Please enable JavaScript.
Coggle requires JavaScript to display documents.
inferential testing - Coggle Diagram
inferential testing
significance levels
based on probability to establish if results are significant
if results significant
accept alternate hypothesis (directional/non-directional)
reject null hypothesis (no difference/increase/decrease)
if results not significant
reject alternate hypothesis
accept null hypothesis
generally accepted level of significance in psychology is p=0.05
means 5% probability that results were due to another factor and researchers are 95% confident in their results
psychologist has a 5% chance of making a type 1 error
sometimes psychologists use stricter level of significance of p=0.01
if significant consequences for findings such as medical testing or socially sensitive research
means 1% probability results due to something other than IV and 99% confident in results
most common level of probability 0.05 as represents a reasonable balancing point between the chances of making a type 1 and type 2 error
factors affecting the choice of statistical test
test of difference or correlation
was reasearcher looking at difference between groups (experiment) or the relationship/association between variables (correlation)
2.experimental design
unrelated design
independent groups
related design
repeated measures
matched pairs
level of measurement
ordinal
interval
nominal
Carrots Should Come Mashed With Swede Under Roast Potatoes
chi squared, sign test, chi squared, Mann-whitney, Wilcox, spearmans rho, unrelated t-test, related t-test, Pearsons r
type 1 and type 2 errors
type 1
false positive: the researcher has incorrectly rejected the null hypothesis
occurs when a researcher claims support for the researcher with a significant result, when the results were caused by random variables (chance)
the likelihood of making a type 1 error is always the same as the significance level
Type 2
false negative: the researcher has incorrectly accepted the null hypothesis
researcher claims there is no significance in the results when the effect the researcher was trying to demonstrate does exist
impossible to determine the likelihood of making a type 2 error
use of statistical tables and critical values in the interpretation of significance