Statistical Methods for Psychology Howell
Chapter 1 Basis Concepts
1.1 Important Terms
Random sample: to draw a random sample, we would follow a particular set of
procedures to ensure that every element of the population has an equal chance of
being selected.
Population: the entire collection of events in which you are interested, it can be of
any size (students’ scores, people’s incomes, running speeds, etc.).
Sample: a selected part of the population, which infers something about the
characteristics.
External validity: refers to the question of whether the sample reflects the
population.
Random assignment: fundamental to the integrity of our experiment, it is the
random assignment of subjects into treatment groups.
Internal validity: we want to ensure that the results we obtain are the result of the
differences in the way we treat our groups, not a result of who we happen to place in
those groups.
Variable: a property of an object or event that can take on different values, for
example hair color.
Independent variable: the variable that we can control, for example the amount and
intensity of shocks.
Dependent variable: the variable that is influenced by the independent variable, for
example the performance on a test (while receiving those shocks).
Discrete variables: variables which can take on a limited number of values, such as
gender.
Continuous variables: variables which can take on any value between the lowest
and highest points on a scale, such as age and self-esteem score.
Quantitative data (measurement data): the results of any sort of measurement, for
example grades on a test, people’s weights, etc.
Categorical data (frequency data/qualitative data): categorized results, and our
data consist of frequencies of each category. For example, a lot of subjects might be
involved but the results will consist of only two or three numbers.
1.2 Descriptive and Inferential Statistics
Descriptive statistics: they aim to describe the data: we want to graph our data,
calculate the means (averages) and other measures, and look for extreme scores or
oddly shaped distributions of scores.
Exploratory data analysis (EDA): exploratory statistics, the necessity of paying
close attention to the data and examining them in detail before invoking more
technically involved procedures.
Inferential statistics: where you take data from samples and make generalizations
about a population, to see if the data from the samples corresponds to the whole
population.
Parameter: a measure that refers to an entire population
, Statistic: a parameter when it is calculated from a sample of data that we have
collected.
1.3 Measurement Scales
Nominal scales: categories, no order or direction.
They do not scale items along any dimension, but they label them. Categorical data
can be measured on a nominal scale, because we merely assign category labels.
Example, what is your gender? Male, female, other)
Ordinal scales: ordered categories, rankings, orders, or scaling.
Orders people, objects, or events along some continuum. Nothing is implied about
the differences between points on the scale. We do not assume that the difference
between 10 and 15 points represents the same difference in stress as the difference
between 15 and 20 points. Example, what is your level of stress while studying? No
stress 1 2 3 4 5 6 7 8 9 10 A lot of stress.
Interval scales: differences between measurements but no true zero.
We can speak of differences between scale points. the difference between 10ºC and
20ºC is the same as 22ºC and 32ºC. But we do not have the ability to speak
meaningfully about ratios: we cannot say that 20ºC is twice as hot as 10ºC.
Ratio scales: differences between measurement, true zero exists. Example,
It has a true zero point: the point corresponding to the absence of the thing being
measured. 0ºC does not mean that nothing is measures, it still represents a presence
of temperature. 10 seconds is twice as long as 5 seconds, and 100 lb is one-third as
heave as 300 lb. Example, how long ago did you have your most recent crush? . . .
years, . . . months, . . . days ago.
Chapter 2 Describing and Exploring Data
2.1 Plotting Data
Frequency distributions: organizing the frequencies of the data in some sort of
logical order.
So for example, when we test someone’s reactions time, it would look like this:
Reaction time Frequency
in 100ths of a second
36 1
37 1
38 2
39 3
40 4
41 3
Etc. etc.
2.2 Histograms
Histogram: a way of distribution the data in a comprehensive way. To obscure some
of the random “noise” that is not likely to be meaningful but preserve important trends
in the data.
Real lower limit: the smallest value that would be classed as being in the interval
Real upper limit: the largest value that would be classed as being in the interval.
