Quantitative Analysis Flashcards
Could we have analyzed the questionnaire data in another way?
Propose at least other method of analysis and a reflection about it.
To use ANOVA the independent (x) variables should be nominal not continuous as they are in our case. Moreover, we analyze 9 facts, and ANOVa only goes up to two independent variables. Otherwise the questionnaire should be changed completely.
What is non response bias?
occurs when some respondents included in the sample do not respond. The key difference here is that the error comes from an absence of respondents instead of the collection of erroneous data.
What is the assumption of Variation in X
It ensures that you have different observations and thereby including different answers/perspectives to the research.
What is the assumption of Normal distributed residuals (y)?
It shows that data near the mean are more frequent in occurrence than data far from the mean
What is the assumption of Homoscedasticity?
It wants the error terms to be the same across all variables
What is the assumption of Independence between errors?
the distribution of errors is random and not influenced by or correlated to the errors in prior observations.
What is the assumption of Zero conditional mean?
we do not want more negative than positive observations, or vice versa, but want them to cancel out to make the average of the independent variables close to 0.
What is the assumption of Serial correlation?
the relationship between a given variable and a lagged version of itself over various time intervals. It measures the relationship between a variable’s current value given its past values. → we have cross section (snapshot of time) hence we do not check for time intervals
What does the F ratio and P-value from the analysis of variance is
F ratio: The F Value or F ratio is the test statistic used to decide whether the model as a whole has statistically significant predictive capability, that is, whether the regression SS is big enough, considering the number of variables needed to achieve it. F is the ratio of the Model Mean Square to the Error Mean Square.
P-value: The smaller the p-value, the stronger the evidence that you should reject the null hypothesis. indicates how confident you can be that a result isn’t due to random noise
Mention the possible reasons for having insignificant results
- Multicollinearity: The problem with multicollinearity is that it can lead to the conclusion that no independent variable has a linear relationship with the dependent variable, even though one or more in reality is linearly related
· What about Other assumptions which are not fulfilled?
- Normal distribution not fulfilled for model 1.
- Heteroscedasticity
· high std. Dev: Because it is a sample size and the are very spread, it becomes more difficult
What other methods/approaches did we also tried or look for finding significant results?
Explain
Stepwise regression: It involves adding or removing potential explanatory variables in succession and testing for statistical significance after each iteration.
o F-to-enter ratio
