Chapters 1 to 4.

Question 1

Chapter 1 Concept
Population vs Sample

Answer 1

population: everyone/everything you’re interested in.
sample: a representative group of who/what you’re interested in.

Question 2

Chapter 1 Concept
Parameter vs Statistic

Answer 2

parameter: a value describing a Population.
statistic: a value describing a Sample

Question 3

Chapter 1 Concept
What is Correlational Research ?

Answer 3

occurs when one group is observed on two or more variables, to see if those variables are related.
- Example: a group of students report how much they sleep and their grades, and researcher looks for a relationship.

Question 4

Chapter 1 Concept
What is Experimental Research ?

Answer 4

occurs when one variable is manipulated to see if it affects a second variable; other variables are controlled for.
- Example: does sleep deprivation affect scores on quizzes ?
- researcher instructs one group of students to sleep only four hours (experimental condition)
- a second group is instructed to sleep for eight hours (control condition)
- the quiz scores are compared the following morning
- this is the only form of research that can prove CAUSAL relationships.

Question 5

Chapter 1 Concept
What is Non-Experimental Research ?

Answer 5

• one variable is only “quasi”- manipulated to see if it affects a second variable.
• Example: does meditation improve depression ?
• researcher measures depression before and after meditation, a “pre-post” design.
• because we cannot actually manipulate the passage of time , the pre vs. post variable is not truly manipulated

Question 6

Chapter 1 Concept
Types of Variables

Answer 6

• Independent: one that the researcher manipulates, such as the treatment people receive or the stimuli they are shown.
• Quasi-independent: the researcher chooses the values but cannot actually manipulate them, like gender or time.
• Dependent: the variable the researcher observes and measures, used to answer research question.

Question 7

Chapter 1 Concept
Types of Variables Continued

Answer 7

• Discrete: separate categories, with no in-between values.
• Example: occupation, major, colds (you can’t have half of a cold, either you have a cold or you don’t, etc.
• Continuous: an infinite number of possible values, including in-between values.
• Example: temperature (60 °, 75 °, 50.8 °)

Question 8

Chapter 1 Concept
Scales of Measurement

Answer 8

• Nominal: values are names and/or categories, but aren’t quantitative.
• Example: gender, genres, colors, etc.
• Ordinal: values can be ordered in a sequence, but the differences between them are quantifiable.
• Example: t-shirt size (small, medium, large)
• Interval: values can be ordered and the difference between them IS quantifiable, but zero is arbitrary.
• Example: degrees Fahrenheit
• Ratio: the same as interval, except zero actually means the absence of what is being measured.
• Example: weight

Question 9

Chapter 1 Concept
Constructs and Operational Definitions

Answer 9

• Construct: attributes that cannot be directly observed but are used to describe and explain behavior
• Operational definition: identifies the procedure used to measure a construct, and so defines the construct in terms of the resulting measurements.
• Example: A researcher wants to measure “openness” (construct). They measure it by noting how many conversations someone has with strangers during a mixer (number of conversations = operational definition).

Question 10

Chapter 1 Concept
Summation Notation

Answer 10

∑ - the Greek uppercase sigma, and it means sum (add).
- ∑X means to add up all of the numbers given to you (X refers to whatever numbers are given)
- ∑X^2 means to square each value then add the results together
- (∑X)^2 means to add all the X values and then square the total
- Example: ∑(X+1)^2 if X = 2, 3, & 3
- (2+1) = 3, (3+1) = 4, (3+1) = 4
- 3^2 = 9, 4^2 = 16, 4^2 = 16
- 9 + 16 + 16 = 41

Question 11

Chapter 2 Concept
What Are Descriptive Statistics ?

Answer 11

They organize and summarize data

Question 12

Chapter 2 Concept
What Are Frequency Distribution Tables ?

Answer 12

• A way to organize a list of values in a set of data, by listing each time the number of values or range of values observed in that set.
• grouped frequency distribution tables are used when there are too many values to show (using “real intervals”).
• Example: When looking at depression scores, the interval (bin) of 21-30 contains students who scored a 20.5 or more, up to but not including 30.5. this is because of rounding. Notation: [20.5, 30.5).

Question 13

Chapter 2 Concept
Frequency Distribution Graphs

Answer 13

• Histograms: plot the frequency distribution with bars
• Polygons: lines instead of bars
• Bar Graphs: for nominal or ordinal data

Question 14

Chapter 2 Concept
Shape of Distribution

Answer 14

• Distributions have characteristic shapes, the shape helps us understand the data.
• symmetrical distribution: when the left side of the distribution mirrors the right side. it is never skewed.
• positive skew: when the graph “points” to the more positive (bigger) values
• negative skew: when the graph “points” to the more negative (smaller) values

Question 15

Chapter 2 Concept
Rank, Percentile, and Percentile Rank

Answer 15

• Percentile rank refers to % (50 %), and percentile refers to the score (50th percentile).
• Rank: score of 20, ranked 24

Question 16

Chapter 2 Concept
Cumulative Frequency

Answer 16

• To compute percentiles and ranks, we need a table that shows cumulative frequency and percentage.
• To get cumulative frequency (cf), add up frequencies from one bin to the next
• cf for the first bin = f for first bin. cf for second bin = f for first bin + f for second bin, etc.
• Cumulative percentage: cf/n. the highest cf value will always be n

Question 17

Chapter 2 Concept
Interpolation

Answer 17

• we can use interpolation recover information from the cumulative frequency table. values that aren’t represented in the table can be interpolated. interpolation can only provide estimates because it assumes that the data is evenly distributed across the intervals.
• use real intervals

Question 18

Chapter 2 Concept
Stem and Leaf Displays

Answer 18

• an alternative grouped frequency table
• groups values by 10’s = stems
• lists single digits as frequencies = leaves

Question 19

Chapter 3 Concept
Central Tendency

Answer 19

• what does the data tend to look like?
• descriptive statistics used to summarize a dataset with one single number
• should be representative of the data in general-hence “central tendency”. makes it easy to compare groups

Question 20

Chapter 3 Concept
Mean

Answer 20

• Mean: sample - M. population: μ (mu, “mew”).
• often the best measure of central tendency. we can find it using summation notation. M= (∑X)/n
• add up all the values (∑X), and divide them equally among all people (/n).
• the balancing point: the point where the scores on one side balance out the scores on the other side.
• it is not always possible to calculate the mean. Example: nominal or ordinal data, open-ended distributions (5 or more pizzas), undetermined scores (didn’t answer the question).
• not the best choice if the distribution is skewed. Example: income - a billionaire drastically changes the data.

Question 21

Chapter 3 Concept
Median

Answer 21

• the middle value (in terms of ordering the values)
• the point at which half of the values are greater, and half of the values are less.
• NOT the balancing point unless the mean and median are equal

Question 22

Chapter 3 Concept
Precise Median

Answer 22

• for continuous data, the precise median is the 50th percentile. this is because of real intervals.
• Example: how many hours do you sleep per night ? - time is a continuous measure, so even if you report a whole number, you are really rounding up or down. No one sleeps exactly 5 hours. % hours really means between 4.5 & 5.5 hours (the real interval).
• the precise median is found by interpolating the 50th percentile

Question 23

Chapter 3 Concept
Mode

Answer 23

• the most frequent value
• can be computed for any type of data but it isn’t helpful if there is no single most frequent value (or a small number of ties)

Question 24

Chapter 4 Concept
Variability

Answer 24

• what is the spread of the data ? in other words, how close to the mean do the scores tend to be ?
• measures of variability tell you how well the mean represents the data overall.
• there are three measures of variability: range, variance, and standard deviation

Question 25

Chapter 4 Concept
Range

Answer 25

• the difference between the greatest and the smallest values
• Definition 1: maximum - minimum
• Definition 2: maximum - minimum + 1, ex: 1, 2, 5. (5-1 +1 = 5). Logic: there are five whole numbers in this range: 2, 2, 3, 4, and 5.

Question 26

Chapter 4 Concept
Standard Deviation

Answer 26

• standard deviation is the square root of variance. for a population, standard deviation is written as σ (lowercase Greek “sigma”).
• the most useful
• it is the typical distance (deviation) of scores from their mean. in other words, how far away from the mean are most scores ?
• 68% of scores fall +- 1 stdev from the mean
• 95% of scores fall +- 2 stdev from the mean
• this means we typically consider scores greater than or less than 2 stdev from the mean to be extreme.
• Example: mean exam score: 75 points. if stdev = 5, then 68% of students scored between 70 & 80 points (75 +- 5) and 95% of students scored between 65 and 85 points (75 +- 10).
• standard deviation/variance describe how narrow or wide a distribution is

Question 27

Chapter 4 Concept
Variance

Answer 27

• variance is written as σ^2 (for a population), sample variance is written as s^2
• to compute variance you need to find the sum of squares (SS)
• you want to know how far on average the scores deviate from the mean. you can’t just average the deviance scores because they always sum to zero. (the mean is the balancing point). for every point above the mean, there is a point below the mean, so on average they will cancel out.
• square the deviance scores because squares are always positive. the negative & positive scores will not cancel each other out.
• SS: Definitional: ∑(X - μ) ^2. Computational: ∑X^2 - (∑X)^2/N
• Population Variance: σ^2 = SS/N, Sample Variance: s^2 = SS/(n-1)

Question 28

Chapter 4 Concept
Transformations

Answer 28

• adjusting the scores in some way
• transformations have predictable effects on both the mean and standard deviation:
• addition/subtraction - means shifts up or down by the same amount & the stdev is unaffected.
• multiplication/division - both mean and stdev are multiplied/divided by that amount