Chapter 14 Flashcards
Define variables:
Any characteristics/attribute that can be measured.
Define independent variables:
Independent variables (IVs)– variable is systematically controlled/manipulated by researcher & is believed to predict/cause
change in a dependent variable (DV). It’s independent in the changes in
other variables.
Define dependent variables:
Dependent variables (DVs)– Observed variable whose changes are determined by presence/degree of 1/more IVs. Value depends on changes made to IVs.
Explain assumptions:
Each statistical technique has certain assumptions that must be satisfied in order to avoid making possible wrong conclusions.
Explain parametric vs. non-parametric tests:
o Parametric: continuous data, assumption of normality, > effective and accurate.
o Non-parametric: categorical data, normality not assumed, less strict.
What are some sample size considerations?
Sample size depends on:
- Variation of the data.
- The type of study undertaken
What is the criteria for choosing a statistical technique?
(flow diagram p.315) (5 parts)
- What the analysis technique is supposed to do.
- The scale with which the variables were measured, or variable measurement type.
- The number of variables that must be analysed.
- Dependent vs Independent variables.
- Number of categories.
What are the four statistical techniques we use?
- The Chi-square Test
- One-way ANOVA
- Independent T-Test
- Correlations
Explain the Chi-Square Test:
- Determines if there is an association between two categorical variables.
- p-value < 0.05 = statistically significant difference
E.g. Analyse relationship between Gender and Consumption of coffee
The proportion of males who have consumed coffee (85/97 = 88%) is lower than the proportion of females (92/95 = 97%).
A Chi-square statistic of 6.24 (p-value of 0.012) indicates that there is a statistically significant difference between the categories (consumption of coffee by males vs females)
Explain One-Way Analysis of Variance (ANOVA)
ANOVA = determines if > 2 means are equal
One-way ANOVA = test relationship between 1 DV (continuous) and 1 IV (categorical)
Two-way ANOVA = test relationship between 1 DV (continuous) and >1 IV (categorical)
E.g. Analyse relationship between the price consumers are willing to pay and the type
of coffee.
Consumers are willing to pay more for a Cappuccino (mean = 32.95) and Americano
(mean = 30.32) than for filter coffee (mean = 15.01).
An F-test produces a p-value of 0.032, showing a statistically significant (p<0.05)
difference between the prices consumers are willing to pay for the different types of
coffee.
Explain the Independent T-Test:
Determine if there’s a significant difference between mean scores of 2 categories/groups that are independent.
E.g. Analyse the differences in the price consumers are willing to pay for coffee
according to gender (male vs female).
An independent T-test is conducted to determine if the difference between males
and females is statistically significant. The p-value of 0.015 is statistically significant (p<0.05) which indicates a significant difference between the price that males and
females are willing to pay for coffee.
Explain Correlations:
Measures extent to which a change in 1 continuous variable is associated with a change in another continuous variable.
Correlation analysis produces correlation coefficient (r) which indicates strength & direction of relationship between 2 continuous variables.
In linear relationship r ranges from -1 to 1.
r = 1 – perfect positive correlation,
r = 0 – no correlation,
r = -1 perfect negative correlation
Positive correlation – as value for 1 variable increases, value for other variable increases.
Negative correlation – as value for 1 variable increases, value for other variable decreases.
