Statistics chpt 3
negative skew
mean is less than the median has more high values graph is pulled to the left
Positively skewed
more scores on the left-hand side of the distribution
Negatively skewed
more scores on the right-hand side of the distribution
Frequency (f)
number of scores in that class interval
cumulative frequency (or sum of the frequencies for each class size interval) for the highest class interval should be equal to ______
the sample size
Frequency distributions are not very helpful when ____________
there are lots of categories
histogram
used to plot frequencies using a separate bar for each score
When are histograms or frequency distributions best used?
when the y-axis is the frequency of the score on the x-axis.
When is it best to use a scatter plot rather than a histogram?
when you have pairs of data points (X and Y pairs) that are intended to reveal any potential relationship between the two variables.
it is traditional to show the dependent variable on the ______
x-axis
abscissa
x-axis, horizontal axis
ordinate
y-axis or the axis in the vertical position
frequency distribution
data collapsed into classes or ranged of values, and then the number of observations (or frequency) of each class, or range of values, is recorded in a table or graph
kurtosis
descriptive statistical measure of whether the frequency of scores in a distribution are more or less heavily clustered around the center (peaked) as opposed to evenly distributed across the range of scores
Properties of Median
1. Less sensitive to extreme scores 2. More sensitive to sampling variation.
Advantage of the Median
1. always shows the middle score 2. is not effected by outliers
Properties of the Mean
1. sensitive to outliers & extreme scores 2. sensitive to exact value 3. Least subject to sampling variation
General rules on creating a graph
1. starting both axes at 0 2. having the graph at least 3/4 filled 3. making the height at least 3/4 of the width
symmetry
distribution that is identically shaped on either side of the central point, or mirrow images of one another
relative frequency
frequency of scores in that class interval divided by the total number of scores in the distribution (reflects how common scores are in each class interval relative to the other intervals)
scatter plot
graphical display of pairs of continuous data points (X and Y pairs). intended to reveal any potential relationship between the 2 variables.
frequency curve
a 2D graph. plott's continuous variable on the X-axis and frequency on the Y-axis with a smooth line. Technically, it is a smooth version of a histogram or graphical representation of a frequency distribution.
skewness
a descriptive statistical measure of whether a distribution has a higher frequency of scores on one side compares to the other side of the distribution.
what is the difference between a histogram and a bar graph
histogram is a frequency distribution with the score on the X-axis and the frequency on the Y-axis except that the frequencies are notes as rectangular bars. Bar graph differs from the histogram in that dimension represents the independent variable and the other represents the dependent variable.
measure of whether the distribution is flat and spread out or peaked
kurtosis
Bar Graph
magnitude of the dependent variable is represented by the height of the bar
Positive skew
mean is greater than the median has more low values graph is pulled to the right
difference between relative frequency and cumulative frequency
relative frequency is frequency of scores in that class interval divided by the total number of scores in the distribution. cumulative frequency is the sum of the frequency of scores starting from lowest class interval going to the highest class interval.
cumulative frequency
sum of frequency of scores starting from lowest class interval to highest class interval. The cumulative frequency (sum of the frequencies for each class interval) for the highest class interval should be equal to the same size (N).
cumulative percentage
the cumulative frequency divided by N and then the product multiplied by 100. the cumulative percentage for the highest class interval should equal 100.