{"id":378453,"date":"2022-05-06T11:00:53","date_gmt":"2022-05-06T09:00:53","guid":{"rendered":"https:\/\/www.scribbr.nl\/?p=378453"},"modified":"2022-09-14T18:28:29","modified_gmt":"2022-09-14T16:28:29","slug":"null-and-alternative-hypotheses","status":"publish","type":"post","link":"https:\/\/www.scribbr.com\/statistics\/null-and-alternative-hypotheses\/","title":{"rendered":"Null and Alternative Hypotheses | Definitions & Examples"},"content":{"rendered":"
The null and alternative hypotheses are two competing claims that researchers weigh evidence for and against using a statistical test<\/a>:<\/p>\n The effect is usually the effect of the independent variable<\/a> on the dependent variable<\/a>. The null and alternative hypotheses offer competing answers to your research question<\/a>. When the research question asks \u201cDoes the independent variable affect the dependent variable?\u201d:<\/p>\n The null and alternative are always claims about the population. That\u2019s because the goal of hypothesis testing<\/a> is to make inferences<\/a> about a population based on a sample<\/a>. Often, we infer whether there\u2019s an effect in the population by looking at differences between groups or relationships between variables in the sample. It’s critical for your research to write strong hypotheses<\/a>.<\/p>\n You can use a statistical test to decide whether the evidence favors the null or alternative hypothesis. Each type of statistical test comes with a specific way of phrasing the null and alternative hypothesis. However, the hypotheses can also be phrased in a general way that applies to any test.<\/p>\n The null hypothesis is the claim that there\u2019s no effect in the population.<\/p>\n If the sample provides enough evidence against the claim that there\u2019s no effect in the population (p<\/em> \u2264 \u03b1), then we can reject the null hypothesis<\/a>. Otherwise, we fail to reject the null hypothesis.<\/p>\n Although \u201cfail to reject\u201d may sound awkward, it\u2019s the only wording that statisticians accept. Be careful not to say you \u201cprove\u201d or \u201caccept\u201d the null hypothesis.<\/p>\n In other words, the null hypothesis (i.e., that there is no effect) is assumed to be true until the sample provides enough evidence to reject it.<\/figure>\n Null hypotheses often include phrases such as \u201cno effect,\u201d \u201cno difference,\u201d or \u201cno relationship.\u201d When written in mathematical terms, they always include an equality (usually =, but sometimes \u2265 or \u2264).<\/p>\n You can never know with complete certainty whether there is an effect in the population. Some percentage of the time, your inference about the population will be incorrect. When you incorrectly reject the null hypothesis, it’s called a type I error<\/a>. When you incorrectly fail to reject it, it’s a type II error.<\/p>\n The table below gives examples of research questions<\/a> and null hypotheses. There\u2019s always more than one way to answer a research question, but these null hypotheses can help you get started.<\/p>\n\n
\n<\/p>\nAnswering your research question with hypotheses<\/h2>\n
\n
What is a null hypothesis?<\/h2>\n
Examples of null hypotheses<\/h3>\n