Lecture 9 Flashcards
What do cross-tabulation and chi-square tests enable marketers to analyse?
The association between two ‘categorical variables’
What are the limitations of a chi-squared test?
1- A sample size too large or too small
2- It can only determine whether two variables are related; does not establish causality
What does the t-test determine?
Whether the sample mean and mean of the population differ
What does the Pearson’s chi-squared test show?
Determines if there is a significant difference between observed and expected frequencies in categorical data
What is typically the critical value?
0.5
What can we do if our P-value is smaller than the critical value?
The null hypothesis can be rejected
What is one of the most popular hypothesis tests in statistics?
T-test
What groups are used for an independent sample t-test?
Two independent groups (categories)
Independent = participants cannot be in both groups
What groups are used for a paired sample t-test?
Two paired groups (categories)
Paired = participants at two different time points
What groups are used for an ANOVA test?
Three or more groups (categories) (participants cannot be in more than one group)
What do t-tests examine?
The differences between group means measured on interval or ratio scales.
What type of statistic is a t-test?
Inferential
What three data values are required to calculate a t-test?
1- The difference between the mean values from each data set (the mean difference)
2- The standard deviation of each group(s)
3- The number of data values for each group
What does interval and ratio data provide for t-tests?
Provides mean and we can calculate the standard deviation (SD) from this
What test checks for ‘normality’?
Kolmogorov-Smirnov & Shapiro-Wilk test
What does it mean if there is not a significance in independent t-tests?
It is not normally distributed
What’s an outlier?
A data point that is significantly different from others
What can non-normal data lead to?
Inaccurate p-values, increasing the risk of Type I and Type II
What does the one-way ANOVA test?
Whether there is a difference between the means of
more than 2 groups.
What data do we need for ANOVA tests?
Independent variables: Categorical (nominal/ordinal)
Dependent variables: Continuous (interval/ratio)
What should the scale level of the dependent variable be for ANOVA tests?
Metric
What should the scale level of the independent variable be for ANOVA tests?
Nominal
What is homogeneity?
Drawn from a single population (can be checked with the Levene test)
What is a Type I (false positive)?
False positive- positive association even if there is none
What is a Type II (false negative)?
False negative- don’t find significance but they are actually in the data
