PSYC 2320 Study Guide - Fall 2018, Comprehensive Midterm Notes - Normal Distribution, Standard Deviation, Skewness
12 Oct 2018
School
Department
Course
Professor
PSYC 2320
MIDTERM EXAM
STUDY GUIDE
Fall 2018
What are Stats?
● Tools for organizing, summarizing, generalizing data
○ Summarize, collect, present
○ Draw bigger conclusions from data
■ Say what we think people outside the sample do
● Variability exists in life, account for and explain it
○ Chance vs. other factors
■ Is there enough variability for something interesting to explain it
Descriptive vs. Inferential Stats
● Descriptive
○ Describe data in actual observations or scores
○ Makes things concise
● Inferential
○ Generalize beyond collections of observations
○ Help make decisions and test hypotheses
Types of Data
● Qualitative
○ Words, letters, numerical codes
○ Represent category
■ Number of men in a race
■ How many
■ Not time taken to complete race
● Ranked
○ Represent relative standing
○ Don’t necessarily represent direct reality
■ Doesn’t actually say the times of people finishing the race → just 1st, 2nd,
3rd etc.
● Quantitative
○ Represents an amount or count
■ Time of individual to finish race
■ Exact number
○ *Focus throughout semester*
Levels of Measurement
● Nominal (qual.)
○ Doesn’t really mean anything
○ Numbers only help to distinguish one from another
○ 1=male 2=female (classification)
● Ordinal (ranked)
○ Numbers place things in order
○ 1=first 2=second 3=third (order)
○ *No info on how far apart*
● Interval/ratio (quan.)
○ Numbers place objects in order with meaningful differences
find more resources at oneclass.com
find more resources at oneclass.com
■ Rating on a scale
■ Number of accurate responses
○ Ratio: true zero
■ Time → 0 seconds does mean something
○ Sometimes won’t have a zero
■ Rating scale of 1-10
■ Scales can be very subjective
● Give meaning/descriptors to values but still not great
○ Equal intervals stay consistent across scales
Distributions of Data
● How often scores occur in data (frequency)
● Distributions have both spread (x axis) and frequency (y axis)
○ Histogram
○ → creates a distribution
Characteristics of Distributions
● Modality
○ How many peaks?
■ → which values have highest frequeny
● Skewness
○ Is the graph symmetric?
■ Bell curve / normal curve
Skewness
● Normal
○ Mean, median, mode about the same
● Positive skew
○ Tail toward right side
○ More low numbers
● Negative skew
○ Tail toward left
○ More high numbers
Describing Data
● Measures of central tendency (mean, median, mode)
○ Middle or typical value in a data set
● Mode: most frequently occuring number in set
○ Advantages
■ Not affected by extreme values
■ Frequency distributions show peaks → modes
○ Disadvantages
■ Can be misleading → doesn’t take all scores into account → dist. can have
the same mode but look very different
● Median
find more resources at oneclass.com
find more resources at oneclass.com
Document Summary
Say what we think people outside the sample do. Variability exists in life, account for and explain it. Is there enough variability for something interesting to explain it. Describe data in actual observations or scores. Doesn"t actually say the times of people finishing the race just 1st, 2nd, Numbers only help to distinguish one from another. Numbers place objects in order with meaningful differences. Time 0 seconds does mean something. Give meaning/descriptors to values but still not great. How often scores occur in data (frequency) Distributions have both spread (x axis) and frequency (y axis) Measures of central tendency (mean, median, mode) Middle or typical value in a data set. Mode: most frequently occuring number in set. Can be misleading doesn"t take all scores into account dist. can have. Median the same mode but look very different. Middle value in a set number in the center or mean of 2 middle values (position. Need to arrange all data in order.
