Download as PPTX, PDF, TXT or read online on Scribd
Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1/ 30
Making Predictions
Statistical Inference • Recall:
Statistical inference is the process of making
an estimate, forecast or decision about a population based on sample results. Statistical inference is the primary purpose of statistics. Some Important Concepts in Statistical Inference • Parameters and Statistic
Parameters are characteristics of the population.
Statistic is a characteristic of the sample. Means and standard deviations are examples of parameter and statistic, depending on whether we are talking of the population mean or standard deviation; or sample mean or standard deviation. Parameters are fixed values and these are generally unknown. For example, at any point in time, no one probably knows what the mean age of all XXX students would be. But, if one or two or more groups try to get the information on the age of all XXX students, they should all arrive at the same value. • Statistic, on the other hand, will vary from sample to sample, and these may be easily computed. For instance, one group may get a representative sample of the population of all xxx students. Another group may pick a different representative sample. The means of the two samples may be different. Two General Types of Statistical Inference • Estimation Concept of Estimation As its name suggests, the objective of estimation is to determine the approximate value of a population parameter on the basis of a sample statistic. An estimator of a population parameter is a random variable that is a function of the sample data. An estimate is the calculation of a specific value of this random variable. The sample mean is the estimator of the population mean. The sample standard deviation is the estimator of the population standard deviation. Once the sample has been drawn and the statistics calculated, the value of the sample mean becomes the estimate of the population mean, and the value of the sample standard deviation becomes the estimate of population standard deviation. We can use sample data to estimate a population parameter in two ways. First, we can make a point estimate. We can compute the value of the estimator and consider that value as the estimate of the parameter. We are using one value or point to infer the value of the parameter. When drawing inferences about a population, our intuition tells us that the larger the sample, the more accurate the results. But, point estimates don’t reflect the effects of larger sample sizes. • A second way of estimating a population parameter is to make an interval estimate. We estimate the value of the parameter by reference to an interval rather than a single point. The interval estimator is affected by the sample size. Concept of Hypothesis Testing • Another way of drawing inference about a population is through hypothesis testing. The objective of the hypothesis testing is to determine whether or not the sample data support some belief or hypothesis about the population. Steps in Hypothesis Testing
1. Formulate the hypothesis
Types of hypotheses: a. Null Hypothesis (Ho) b. Alternative hypothesis (Ha) The null hypothesis is usually one that a researcher wants to reject. If we reject the null hypothesis, declare it to be false, we accept the alternative hypothesis. The null hypothesis hypothesizes “no difference”, or “no effect”, or “no relationship”. The null hypothesis may also specify that the value of a parameter of interest is some value. The alternative hypothesis is the hypothesis the researcher wants to prove. The purpose of the alternative hypothesis is to determine whether or not the evidence provided by the sample is enough to establish that the null hypothesis is not true. If there is enough such evidence, then we will say that there is evidence to support the alternative hypothesis. • There are several types of null hypothesis that we will discuss in this course. These may be categorized according to problem objective: (1) Description of a Single Population; (2) Comparison of two populations; (3) Analysis of the relationship between two variables Three Possible Forms of the Alternative Hypothesis a. If we are interested in determining whether or not the parameter is not equal to the value of the parameter specified by the null hypothesis, the alternative hypothesis will use the “not equal” sign. b. If we want to determine whether or not the sample data allow us to conclude that the parameter exceeds the value of the parameter specified by the null hypothesis, the alternative hypothesis will use the “greater than” sign. If we want to determine whether or not the sample data allows us to conclude that the parameter is less than the parameter specified by the null hypothesis, the alternative hypothesis will use the “less than” sign. 2. Selecting the Statistical Analysis Model to be used Having specified the null and alternative hypotheses, we then select the appropriate test statistic or statistical model to be used. The choice of our statistic would depend on a number of factors. (1) the nature of the hypothesis problem; (2) the level of measurement; and (3) assumptions of normality. Some statistical models • The Z-test for a single sample test of the mean • The T-test for a single sample test of the mean • The Z-test for a single sample test of proportion • The Z-test for a difference of means test • The T-test for a difference of means test • The Z-test for a difference of proportions test • Pearson’s product moment correlation coefficient test • Spearman’s rank correlation coefficient test • Chi-square test of independence 3. Setting Criteria for rejecting the null hypothesis
a. Selecting a significance level
b. Determining the area of rejection • The level of significance refers to the probability of rejecting the null hypothesis when it is true. This is called a Type I error or alpha error. The level of significance refers to the probability that we will reject the null hypothesis. We make the selection of the level of significance before we compute for the test statistic. We need to select a level of significance that we think is reasonable. The decision as to which significance level to use depends on the question involved. Social scientists routinely accept a probability of .05 for rejecting the null hypothesis. If a statistical test would lead to significant policy recommendations, then you may wish to reduce the risk of being in error and signify a significance level of .01 or .001. Based on the significance level we choose, we then delineate our region of acceptance and region of rejection. The region of rejection is also called the critical region. Outcomes falling here mean we reject the null hypothesis. Our critical region will also depend on whether we are doing a right-tailed test, a left-tailed test or a two-tailed test. If our alternative hypothesis involves the greater than sign, we use a right-tailed test. When our alternative hypothesis involves the less than sign, we use a left-tailed test. When our alternative hypothesis involves the not equal sign, we will use a two-tailed test. “I know this is difficult to comprehend at the moment. When we start going through process of hypothesis testing using concrete examples, this will be clearer to you”. 4. Analysis The analysis part is the process of computing for our test statistic based on the assumptions we made and the data we have. 5. Making a decision In assessing the null hypothesis, we can either accept the null hypothesis or reject it in favor of the alternative hypothesis. Our decision will be based on the value of the test statistic we obtain in the analysis stage. If the value of the test statistic is located in the critical region, we reject the null hypothesis in favor of the alternative hypothesis. Our findings may be taken conclusive even if there is the probability that we may be in the error. If the test statistic is located in the acceptance region, we accept the null hypothesis but our findings are not conclusive. We simply do not have evidence to prove our alternative hypothesis. • This may be compared to a judge who, upon making a decision, for instance, hands down a verdict of “guilty”. When the judge makes this pronouncement, the defendant is conclusively declared as guilty and he serves the sentence imposed even if there is the probability he is actually not guilty (only God and the defendant can really say whether he is guilty or not). But, when the judge hands down the verdict of “not guilty”, it usually is not because it has been proven, beyond reasonable doubt, that he is not guilty. There simply is not enough evidence to prove the defendant guilty. Directional and non-directional hypothesis • Directional test of hypothesis is considered if the direction of the difference is stated. This test makes use of the one-tailed test or one-sided test. • The test is considered non-directional if the direction or the nature of the difference is not stated. The non-directional test makes use of the two-tailed test.
The Art of Selfishness by David Seabury -- David Seabury -- 1973-01-01 -- Cornerstone Library Publicatio -- 9a91c73e2218159eba498e52d440042d -- Anna’s Archive
The Art of Selfishness by David Seabury -- David Seabury -- 1973-01-01 -- Cornerstone Library Publicatio -- 9a91c73e2218159eba498e52d440042d -- Anna’s Archive