Block 1.3 Statistics/SPSS
I. Lecture 1 – Introduction to Statistics
1. Why Statistics is important?
- Able to read/understand and study other people’s studies
- If the research was done well/assessing the information
- Tend to make my own assessment/research design
- Analyze and interpret your own data
- Gain valuable insight on whether it is true, how do we prove it, what are the results
- For development and assessment of psychological tests
- Ability to calculate with data and interpret it from psychological tests
- Based on the gathered information to draw the correct conclusions (test/study)
- Being able to assess what other people say, to see critically the information and to
estimate its worth
- Investigation on certain effects needs this kind of methodology
2. Sources of knowledge
- Intuition -> feel it
- Habit/tradition -> certain way, accustomed to it/beliefs
- Authority -> an authoritative figure tells you and you tend to believe because of his
status
- Reasoning based on logic and arguments (premises can be wrong)
- Empiricism: knowledge based on experience (confirmation bias)
- Science: knowledge based on systematic empiricism
3. Goals of science
- Description:
Looking what is there and describing it (diff types of behavior/emotions)
- Explanation:
Formulating a hypothesis/thought about reality, use it to guide empirical testing
We build a theory and specify causes and processes behind the behavior behind
emotions/thoughts (why do ppl behave the way they do -> test it)
- Prediction:
Trying to make predictions for the future, feeling something certain -> what
would mean for future me
Be able to predict which people are more likely to be more susceptible towards
depression then maybe I can help them before they have any serious symptoms
- Control: “enables you to influence the (experimental) conditions under study and to
draw causal conclusions”
4. Characteristics of empirical science
,- Important assumption: there exists an objective truth exists, and we can discover it
Observation: what we see
Induction: formulation of a hypothesis/statement about what is true in this world
To test this hypothesis
Deduction: how are you going to test/what are you going to do
Testing: Carrying out the test
Evaluation: Answer to the hypothesis/ initial hypothesis -> if evidence to confirm
is found, then true; but if there is a fluctuation (one thing that disproves the H),
then you have to adjust the initial hypothesis and start all over again/
- Systematic testing of hypotheses to reality:
Focus testable questions (falsifiability) -> there needs to be a possibility that
the answer might be no
Strive for accuracy and objectivity
Requires clear operational definitions -> define the subjective and investigate
how to measure the objective action (tests) = what am I measuring and who I
am measuring
Public accountability / reporting -> ppl should be able to check your research
hand maybe replication studies (reference you)
Is tentative, not absolute: theories are challenged and refined
Self-correcting via replication studies
Is but one source of knowledge: focus to empirical, testable, questions
5. Critical thinking: questions to ask yourself
- What is the claim?
- Source of this claim?
- Can I gather info about source credibility/reliability?
- Is there evidence that supports it or something that counters it? (quality!)
- Are the interpretations of the findings reasonable?
- Are there plausible alternative explanations for the findings?
- Is additional evidence needed to reach a clearer conclusion?
- Given the current state of the evidence, what conclusion is most reasonable?
, II. Lecture 2 – Chapter 1: Looking at Data Distributions (MMC)
1. Statistics and data
a) Statistics:
- Definition -> Science that deals with recognizing the patterns & the randomness (the
patterns in randomness)
- Concerned with extracting regularities that we will find in reliability of data (sources
of info that we collect to answer the research question)
- How best to understand data – describing data (intelligible way)
- 2 types:
Descriptive Stats – describing data & displaying data
Inferential Stats – making decisions about population parameters based on
sample data
- Regularity: (1) first design a study (addressing & answer the RQ), (2) collect data, (3)
analyze the found data, (4) interpret what the data says (conclusions)
- Operationalize: ‘convert theoretical concepts into measurable constructs’
How do we measure a theoretical concept – by transforming it into a
measurable construct (designing measurement procedures)
b) Data:
- Making decisions in the face of variability
Making inferences about population characteristics based on info that you collect
from the sample
2. Cases, variables and values
a) Case – the objects that are described by a set of data (case that you describe – by
several variables) rows on a dataset on SPSS
b) Variable – characteristic of a case that differs between cases (can take on diff value)
columns on a dataset on SPSS
c) Value – the value of a case of a specific variable is called a score the definition in the
box on a dataset on SPSS
Who? -> What? -> Why? *
3. Scales of measurement (examining psychological research) NOIR
TYPES of variables: categorical (not a number, not meaningful) and
quantitative (a number is meaningful related to values)
a) Nominal (categorical) -> values represent categories, differ in kind
For example: gender/hair color/name/marital status
b) Ordinal (categorical) -> values represent categories, differ in rank order
For example: military rank/political interest/movie ratings/education
c) Interval (quantitative) -> there is order and the difference between two values is
meaningful; also, they do not have a “true 0” (represents the absence of the
property being measured)
For example: temperature/ grades/ IQ
d) Ratio (quantitative) -> interval scales, but zero point reflects true absence of
