Get Started. It's Free
or sign up with your email address

1. Measuring uncertainty in raw data

1.1. Measurements aren´t perfect, they always have a certain amount of error, measuring devices aren´t very detailed, they will always give us uncertainty.

1.2. Uncertainty can be measured in many ways depending on the type of measuring material used. When its analog, we need to round the number to the closer number, meanwhile, when it´s digital, we have to look down the smallest number given.

2. Processing data

2.1. calculation tables

2.1.1. We need to label the calculations table, so readers understand what it´s showing. The variables must be used while calculating and the columns headers must be labeled. We also need to include the averages of the raw data and the uncertainty must be propagated.

2.2. Usually, raw data will not actually be the variables that we are investigating, it´s actually the data that will help you calculate the variables. Raw data can sometimes contain the independent and dependent variable.

3. Types of error

3.1. Systematic error: they occur due to the system being used. It´s unaffected by averages when the errors are small, values are said to be accurate and there are calibration errors.

3.2. Random error: it occurs due to natural events that scatter about the true value, like Air currents and air displacement. Averaging and taking multiple data reduces these errors.

3.3. Human error: due to mistakes during data collection or manipulation. Sometimes a misreading of a measuring device or making wrong calculations.

4. Collecting raw data

4.1. We also need to elaborate a raw data table, which is the first table made during the experiment. It needs to have numeric values and labels.

4.2. We need to collection 2 basic types of raw data, quantitative and qualitative data.

5. Accuracy and precision

5.1. Accuracy: how close a measurement is to the “correct” value.

5.2. Precision: how exact or detailed a measurement (or average) is. Indicated by the uncertainty.