## Statistics is all Maths!

Surprisingly, business statistics is not that much of maths but rather concepts and understanding when to use the right tools. Imagine yourself as a carpenter. You will have tools such as hammer, screw drivers and saw. You will have to know what tools to use at the right time. That is how business statistics should be applied into. You will be given statistics questions that requires certain use of the right test to do it. Identifying the right test and apply it into the question is all it takes to do this course.

## Introduction to statistics

Statistics is the science of collecting and analyzing data in order to infer characteristics about the population.

✔ Descriptive data

✔ Inferential data

✔ Quantitative

✔ Qualitative

✔ Ordinal, Interval, Ratio and Nominal Measurements

## Probabilities

In statistics, proability is everything. Probability is simply the chance of a particular event happening. Usually, the course will cover topics such as

✔ Probability Rules

✔ Conditional probability

✔ Joint probability

✔ Independent and Mutually Exclusive events

✔ Ordinal, Interval, Ratio and Nominal Measurements

## Discrete and Continuous Probabilities

A discrete distribution describes the probability of occurrence of each value of a discrete random variable. In other words, it calculates the probability of an event happening that has no decimal points or fraction involved. continuous distribution describes the probabilities of the possible values of a continuous random variable. In this sense, it is just a probability distribution for a variable that can contain decimal values. Some examples of the distributions are

✔ Binomial

✔ Poisson

✔ Uniform

✔ Exponential

## Measures of Central Tendency

In statistics, the 3 main types of central tendency are

✔ Mode

✔ Median

✔ Mean

Mode is the most commonly appearing number or value in a distribution. Median is the “middle number” when listing the whole data set in a ascending order. Lastly, mean is the average number.

The mode has an advantage over the median and the mean as it can be found for both numerical and categorical data. The median is less affected by outliers and skewed data. The mean can be used for both discrete or continuous numeric data.

## Confidence intervals

Confidence interval is a range within the distribution that reflects where the true mean lies within a determined probability percentage. ie. Alpha Basically, it is to derive the 2 values at the both ends represented by (1-C)/2 , in order to conclude on the range for a certain determined Alpha.

## Z Score

A Z-score is a numerical measurement that describes a value’s relationship to the mean of a group of values. Simply put, it is calculating for a random number, where it stands away from the mean. This is done such that we can calculate the probability. The formula is as follows : It requires the population standard deviation represented by Sigma, . Standard deviation measures how the fluctuations of the data set in the distribution.

## hypothesis testings

Hypothesis testing is to conduct a test whereby a null (What i believe in) vs alternate (What the opposite result would be if it goes against null) hypothesis would be conducted to determine which is true. Basically, it means that we have a certain believe and now we are going to test whether which believe is true.

For example, you believe that the students in the school on average is around the height of 1.7m. You go around collecting data of 30 students’ heights and the average came out to be 1.69m. Are you statistically wrong? We will conduct a test to prove so.

## annova

Analysis of variance (ANOVA) is a collection of statistical models and their associated estimation procedures (such as the “variation” among and between groups) used to analyze the differences among group means in a sample. The one-way analysis of variance (ANOVA) is used to determine whether there are any statistically significant differences between the means of three or more independent (unrelated) groups.

For example, we have 3 sales averages from 3 stores located in East, West, and North. Are the averages statistically different or are the averages the same?

## chi square

A chi-square (χ2) statistic is a test that measures how expectations compare to actual observed data (or model results). There are 2 forms of tests – Chi Square Test of Independence and Chi Square Test of Homogeneity.

The formula for chi-sqaure is as follows: In the Chi Square Test of Independence, we are trying to determine if there exist any relationships between variables in our data set while in the chi square test of homogeneity, we are trying to determine if the distributions shape is the same for the different group of data sets.

## regression

In statistics, linear regression is a linear approach to modeling the relationship between a scalar response (or dependent variable) and one or more explanatory variables (or independent variables). The formula for liner regression is : It is use to determine if an X, which is the independent variable influence the Y, which is the dependent variable. Take it as though X is the master and Y is the slave. The Y will listen to the changes in X and change its value accordingly.

## Was the content above overwhelming?

It will be if you are not numerical inclined. Don’t worry though, it will be much easily handled as the calculator or software such as Minitab or SPSS can do some of the work for you.

What I can do in delivering the statistics tuition content is to break the concepts into parts and translating the statistics jargons and concepts into layman wording. Usually, this will do the trick in understanding this topic.

We will look into different statistics questions so as to understand how to apply the right statistics tool into the questions.