.
|
Frequency Polygon
|
|
This graph gives us a better idea of the shape of the distribution as well as the frequency of scores
|
Smoothed Frequency Polygon (or frequency curve)
|
|
A frequency curve (smoothed frequency polygon) that is not symmetrical is called a
|
Skewed curve
|
|
In this skewed curve, the majority of data falls on the lower end of the scale
|
Positively skewed curve
|
|
In this skewed curve, the majority of data falls on the upper end of the scale
|
Negatively skewed curve
|
|
Three common measures of central tendency are the
|
Mean,
Median, Mode |
|
The average score in a distribution is referred to as the
|
Mean
|
|
Given these numbers, calculate the mean, median, and mode:
78,85,86,90,98,100,100,102,110,115,142,146,165 |
Mean = 109
Median = 100 Mode = 100 |
|
In descriptive statistics, this type of central tendency has two modes
|
Bi-modal
|
|
This measure of central tendency is the middle score, or the score that divides the distribution in half
|
Median
|
|
For symmetrical distributions, these 3 measures of central tendency are equal
|
Mean
Median Mode |
|
In central tendency measures, this is the score that appears most frequently
|
Mode
|
|
Calculate the range of these numbers:
1,2,2,3,3,3,4,4,5,5,6,6,40 |
39
|
|
Range is an example of the measurement of these types of descriptive statistics
|
Variability
|
|
This measure describes the average distance of test scores from the mean
|
Standard deviation
|
|
This curve has the following properties:
*bell shaped, *bilaterally symmetrical, *mean, median and mode are equal to each other *Asymptotic tails *Unimodal *100% of the scores fall between -3 and +3 standard deviations from the mean |
Normal Curve (aka normal distribution or bell curve)
|
|
68% of a population within a normal curve falls between what standard deviations
|
-1 and +1 standard deviations
|
|
This measure of relationship indicates that two variables move in the same direction
|
Positive correlation
|
|
This measure of relationship indicates that two variables move in opposite directions
|
Negative correlation
|
|
A complete absence of a relationship between 2 variables is indicated by this number
|
0
|
|
A perfect positive relationship between two variables has this correlation coefficient
|
+1
|
|
A perfect negative relationship between two variables has this correlation coefficient
|
-1
|
|
The number of violent crimes committed is strongly positively correlated with the number of ice cream sales at a given time. Does this mean that one causes the other?
|
No. Correlation does not mean causation.
|
|
Linear relationships between two continuous variables are measured using this type of correlation coefficient
|
Pearson Product Moment Correlation (r)
|
|
A variant of Pearson's r used for finding the association between two ordinal variables and does not require a linear relationship between variables is
|
Spearman's Rho (r)
|
|
Likert scales often use this type of correlation coefficient measure
|
Spearman's Rho (r)
|
|
The degree of association between two nominal variables is assessed by this correlation coefficient measure
|
Phi Coefficient
|
|
This is used to assess the size and direction of a relationship between variables
|
Correlation
|
|
This statistical method is used in the analysis of relationships among variables for predictive purposes
|
Regression
|
|
In measurements of relationship, this is used to predict the value of one variable based on the value of another single variable
|
Simple linear regression
|
|
In measurements of relationship, this is used to predict the value of one variable based on the value of two or more independent variables
|
Multiple regression
|
|
This analyzes the relationship among variables for purposes of reducing the number of necessary variables
|
Factor Analysis
|
|
Creat demographic questionnaire for study with 5 questions/statements including: 2 nominal, 1 ratio, 1 ordinal, and 1 interval scale. Identify each type.
|
Nominal:
Relationship Status, Gender Ordinal: Rate your interest in taking this test on a scale from 1 to 5 . . . Interval: What was your temperature in Fahrenheit degrees on your last doctor's visit Ratio: What is your current weight |
|
Difference between regression, factor analysis, and spearman's rho. Explain how you would determine which analysis to conduct and provide an example of each.
|
The all are measurement methods involving relationships between variables, however they are used for different purposes. Regression measures correlation strength and direction of a relationship between variables. There are different types of regression (Simple linear and Multiple Regression) analysis; all are used for predictive purposes.
(example - if there is a strong positive correlation between IQ and grades, I could take one of the two variables and figure out the other (dependent) variable based on that. Spearman's Rho is a way to calculate the correlation coefficient (used in regression). It is used to find the relationship between ordinal variables and doesn't require a linear relationship between the variables. You would use Spearman's Rho to figure out if a correlation between 2 ordinal variables exists. Factor Analysis is used to simplify variables. You would use it to reduce the number of questions necessary on a given test while still yielding accurate results. |