## Noveltydisruption Effect

EXPERIMENTER EFFECTS.

NUDISM THEORIES. See LABELING/ DEVIANCE THEORY.

NULL HYPOTHESIS. = statistical hypothesis. The term null hypothesis refers to any statement, proposition, or assumption that serves as a tentative explanation of certain facts where the assumption of no difference exists between the studied groups (e.g., the effects of a tested drug will be the same for both the experimental and control groups of participants). When statistical analyses are used to test hypotheses, experimenters typically set up the null hypothesis prior to collecting data. This predetermined postulation allows for an evaluation of research results on the basis of sampling distribution and normal curve probability theory. A null hypothesis deals with the relationship between variables and is stated so that either it or its negation will result in information that may be used to advance a particular research hypothesis (cf., partial null hypothesis - a null hypothesis stating that there is no difference between any pair of group means on the dependent variable in a study containing several groups). In the standard hypothesis-testing approach in science, one attempts to demonstrate the falsity of the null hypothesis (in a "straw-man" type of reasoning strategy called falsification; for example, a tested drug shows that there is a difference between the experimental and control groups of participants), leaving one with the implication that the alternative (or mutually exclusive/opposite) hypothesis is the "correct" or acceptable one. The alternative hypothesis (also called the experimental or research hypothesis) functions as an alternative to the null hypothesis and typically asserts that the independent variable has an influence on the dependent variable, an effect that cannot be accounted for by chance alone. After the data in a study are collected, and the actual statistics are calculated, the researcher must decide whether or not to reject the null hypothesis [cf., Simpson's paradox - named after the British mathematician Edward H. Simpson (1927- ), refers to a statistical paradox where the sets of data, when considered separately, each support a particular conclusion, but when taken together support the opposite conclusion]. In the hypothesis-testing activity, several hypothetical, or potential, statistical errors may be identified vis-à-vis the null hypothesis decision: Type I error - refers to the rejection of the null hypothesis when it is actually true; Type II error - refers to the failure to reject the null hypothesis when it is actually false; and a related interpretative error, Type III error - is an error arising from a misinterpretation of the nature of the scores being compared in a statistical significance test (cf., grounded theory -

refers to a systematic approach in theory development that advances the notion of close observation of the world without any prior theoretical framework or bias; such a theory is developed via the use of conceptualizations that link facts together rather than the use of inferences and hypothesis-testing strategies; this approach finds its value in the inductive generation of associations and categories that facilitate the attack of topical issues that are difficult to explore in the normal laboratory setting). The concept of the null hypothesis was developed by the English geneticist/statistician Sir Ronald Aylmer Fisher (1890-1962) and approximates the Austrian-born British philosopher Sir Karl Popper's (1902-1994) philosophy of science approach that views science to be a process for the elimination of false theories (i.e., the major role of science should be the falsification of incorrect theories). According to these reasoning viewpoints or strategies, science - particularly psychology - never "proves" hypotheses. Science shows only that certain hypotheses (e.g., the null hypothesis) have been "disproved" [cf., the American philosopher of science Thomas S. Kuhn's (1922-1996) anti-confirmationism viewpoint which states that proving a hypothesis has little meaning, but disconfirming a hypothesis may be very meaningful]. Therefore, the null hypothesis itself cannot be proved without knowing the "true" state of affairs, but it can be disproved if the obtained results in a study are too unlikely to be compatible with it. Decisions based on statistical hypothesis-testing procedures are usually cast in terms of levels of probability, or levels of confidence, as to the correctness of various outcomes vis-à-vis the null hypothesis. Other related forms of the theory of confirmation and inductive reasoning (i.e., inferring a general law/principle from particular observed instances) include the following: problem of induction/Hume's problem -named after the Scottish philosopher David Hume (1711-1776) - is an apparent inconsistency of inductive reasoning that is solved by using empirical evidence to falsify, rather than to confirm, hypotheses; confirmation para-dox/Hempel 's paradox - named after the German-born American philosopher Carl Gustav Hempel (1905-1997) - is confirmation of a statement via a process that contains no logical flaw in reasoning but has psychological difficulties arising from "misguided intuition;" for example, proving the statement that "all presidents live at the White House" tends to be confirmed (falsely) by finding or observing, say, a kennel containing a dog, because this is an instance of a dwelling that is not the White House which is the home of a nonpresident - which is a logically equivalent statement; the resolution of Hempel's paradox is to restrict the universe in which the data search is made; Goodman's paradox - named after the American philosopher Nelson Goodman (1906-1998) - is an apparent paradox, or refutation, of induction; for example, suppose that you note that all rubies that have ever been observed are red, and argue inductively that to conclude that all rubies are red; next, suppose one defines "roja" as the property of being red up to some time t (say, the end of the year 2040) and yellow thereafter; all the inductive evidence supports the conclusion that all rubies are "roja" just as it supports the conclusion that all rubies are red; therefore, one has no grounds for preferring either conclusion. See also MEEHL'S SIXTH LAW OF SOFT PSYCHOLOGY; PROBABILITY THEORY/LAWS. REFERENCES

Fisher, R. A. (1925). Statistical methods for research workers. New York: Hafner.

Popper, K. (1935). The logic of scientific discovery. New York: Basic Books. Hempel, C. G. (1937). Le probleme de la vea-

cuterite. Theoria, 3. 3. Goodman, N. (1955/1983). Fact, fiction, and forecast. Fourth edition. Cambridge, MA: Harvard University Press. Schoffler, I. (1963). The anatomy of inquiry.

New York: Knopf. Kuhn, T. S. (1977). Objectivity, value judgment, and theory choice. In T. S. Kuhn (Ed.), The essential tension: Selected studies in scientific tradition and change. Chicago: University of Chicago Press. Campbell, D. T. (1990). The Meehlian cor-roboration-verisimilitude theory of science. Psychological Inquiry, 1, 142-172.

## Sleeping Sanctuary

Salvation For The Sleep Deprived The Ultimate Guide To Sleeping, Napping, Resting And Restoring Your Energy. Of the many things that we do just instinctively and do not give much of a thought to, sleep is probably the most prominent one. Most of us sleep only because we have to. We sleep because we cannot stay awake all 24 hours in the day.

## Post a comment