Frequency distribution: Ana> DS> Frequencies Different groups within the data: Ana >DS>Explore
Variables (traits or chara) Values or scores (Gender; Depression; Test Scores) Levels (the possible values) (M/F) Independent (divide
into groups; ex. gender) vs Dependent (see difference in; ex type of “”) Scales of Measurement: Nominal: names to grps (Ex. Types
of Cereal)-No order, but categ; Ordinal/Rank-Order: Divided. Somewhat orderly; Interval/Ration or Equal-Interval: Difference
between the groups stays consistent. Graphs: Across the bottom (x axis) values, Height (y-axis) represents frequency. Discrete (bar):
Gaps. No midpoints. Continuous (histogram): Midpoints. Continuous, no breaks. Positively Skewed-pulls the mode to be less than
the mean. Negatively Skewed- mean is less than the mode. Descriptive Statistics: Summarize data (sample size), through tables,
charts, and graphs, through central tendency & variability. Inferential Statistics: Draw conclusions about large group from small
subset of the group, Infer to the population from the sample. Central Tendency - the score/ value of our variable. Mode: most,
nominal data; Median: middle, ordinal; Mean: average, Mean=sum of scores/ total number of scores. Variability- how spread out
they are. Not all fit in the mean or mode. Low Variability- not spread out very far, peaked distribution. High Variability- scarce, flatter
distribution. Measures of Variability: Range (High-Low) +1, Deviation (D = X – mean), Squared Deviation: SS = S (X – M)2, Variance
(Divide by N (for a population) s2 = SS / N or Divide by n-1 (for a sample) s2 = SS / (n-1)), Standard Deviation.
SPSS: Rows represent cases, Columns represent variables.
Linear Transformation: Add & Subtract (Mean changes, SD same) Multiple & Divide (Mean Changes, SD changes), “shape” stays the
same, If skewed/normal before transformation, remains skewed/normal.
To get M = 0, subtract mean from all scores (individual “deviation” score on top), To get SD = 1, divide by the SD (“average” deviation
on bottom) In the end the z-score gives us a measure, in standard deviation units, of the distance of an individual score from the M
Mean=0, SD=1/ 0 to +1 = 34.14% of scores/ +1 to +2 = ~14% of scores/ -1 to +1 = 68.28% of scores/ -1.96 to +1.96 = 95%
Standard deviation and variance are based on the logic of an average deviation value.
A raw score above the sample mean will result in a z-score greater than zero.
Measure of central tendency describes the typical or average score.
The z-score is also called a standardized value.
Distribution= 0, Variance= 1; The word “frequency” refers to how many scores there are at each value.
