Statistics Flashcards
Ordered Array
Data table organized in a way to serve a specific purpose. e.g. ordering test grades from highest to lowest
Percentile
The value or score on an ordered array of data that indicates the percentage of the scores that fall at or below that value
Quartile
Three specific percentiles: Q1 - 25%, Q2 - 50%, and Q3 - 75%
Interquartile Range (IQR)
Difference between Q3 and Q1. Used to characterize the bulk of the population
Frequency Distribution
Shows the repetition of the same result in a data set. A frequency distribution indicates how many students scored at the same level.
Histogram
a graphic representation of related data. In simplest terms, a histogram is a connected bar graph of the data.
Normal Curve
Standard distribution curve
mode = mean = median
Negative Skew
Data that causes a longer tail on the left side. The mean is to the left of the peak.
Mean < Median < Mode
Data that favors the right side of a normal curve. The right side of the normal curve is increased.
Positive Skew
Data that causes a longer tail on the right side. The mean is to the right of the peak.
Mean > Median > Mode
Data that favors the left side of the normal curve. Data that causes the left side of the normal curve to increase.
Central Tendency
A single data value used to describe an entire data set. This answers the question, “How did the class do as a whole?”
How is central tendency measured?
By the mean, median, or mode.
Mode
The data value that occurs most often
Which do the highest and lowest points in a data set affect more, Mean or Median
The value of highest and lowest scores affects the mean value but not the median value
What is the formula for calculating the boundaries of a data set?
Lower boundary: Q1 - IQR
Upper boundary: Q3 + IQR
Used to determine outlier scores
Box and Whisker Plot
A graphical way to determine how spread out the quartiles are
Stem and Leaf Plot
Simple way to create a bar graph (histogram) using the first common number of a set of test scores (the stem) and ordering all the scores with that first common number behind it (the leaves)
e.g.
9|0,2,4 from 90, 92, 94
8|1,6,8 from 81,86,88
7|2,4,5,7,9 from 72,74,75,77,79
etc.
The longer the stem that holds the leaves, the more people who earned that grade.
Variance or Variability
Describes how spread out the data is
Value Added Assessment
A method of determining what you personally have added to the education of the students compared to other teachers of the same course
Steps to calculating one standard deviation
Step 1: determine the mean
Step 2: Subtract the mean from each score
Step 3: Square the result of each answer from step 2
Step 4: Add the numbers from step 3 together
Step 5: divide the total from step 4 by the number of scores minus 1
Step 6: take the square root of step 5
Percentages that correlate to results falling within one, two, and three standard deviations.
68% = 1 Standard deviation
95% = 2 Standard deviations
99.7% = 3 Standard deviations
Pearson correlation coefficient scores of -1, 0, and 1
-1 = inversely related
1 = directly related
0 = unrelated
Bimodal distribution
Two modes or peaks within the same distribution of data
What is the best method for calculating central tendency when the variance is small
mean
Relationship between Scale Score, the Standard Error of Measurement (SEM), +1 SEM, and -1 SEM
+1SEM = Scale score + SEM
-1SEM = Scale score - SEM
SEM = half the range between -1SEM and +1SEM
A standard score is calculated by . . .
using the
1) raw score, (x)
2) the distance from the mean, (m)
3) the standard deviation of the distribution. (s)
standard score = (x - m)/s
Disaggregated
separated into parts.
e.g. breaking data down by socioeconomic status
Reliable test
Yields consistent results
Valid test
Yields accurate results
What is a Standard Error of Measurement (SEM)?
The difference between the actual score that a student achieves on an exam and her hypothetical score.
a measure of how much measured test scores are spread around a “true” score.
What is a Standard Error of Measurement (SEM) useful for?
This measurement is used to determine the accuracy of a test in gauging student knowledge.