logic of testing, sampling distribution of null hypothesis

The alternative hypothesis, denoted by H1 or Ha, is the hypothesis that sample observations are influenced by some non-random cause.

1. statistical reasoning allows calculating the probability that

observed differences (e.g., between means) are due to error

2. if this probability is low, we can assume this is not due to error

3. we reject the null hypothesis, and accept the research hypothesis

4. what is the probability that differences that are large are just sampling error

Type II errors

.05

Having a p value that excessed the critcal vaule p < .05

A statistical test that takes the probability level to reject the null from the area under one tail of the sampling distribution

Takes the probability level required to reject a null hypotheses from the areas under both tails of a sampling distribution's curve

two categorical variables (e.g. is watching soap operas (yes/no) related to using facebook (y/n)?

assess the differences between two or more independent groups with frequencies ranging through small and large. It can perform operations with frequency data that are analogous in function and complexity to single-factor and multiple-factor analysis of variance. Commonly used for frequency differences.

small samples, 2 means, 30 or less. suppose you want to test a hypothesis comparing means for two groups. -for example, is the average com exam score for females different from the average for males, independent samples t-test

-dependent variable must be interval or ratio

-(2 groups only) Independent variable, interval or ration DV (e.g. does taking COM 300 (y/n) relate to your future income in dollars?

-a correlation of 1 indicated that there is a perfect linear relationship between the two variables ( as one variable increases, the other increases)

-a correlation of -1 indicates a perfect linear relationship also, but the relation ( As on increases, the other decreases)

-0= No relationship

indicated that there is a perfect linear relationship between the two variables ( as one variable increases, the other increases)

indicates a perfect linear relationship also, but the relation ( As on increases, the other decreases)

a correlation of 0

Means that there is no relationship

The quantity r, called the linear correlation coefficient, measures the strength and 
      the direction of a linear relationship between two variables. The linear correlation
       coefficient is sometimes referred to as the Pearson model. 

Ranges are 1 to -1.

All other units of measuments gets calucated out you use the z score to measure it. Only measures linear realtionships

Correlation does not always cause causation.

the mean z score for the x, y, variables will be 0

-scores higher than the mean are positive.

-scores lower than the mean are negative.

1. Universalism

2. Communality

3. Organized skepticism

4. Honesty

5. Respect (the people in the study)

Obligations to research participants

Voluntary participation and informed consent

Freedom from harm

Anonymity and confidentiality

Honesty and the practice of deception

Privacy of thought and action

2. Obligations to the research community

Accuracy of reporting

Minimization of bias

Philip Zimbardo conducted the study

-Guards exhibited sadistic tendencies

-Prisoners suffered emotional trauma

-Terminated after 6 days

-rural African American men were studied.

-low income African American men were not informed about treatment after treatment was disovered.

Principles of ethical research

Beneficence: maximize benefit and minimize participants’ risks

-justice

-Informed consent: researches should explain the purpose of the reaserach and its duration and procedures used.

Anonymity: researches do not know the real name of participants

Confidentiality: researcher guarantee that they will not disclose participants identifiable information to anyone else. (ex: police comes in and wants information on cocaine users and they want their info, and they won't give it out)

You can reject your Null Hypothesis when the p value is less than your selected alpha level.