HPS201 Final: HPS201 Research Methods A
HPS201
Research Methods A
Emily Zukic
Dr Christian Hyde: [email protected]du.au
Week 1: Introduction to Statistics & Frequency Distributions
-An introduction to the key principles of research methods in psychology
-SPSS: real world data analysis
- Difference between population and sample
-Population: entire set of individuals, or events of interest in a particular study
-Sample: set of individuals selected from a population
-Representative sample: sample that shares the key characteristics of the population from which it
has been taken: so that the results can be generalised back to population
- Distinguish between parameters and statistics
-Parameter: a value that describes a key characteristic of the population
-Statistic: a value that describes a key characteristic of the sample
-Statistics are used to estimate values that exist in the whole population of interest
- Distinguish between descriptive and inferential statistics
-Statistics: using mathematics to organise, summarise and interpret numerical data
-Descriptive: organising and summarising data
-Inferential: interpreting data and drawing conclusions: see if there is a statistically significant and
reliable difference between findings
- Distinguish between discrete and continuous variables
-Variable: characteristic/condition that changes or has diff values for diff individuals ex. Age
-Discrete: contain only a small number of values
ex. Handedness, favourite season. Categorical data
-Continuous: many different values
ex. Weight 40-140, age 0-100. Measurement Data
-The type of data used will impact the types of statistical approaches used to analyse it
- Categorical data and measurement data
-Categorical: (frequency or qualitative data) categorise things and data consists of frequencies for
each category.
-Ex. 15 people classed as highly anxious, 33 as neutral and 12 as low anxious
-Measurement: (quantitative) the results of any sort of measurement.
-Ex. Grades on a test, weight, scale of self-esteem
- Independent & dependent variables
-IV: variables we manipulate as we believe it will effect the DV
-DV: variable that we measure
-Measured via measurement scales
- Different types of measurement scales (nominal, ordinal, interval and ratio)
-Nominal: not really scales, do not scale items along a dimension, just label them, categorical data
usually used
-Ex. Variables such as gender/ political party are often used
find more resources at oneclass.com
find more resources at oneclass.com
-Ordinal: simplest true scale, which orders people/objects/events along the same continuum
-Ex. Someone with a score of 20 has experienced more stress than someone with a score of 15, as
nothing is implied by the differences
-Interval: a measurement scale where there are differences between scale points
-Ex, Fahrenheit scale of temperature, the difference between 10F-20F is the same as between 80F-
90F
-Ratio: has a TRUE zero point that corresponds to the absence of it being measured
-Ex. Length, time, volume
- How to construct frequency distribution, histograms and stem-leaf plots
-Frequency table/graphs: organising and simplifying the data collected into a logical order
-Provide 1. The set of scores/range of categories that people could have either obtained or fallen into
on the variable of interest
-Provide 2. A record of frequency/number of individuals who obtained each score/ fell in each
category
-Neg: can retain values of the individual observations but difficult to use as data isn’t summarised
efficiently
-Histograms:
-Most frequently adopted graph/table
-Results of histogram TYPE, CENTRAL TENDENCY, VARIABILITY
-Neg: often lose the actual numerical values of the individual scores in each interval
-Stem & Leaf Plots
-Avoid both the criticism of histograms and frequency distributions
-Useful for comparing 2 different distributions
-Leading digits: (most significant) form the stem/vertical axis
-Trailing units: (less significant) form the leaves/horizontal elements
-Neg: some data sets it will lead to a grouping that is too large
- Positive skew, Negative Skew & Kurtosis
find more resources at oneclass.com
find more resources at oneclass.com
-Normal distribution: unimodel (one peak), symmetrical, score with the highest frequency is in the
middle of the distribution, the relative frequency of scores decreases as you move towards the tail
-Skewed:
-Positive: scores tend to pile up to the left hand side of the distribution
-Negative: scores pile up to the right hand side of the distribution
-Kurtosis:
-refers to the relative concentration of the scores in the centre, upper and lower ends (tails), the
shoulders (between the centre) of a distribution.
-Mesokurtic: A normal distribution
-Platykurtic: Curve becomes flatter
-Leptokurtic: the tails become more peaked and thicker
Week 2: Central tendency, variability, z-scores
- Central Tendency
-Statistics that represent the ‘centre’ of a distribution
-Provide a single value to represent all scores in the distribution
- 3 Measures of Central Tendency
-Mean: average score within a distribution: sum/amount of people
-Median: middle point within an entire range of scores, if scores are listed from smallest to largest
median is placed in middle, 50% will fall below it
-Mode: most frequently occurring value
- Variability
-A quantitative measure of the degree to which scores in a distribution are spread out or clustered
together
-Standard Deviation: most commonly reported measure of variability
- Variance and Standard Deviation
-4 Step Calculation
-1. Determine the deviation/distance between each individual score & the mean
-Deviation Score: difference between individual score – sample mean
-2. Goal is to calculate average deviation between scores in the group and the mean, calculate the
average of the deviation scores
-Problem: the sum of the deviation scores will always = 0
-Therefore add out deviation scores, then square them to ensure they are positive
-3. Sum the squared deviation scores
-4. Compute the mean squared deviation score: referred to as VARIANCE (S2)
find more resources at oneclass.com
find more resources at oneclass.com
Document Summary
Week 1: introduction to statistics & frequency distributions. An introduction to the key principles of research methods in psychology. Population: entire set of individuals, or events of interest in a particular study. Sample: set of individuals selected from a population. Representative sample: sample that shares the key characteristics of the population from which it has been taken: so that the results can be generalised back to population. Parameter: a value that describes a key characteristic of the population. Statistic: a value that describes a key characteristic of the sample. Statistics are used to estimate values that exist in the whole population of interest. Statistics: using mathematics to organise, summarise and interpret numerical data. Inferential: interpreting data and drawing conclusions: see if there is a statistically significant and reliable difference between findings. Variable: characteristic/condition that changes or has diff values for diff individuals ex. Discrete: contain only a small number of values ex.
