Statistics in Psychology ppt

descriptive statistics psychology ppt and inferential statistics psychology ppt and inferential statistics psychology definition
JuliyaMadenta Profile Pic
JuliyaMadenta,Philippines,Researcher
Published Date:15-07-2017
Your Website URL(Optional)
Comment
Introduction to Statistics for Psychology and Quantitative Methods for Human Sciences Jonathan MarchiniCourse Information There is website devoted to the course at http://www.stats.ox.ac.uk/marchini/phs.html This contains  Course timetable/information  Lecture slides (on the website before each lecture)  Lecture notes (a bit more detailed than the slides)  Exercise sheets (tutors may or may not use these)  Formulae booklet and definitions booklet  Links to past exam papers on the web PLEASE ENTER THE LECTURE THEATRE QUICKLYLecture 1 : Outline  Why we need Statistics? - The scientific process  Different types of data - Discrete/Continuous - Quantitative/Qualitative  Methods of looking at data - Bar charts, Histograms, Dot plots, Scatter plots, Box plots  Calculating summary measures of data - Location - Mean, Median, Mode - Dispersion - SIQR, MAD, sample variance, sample standard deviationThe role of Statistics in the Scientific Process Examine the results of the statistical test Use statistics to test We start with a Propose a Collect our hypothesis based question/hypotheis study/experiment Data on a model of the data that aims to provide about a given i.e. take data to help test our population of a sample hypothesis objects/events from the population Study Design (How can we design STATISTICS our study to get the most information about our hypothesis)An Example Psychologists have long been interested in the relationship between stress and health. A focused question might involve the study of a specific psychological symptom and its impact on the health of the population. To assess whether the symptom is a good indicator of stress we need to measure the symptom and stress levels in a sample of individuals from the population. It is not immediately clear how we should go about collecting this sample, i.e. how we should design the study. We haven’t got very far before we need StatisticsThe general focus of this course Examine the results of the statistical test Use statistics to test We start with a Propose a Collect our hypothesis based question/hypotheis study/experiment Data on a model of the data that aims to provide about a given i.e. take data to help test our population of a sample hypothesis objects/events from the population Study Design (How can we design STATISTICS our study to get the most information about our hypothesis)Datasets consist of measured variables The datasets that Psychologists and Human Scientists collect will usually consist of one more observations on one or more “variables”. A variable is a property of an object or event that can take on different values. Example Suppose we collect a dataset by measuring the hair colour, resting heart rate and score on an IQ test of every student in a class. The variables in this dataset would then simply be hair colour, resting heart rate and score on an IQ test, i.e. the variables are the properties that we measured/observed.2 main types of variable 1 Measurement (Quantitative) Data occur when we ‘measure’ things e.g. height or weight. 2 Categorical (Qualitative) Data occur when we assign objects into labelled groups or categories e.g. when we group people according to hair colour or race. (i) Ordinal variables have a natural ordering e.g. gold/silver/bronze medal (i) Nominal variables do not have a natural ordering e.g. genderDiscrete and Continuous Variables Discrete Data No. of students late for a lecture 0 1 2 ................................................... 