This adds to the credibility of the original findings. People do make inadvertent errors, and sometimes unexpected variables are left uncontrolled. There are rare but important examples of researchers just out-and-out faking data, sometimes because they are simply dishonest, and sometimes because they are so totally convinced that they are right (only to be exposed and humiliated, usually ending careers). There is also the nature of information itself, and its analysis from a statistical point of view. Sometimes, for no reason other than "the fall of the dice", a result may survive a statistical analysis as significant, when it is not. [a false positive] This has nothing whatever to do with dishonesty or bad research technique. When statistical models are used to analyze data, the concept usually is to compare the real experimental data against theoretical models that are built on all possible outcomes assuming that there is no experimental effect whatsoever. A Little Added Detail: In other words, say that you get a certain result on a statistical analysis. You go to your tables and you see that results just like yours do come up by chance alone, but only one time in a thousand. This "one time in a thousand" comes from the fact that the theoretical model for the test you are using represents thousands or tens of thousands (or more) of theoretical results based on completely random data. So when you see that your results are similar to the "one time in a thousand" frequency in the model, you have considerable confidence that your results represent a real effect, and not the rather unlikely "one in a thousand" outcome. Confidence never actually reaches absolutely 100%, But we can (and should) set the desired confidence level even before we gather one bit of data, and can then carry on with our work.
To make sure that the result you got the first time is accurate and true. Things like the environment, equipment and even the amount of chemicals added can change the overall outcome of your experiment; so to make sure you have the correct result, you need to retest.
because the are diffident student every year......
To test if something has been done wrong or out of order. Id repeated data can be well-defined.
It's important to repeat experiments so then you know that you did the experiment right.
Many different experiments are performed and repeated.
It means how many times it is used in or thought of in an expieriment
because the are diffident student every year......
A scientific law is based on many repeated correct experiments.
To test if something has been done wrong or out of order. Id repeated data can be well-defined.
It's important to repeat experiments so then you know that you did the experiment right.
Many different experiments are performed and repeated.
Many different experiments are performed and repeated.
A scientific fact is a fact surely constated by a great number of repeated experiments and having a theoretical explanation.
It means how many times it is used in or thought of in an expieriment
once a hypothesis has been supported in repeated experiments, scientists can begin to develop a theory.
once a hypothesis has been supported in repeated experiments, scientists can begin to develop a theory.
The principal condition is that the theory must be confirmed by repeated experiments.
A scientific theory must be based on many repeated correct experiments; also this theory must be related with other accepted theories.