Probability and Statistics:Psychology and Business statistic

What is statics? Also, how do you decipher between descriptive and inferential statistics? What role do each play? I'll show you a concrete example what role each of them play.

These four terms (population, sample, parameter, and statistic) are used so often that it's critical to understand what they are. You will not only be understand what each of them means, but you will see how concepts are all intertwined.

Discrete and continuous variables are difficult to understand if you aren't a researcher. I give you a process to follow to easily be able to decipher if something is a discrete or continuous variable. Definitions can be difficult to understand for these terms..my process on the other hand is easy to follow! 

Understanding what type of measure of central tendency to describe your data is critical. The focus in this lesson is the mean, but we also consider the mode and median. The mean is used for a hypothesis testing so it is of particular interest to us.

The standard deviation measures how well the mean represents the data. Understand the importance of the standard deviation in hypothesis testing.

I answer 5 questions in this video related to variability (standard deviation). 

1. Can variance or standard deviation be negative?

2.  What does it mean when standard deviation is 0?

3.  Why do we use n-1 and not n?

4. On an exam with a mean of 78, you obtain a score of X-84

a. would you prefer a standard deviation of 2 or 10?

b. if you scored x=72, would you prefer standard deviation of 2 or 10?

5. 

a. After 3 points have been added to every score in a sample, the mean is found to be M=83 and the standard deviation is s=8. What were the values for the mean and standard deviation for the original sample?

b. After every score in a sample has been multiplied by 4, the mean is found to be M=48 and the standard deviation is 12. What were the values for the mean and standard deviation for the original sample?

The normal distribution is the most important distribution in statistics. It describes a symmetric bell-shaped distribution. I explain when we utilize the normal distribution. 

The purpose of z-scores, or standard scores, is to identify and describe the exact location of each score in a distribution. Find out how it is done.

I call this lesson "Probability made easy". I address what probability is in it's simplest form, I show you an example, and I explain how probability bridges/connects populations and samples.

The distribution of sample means is defined as the set of means from all the possible random samples of a specific size (n) selected from a specific population. I'll use a concrete example to show you what this definition means, and also explain why it's important to understand to understand sampling distribution of mean.

The standard error of the mean (SEM) (i.e., of using the sample mean as a method of estimating the population mean) is the standard deviation of those sample means over all possible samples (of a given size) drawn from the population.

A hypothesis test is a statistical method that uses sample data to evaluate a hypothesis about a population.

These are not errors of calculation made by you, but just a result of the fact that we get to select what's called a significance level or alpha during the hypothesis testing process. When we select an alpha, we are in essence choosing what "bar" we want to set for ourselves in determining if we have a significant result. We can make it easier or harder to get a significant result, but there are ramifications for both, and this is what this lesson is about.

The t statistic is used to test hypotheses about an unknown population mean, μ,
when the value of population standard deviation  is unknown. The formula for the t statistic has the same
structure as the z-score formula, except that the t statistic uses the estimated standard error in the denominator.

A t-test for independent samples, or t-test for a repeated measures design, uses a separate group of participants to represent each of the populations or treatment conditions being compared.

Do males have higher self esteem than females? I show you how to do an independent samples t-test, so you can find out.

Effect size is a measure of the magnitude or size of the treatment effect. It tells us about the separation between distributions. Since a significance test is impacted by sample size (the more sample, the more likely we are to have a significant result), effect size becomes really important.

Estimating an unknown population mean involves constructing a confidence interval. A confidence interval is based on the observation that a sample mean tends to provide a reasonably accurate estimate of the population mean. As a result, a confidence interval consists of an interval of values around a sample mean, and we can be reasonably confident that the unknown population mean is located somewhere in the interval.

For a t-test for repeated measures design,the same group of individuals is tested in both of the treatments..

Does being sleep deprived have a significant effect on problem solving? I help you answer this question by showing you how to perform a repeated samples t-test.

The t statistic is limited to situations that compare no more than two population means. Often, a research question involves the differences among more than two means and, in these situations, t tests are not appropriate.

ANOVA permits researchers to evaluate the mean differences among two or more
populations using sample data.

Is there a link between perfectionism and binge drinking? I show you an example of an independent measures ANOVA.

What is the effect of sleep deprivation on motor-skills performance? I show you an example of a repeated measures ANOVA.

A correlation measures the relationship between two variables, X and Y. The relationship is described by three characteristics: direction, form, strength.

Is there a correlation between a new 7-minute screen developed for Alzheimer's and the usual long cognitive-battery of tests? I show you an example of how correlation works, so you can find this answer for yourself!

Linear regression attempts to model the relationship between two variables by fitting a linear equation to observed data. One variable is considered to be an explanatory variable, and the other is considered to be a dependent variable.

Is the 7-minute screen for Alzheimer's (mentioned in the last example), predictive of what scores a patient would get by doing the longer set of tests? If so, how can this help us? I'll show you an example of linear regression?

Do children have color preferences? I show you an example of a chi-square goodness of fitness test..so you can find out for yourself.

How can using certain words, or asking a question in a certain way, impact eyewitness testimony? This might be crucial for forensic psychologists. I show you how to do a test of independence (chi-square), so you can find the answer to questions like this by yourself.