Learning Goal 1 - Understand the empirical cycle’s role in science
Empirical research: Research that is based on observation and measurement of phenomena, as
directly experienced by the researcher.
Empirical evidence: Objective evidence that appears the same, regardless of the observer.
Empirical cycle:
1 - Observation: identifying the problem, what am I going to research? Patterns, events, effects.
2 - Reviewing literature: previous findings, are there gaps in the literature?
3 - Research questions and hypotheses: What do u wanna find out/what do u think will happen?
4 - Study design: How to measure, which variables?
5 - Sample: how do you choose persons or events? Does this represent the population?
6 - Collecting data: data collection following the study design
7 - Analyzing the data: apply a statistical method in order to accept/reject hypotheses
8 - Evaluating the data: prediction confirmed/refuted
The cycle does not end, unlimited research :)
Learning Goal 2 - Understand the roles of descriptive and inferential statistics in science
Statistics: A set of mathematical tools that help us draw some conclusions about our data.
- To describe our sample (= group of individuals from the researched population)
- To make inferences about our population
Descriptive statistics: Mathematical operations that help us summarize (describe) our sample
data. Cannot provide us with any information regarding the population.
WHY? → Raw data cannot help us answer questions, to help us understand our
sample. To see through the “mess” of our data and help summarize & see patterns.
To look at our data objectively despite variation within.
1. Frequency (times an observation appears in dataset) and proportions (frequency relative
to the total number of observations)
2. Measures of central tendency: A single value that describes where most observations in
a dataset are clustered.
a. Mode: value that appears most frequently in dataset
b. Mean: average value in dataset
c. Median: value that appears in the middle of the dataset
3. Measures of spread: A single value that describes how spread out the data points are.
a. Range: difference between largest and smallest value
b. Five number summary
- Q0: minimum Q1: lower median Q2: median Q3: upper median Q4: maximum
c. IQR: middle 50% of the data
- Q3 - Q1 = median of upper 50% - median of lower 50%
d. Variance: difference between each datapoint and mean Σ¿¿
e. Standard deviation: same as variance but easier to interpret √ ❑
Squaring WHY → positive and negative values don’t cancel each other out (-12 =
144)
, ensures more extreme values that contribute exponentially to V or SD
The bars in graphs represent the SD
68-95-99.7-rule: 68% of data ± 1 s.d. / 95% of data ± 2 s.d. / 99.7% of data ± 3 s.d.
Inferential statistics: Use analysis from our sample data to make inferences about the total
population. Covered in RBMS, not IBMS!!
Learning Goal 3 - Remember methodology terminology, variable types (categorical vs
quantitative), trade-offs of different data types, roles of variables in studies
(independent/dependent/control/confound variables)
Variable: any characteristic of an individual (height, color, treatment, amount of sunlight or food)
a) Their role in a research study
- Independent variable: intentionally manipulated (treatment with X factor)
- Dependent variable: measured to determine outcome (height of plant)
- Control variable: consistent to minimize confounding effects (water, sun)
b) The type of data they represent
- Categorical: in words & place individuals in categories
- Nominal: blue, green, brown eyes (no order)
- Dichotomous: married or unmarried
- Ordinal: small, medium, large (order)
- Quantitative:
- Discrete: babies born each day (whole numbers)
- Continuous: Height, blood pressure (decimals allowed)
Learning Goal 4 - Analyze written examples to identify variable types being described
WG
Learning Goal 5 - Understand that the type of variable determines what type of
descriptive statistics are appropriate, apply this in given examples
WG
Learning Goal 6 - Understand & interpret descriptive statistics
WG
Learning Goal 7- Apply & analyze descriptive statistics, graphical information & calculate
descriptive statistics
WG + pics end of summary
Learning goal 8 - Understand the importance of randomization & random sampling in
study design
Placebo effect: the psychological impact of undergoing any kind of treatment.
