Can be manipulated Algebraically

Every score in the distribution contributes

Unbiased and efficient

The Mean value may not actually exist in the data

Only good for Interval/Ratio data

Not resistant to outliers

Not as efficient as mean

Not always good representation of the data, skewed distributions

Resistant to Outliers

Can be used with nominal data

Is an actual score in the data

Not unbiased or efficient

May not represent data well. ex-0,0,0,1,1,4,9,20,42

0 is not good representation of the data

The mean = median = mode

They are all equal

Means the graph is higher on the left

The tail tapers to the right

It goes mode, median, mean from left to right

The graph leans to the right

The tail tapers to the left

It goes mean, median, mode

Frequency tables

Graphs: Histograms, Line graphs, Bar graphs, stem and leaf, and symmetry, skew, kurtosis

Measures of central tendency: mean, median, mode

Measures of variability: range, standard deviation, variance

How far do scores vary from the center?

How wide is the distribution?

From the lowest score to the highest score

Very sensitive to outliers

Use Interquartile Range: 25%-75% of the data

(X_i-Xbar)

variable minus mean

Shows dispersion

With a few more calculations, it measures the spread of the observations about their mean value.

SS=Sum(X_i-Xbar)²

[image]

[image]

Advantages:

Used in algebraic equations

Considers every score in sample

Disadvantages:

Not resistant to outliers

Requires interval/ratio data

Requires a formula that debiases sample statistic

Not in the same metric as scores

Advantages:

Is in the same metric as scores

Uses every score in sample

Manipulate algebraically

Disadvantages:

Not resistant to outliers

Only I/R data

Requires formula to debias