8 There are only a limited set of distinct values/categories i.e. we can’t have exactly 2.23 students late, only integer values are allowed. Continuous Data Time spent studying statistics (hrs) 3.76 5.67 0 In theory there are an unlimited set of possible values There are no discrete jumps between possible values.Summary of Data Types Types of data Quantitative Qualitative (Measurement) (Categorical) Discrete Continuous Discrete e.g. No. of students e.g.Height, Weight in a class Nominal Ordinal e.g. League position, e.g. Hair colour, Race, Medal awarded in Smoking status an Olympic eventPlotting Data One of the most important stages in a statistical analysis can be simply to look at your data right at the start. By doing so you will be able to spot characteristic features, trends and outlying observations that enable you to carry out an appropriate statistical analysis. Also, it is a good idea to look at the results of your analysis using a plot. This can help identify if you did something that wasn’t a good idea REMEMBER Data is messy No two datasets are the same ALWAYS LOOK AT YOUR DATAThe Baby-Boom dataset Forty-four babies (a new record) were born in one 24-hour period at the Mater Mothers’ Hospital in Brisbane, Queensland, Australia, on December 18, 1997. For each of the 44 babies, The Sunday Mail recorded the time of birth, the sex of the child, and the birth weight in grams. Whilst, we did not collect this dataset based on a specific hypothesis, if we wished we could use it to answer several questions of interest.  Do girls weigh more than boys at birth?  What is the distribution of the number of births per hour?  Is birth weight related to the time of birth?  Is gender related to the time of birth?  Is there an equal chance of being born a girl or boy?Time Gender Weight Time Gender Weight Time Gender Weight 5 1 3837 649 1 3746 1105 1 2383 64 1 3334 653 1 3523 1134 2 3428 78 2 3554 693 2 2902 1149 2 4162 115 2 3838 729 2 2635 1187 2 3630 177 2 3625 776 2 3920 1189 2 3406 245 1 2208 785 2 3690 1191 2 3402 247 1 1745 846 1 3430 1210 1 3500 262 2 2846 847 1 3480 1237 2 3736 271 2 3166 873 1 3116 1251 2 3370 428 2 3520 886 1 3428 1264 2 2121 455 2 3380 914 2 3783 1283 2 3150 492 2 3294 991 2 3345 1337 1 3866 494 1 2576 1017 2 3034 1407 1 3542 549 1 3208 1062 1 2184 1435 1 3278 635 2 3521 1087 2 3300Bar Charts A Bar Chart is a useful method of summarising Categorical Data. We represent the counts/frequencies/percentages in each category by a bar. Girl Boy Frequency 0 4 8 12 16 20 24Histograms ‘A Bar Chart is to Categorical Data as a Histogram is to Measurement Data’ 1500 2000 2500 3000 3500 4000 4500 Birth Weight (g) Frequency 0 0 5 5 10 10 15 15 20 20Constructing Histograms (an example) For the baby-boom dataset we can draw a histogram of the birth weights. To draw the histogram I found the smallest and largest values smallest = 1745 largest = 4162 There are only 44 weights so I decided on 6 equal sized categories Interval 1500-2000 2000-2500 2500-3000 3000-3500 3500-4000 4000-4500 Frequency 1 4 4 19 15 1 Using these categories works well, the histogram shows us the shape of the distribution and we notice that distribution has an extended left ‘tail’.Too few categories Too many categories 1500 2500 3500 4500 1500 2500 3500 4500 Birth Weight (g) Birth Weight (g) Too few categories and the details are lost. Too many categories and the overall shape is obscured by too many details Frequency 0 5 10 15 20 25 30 35 Frequency 0 1 2 3 4 5 6 7Cumulative Frequency Plots and Curves Interval 1500-2000 2000-2500 2500-3000 3000-3500 3500-4000 4000-4500 Frequency 1 4 4 19 15 1 Cumulative 1 5 9 28 43 44 Frequency Cumulative Frequency Plot Cumulative Frequency Curve 1500 2000 2500 3000 3500 4000 4500 2000 2500 3000 3500 4000 4500 Birth Weight (g) Birth Weight (g) Cumulative Frequency 0 10 20 30 40 50 Cumulative Frequency 0 10 20 30 40 50Dot plots A Dot Plot is a simple and quick way of visualising a dataset. This type of plot is especially useful if data occur in groups and you wish to quickly visualise the differences between the groups. 1500 2000 2500 3000 3500 4000 4500 Birth Weight (g) Gender Girl BoyScatter Plots Scatter plots are useful when we wish to visualise the relationship between two measurement variables. 2000 2500 3000 3500 4000 Birth Weight (g) Time of birth (mins since 12pm) 0 200 400 600 800 1000 1200 1400