Exam 1 Study Guide: Lectures 1-5 PSY 230Lecture 1Statistics is the process of collecting data and making decisions based on the analysis of these data. The difference between a constant number and a variable is that a constant number is a symbol representing something that does not change and a variable is a measurable characteristic that changes with experiment.The Independent Variable is a variable that is under the control of the experimenter and is manipulated. The Dependent Variable is the outcome of interest that depends on the experiment and is not controlled by the experimenter. A Subject or Organismic Variable is a naturally occurring independent variable that is not controlled, like eye color.Data are measurements collected. The difference between population and parameter is that population is a complete set of people having a characteristic in common and a parameter is a value summarizing a characteristic of population (represented by GREEK letters). The difference between sample and statistic is that sample is a subset of a population that shares the same characteristics and a statistic is based on a sample and summarizes a characteristic of a sample (and is a variable, represented by ROMAN letters).A simple random sample is a subset of a population that is randomly selected so that every member of the population has equal and independent chance of being chosen. Random assignment comes after simple random sample and assigns subjects to treatments in an independent manner to avoid bias (divided into groups like placebo and treatment). Confounding is where a variable related to the independent variable affects the dependent variable.Lecture 2X or Y represent variables. Xi and Yi represent individual observation. N or n represents the number of data points in a set. Σ represents summation.In summation, an equation is noted as Σ Xi. Below this is where you indicate the place you start in the series of numbers. For example, if you start with the third number in a group, it would be written as i=3 under the Σ Xi. The number above the Σ Xi indicates the stopping point. For example, a 6 above the Σ Xi indicates that you stop at the 6th number in the sequence.N above the Σ Xi represents that you use all numbers from the start point (i=__).There are 4 types of measurement scales in statistics.1. Nominal: qualitative and mutually exclusive with no logical order (meaning none of the subjects would logically come before the others. For example, cat, dog, fish)2. Ordinal: mutually exclusive with logical rank ordering (for example, 1st grade, 2nd grade, etc.)3. Interval: quantitative with equal units of measurement and an imaginary zero point (such as a calendar. You can theoretically have negative days because if Jan 1, 2013 is day0, December 31, 2012 would be day -1.4. Ratio: quantitative with equal units of measurement and an absolute real zero point, meaning the quantity can’t go below zero (height, weight, length).Reliability is the degree to which repeated measurements in the same conditions give the same results. Measurement Error is an uncontrolled recording error. Validity is an accuracy test that actually measures a thing of interest. Discontinuous (discrete) variables are whole numbers (no fractions). Continuous Variables are variables that allow for any values including fractions.True limits are #’s that limit where the true value lies. There could potentially be more precise measurements so we must define the limits of our measurements.True Limit Equation: +/- ½ the unit of measurementFrequency: count. Ratio: 13:7, women to men, DO NOT REDUCE. Proportion: fraction. 13/20=0.65. Percentage: Proportion x100Lecture 3Exploratory Data Analysis: ways to arrange and display numbers to quickly organize and summarize data. I=width= (hi-lo + 1)/#groupsPercentiles are numbers that divide distribution into 100 equal parts. Percentile Rank is a number that represents the % of cases in a comparison group that achieved scores less than or equal to the one cited.Lecture 4cumfLL= cumulative frequency at lower true limit of X (the score of interest)X= score of interestXLL= score at lower true limit of Xi= widthfi= # cases in x’s groupN= total number of scoresLecture 5Visual Methods to Display Data:A figure is a pictorial, photo, or drawing. A table consists of organized numerical information. A graph is pictorial that includes axes and numbers. The x-axis (abscissa) is thehorizontal axis (independent variable) and the y-axis (ordinate) is the vertical axis (dependent variable)A bar graph is nominal, sometimes ordinal and bars do not touch. A histogram is used for discrete data and is the same as a bar graph except the bars DO touch. A frequency or line graph is used for continuous data.Cumulative Frequency can be a bar, histogram, or line graph.Normal graphs are bell shaped and are symmetric. Within normal graphs are mesokurtic, leptokurtic, and platykurtic graphs. Mesokurtic graphs are middle graphs. Leptokurtic graphs are peaked (leaping) graphs. Platykurtic graphs are flat and look like a prairie.MesokurticLeptokurticPlatykurticPositive SkewNegative