When you open the file in a text editor you see that: Remember to first create a new data table (File -> New -> New Data Table and Graph) before importing the normTemp data into Prism. This data set is a csv file containing data on human body temperature and heart rate. We will calculate the correlation between male and female body temperatures using the normTemp data. If the demand is high, the price will also high and vice versa. For instance, a correlation exists between the demand for a product and its price. If the correlation is equal to 0 it does not mean that there is no relationship between the groups, it just means that there is no linear relationship. If the correlation is not equal to 0, it means that the two groups of data show similar (they increase or decrease together) or completely opposite (one increases while the other decreases) behaviour. Now perform a "Column statistics" analysis on the "Cleaned data" results file.Ĭorrelation (r) is a measure of the linear relationship between two groups of data. This analysis generates three results files: For all other analyses on this data set we will use the complete instead of the trimmed data set. This is ok since we are only doing this to calculate the trimmed mean. Although we did say in Exercise7 that you may only remove values if you're 100% certain that they are the result of measurement errors, we now happily throw away some of our data values. It means at least 99% of the identified outliers are actual outliers.
If you set Q to 1%, you allow no more than 1% of the identified outliers to be false (not real outliers but just making up the tail of the normal distribution). The percentage Q that you see in the "How aggressive" section represents the percentage of false positives you allow. This opens the "Parameters" window: leave the parameters at their default settings.
This means that we first have to identify the extreme data values. The trimmed mean is the mean of the data set after removal of the most extreme data values. IQR = 75% Percentile - 25% Percentile = 49340.Ĭalculate the trimmed mean of the "INCOME" column. You can calculate the variance as the square of the standard deviation = 13070891584.Ĭalculate the interquartile range (IQR) of the "INCOME" column. The results table contains all the values that you need:Ĭalculate the variance of the "INCOME" column. Select the statistics that you need and click "OK". Here you can specify the descriptive statistics that you want to calculate. Select the type of analysis and the column on which you want to perform the analysis:.Click the "Analyze" button in the "Analysis" section of the upper toolbar.Descriptive statistics are calculated for each column of a column table in the "Column statistics" analysis.Īs an example, we will use the cfb data (see Exercise 2C).Ĭalculate mean, median, standard deviation and quartiles of the "INCOME" column, which represents the yearly income per household.
the dispersion of the values in the data set: standard deviation, variance, minimum, maximum, kurtosis, skewnessįor a detailed description of these measures we refer to the tutorial, Chapter 8.Ĭalculation of descriptive statistics is a statistical analysis so you have to use the "Analyze" button in the "Analysis" section of the upper toolbar.the center of the data set: mean, median, mode.Go to parent GraphPad Prism statistical analyses Exercise 9A: Descriptive statistics of cfb data setĭescriptive statistics is a set of statistical measures that describe the main characteristics of a data set including: