Musselwhite

Musselwhite - Musselwhite 11:00 Introduction Statistics is...

This preview shows pages 1–2. Sign up to view the full content.

Musselwhite 11:00 Introduction: Statistics is defined as the likelihood of the results of an investigation being the product of random chance. The practice of statistics was first used by the Romans to designate data of political importance such as: population counts, deaths, tax returns, and the amount of internal or external trade. Since its invention, statistics has grown to serve a major role not only in the political realm, but also in the field of science by becoming a more quantitative set of data. In the sciences statistics plays the role of validating the likelihood of obtaining a certain set of results from a scientific experiment. A statistical inference is made based on the results of a single scientific experiment. In order to prove this set of data as valid it must follow the concept of repeatability. The concept of repeatability states that experimented results must be able to be replicated and produce identical results following the same scientific process. In order to test a statistical question, a hypothesis must first be formulated. This is called the null hypothesis, which is a true of false statement that is tested. For every null hypothesis formulated, there is also an alternate hypothesis which states that the null hypothesis was not supported by the statistical evidence gathered. The null hypothesis is rejected and the alternate accepted if, and only if, the calculated t value is above the critical value. Falsely rejecting a true null hypothesis is called a type one statistical error. The failure to accept a true null hypothesis is called a type two statistical error. One commonly used statistical test used today is the student t test. The t test was developed by William Gosset, a chemist at the Guiness Brewery in Dublin, Ireland, to assure that each batch of brew was as similar as possible to the others. This parametric statistical test is used to compare two groups of data points. There are two types of t tests, paired and unpaired. The paired t test investigates the relationship between two set groups where there is a meaningful one to one correspondence between the two test groups. There are two types of paired t tests. The one tailed test is one where there is a preexisting bias to predict the direction of difference. The two tailed test is one where there is no bias to assume difference between the two groups of data. The second type of t test is the unpaired t test. It does not require any relationship between the two data groups, but the calculations are slightly more complicated. In this lab three different experiments were performed. The first one consisted of flipping a standard mint quarter a varying number of times in order to calculate statistical information using the Chi Square testing method. Secondly, genetic crosses were used to determine if the yield ratios of plants with different phenotypes were

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

Page1 / 10

Musselwhite - Musselwhite 11:00 Introduction Statistics is...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online