I am trying to compare the student population in one city with the rest of the country in the UK. I am thinking of comparing the means and the p-value during the same period of time. what type of statistical test do I use to compare among multiple populations?
Hello Aysha,
The answer depends on: (a) how the data were collected; and (b) the nature of the score(s) to be compared.
If you're confident that the data you have fully captures the respective populations (e.g., all the students in the target city; all the students in the U.K.), then you have population parameters, not sample statistics. A direct comparison of the two values of interest (e.g., mean of annual marks in mathematics) will suffice to determine whether they are or are not equal; no test is required. Whether an observed difference is of such magnitude as to be meaningful, however, is a judgment call.
If, on the other hand, you are sampling students from multiple cities for this comparison, then, for continuous, interval-strength variables you could compare any two batches via the independent t-test, or more than two batches (e.g., city X vs. city Y vs. city Z) via one-way anova.
Good luck with your work.
That depends on variables used in your experiment. If the objective is to compare two groups you may use chi square or t test, but if you have two or three variables with different levels each you should go to ANOVA.Regards.
Use G-power to find the right sample size. Data needs to be large enough to approximate the true distribution of the population being studied. To determine which statistical test to use, you need to know: whether your data meets certain assumptions. the types of variables that you're dealing with
Thank you very much for taking the time to answer my question. All of your answers give insight into how I need to decide on the statistical test.
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Modeling
- Analyses of Variance
- ANOVA