Introduction To Quantitative Methds And MCT. Flashcards
Week 1 covering: Introduction to quantitative methods. Week 1.
What will be covered this week:
-What is quantitative research methods?
-Types of data
-Measures of central tendency
-Sample and population
Week 1 (intro) covering: What are quantitative methods.
Recap from last term, this is what we know:
-Numerical data
-Looking at differences and relationships in data
-Generalisable results (within reason!)
-Test hypotheses
-Strict practices (rules!)
Objective interpretation
Week 1 (intro) covering: Why is quantitative research methods important for you?
How you will be using quantitative methods in your degree (and further):
-You’ll be able to interpret and read statistics (helpful for all modules!)
-Prepare you for dissertation analysis
Will need this if you want to do a psychology-based masters or be a psychologist in the future.
Week 1 (intro) covering: How to do quantitative research.
First thing - as quantitative research is the objective/structured path of research we need to follow some rules…
When working with numbers we need to:
-Ask answerable questions
-Group and measure our data
—
Example - Does your profession affect how tall you are?
Week 1 (intro) covering: Asking an answerable question - what does this mean?
All questions can hypothetically be answered but what’s different about quantitative questions?
-We want to test a hypothesis
-In this example, X affects Y
-X and Y are variables
A variable is a characteristic that can be measured or counted
We will revisit this in more depth in another week, but the important point here is that X and Y need to be measured to answer our research question.
How do we do this? Let’s break it down…
Example - Does your profession affect how tall you are?
What are our variables?
How can we define the variables to measure them?
Week 1 (intro) covering: Types of data.
- Categorical
There is no order to the data, just groups
Examples - ice cream flavours, Y/N, course studied at university, agree/disagree
Binary - two categories
Nominal - more than two categories. - Continuous
There is an order to the data, groups aren’t needed
Examples - shoe size, likert scales, temperature in °C, age
Ratio - Continuous scale data with an absolute zero
Interval - Continuous scale data with no absolute zero
Ordinal - Categorised data with a natural order
Week 1 (intro) covering: Types of data Pt2.
Question = does your profession effect how tall you are?
Categorical
There is no order to the data, just groups
Examples - ice cream flavours, Y/N, course studied at university, agree/disagree
Binary - two categories
Nominal - more than two categories. = THE PROFESSION.
Continuous
There is an order to the data, groups aren’t needed
Examples - shoe size, likert scales, temperature in °C, age
Ratio - Continuous scale data with an absolute zero. = HOW TALL YOU ARE.
Interval - Continuous scale data with no absolute zero
Ordinal - Categorised data with a natural order.
Week 1 (intro) covering: Measures of central Tendency (mode, mean, medium).
“A measure of central tendency is a single value that attempts to describe a set of data by identifying the central position within that set of data”
A summary statistic
-Mean
-Median
-Mode
Usually slightly different unless…
Week 1 (intro) covering: Normal distribution.
The bell curve - symmetrical.
In the normal curve, the mean, median, and mode are all the same.
(Remember when using the sum of the dataset in a 0.00 formula to round either up or down).
Week 1 (intro) covering: Mean.
What is the mean?
Sum of the data, divided by number of data points
-E.g 1, 2, 3, 4, 5
-1 + 2 + 3 + 4 + 5 = 15
-15/5 = 3
-Mean = 3
When to use:
-Most of the time for continuous data.
-When data is normally distributed.
Pros & Cons of the mean:
Pros
Most used MCT - accounts for all data points
Therefore, the mean is the best representation of your dataset!
Cons
-Not effective if you have outliers
-E.g. 1, 2, 3, 4, 5, 100
Not effective if your data is skewed.
(Skewed distribution in the bell curve).
Week 1 (intro) covering: Median.
What is the median?
The middle number of data points
E.g. 1, 2, 3, 4, 5
Median = 3
If there is an even number of data points we find the mean of the two data points only
E.g. 1, 2, 3, 4
2 + 3 = 5
5/2 = 2.5
Median = 2.5.
When to use
When continuous data isn’t normally distributed (outliers or skew).
Week 1 (intro) covering: Median pros and cons.
Pros
Good for non-normal distributions
Isn’t affected by outliers.
Cons
Doesn’t account for all data
Small snapshot of continuous data.
Week 1 (intro) covering: mode.
What is the mode?
From the french word mode, meaning ‘fashion’, this is the most popular number/item in our dataset
E.g. 1, 2, 3, 4, 5, 5
Mode = 5
In some cases we can have one than one mode
E.g. 1, 1, 2, 2, 3, 4, 5
Mode = 1 and 2.
When to use
Categorical data only.
Week 1 (intro) covering: mode pros & cons.
Pros:
Useable for categorical data
(you couldn’t find the mean of professions!).
Cons:
Not usable for continuous data.
Doesn’t give you an accurate representation of the data for most datasets.
Week 1 (intro) covering: populations and samples.
Taking our research question:
“Does your profession affect how tall you are?”
To know for sure we would have to survey every single working person
(Remember, by population we don’t mean all the people in the world, but the group of people we are interested in for our research)
It isn’t possible to take the heights of every working person… So what can we do?
Taking our research question:
“Does your profession affect how tall you are?”
To know for sure we would have to survey every single working person
(Remember, by population we don’t mean all the people in the world, but the group of people we are interested in for our research)
It isn’t possible to take the heights of every working person… So what can we do?