property, scores can be compared as ratios
For example: number of questions correct on the exam/age/height
I. Lecture 1 – Introduction to Statistics
1. Why Statistics is important?
- Able to read/understand and study other people’s studies
- If the research was done well/assessing the information
- Tend to make my own assessment/research design
- Analyze and interpret your own data
- Gain valuable insight on whether it is true, how do we prove it, what are the results
- For development and assessment of psychological tests
- Ability to calculate with data and interpret it from psychological tests
- Based on the gathered information to draw the correct conclusions (test/study)
- Being able to assess what other people say, to see critically the information and to
estimate its worth
- Investigation on certain effects needs this kind of methodology
2. Sources of knowledge
- Intuition -> feel it
- Habit/tradition -> certain way, accustomed to it/beliefs
- Authority -> an authoritative figure tells you and you tend to believe because of his
status
- Reasoning based on logic and arguments (premises can be wrong)
- Empiricism: knowledge based on experience (confirmation bias)
- Science: knowledge based on systematic empiricism
3. Goals of science
- Description:
Looking what is there and describing it (diff types of behavior/emotions)
- Explanation:
Formulating a hypothesis/thought about reality, use it to guide empirical testing
We build a theory and specify causes and processes behind the behavior behind
emotions/thoughts (why do ppl behave the way they do -> test it)
- Prediction:
Trying to make predictions for the future, feeling something certain -> what
would mean for future me
Be able to predict which people are more likely to be more susceptible towards
depression then maybe I can help them before they have any serious symptoms
- Control: “enables you to influence the (experimental) conditions under study and to
draw causal conclusions”
4. Characteristics of empirical science
,- Important assumption: there exists an objective truth exists, and we can discover it
Observation: what we see
Induction: formulation of a hypothesis/statement about what is true in this world
To test this hypothesis
Deduction: how are you going to test/what are you going to do
Testing: Carrying out the test
Evaluation: Answer to the hypothesis/ initial hypothesis -> if evidence to confirm
is found, then true; but if there is a fluctuation (one thing that disproves the H),
then you have to adjust the initial hypothesis and start all over again/
- Systematic testing of hypotheses to reality:
Focus testable questions (falsifiability) -> there needs to be a possibility that
the answer might be no
Strive for accuracy and objectivity
Requires clear operational definitions -> define the subjective and investigate
how to measure the objective action (tests) = what am I measuring and who I
am measuring
Public accountability / reporting -> ppl should be able to check your research
hand maybe replication studies (reference you)
Is tentative, not absolute: theories are challenged and refined
Self-correcting via replication studies
Is but one source of knowledge: focus to empirical, testable, questions
5. Critical thinking: questions to ask yourself
- What is the claim?
- Source of this claim?
- Can I gather info about source credibility/reliability?
- Is there evidence that supports it or something that counters it? (quality!)
- Are the interpretations of the findings reasonable?
- Are there plausible alternative explanations for the findings?
- Is additional evidence needed to reach a clearer conclusion?
- Given the current state of the evidence, what conclusion is most reasonable?
, II. Lecture 2 – Chapter 1: Looking at Data Distributions (MMC)
1. Statistics and data
a) Statistics:
- Definition -> Science that deals with recognizing the patterns & the randomness (the
patterns in randomness)
- Concerned with extracting regularities that we will find in reliability of data (sources
of info that we collect to answer the research question)
- How best to understand data – describing data (intelligible way)
- 2 types:
Descriptive Stats – describing data & displaying data
Inferential Stats – making decisions about population parameters based on
sample data
- Regularity: (1) first design a study (addressing & answer the RQ), (2) collect data, (3)
analyze the found data, (4) interpret what the data says (conclusions)
- Operationalize: ‘convert theoretical concepts into measurable constructs’
How do we measure a theoretical concept – by transforming it into a
measurable construct (designing measurement procedures)
b) Data:
- Making decisions in the face of variability
Making inferences about population characteristics based on info that you collect
from the sample
2. Cases, variables and values
a) Case – the objects that are described by a set of data (case that you describe – by
several variables) rows on a dataset on SPSS
b) Variable – characteristic of a case that differs between cases (can take on diff value)
columns on a dataset on SPSS
c) Value – the value of a case of a specific variable is called a score the definition in the
box on a dataset on SPSS
Who? -> What? -> Why? *
3. Scales of measurement (examining psychological research) NOIR
TYPES of variables: categorical (not a number, not meaningful) and
quantitative (a number is meaningful related to values)
a) Nominal (categorical) -> values represent categories, differ in kind
For example: gender/hair color/name/marital status
b) Ordinal (categorical) -> values represent categories, differ in rank order
For example: military rank/political interest/movie ratings/education
c) Interval (quantitative) -> there is order and the difference between two values is
meaningful; also, they do not have a “true 0” (represents the absence of the
property being measured)
For example: temperature/ grades/ IQ
d) Ratio (quantitative) -> interval scales, but zero point reflects true absence of
property, scores can be compared as ratios
For example: number of questions correct on the exam/age/height