Chapter 1 Basis Concepts
1.1 Important Terms
Random sample: to draw a random sample, we would follow a particular set of
procedures to ensure that every element of the population has an equal chance of
being selected.
Population: the entire collection of events in which you are interested, it can be of
any size (students’ scores, people’s incomes, running speeds, etc.).
Sample: a selected part of the population, which infers something about the
characteristics.
External validity: refers to the question of whether the sample reflects the
population.
Random assignment: fundamental to the integrity of our experiment, it is the
random assignment of subjects into treatment groups.
Internal validity: we want to ensure that the results we obtain are the result of the
differences in the way we treat our groups, not a result of who we happen to place in
those groups.
Variable: a property of an object or event that can take on different values, for
example hair color.
Independent variable: the variable that we can control, for example the amount and
intensity of shocks.
Dependent variable: the variable that is influenced by the independent variable, for
example the performance on a test (while receiving those shocks).
Discrete variables: variables which can take on a limited number of values, such as
gender.
Continuous variables: variables which can take on any value between the lowest
and highest points on a scale, such as age and self-esteem score.
Quantitative data (measurement data): the results of any sort of measurement, for
example grades on a test, people’s weights, etc.
Categorical data (frequency data/qualitative data): categorized results, and our
data consist of frequencies of each category. For example, a lot of subjects might be
involved but the results will consist of only two or three numbers.
1.2 Descriptive and Inferential Statistics
Descriptive statistics: they aim to describe the data: we want to graph our data,
calculate the means (averages) and other measures, and look for extreme scores or
oddly shaped distributions of scores.
Exploratory data analysis (EDA): exploratory statistics, the necessity of paying
close attention to the data and examining them in detail before invoking more
technically involved procedures.
Inferential statistics: where you take data from samples and make generalizations
about a population, to see if the data from the samples corresponds to the whole
population.
Parameter: a measure that refers to an entire population
, Statistic: a parameter when it is calculated from a sample of data that we have
collected.
1.3 Measurement Scales
Nominal scales: categories, no order or direction.
They do not scale items along any dimension, but they label them. Categorical data
can be measured on a nominal scale, because we merely assign category labels.
Example, what is your gender? Male, female, other)
Ordinal scales: ordered categories, rankings, orders, or scaling.
Orders people, objects, or events along some continuum. Nothing is implied about
the differences between points on the scale. We do not assume that the difference
between 10 and 15 points represents the same difference in stress as the difference
between 15 and 20 points. Example, what is your level of stress while studying? No
stress 1 2 3 4 5 6 7 8 9 10 A lot of stress.
Interval scales: differences between measurements but no true zero.
We can speak of differences between scale points. the difference between 10ºC and
20ºC is the same as 22ºC and 32ºC. But we do not have the ability to speak
meaningfully about ratios: we cannot say that 20ºC is twice as hot as 10ºC.
Ratio scales: differences between measurement, true zero exists. Example,
It has a true zero point: the point corresponding to the absence of the thing being
measured. 0ºC does not mean that nothing is measures, it still represents a presence
of temperature. 10 seconds is twice as long as 5 seconds, and 100 lb is one-third as
heave as 300 lb. Example, how long ago did you have your most recent crush? . . .
years, . . . months, . . . days ago.
Chapter 2 Describing and Exploring Data
2.1 Plotting Data
Frequency distributions: organizing the frequencies of the data in some sort of
logical order.
So for example, when we test someone’s reactions time, it would look like this:
Reaction time Frequency
in 100ths of a second
36 1
37 1
38 2
39 3
40 4
41 3
Etc. etc.
2.2 Histograms
Histogram: a way of distribution the data in a comprehensive way. To obscure some
of the random “noise” that is not likely to be meaningful but preserve important trends
in the data.
Real lower limit: the smallest value that would be classed as being in the interval
Real upper limit: the largest value that would be classed as being in the interval.
