Professional Documents
Culture Documents
Z Scores
Z Scores
In a normal distribution: Approximately 68% of scores will fall within one standard deviation of the mean
In a normal distribution: Approximately 95% of scores will fall within two standard deviations of the mean
In a normal distribution: Approximately 99% of scores will fall within three standard deviations of the mean
80 -2 sd
90 -1 sd
100
110 1 sd 90 120
120 2 sd
What score is one sd below the mean? What score is two sd above the mean?
80 -2 sd
90 -1 sd
100
110 1 sd
120 2 sd 1 2
How many standard deviations below the mean is a score of 90? How many standard deviations above the mean is a score of 120?
Z scores
What is a z-score? A z score is a raw score expressed in standard deviation units.
XX z! S
Computational Formula
z = (X
M)/SX
Score minus the mean divided by the standard deviation Different formula for the population
Calculating z scores
What is the z score for your test: raw score = 80; mean = 75, S = 5?
XX z! S
80 75 z! !1 5
What is the z score of your friends test: raw score = 80; mean = 75, S = 10?
XX z! S
80 75 z! ! .5 10
Who do you think did better on their test? Why do you think this?
Why z-scores?
Transforming scores in order to make comparisons, especially when using different scales Gives information about the relative standing of a score in relation to the characteristics of the sample or population
Location relative to mean Relative frequency and percentile Slug, Binky and Biff example p 133
below
X = (z) (SX) + M
Z-score Distribution
Mean of zero
Negative z-scores aren t bad Z-score distribution always has same shape as raw score
Statistics versus English test performance Can plot different distributions on same graph increased height reflects larger N
Useful for evaluating the sample and for inferential statistical procedures Evaluate the sample mean s relative standing Sampling distribution of means could be created by plotting all possible means with that sample size and is always approximately a normal distribution Sometimes the mean will be higher, sometimes lower The mean of the sampling distribution always equals the mean of the underlying raw scores of the population (most of the means will be around Q)
Used for creating a theoretical sampling distribution A statistical principle that defines the mean as equal to Q, SD that is equal to W, and the shape of the distribution which is approximately normal Obtain information without having to actually sample the population Interpretation is the same: if close to mean occurs more frequently Compute z-scores to indicate relative frequency of the sample mean
WM = WX/square root of N
Larger N produces more representative samples Determine on average how much the means differ from the Q