Randomization is used as a solution for bias; using impersonal chance to select a group
Learning goal 9 - Understand different study designs & their strengths and weaknesses
Empirical research: Research that is based on observation and measurement of phenomena, as
directly experienced by the researcher.
Empirical evidence: Objective evidence that appears the same, regardless of the observer.
Empirical cycle:
1 - Observation: identifying the problem, what am I going to research? Patterns, events, effects.
2 - Reviewing literature: previous findings, are there gaps in the literature?
3 - Research questions and hypotheses: What do u wanna find out/what do u think will happen?
4 - Study design: How to measure, which variables?
5 - Sample: how do you choose persons or events? Does this represent the population?
6 - Collecting data: data collection following the study design
7 - Analyzing the data: apply a statistical method in order to accept/reject hypotheses
8 - Evaluating the data: prediction confirmed/refuted
The cycle does not end, unlimited research :)
Learning Goal 2 - Understand the roles of descriptive and inferential statistics in science
Statistics: A set of mathematical tools that help us draw some conclusions about our data.
- To describe our sample (= group of individuals from the researched population)
- To make inferences about our population
Descriptive statistics: Mathematical operations that help us summarize (describe) our sample
data. Cannot provide us with any information regarding the population.
WHY? → Raw data cannot help us answer questions, to help us understand our
sample. To see through the “mess” of our data and help summarize & see patterns.
To look at our data objectively despite variation within.
1. Frequency (times an observation appears in dataset) and proportions (frequency relative
to the total number of observations)
2. Measures of central tendency: A single value that describes where most observations in
a dataset are clustered.
a. Mode: value that appears most frequently in dataset
b. Mean: average value in dataset
c. Median: value that appears in the middle of the dataset
3. Measures of spread: A single value that describes how spread out the data points are.
a. Range: difference between largest and smallest value
b. Five number summary
- Q0: minimum Q1: lower median Q2: median Q3: upper median Q4: maximum
c. IQR: middle 50% of the data
- Q3 - Q1 = median of upper 50% - median of lower 50%
d. Variance: difference between each datapoint and mean Σ¿¿
e. Standard deviation: same as variance but easier to interpret √ ❑
Squaring WHY → positive and negative values don’t cancel each other out (-12 =
144)
, ensures more extreme values that contribute exponentially to V or SD
The bars in graphs represent the SD
68-95-99.7-rule: 68% of data ± 1 s.d. / 95% of data ± 2 s.d. / 99.7% of data ± 3 s.d.
Inferential statistics: Use analysis from our sample data to make inferences about the total
population. Covered in RBMS, not IBMS!!
Learning Goal 3 - Remember methodology terminology, variable types (categorical vs
quantitative), trade-offs of different data types, roles of variables in studies
(independent/dependent/control/confound variables)
Variable: any characteristic of an individual (height, color, treatment, amount of sunlight or food)
a) Their role in a research study
- Independent variable: intentionally manipulated (treatment with X factor)
- Dependent variable: measured to determine outcome (height of plant)
- Control variable: consistent to minimize confounding effects (water, sun)
b) The type of data they represent
- Categorical: in words & place individuals in categories
- Nominal: blue, green, brown eyes (no order)
- Dichotomous: married or unmarried
- Ordinal: small, medium, large (order)
- Quantitative:
- Discrete: babies born each day (whole numbers)
- Continuous: Height, blood pressure (decimals allowed)
Learning Goal 4 - Analyze written examples to identify variable types being described
WG
Learning Goal 5 - Understand that the type of variable determines what type of
descriptive statistics are appropriate, apply this in given examples
WG
Learning Goal 6 - Understand & interpret descriptive statistics
WG
Learning Goal 7- Apply & analyze descriptive statistics, graphical information & calculate
descriptive statistics
WG + pics end of summary
Learning goal 8 - Understand the importance of randomization & random sampling in
study design
Placebo effect: the psychological impact of undergoing any kind of treatment.
Randomization is used as a solution for bias; using impersonal chance to select a group
Learning goal 9 - Understand different study designs & their strengths and weaknesses
