PSYC10004 Study Guide - Final Guide: Central Limit Theorem, Null Hypothesis, Technology In Revelation Space
7 Sep 2018
School
Department
Course
Professor
Mind, Brain, & Behaviour 2 (PSYC10004) – Notes
Research Methods
MODULE 1: INFERENCE
• Quantitative psych research asks questions which fall into one of categories:
• Difference: is one group different to another in some way?
• Association: is one construct related to another?
• Prediction: does one construct influence another?
• Goal is to make inferences (suggestions or claims) about a population (everyone of interest to a
research question), based on evidence observed in the samples (a group of people taken form the
population to participate in a study)
MODULE 2: TYPICAL AND EXTREME SCORES
• The collective values from different people in the sample form a distribution of
data, which can be described in terms of central tendency (m) & variability (s)
• Histogram: represent a distribution of data (diagram to left)
• Normal Distribution: symmetrical with most people around the middle (->)
• Typical scores: occur frequently – within 2 standard deviations
• Extreme scores: occur infrequently in the distribution – outside 2 SDs. Are
noteworthy as they indicate a difference from what is typical
• 2s Rule of Thumb: defines a critical limit beyond which, scores are considered extreme
MODULE 3: THE DISTRIBUTION OF SAMPLE MEANS
• When we conduct research we usually recruit one sample from each population of interest, but
this sample mightn’t always be typical of the population – can use a distribution of sample means
to determine if the sample is typical or extreme:
Distribution of Sample Means (DoSM): is made up of the sample means from all of the random
samples of a certain size (n) that could possibly be obtained from a population
• A theoretical distribution governed by a mathematical theorem (Central Limit Theorem), which
tells us the precise characteristics of the distribution of any DoSM
• Central Limit Theorem: tells us:
• The mean of the DoSM is the same as the population mean
• For large sample sizes (30+) the DoSM will have a normal shape
• The standard deviation of the DoSM (standard error) – as sample size increases,
standard error decreases, & estimation of the population mean becomes more precise
• If sample is large enough, the DoSM will be normal. We know the mean of the DoSM &
can calculate its standard error. Can therefore use our 2s rule of thumb to test if our
sample mean is typical or extreme
MODULE 4: NULL HYPOTHESIS SIGNIFICANCE TESTING
Experimental hypothesis (aka alternative hypotheses): a statement that predicts an effect of either
difference or association. Denoted as H0
Document Summary
Mind, brain, & behaviour 2 (psyc10004) notes. Are noteworthy as they indicate a difference from what is typical: 2s rule of thumb: defines a critical limit beyond which, scores are considered extreme. We know the mean of the dosm & can calculate its standard error. Can therefore use our 2s rule of thumb to test if our sample mean is typical or extreme. Experimental hypothesis (aka alternative hypotheses): a statement that predicts an effect of either difference or association. Null hypothesis: a statements that predicts there will be no effect (no difference or no association). If the probability is large, do not reject the null hypothesis. Level are precisely +/-1. 96 standard errors from the mean of the distribution. If the sample is inside these limits, the probability is >5%, so the null hypothesis isn"t rejected. Single sample z-test: calculates a z-score for the sample mean (how many standard errors the sample mean is away from h0: calculated using.
